Urban resident space-time activity identification method, device, equipment and medium

Abstract

The invention relates to an urban resident space-time activity identification method, device and equipment and a medium, and the method comprises the steps: employing a K-means clustering algorithm to cluster each building complex according to a clustering feature set, so as to determine the building complex corresponding to each cluster; calculating and determining a regional service function attribute index corresponding to each service function attribute of the building complex in the coverage range of each base station, and determining an activity weight parameter of each service function attribute of the building complex in the coverage range of each base station based on a Sigmoid function; and performing space-time anchor point matching on the activity weight parameter and the activity sequence of each service function attribute of the building complex in the coverage range of each base station in the activity range of the urban residents by adopting ArcGIS so as to display the activity track of the urban residents with the highest activity weight parameter of the service function attribute of each building complex. According to the invention, the accuracy of activity identification can be dynamically adjusted and optimized, and the identification capability of short-time activities is remarkably improved.

Description

Technical Field

[0001] The present application relates to the field of urban resident behavior recognition, and in particular to a method for identifying urban resident spatiotemporal activities, a corresponding device, an electronic device, and a computer-readable storage medium. Background Art

[0002] With the acceleration of urbanization, understanding the spatiotemporal behavior patterns of urban residents is crucial for urban planning, traffic management, and the layout of public service facilities. Traditional methods, such as questionnaires and GPS tracking, are limited in terms of sample size, spatiotemporal resolution, and implementation costs. The emergence of MSDs provides a new approach for identifying residents' daily activity chains and spatial preferences. However, existing methods still face challenges in inferring activity types, such as insufficient base station positioning accuracy and gaps in semantic information. Furthermore, existing methods have limitations in classifying short-term activities; for example, the accuracy of distinguishing between activities such as shopping and entertainment needs to be improved.

[0003] To sum up, there are certain limitations in the classification of short-term activities in the existing technology. For example, the accuracy of distinguishing between behavior types such as shopping and entertainment needs to be improved. The applicant has made corresponding explorations to solve this problem. Summary of the Invention

[0004] The purpose of this application is to solve the above problems and provide a method for identifying the spatiotemporal activities of urban residents, a corresponding device, an electronic device and a computer-readable storage medium.

[0005] In order to meet the various objectives of this application, this application adopts the following technical solutions:

[0006] A method for identifying spatiotemporal activities of urban residents proposed to meet one of the purposes of this application includes:

[0007] Obtaining mobile signal data of urban residents, extracting anonymous user IDs, timestamps, base station IDs, and base station coordinates from the mobile signal data to determine a base station overlap area, wherein the base station overlap area represents an activity range of urban residents, the urban resident activity range includes multiple base stations and multiple building complexes, the building complexes include multiple first-level points of interest, each first-level point of interest corresponds to each service function attribute, the first-level points of interest include multiple second-level points of interest, and each service function attribute corresponds to multiple second-level points of interest;

[0008] Calculate and determine the proportion of service function attributes corresponding to each service function attribute in each building complex, construct a cluster feature set corresponding to all building complexes within the activity range of urban residents based on the proportion of service function attributes corresponding to each service function attribute in each building complex, and cluster each building complex based on the cluster feature set using a preset K-means clustering algorithm to determine the building complex corresponding to each cluster;

[0009] Calculate and determine the product between the number of building complexes belonging to each cluster within the coverage area of ​​each base station within the activity range of urban residents and the cluster center corresponding to the cluster, so as to determine the regional service function attribute index corresponding to each service function attribute of the building complex within the coverage area of ​​each base station;

[0010] Based on the Sigmoid function, the activity weight parameter of each service function attribute of the building complex within the coverage of each base station is determined according to the regional service function attribute index of the building complex within the coverage of each base station within the activity range of urban residents and the corresponding stay time of the building complex;

[0011] ArcGIS was used to perform spatiotemporal anchor matching on the activity weight parameters and activity sequences of each service function attribute of the building complex within the coverage area of ​​each base station within the activity range of urban residents, so as to display the activity trajectories of urban residents with the highest activity weight parameters of the service function attributes of each building complex, and thus complete the identification of the spatiotemporal activities of urban residents.

[0012] Optionally, the step of calculating and determining the service function attribute ratio corresponding to each service function attribute in each building complex includes:

[0013] Calculating and determining a first ratio between the number of secondary points of interest belonging to each service function attribute in each building complex within the activity range of urban residents and the number of all secondary points of interest in the building complex;

[0014] calculating and determining a first product between a service attraction coefficient corresponding to each secondary point of interest in the building complex and the first ratio to determine a service function attribute index corresponding to each service function attribute in each building complex;

[0015] The proportion of service function attributes corresponding to each service function attribute in each building complex is determined based on a second ratio between the service function attribute index corresponding to each service function attribute in each building complex and the sum of all service function attribute indices in the building complex.

[0016] Optionally, a first ratio between the number of secondary POIs belonging to each service function attribute in each building complex within the activity range of the urban residents and the number of all secondary POIs in the building complex is calculated and determined, and the calculation formula is expressed as follows:

[0017]

[0018] Among them, d i，j represents the ratio of the number of the i-th type of secondary interest points belonging to each service function attribute in the j-th building complex, that is, the first ratio; n i,j represents the number of the i-th type of secondary interest points belonging to each service function attribute in the j-th building complex; represents the number of all secondary interest points in the jth building complex;

[0019] A first product of the service attraction coefficient corresponding to each secondary point of interest in the building complex and the first ratio is calculated to determine a service function attribute index corresponding to each service function attribute in each building complex; and a second ratio of the service function attribute index corresponding to each service function attribute in each building complex to the sum of all service function attribute indices in the building complex is used to determine a service function attribute ratio corresponding to each service function attribute in each building complex, wherein the calculation formula is expressed as follows:

[0020]

[0021] Among them, W q,j represents the proportion of service function attributes corresponding to the qth service function attribute in the jth building complex; represents the service function attribute index corresponding to the qth service function attribute in the jth building complex; It represents the sum of all service function attribute indices in the j-th building complex.

[0022] Optionally, based on the ratio of service function attributes corresponding to each service function attribute in each building complex, a cluster feature set corresponding to all building complexes within the activity range of urban residents is constructed, wherein the ratio of service function attributes corresponding to each service function attribute in each building complex is expressed as:

[0023] F j =[W R,j , W O,j , W C,j , W CR,j ];

[0024] Among them, W R，j W represents the proportion of service function attributes corresponding to the Rth service function attribute in the jth building complex;O，j W represents the proportion of service function attributes corresponding to the Oth service function attribute in the jth building complex; C，j W represents the proportion of service function attributes corresponding to the Cth service function attribute in the jth building complex; CR，j represents the proportion of service function attributes corresponding to the CR-th service function attribute in the j-th building complex, R represents residential activities, O represents office activities, c represents commercial activities, and CR represents cultural, sports and entertainment activities;

[0025] The clustering feature set is expressed as:

[0026] FR=[F1,F2,F J ],

[0027] Among them, FR represents the service function attribute ratio corresponding to each service function attribute of each building complex; F1 represents the service function attribute ratio corresponding to each service function attribute of the first building complex; F2 represents the service function attribute ratio corresponding to each service function attribute of the second building complex; F J It represents the proportion of service function attributes corresponding to each service function attribute of the J-th building complex within the activity range of urban residents; J represents the total number of building complexes.

[0028] Optionally, a preset K-means clustering algorithm is used to cluster each building complex according to the clustering feature set to determine the building complex corresponding to each cluster, wherein the expression of the K-means clustering algorithm includes:

[0029]

[0030] μ k =[w R,k , w O,k , w C,k , w CR,k ];

[0031] μ=[μ k＝1 , μ k＝2 ,…,μ k＝K ] Τ ;

[0032] Among them, Inertia is used to measure the compactness of clustering; C k represents all building complexes in the kth cluster; μ k represents the cluster center of the kth cluster; ||F j -μ k || represents the proportion of service function attributes corresponding to each service function attribute in each building complex F j and cluster centers μk The Euclidean distance between q,k represents the proportion of service function attributes corresponding to the q service function attributes of the k-th cluster center; K represents the optimal number of clusters, and J represents the total number of building complexes.

[0033] Optionally, the product of the number of building complexes belonging to each cluster within the coverage area of ​​each base station within the activity range of urban residents and the cluster center corresponding to the cluster is calculated to determine the regional service function attribute index corresponding to each service function attribute of the building complex within the coverage area of ​​each base station, wherein the expression of the regional service function attribute index includes:

[0034] P c =μn c ;

[0035] n c =[n c,k＝1 ,n c,k＝2 ,…,n c,k＝K ] Τ ;

[0036] Where, c represents the cth base station; n c represents the total number of building complexes belonging to each cluster in the coverage area of ​​the c-th base station, P c Indicates the regional service function attribute index corresponding to each service function attribute within the coverage area of ​​each base station.

[0037] Optionally, the first-level points of interest include residential, office, commercial, and cultural, sports, and entertainment categories; the service function attributes include residential activities, office activities, commercial activities, and cultural, sports, and entertainment activities; the second-level points of interest include any number of accommodation services, commercial residences, life services, financial and insurance services, companies, government agencies and social groups, automobile services, automobile repairs, automobile sales, shopping services, catering services, sports and leisure services, medical care services, motorcycle services, science, education, and culture services, and scenic spots.

[0038] A device for identifying spatiotemporal activities of urban residents provided for another purpose of the present application includes:

[0039] an activity range determination module configured to obtain mobile signal data of urban residents, extract a user anonymous ID, a timestamp, a base station ID, and base station coordinates from the mobile signal data, to determine a base station overlap area, wherein the base station overlap area represents an activity range of urban residents, the urban resident activity range includes multiple base stations and multiple building complexes, the building complex includes multiple first-level points of interest, each first-level point of interest corresponds to each service function attribute, the first-level point of interest includes multiple second-level points of interest, and each service function attribute corresponds to multiple second-level points of interest;

[0040] A building complex clustering module is configured to calculate and determine the proportion of service function attributes corresponding to each service function attribute in each building complex, construct a cluster feature set corresponding to all building complexes within the activity range of urban residents based on the proportion of service function attributes corresponding to each service function attribute in each building complex, and cluster each building complex based on the cluster feature set using a preset K-means clustering algorithm to determine the building complex corresponding to each cluster cluster;

[0041] a regional function attribute quantification module configured to calculate the product between the number of building complexes belonging to each cluster within the coverage area of ​​each base station within the activity range of urban residents and the cluster center corresponding to the cluster, so as to determine the regional service function attribute index corresponding to each service function attribute of the building complex within the coverage area of ​​each base station;

[0042] An activity weight parameter determination module is configured to determine an activity weight parameter for each service function attribute of a building complex within the coverage area of ​​each base station based on a sigmoid function according to the regional service function attribute index of the building complex within the coverage area of ​​each base station within the activity range of urban residents and the corresponding length of stay of the building complex;

[0043] The residents' spatiotemporal activity identification module is set to use ArcGIS to perform spatiotemporal anchor matching on the activity weight parameters and activity sequences of each service function attribute of the building complex within the coverage area of ​​each base station within the activity range of urban residents, so as to display the activity trajectory of urban residents with the highest activity weight parameters of the service function attributes of each building complex, so as to complete the identification of urban residents' spatiotemporal activities.

[0044] An electronic device provided to meet another purpose of the present application includes a central processing unit and a memory, wherein the central processing unit is used to call and run a computer program stored in the memory to execute the steps of the urban resident spatiotemporal activity identification method described in the present application.

[0045] A computer-readable storage medium is provided to meet another purpose of the present application, which stores a computer program implemented according to the urban resident spatiotemporal activity identification method in the form of computer-readable instructions. When the computer program is called and executed by a computer, the steps included in the corresponding method are executed.

[0046] Compared with the existing technology, this application addresses certain limitations in the existing technology in the classification of short-term activities, such as the need to improve the accuracy of distinguishing between shopping, entertainment and other types of behavior. This application includes but is not limited to the following beneficial effects:

[0047] First, by quantifying the semantics and spatial configuration of points of interest (POIs), this application can accurately characterize the service function attributes of building complexes at a fine scale. This precise functional characterization supports the identification of residents' activity characteristics in a smaller spatial range. Traditional methods are generally difficult to provide such fine-grained functional analysis, and this method achieves more accurate resident activity identification, especially in complex urban environments, by combining the hierarchical features of base station overlap areas, building complex functions, and points of interest.

[0048] Secondly, by using mobile phone signaling data instead of traditional questionnaires or GPS tracking, this application greatly reduces the cost of data collection. As a widely used data source, mobile phone signaling is more convenient to collect and process and has a wide coverage. Especially in the context of increasingly accelerated urbanization, it can effectively capture the spatiotemporal behavior information of a large number of urban residents. At the same time, the universality and high coverage of mobile phone signaling data make this method have strong generalization capabilities, and it can adapt to the activity spaces of different cities and different groups of people. Therefore, it is also suitable for the diverse activity space needs of residents.

[0049] Third, traditional activity classification methods often rely on static thresholds for classification, which may lead to low recognition accuracy of short-term activities, especially for some fast and short-term activities (such as shopping, entertainment, etc.). By considering the duration of stay and the attribute information of the building complex, combining the Sigmoid function and K-means clustering algorithm for modeling, this application can dynamically adjust and optimize the accuracy of activity recognition and significantly improve the recognition ability of short-term activities. This method can effectively distinguish different types of activities such as living, office, business, and entertainment, and has higher accuracy for the spatiotemporal preferences of various activities.

[0050] Fourthly, this application not only identifies residents' spatiotemporal activity trajectories but also builds a more flexible and detailed spatial analysis model based on service function attributes and activity weight parameters. By combining Sigmoid-K-means modeling with residents' length of stay and spatial function attributes, we can better understand residents' activity preferences in different building complexes. This enables urban planners, traffic managers, and others to more accurately analyze and predict the behavioral patterns of urban residents, thereby making more scientific and targeted decisions regarding urban management and the layout of public facilities.

[0051] Fifth, using ArcGIS for spatiotemporal anchor point matching can correlate residents' activity trajectories within different building complexes with the activity weight parameters of service function attributes, generating a more intuitive and accurate representation of spatiotemporal activity trajectories. This not only provides researchers with accurate activity pattern data but also provides strong data support for urban management and planners, helping them better understand residents' daily activities and further improve the rational allocation and optimization of urban functions. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0053] Figure 1 This is a flowchart of a method for identifying spatiotemporal activities of urban residents in an embodiment of the present application;

[0054] Figure 2 This is a schematic diagram of data extraction and sorting in the embodiments of the present application;

[0055] Figure 3 A schematic diagram of processing the ping-pong effect in an embodiment of the present application;

[0056] Figure 4 This is a schematic diagram of eliminating static segment data in an embodiment of the present application;

[0057] Figure 5 Schematic diagram of calculating the time interval between adjacent spatiotemporal anchor points and the distance between base station centers in an embodiment of the present application;

[0058] Figure 6 This is a schematic diagram of processing the drift segment in an embodiment of the present application;

[0059] Figure 7 This is a schematic diagram of solving activity weight parameters in an embodiment of the present application;

[0060] Figure 8 This is a schematic diagram of the building complex distribution map of the activity area of ​​resident A in the embodiment of the present application;

[0061] Figure 9Schematic diagram of a clustering feature map of a building complex in an embodiment of the present application;

[0062] Figures 10 to 13 This is a schematic diagram of the spatiotemporal activity chain diagram of resident A in an embodiment of the present application;

[0063] Figures 14 to 17 This is a schematic diagram of a time series analysis chart of the activity index of resident A in an embodiment of the present application;

[0064] Figure 18 This is a schematic diagram of the process in the embodiment of the present application;

[0065] Figure 19 This is a functional block diagram of a device for identifying spatiotemporal activities of urban residents in an embodiment of the present application;

[0066] Figure 20 Schematic diagram of the structure of the computer device in the embodiment of the present application. DETAILED DESCRIPTION

[0067] The following describes in detail embodiments of the present application, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and are not to be construed as limiting the present application.

[0068] It will be understood by those skilled in the art that, unless expressly stated otherwise, the singular forms "a", "an", "said" and "the" used herein may also include the plural forms. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be intermediate elements. In addition, "connected" or "coupled" as used herein may include wireless connections or wireless couplings. The term "and / or" used herein includes all or any units and all combinations of one or more associated listed items.

[0069] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs. It should also be understood that terms such as those defined in common dictionaries should be understood to have meanings consistent with their meanings in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0070] It will be understood by those skilled in the art that the terms "client," "terminal," and "terminal device" as used herein include both devices that are wireless signal receivers, i.e., devices that only have wireless signal receivers without transmission capabilities, and devices that have receiving and transmitting hardware capable of two-way communication over a two-way communication link. Such devices may include: cellular or other communication devices such as personal computers and tablet computers, which have single-line displays, multi-line displays, or cellular or other communication devices without multi-line displays; PCS (Personal Communications Service), which may combine voice, data processing, fax, and / or data communication capabilities; PDA (Personal Digital Assistant), which may include a radio frequency receiver, a pager, Internet / Intranet access, a web browser, a notepad, a calendar, and / or a GPS (Global Positioning System) receiver; and conventional laptop and / or palmtop computers or other devices, which have and / or include a radio frequency receiver. As used herein, the terms "client," "terminal," or "terminal device" may be portable, transportable, or installed in a vehicle (air, sea, and / or land), or may be adapted and / or configured to operate locally and / or in a distributed manner at any other location on Earth and / or in space. As used herein, the terms "client," "terminal," or "terminal device" may also refer to a communication terminal, an Internet terminal, or a music / video playback terminal, such as a PDA, an MID (Mobile Internet Device), and / or a mobile phone with music / video playback capabilities, or may include a smart TV, a set-top box, or other device.

[0071] The hardware referred to by names such as "server", "client", and "service node" in this application is essentially an electronic device with capabilities equivalent to those of a personal computer. It is a hardware device that has the necessary components revealed by the von Neumann principle, such as a central processing unit (including an arithmetic unit and a controller), a memory, an input device, and an output device. Computer programs are stored in its memory, and the central processing unit loads the program stored in the external memory into the internal memory for execution, executes the instructions in the program, and interacts with the input and output devices to complete specific functions.

[0072] It should be noted that the concept of "server" referred to in this application can also be extended to server clusters. Based on the network deployment principles understood by those skilled in the art, the servers described should be logically divided. In physical space, these servers can be independent of each other but callable through interfaces, or integrated into a single physical computer or a computer cluster. Those skilled in the art should understand this flexibility and should not use it to constrain the implementation of the network deployment method of this application.

[0073] Unless expressly specified, one or more technical features of the present application can be deployed on a server for implementation and accessed by a client through a remote call to obtain an online service interface provided by the server, or can be directly deployed and run on a client for implementation.

[0074] Unless expressly specified otherwise, the neural network models referenced or may be referenced in this application may be deployed on a remote server and remotely called on the client, or may be deployed and directly called on a client with sufficient device capabilities. In some embodiments, when it runs on the client, its corresponding intelligence may be obtained through transfer learning to reduce the requirements for the client's hardware operating resources and avoid excessive occupation of the client's hardware operating resources.

[0075] Unless explicitly specified, the various data involved in this application can be stored remotely on a server or on a local terminal device, as long as they are suitable for being called by the technical solution of this application.

[0076] Those skilled in the art should be aware that although the various methods of this application are described based on the same concept and thus exhibit commonality, unless otherwise specified, these methods can be independently executed. Similarly, the various embodiments disclosed in this application are all based on the same inventive concept. Therefore, concepts with the same expression, as well as concepts that are appropriately transformed for convenience despite different expression, should be understood as equivalent.

[0077] Unless expressly stated to be mutually exclusive, the various embodiments disclosed in this application may be cross-combined with the relevant technical features of the various embodiments to flexibly construct new embodiments, as long as such combination does not deviate from the creative spirit of this application and can meet the needs of the prior art or resolve certain deficiencies in the prior art. Those skilled in the art should be aware of such flexibility.

[0078] See also Figure 1 In one embodiment, the method for identifying spatiotemporal activities of urban residents of the present application includes:

[0079] Step S10: obtaining mobile signal data of urban residents, extracting user anonymous IDs, timestamps, base station IDs, and base station coordinates from the mobile signal data to determine base station overlap areas, wherein the base station overlap areas represent the activity range of urban residents, the activity range of urban residents including multiple base stations and multiple building complexes, the building complexes including multiple first-level points of interest, each first-level point of interest corresponding to each service function attribute, the first-level points of interest including multiple second-level points of interest, each service function attribute corresponding to multiple second-level points of interest;

[0080] The urban resident spatiotemporal activity identification system in the terminal device can obtain the mobile signal data of urban residents, extract the user anonymous ID, timestamp, base station ID and base station coordinates from the mobile signal data to determine the base station overlapping area, wherein the base station overlapping area represents the activity range of urban residents, and the urban resident activity range includes multiple base stations and multiple building complexes, and the building complex includes multiple first-level points of interest, each first-level point of interest corresponds to each service function attribute, and the first-level points of interest include multiple second-level points of interest, and each service function attribute corresponds to multiple second-level points of interest; specifically, the first-level points of interest include residential, office, commercial and cultural, sports and entertainment categories; the service function attributes include residential activities, office activities, commercial activities and cultural, sports and entertainment activities; the second-level points of interest include any number of accommodation services, commercial residences, life services, financial and insurance services, companies, government agencies and social groups, automobile services, automobile repairs, automobile sales, shopping services, catering services, sports and leisure services, medical care services, motorcycle services, science, education and culture services and scenic spots.

[0081] In some embodiments, see Figure 2 Data extraction and sorting: First, extract the user anonymous ID (Traveler ID) and base station switching information from the MSD, including timestamp, base station ID (BSID), and base station coordinate information. Then, sort the MSDs of the same user according to the timestamp to ensure that the data is processed in chronological order.

[0082] For further examples, please refer to Figure 3 , handle the ping-pong effect: The ping-pong effect refers to the phenomenon that mobile devices frequently switch base stations in the overlapping base station coverage areas. The specific method of handling the ping-pong effect is as follows: through the preset rules, it is determined that if two or more base stations (BSIDs) are within the time range T range Frequent switching within N switch Then, the residents' activity range is narrowed down to the overlapping coverage area of ​​these base stations. And by calculating the geometric center between the base stations, the actual activity location of the residents is determined.

[0083] For further examples, please refer to Figure 4 ,Eliminate static segment data: A static segment refers to a continuous record in which residents do not switch base stations for a long time.,If adjacent spatiotemporal anchor points (SA) have the same base station ID,,then remove the subsequent redundant spatiotemporal anchor points (SA).

[0084] For further examples, please refer to Figure 5 , calculate the time interval between adjacent spatiotemporal anchor points (T int ) and base station center distance (D bs ).

[0085] For further examples, please refer to Figure 6 , deal with the drift segment: if T int >T threshold and D bs >D threshold , the user is considered to be in motion and the subsequent drift segments are removed. The BSID of the user's residence and work place is determined by the rule method. If the user is in the base station BSID R Single residence time T int >180 minutes, and the cumulative stay time is T int >300 minutes (time period is 9:00 pm to 8:00 am the next day), then BSID R For the place of residence; if the user is at the base station BSID O Single residence time T int >180 minutes, and the cumulative stay time is T int >300 minutes (time period is 9:00 am to 8:00 pm the next day), then BSID O If the base station (BSID) of the residence and the workplace are the same, it is considered that the user has no workplace on that day.

[0086] In some embodiments, POIs are classified according to service function attributes, including four primary POI categories: residential (R), office (O), commercial (C), and cultural and recreational (CR), and POI data without clear attributes are removed. A service attractiveness coefficient A is assigned to each secondary POI through expert evaluation. i .

[0087] In some embodiments, buildings with similar outlines are considered a single building complex based on the distribution of points of interest (POIs) and road networks within the base station's coverage area. Because the latitude and longitude coordinates of some POI data may deviate from the actual coordinates, these POIs should be grouped with the nearest building. Furthermore, if the POIs are located in an area without buildings, the POI cluster area is designated as a virtual building complex.

[0088] Step S20: Calculate and determine the service function attribute ratio corresponding to each service function attribute in each building complex; construct a cluster feature set corresponding to all building complexes within the activity range of urban residents based on the service function attribute ratio corresponding to each service function attribute in each building complex; and cluster each building complex based on the cluster feature set using a preset K-means clustering algorithm to determine the building complex corresponding to each cluster;

[0089] Obtaining mobile signal data of urban residents, extracting anonymous user IDs, timestamps, base station IDs, and base station coordinates from the mobile signal data to determine base station overlap areas, calculating and determining the ratio of service function attributes corresponding to each service function attribute in each building complex, constructing a clustering feature set corresponding to all building complexes within the activity range of urban residents based on the ratio of service function attributes corresponding to each service function attribute in each building complex, and clustering each building complex based on the clustering feature set using a preset K-means clustering algorithm to determine the building complex corresponding to each cluster cluster;

[0090] In some embodiments, the step of calculating and determining the service function attribute ratio corresponding to each service function attribute in each building complex includes:

[0091] Step S201: Calculate and determine a first ratio between the number of secondary POIs belonging to each service function attribute in each building complex within the activity range of the urban residents and the number of all secondary POIs in the building complex;

[0092] Step S202: Calculate and determine a first product between the service attraction coefficient corresponding to each secondary point of interest in the building complex and the first ratio to determine a service function attribute index corresponding to each service function attribute in each building complex;

[0093] Step S203: Determine the service function attribute ratio corresponding to each service function attribute in each building complex based on a second ratio between the service function attribute index corresponding to each service function attribute in each building complex and the sum of all service function attribute indices in the building complex.

[0094] In a specific embodiment, a first ratio between the number of secondary POIs belonging to each service function attribute in each building complex within the activity range of urban residents and the number of all secondary POIs in the building complex is calculated and determined, and the calculation formula is expressed as follows:

[0095]

[0096] Among them, d i，j represents the ratio of the number of the i-th type of secondary interest points belonging to each service function attribute in the j-th building complex, that is, the first ratio; n i,j represents the number of the i-th type of secondary interest points belonging to each service function attribute in the j-th building complex; represents the number of all secondary interest points in the jth building complex;

[0097] A first product of the service attraction coefficient corresponding to each secondary point of interest in the building complex and the first ratio is calculated to determine a service function attribute index corresponding to each service function attribute in each building complex; and a second ratio of the service function attribute index corresponding to each service function attribute in each building complex to the sum of all service function attribute indices in the building complex is used to determine a service function attribute ratio corresponding to each service function attribute in each building complex, wherein the calculation formula is expressed as follows:

[0098]

[0099] Among them, W q,j represents the proportion of service function attributes corresponding to the qth service function attribute in the jth building complex; represents the service function attribute index corresponding to the qth service function attribute in the jth building complex; It represents the sum of all service function attribute indices in the j-th building complex.

[0100] Furthermore, according to the proportion of service function attributes corresponding to each service function attribute in each building complex, a cluster feature set corresponding to all building complexes within the activity range of urban residents is constructed.

[0101] Among them, the proportion of service function attributes corresponding to each service function attribute in each building complex is expressed as:

[0102] F j =[W R,j , W O,j , W C,j , W CR,j ];

[0103] Among them, WR，j W represents the proportion of service function attributes corresponding to the Rth service function attribute in the jth building complex; O，j W represents the proportion of service function attributes corresponding to the Oth service function attribute in the jth building complex; C，j W represents the proportion of service function attributes corresponding to the Cth service function attribute in the jth building complex; CR，j represents the proportion of service function attributes corresponding to the CR-th service function attribute in the j-th building complex, R represents residential activities, O represents office activities, C represents commercial activities, and CR represents cultural, sports and entertainment activities;

[0104] The clustering feature set is expressed as:

[0105] FR=[F1,F2,F J ],

[0106] Among them, FR represents the service function attribute ratio corresponding to each service function attribute of each building complex; F1 represents the service function attribute ratio corresponding to each service function attribute of the first building complex; F2 represents the service function attribute ratio corresponding to each service function attribute of the second building complex; F J It represents the proportion of service function attributes corresponding to each service function attribute of the J-th building complex within the activity range of urban residents; J represents the total number of building complexes.

[0107] Furthermore, a preset K-means clustering algorithm is used to cluster each building complex according to the clustering feature set to determine the building complex corresponding to each cluster, wherein the expression of the K-means clustering algorithm includes:

[0108]

[0109] μ k =[w R,k , w O,k , w C,k , w CR,k ];

[0110] μ=[μ k＝1 , μ k＝2 ,,μ k＝K ] Τ ;

[0111] Among them, Inertia is used to measure the compactness of clustering; C k represents all building complexes in the kth cluster; μ k represents the cluster center of the kth cluster; ||F j -μ k|| represents the proportion of service function attributes corresponding to each service function attribute in each building complex F j and cluster centers μ k The Euclidean distance between q,k represents the proportion of service function attributes corresponding to the q service function attributes of the k-th cluster center; K represents the optimal number of clusters, and J represents the total number of building complexes.

[0112] Step S30: Calculate and determine the product of the number of building complexes belonging to each cluster within the coverage area of ​​each base station within the activity range of urban residents and the cluster center corresponding to the cluster, so as to determine the regional service function attribute index corresponding to each service function attribute of the building complex within the coverage area of ​​each base station;

[0113] Calculate and determine the proportion of service function attributes corresponding to each service function attribute in each building complex; construct a clustering feature set corresponding to all building complexes within the activity range of urban residents based on the proportion of service function attributes corresponding to each service function attribute in each building complex; cluster each building complex based on the clustering feature set using a preset K-means clustering algorithm to determine the building complexes corresponding to each cluster; and calculate and determine the product between the number of building complexes belonging to each cluster within the coverage range of each base station within the activity range of urban residents and the cluster center corresponding to the cluster to determine the regional service function attribute index corresponding to each service function attribute of the building complex within the coverage range of each base station;

[0114] In some embodiments, the product between the number of building complexes belonging to each cluster within the coverage area of ​​each base station within the activity range of urban residents and the cluster center corresponding to the cluster is calculated to determine the regional service function attribute index corresponding to each service function attribute of the building complex within the coverage area of ​​each base station, wherein the expression of the regional service function attribute index includes:

[0115] P c =μn c ;

[0116] n c =[n c,k＝1 ,n c,k＝2 ,,n c,k＝K ] Τ ;

[0117] Where, c represents the cth base station; n c represents the total number of building complexes belonging to each cluster in the coverage area of ​​the c-th base station, P cRepresents the regional service function attribute index corresponding to each service function attribute within the coverage area of ​​base station c.

[0118] Step S40: determining an activity weight parameter for each service function attribute of the building complex within the coverage area of ​​each base station based on the regional service function attribute index of the building complex within the activity area of ​​urban residents and the corresponding stay duration of the building complex based on a Sigmoid function;

[0119] Calculating and determining the product of the number of building complexes belonging to each cluster within the coverage area of ​​each base station within the activity range of urban residents and the cluster center corresponding to the cluster to determine the regional service function attribute index corresponding to each service function attribute of the building complex within the coverage area of ​​each base station; and then determining the activity weight parameter of each service function attribute of the building complex within the coverage area of ​​each base station based on the regional service function attribute index of the building complex within the coverage area of ​​each base station within the activity range of urban residents and the corresponding length of stay of the building complex;

[0120] In some embodiments, a single stay event within the coverage area of ​​each base station is associated with the spatiotemporal activities of city residents, and the expression includes:

[0121] P p (q,k)=P c λ p ;

[0122] λ p =[λ p,R ,λ p,O ,λ p,C ,λ p,CR ] Τ ;

[0123]

[0124] Among them, P p (q, k) represents the association probability between service function attribute q and cluster k, which is used to quantify the association strength between service function attribute q and the corresponding service function attribute in cluster k in the p-th stay event; λ p represents the activity weight parameter of each service function attribute considering the length of stay time for the p-th stay event; P c represents the regional service function attribute probability of base station c; p represents the activity weight parameter of each service function attribute considering the length of stay time for the p-th stay event; p,R represents the activity weight parameter of the residential service function attribute of the p-th stay event considering the length of stay; p,Oλ represents the activity weight parameter of the office service function attribute of the p-th stay event considering the length of stay; p,C λ represents the activity weight parameter of the shopping service function attribute of the p-th stay event considering the length of stay; p,CR represents the activity weight parameter of the cultural, sports and leisure service function attribute of the p-th stay event considering the length of stay; P p (q) represents the relative probability of service function attribute q in the p-th stay event; PT q The service function attribute ratio of the qth service function attribute is used to analyze the difference characteristics of residents in various service function attributes within a day; Tint q P represents the total length of stay of urban residents for the qth service function attribute in one day; p (k) represents the relative probability of urban residents in the main service function attributes in the pth stay event.

[0125] In a further embodiment, the service function attributes include residential activities, office activities, commercial activities, and cultural, sports and entertainment activities; R represents residential activities, O represents office activities, C represents commercial activities, and CR represents cultural, sports and entertainment activities;

[0126] Considering the proportion of the number of building complexes and the length of stay of the shopping and cultural, sports and entertainment service functional attributes of the spatiotemporal anchor points, the activity weight of short-term activities is solved to solve the semantic ambiguity problem of short-term activities. The flow chart for solving the activity weight parameter is as follows: Figure 7 shown.

[0127] The relative activity weights of residents' commercial activities and cultural, sports and entertainment activities in different time intervals are determined based on the Sigmoid function. The expressions include:

[0128] λ p,C (Tint p )=A C ·P C ·S C (Tint p )+B C ;

[0129] λ p,CR (Tint p )=A CR ·P CR ·S CR (Tint p )+B CR ;

[0130]

[0131] Among them, A CIndicates the control amplitude coefficient of business activities; A CR Indicates the control amplitude coefficient of cultural, sports and entertainment activities; B C Indicates the vertical offset coefficient of commercial activities; B CR is the vertical offset coefficient of cultural, sports and entertainment activities; α C Represents the control frequency coefficient of business activities; α CR represents the control frequency coefficient of cultural, sports and entertainment activities; β C Represents the phase shift coefficient of commercial activities; β CR Represents the phase shift coefficient of cultural, sports and entertainment activities. Considering the reasonable value of the number of commercial activities and cultural, sports and entertainment activities carried out by residents, when Indicates the different percentile intervals (t i-1 ,t i ], where Tint represents the duration of the activity, t i-1 It can be the 25th percentile of Tint, etc. i It can be the 75th percentile of Tint, etc. C (Tint p ), S CR (Tint p ) has different values; P C Indicates the relative quantity ratio of the regional service function attribute index corresponding to commercial activities; P CR Indicates the relative quantity ratio of the regional service function attribute index corresponding to cultural, sports and entertainment activities; n c represents the total number of building complexes belonging to cluster k in the coverage area of ​​the c-th base station.

[0132] Step S50: Use ArcGIS to perform spatiotemporal anchor point matching on the activity weight parameters and activity sequences of each service function attribute of the building complex within the coverage area of ​​each base station within the activity range of urban residents, so as to display the activity trajectory of urban residents with the highest activity weight parameters of the service function attributes of each building complex, so as to complete the identification of the spatiotemporal activities of urban residents.

[0133] Based on the Sigmoid function, the activity weight parameters of each service function attribute of the building complex within the coverage of each base station within the activity range of urban residents are determined according to the regional service function attribute index of the building complex within the coverage of each base station and the corresponding residence time of the building complex. Then, ArcGIS is used to perform spatiotemporal anchor point matching on the activity weight parameters and activity sequences of each service function attribute of the building complex within the coverage of each base station within the activity range of urban residents, so as to display the activity trajectories of urban residents with the highest activity weight parameters of the service function attributes of each building complex, thereby completing the identification of urban residents' spatiotemporal activities.

[0134] In some embodiments, a method for identifying spatiotemporal activities of urban residents may include:

[0135] Step S100, data extraction and sorting. First, extract the MSD of Traveler ID = A from the database. The data contains information such as user ID (Traveler ID), timestamp (Timestamp), base station ID (BSID), base station coordinate information, etc. Then, sort the MSD according to the timestamp, select the last mobile phone signaling data on November 1, 2023 to the first data on November 15, 2023, and screen out a total of 3526 MSDs. Renumber the base station IDs (NO.101-112, see Figure 8 ).

[0136] Step S100: Processing Ping-Pong Effect. If two or more base stations (BSIDs) are in the time range T range = Frequent switching within 10 minutes N switch = 3 times, and the base station records in this period are merged, and the ping-pong effect interference is eliminated 12 times in total.

[0137] Step S200: Eliminate static segment data. If the base station ID (BSID) or coordinates of adjacent spatiotemporal anchor points (SA) are the same, delete the subsequent redundant anchor points and merge a total of 28 static segments.

[0138] Step S300: Calculate the time interval (T int =TS i+1 -t i ) and base station center distance (D bs = Euclidean distance (BSCI i ,BSCI i+1 ).

[0139] Step S400: Process the moving segment. If T int >T threshold =10min and D bs >D threshold =1000m, the user is considered to be in motion, and a total of 9 moving segments are removed.

[0140] Step S500: Determine the BSID of the user's residence and workplace. R Cumulative stay time T int >300 minutes and single residence time T int >180 minutes, mark BSID RAs the residence, the residence of user 1 is determined to be: base station 102 and base station 112 (from the evening of November 5 to the morning of November 6); the user is at base station BSID 102 and base station 112 from 9:00 to 20:00. O Cumulative stay time T int >300 minutes and single residence time T int >180 minutes, mark BSID O The work location is: Base Station 104 or Base Station 108 (on the morning of November 11).

[0141] In some embodiments, the step of quantifying service function attributes includes:

[0142] Step S1100: Classification and calibration of POI data. Remove POI data without clear attributes and classify POIs according to service attributes. Further, determine the service attractiveness coefficient (A) of each secondary category POI through expert scoring method. i ), as shown in Table 1.

[0143] Table 1 Points of interest (POI) classification and A i Value

[0144]

[0145] Step S1200: Constructing building complexes. Based on the points of interest (POIs) and road network distribution within the base station coverage area, buildings with similar architectural outlines are considered as a building complex, and a total of 80 building complexes are constructed.

[0146] Step S1300: Calculate the proportion d of each point of interest (POI) category in the building complex within the full time and space activity range of resident A. i,j .

[0147] Step S1400: Calculate the service function attribute F of the building complex within the full time and space activity range of resident A. j .

[0148] Step S1500: Calculate the service function attributes FR of all activity areas of resident A during the study period A .

[0149] In some embodiments, the step of using a Sigmoid-K-means fusion model to determine the activity weight parameter of each service function attribute within the coverage area of ​​each base station includes:

[0150] Step S11000: Determine the optimal number of clusters (k=5) by the elbow rule, perform K-means clustering on all building complexes, and the clustering characteristics of each building complex are as follows: Figure 9The eigenvalues ​​of each cluster center are shown in Table 2.

[0151] Table 2μ and the number of building complexes in each cluster

[0152]

[0153] Step S12000: Calculate the regional service function attributes of a single base station.

[0154] Step S13000: Calculate the single stay event-space-time activity association of resident A, and convert P p (q) and P p (q) Place them in the same coordinate system for comparison and observation, and compare the values ​​of November 2 ( Figure 10 )November 4( Figure 11 )November 6( Figure 12 ) and November 7 ( Figure 13 )’s event-time-space activity association is displayed.

[0155] In step S14000, it is highly likely that residents will conduct residential activities at their residential locations and office activities at their office locations. Therefore, the values ​​of t1, t2, and t3 are set to the 25th percentile (44 minutes), 50th percentile (126 minutes), and 75th percentile (220.4 minutes) of resident A's total time and space residence time, respectively. Parameter ω O 、ω O1 and ω O2 are all set to 3, and the parameter ω R 、ω R1 and ω R2 The remaining parameters are shown in Table 3.

[0156] Table 3 Different Tint p Parameter value table under value

[0157]

[0158] In some embodiments, the step of visualizing spatiotemporal features includes:

[0159] Step S11: Visualization of spatiotemporal activity chains. Use ArcGIS to match spatiotemporal anchor points for the relative probability and activity sequence of each type of building complex during each stay of resident A, and visualize the spatiotemporal activity chains on November 2 ( Figure 14 )November 4( Figure 15 )November 6( Figure 16 ) and November 7 ( Figure 17 )’s space-time activity chain is displayed.

[0160] In some embodiments, Figure 8This is a distribution map of the building complex in resident A's activity area, showing base station coverage and building functional attributes; Figure 9 This is a clustering feature map of the building complex, showing the functional attributes of buildings in different clusters; Figures 10 to 13 This is the spatiotemporal activity chain diagram of resident A, showing his activity trajectory and behavior pattern; Figures 14 to 17 This is a time series analysis chart of resident A's activity index, showing the temporal distribution of his different activity types.

[0161] Step S12: Visualization of spatiotemporal activity heterogeneity: Calculate the residential, office, shopping, and cultural and entertainment activity indexes within the full spatiotemporal activity range of resident A and visualize them, such as Figure 18 shown.

[0162] See also Figure 19, a device for identifying urban residents' spatiotemporal activities provided to meet one of the purposes of this application, includes an activity range determination module 1100, a building complex clustering module 1200, a regional functional attribute quantification module 1300, an activity weight parameter determination module 1400 and a resident spatiotemporal activity identification module 1500. Among them, the activity range determination module 1100 is configured to obtain mobile signal data of urban residents, extract user anonymous ID, timestamp, base station ID and base station coordinates from the mobile signal data to determine the base station overlapping area, wherein the base station overlapping area represents the activity range of urban residents, the urban resident activity range includes multiple base stations and multiple building complexes, the building complex includes multiple first-level points of interest, each first-level point of interest corresponds to each service function attribute, the first-level point of interest includes multiple second-level points of interest, each service function attribute corresponds to multiple second-level points of interest; the building complex clustering module 1200 is configured to calculate and determine the service function attribute ratio corresponding to each service function attribute in each building complex, according to the service function attribute ratio corresponding to each service function attribute in each building complex, to construct a clustering feature set corresponding to all building complexes within the activity range of urban residents, and adopt a preset K-means clustering algorithm to cluster each building complex according to the clustering feature set to determine the building complex corresponding to each cluster cluster; area The functional attribute quantification module 1300 is configured to calculate the product between the number of building complexes belonging to each cluster in the coverage area of ​​each base station within the activity range of urban residents and the cluster center corresponding to the cluster, so as to determine the regional service function attribute index corresponding to each service function attribute of the building complex within the coverage area of ​​each base station; the activity weight parameter determination module 1400 is configured to determine the activity weight parameter of each service function attribute of the building complex within the coverage area of ​​each base station based on the regional service function attribute index of the building complex within the coverage area of ​​each base station within the activity range of urban residents and the corresponding stay time of the building complex, so as to complete the identification of the spatiotemporal activities of urban residents. The resident spatiotemporal activity identification module 1500 is configured to use ArcGIS to perform spatiotemporal anchor point matching on the activity weight parameter and activity sequence of each service function attribute of the building complex within the coverage area of ​​each base station within the activity range of urban residents, so as to display the activity trajectory of urban residents with the highest activity weight parameter of the service function attribute of each building complex, so as to complete the identification of the spatiotemporal activities of urban residents.

[0163] Based on any embodiment of this application, please refer to Figure 20 Another embodiment of the present application further provides an electronic device, which can be implemented by a computer device, such as Figure 20As shown, a schematic diagram of the internal structure of a computer device. The computer device includes a processor, a computer-readable storage medium, a memory, and a network interface connected via a system bus. The computer-readable storage medium of the computer device stores an operating system, a database, and computer-readable instructions. The database may store a control information sequence. When the computer-readable instructions are executed by the processor, the processor may implement a method for identifying the spatiotemporal activities of urban residents. The processor of the computer device is used to provide computing and control capabilities to support the operation of the entire computer device. The memory of the computer device may store computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor may execute the method for identifying the spatiotemporal activities of urban residents of the present application. The network interface of the computer device is used to connect and communicate with a terminal. Those skilled in the art will understand that Figure 20 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0164] In this embodiment, the processor is used to execute Figure 19 The memory stores the program code and various data required to execute the specific functions of each module in the device. The network interface is used to transmit data between user terminals or servers. The memory in this embodiment stores the program code and data required to execute all modules in the urban resident spatiotemporal activity identification device of this application. The server can call the server's program code and data to execute the functions of all modules.

[0165] The present application also provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the method for identifying the spatiotemporal activities of urban residents described in any embodiment of the present application.

[0166] The present application also provides a computer program product, including a computer program / instruction, which, when executed by one or more processors, implements the steps of the method for identifying the spatiotemporal activities of urban residents described in any embodiment of the present application.

[0167] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments of the present application can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments of the method. The aforementioned storage medium can be a computer-readable storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0168] The above description is only part of the implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for identifying urban residents' spatiotemporal activities, characterized in that: include: Obtaining mobile signal data of urban residents, extracting anonymous user IDs, timestamps, base station IDs, and base station coordinates from the mobile signal data to determine a base station overlap area, wherein the base station overlap area represents an activity range of urban residents, the urban resident activity range includes multiple base stations and multiple building complexes, the building complexes include multiple first-level points of interest, each first-level point of interest corresponds to each service function attribute, the first-level points of interest include multiple second-level points of interest, and each service function attribute corresponds to multiple second-level points of interest; Calculate and determine the proportion of service function attributes corresponding to each service function attribute in each building complex, construct a cluster feature set corresponding to all building complexes within the activity range of urban residents based on the proportion of service function attributes corresponding to each service function attribute in each building complex, and cluster each building complex based on the cluster feature set using a preset K-means clustering algorithm to determine the building complex corresponding to each cluster; Calculate and determine the product between the number of building complexes belonging to each cluster within the coverage area of ​​each base station within the activity range of urban residents and the cluster center corresponding to the cluster, so as to determine the regional service function attribute index corresponding to each service function attribute of the building complex within the coverage area of ​​each base station; Based on the Sigmoid function, the activity weight parameter of each service function attribute of the building complex within the coverage of each base station is determined according to the regional service function attribute index of the building complex within the coverage of each base station within the activity range of urban residents and the corresponding stay time of the building complex; ArcGIS was used to perform spatiotemporal anchor matching on the activity weight parameters and activity sequences of each service function attribute of the building complex within the coverage area of ​​each base station within the activity range of urban residents, so as to display the activity trajectories of urban residents with the highest activity weight parameters of the service function attributes of each building complex, and thus complete the identification of the spatiotemporal activities of urban residents.

2. The method for identifying urban residents' spatiotemporal activities according to claim 1, characterized in that: The steps of calculating and determining the proportion of service function attributes corresponding to each service function attribute in each building complex include: Calculating and determining a first ratio between the number of secondary points of interest belonging to each service function attribute in each building complex within the activity range of urban residents and the number of all secondary points of interest in the building complex; calculating and determining a first product between a service attraction coefficient corresponding to each secondary point of interest in the building complex and the first ratio to determine a service function attribute index corresponding to each service function attribute in each building complex; The proportion of service function attributes corresponding to each service function attribute in each building complex is determined based on a second ratio between the service function attribute index corresponding to each service function attribute in each building complex and the sum of all service function attribute indices in the building complex.

3. The method for identifying urban residents' spatiotemporal activities according to claim 2, characterized in that: A first ratio between the number of secondary points of interest belonging to each service function attribute in each building complex within the activity range of the urban residents and the number of all secondary points of interest in the building complex is calculated and determined, and the calculation formula is expressed as follows: Among them, d i,j represents the ratio of the number of the i-th type of secondary interest points belonging to each service function attribute in the j-th building complex, that is, the first ratio; n i,j represents the number of the i-th type of secondary interest points belonging to each service function attribute in the j-th building complex; represents the number of all secondary interest points in the jth building complex; A first product of the service attraction coefficient corresponding to each secondary point of interest in the building complex and the first ratio is calculated to determine a service function attribute index corresponding to each service function attribute in each building complex; and a second ratio of the service function attribute index corresponding to each service function attribute in each building complex to the sum of all service function attribute indices in the building complex is used to determine a service function attribute ratio corresponding to each service function attribute in each building complex, wherein the calculation formula is expressed as follows: Among them, W q,j represents the proportion of service function attributes corresponding to the qth service function attribute in the jth building complex; represents the service function attribute index corresponding to the qth service function attribute in the jth building complex; It represents the sum of all service function attribute indices in the j-th building complex.

4. The method for identifying urban residents' spatiotemporal activities according to claim 3, characterized in that: According to the proportion of service function attributes corresponding to each service function attribute in each building complex, a cluster feature set corresponding to all building complexes within the activity range of urban residents is constructed. Among them, the proportion of service function attributes corresponding to each service function attribute in each building complex is expressed as: F j =[W R,j ,W O,j ,W C,j ,W CR,j ]; Among them, W R,j W represents the proportion of service function attributes corresponding to the Rth service function attribute in the jth building complex; O，j W represents the proportion of service function attributes corresponding to the oth service function attribute in the jth building complex; C，j W represents the proportion of service function attributes corresponding to the cth service function attribute in the jth building complex; CR,j represents the proportion of service function attributes corresponding to the CR-th service function attribute in the j-th building complex, R represents residential activities, o represents office activities, C represents commercial activities, and CR represents cultural, sports and entertainment activities; The clustering feature set is expressed as: FR=[F1,F2,…,F J ], Among them, FR represents the service function attribute ratio corresponding to each service function attribute of each building complex; F1 represents the service function attribute ratio corresponding to each service function attribute of the first building complex; F2 represents the service function attribute ratio corresponding to each service function attribute of the second building complex; F J It represents the proportion of service function attributes corresponding to each service function attribute of the J-th building complex within the activity range of urban residents; J represents the total number of building complexes.

5. The method for identifying urban residents' spatiotemporal activities according to claim 4, characterized in that: A preset K-means clustering algorithm is used to cluster each building complex according to the clustering feature set to determine the building complex corresponding to each cluster. The expression of the K-means clustering algorithm includes: μ k =[w R,k ,w O,k ,w C,k ,w CR,k ]; μ=[μ k＝1 ,m k＝2 ,…,m k＝K ] Τ ; Among them, Inertia is used to measure the compactness of clustering; C k represents all building complexes in the kth cluster; μ k represents the cluster center of the kth cluster; ||F j -μ k || represents the proportion of service function attributes corresponding to each service function attribute in each building complex F j and cluster centers μ k The Euclidean distance between q,k represents the proportion of service function attributes corresponding to the q service function attributes of the k-th cluster center; K represents the optimal number of clusters, and J represents the total number of building complexes.

6. The method for identifying spatiotemporal activities of urban residents according to claim 5, characterized in that: The product between the number of building complexes belonging to each cluster within the coverage area of ​​each base station within the activity range of urban residents and the cluster center corresponding to the cluster is calculated to determine the regional service function attribute index corresponding to each service function attribute of the building complex within the coverage area of ​​each base station, wherein the expression of the regional service function attribute index includes: P c =μn c ; n c =[n c,k＝1 ,n c,k＝2 ,…,n c,k＝K ] Τ ; Where, c represents the cth base station; n c represents the total number of building complexes belonging to each cluster in the coverage area of ​​the c-th base station, P c Indicates the regional service function attribute index corresponding to each service function attribute within the coverage area of ​​each base station.

7. The method for identifying spatiotemporal activities of urban residents according to any one of claims 1 to 6, characterized in that: The first-level points of interest include residential, office, commercial, and cultural, sports and entertainment categories; the service function attributes include residential activities, office activities, commercial activities, and cultural, sports and entertainment activities; the second-level points of interest include accommodation services, commercial residences, life services, financial insurance services, companies, government agencies and social groups, automobile services, automobile repairs, automobile sales, shopping services, catering services, sports and leisure services, medical care services, motorcycle services, science, education and culture services, and any number of scenic spots.

8. A device for identifying urban residents' spatiotemporal activities, characterized in that: include: an activity range determination module configured to obtain mobile signal data of urban residents, extract a user anonymous ID, a timestamp, a base station ID, and base station coordinates from the mobile signal data, to determine a base station overlap area, wherein the base station overlap area represents an activity range of urban residents, the urban resident activity range includes multiple base stations and multiple building complexes, the building complex includes multiple first-level points of interest, each first-level point of interest corresponds to each service function attribute, the first-level point of interest includes multiple second-level points of interest, and each service function attribute corresponds to multiple second-level points of interest; A building complex clustering module is configured to calculate and determine the proportion of service function attributes corresponding to each service function attribute in each building complex, construct a cluster feature set corresponding to all building complexes within the activity range of urban residents based on the proportion of service function attributes corresponding to each service function attribute in each building complex, and cluster each building complex based on the cluster feature set using a preset K-means clustering algorithm to determine the building complex corresponding to each cluster cluster; a regional function attribute quantification module configured to calculate the product between the number of building complexes belonging to each cluster within the coverage area of ​​each base station within the activity range of urban residents and the cluster center corresponding to the cluster, so as to determine the regional service function attribute index corresponding to each service function attribute of the building complex within the coverage area of ​​each base station; An activity weight parameter determination module is configured to determine an activity weight parameter for each service function attribute of a building complex within the coverage area of ​​each base station based on a sigmoid function according to the regional service function attribute index of the building complex within the coverage area of ​​each base station within the activity range of urban residents and the corresponding length of stay of the building complex; The residents' spatiotemporal activity identification module is set to use ArcGIS to perform spatiotemporal anchor matching on the activity weight parameters and activity sequences of each service function attribute of the building complex within the coverage area of ​​each base station within the activity range of urban residents, so as to display the activity trajectory of urban residents with the highest activity weight parameters of the service function attributes of each building complex, so as to complete the identification of urban residents' spatiotemporal activities.

9. An electronic device comprising a central processing unit and a memory, characterized in that: The central processing unit is configured to call and run a computer program stored in the memory to execute the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that It stores a computer program implemented according to the method described in any one of claims 1 to 7 in the form of computer-readable instructions, and when the computer program is called and executed by a computer, the steps included in the corresponding method are executed.

Images