Urban resident potential activity space evolution feature extraction method and system

Abstract

The invention belongs to the technical field of urban planning, and discloses an urban resident potential activity space evolution feature extraction method and system, and the method comprises the steps: obtaining original mobile phone signaling data, carrying out the preprocessing to recognize key activity resident points, and obtaining a key activity resident point track queue; dividing the track queue into at least two activity periods according to a time period or an event inflection point, constructing a potential activity space measurement model for each activity period, and measuring to obtain a corresponding potential activity space; calculating scale indexes and shape indexes of potential activity spaces in different activity periods, and extracting overall evolution characteristics of the potential activity spaces of the urban residents; and performing space superposition analysis on the potential activity spaces of the adjacent activity periods, determining and quantifying reserved areas, lost areas and newly added areas of the potential activity spaces, extracting the procedural evolution characteristics of the potential activity spaces of the urban residents, and realizing accurate extraction of the overall and procedural evolution characteristics of the potential activity spaces of the urban residents.

Description

Technical Field

[0001] This invention relates to the field of urban planning technology, specifically to a method and system for extracting the spatial evolution characteristics of potential urban residents' activities based on mobile phone signaling data processing. Background Technology

[0002] Understanding the evolutionary characteristics of urban residents' potential activity space is crucial for accurately predicting dynamic changes in urban functional needs, optimizing the layout of public service facilities and transportation network configuration, and enhancing urban spatial resilience and residents' quality of life. In particular, the frequent occurrence of extreme weather events in cities in recent years, such as torrential rains, high temperatures, and typhoons, may lead to significant changes in the potential activity space characteristics of urban residents in certain areas or among certain groups.

[0003] Current research largely relies on traditional multi-period questionnaire surveys to obtain the characteristics of urban residents' activity space evolution. However, this method is costly to implement and struggles to capture the situation of a large urban population. Furthermore, the extracted characteristics of potential activity space evolution are often limited to rough descriptions of low-dimensional indicators, such as activity frequency and distance, while lacking detailed characterization of high-dimensional indicators, such as the scale and shape of activity spaces. In particular, current research lacks the extraction of process-oriented evolutionary characteristics of potential activity spaces, such as the retention and loss of potential activity space scale during the evolution process.

[0004] With the rapid development of information and communication technologies, mobile phone signaling data, with its advantages of wide coverage and low collection cost, has become an important data source for studying the potential activity space of urban residents. However, mobile phone signaling data is characterized by its large volume and low value density, typical of big data. Therefore, designing an accurate and efficient method for extracting the evolution characteristics of the potential activity space of urban residents is an urgent problem to be solved by professionals in the field of urban planning. Summary of the Invention

[0005] This invention provides a method and system for extracting the evolutionary features of urban residents' potential activity space based on mobile phone signaling data, aiming to solve the problems of high cost, single dimension, and lack of process quantification in the extraction of urban residents' activity space evolutionary features in existing technologies. Specifically, it designs an accurate and efficient method for extracting the overall and process evolutionary features of urban residents' potential activity space using large-scale mobile phone signaling data.

[0006] In a first aspect, the present invention provides a method for extracting the potential spatial evolution features of urban residents' activities, comprising the following steps: The original mobile phone signaling data is acquired and preprocessed to identify multiple key activity dwell points, thereby obtaining a key activity dwell point trajectory queue. Based on the time cycle or event inflection point, the trajectory queue of the key activity dwell points is divided into at least two activity periods. For each activity period, a potential activity space measurement model is constructed based on the key activity dwell points within the activity period to measure the potential activity space corresponding to the activity period. Calculate the scale and shape indices of the potential activity space during different activity periods, and extract the overall evolution characteristics of the potential activity space of urban residents; Spatial overlay analysis is performed on the potential activity spaces of adjacent activity periods to determine the retained, lost, and newly added areas of potential activity spaces between adjacent activity periods, and to extract the process evolution characteristics of urban residents' potential activity spaces.

[0007] As an optional implementation of the first aspect of this application, the step of acquiring raw mobile phone signaling data, preprocessing the raw mobile phone signaling data to identify multiple key activity dwell points, and obtaining a key activity dwell point trajectory queue specifically includes: deleting duplicate records and abnormal records in the raw mobile phone signaling data to generate a valid trajectory queue; the abnormal records include records with missing information and records with abnormal jumps; merging adjacent trajectory points in the valid trajectory queue based on a distance threshold to generate multiple candidate activity dwell points; filtering the candidate activity dwell points based on a time threshold, identifying candidate activity dwell points with a dwell time greater than the time threshold as key activity dwell points, and generating the key activity dwell point trajectory queue.

[0008] As an optional implementation of the first aspect of this application, the step of constructing a potential activity space measurement model to measure the potential activity space corresponding to the activity period specifically includes: classifying each key activity dwell point into the corresponding activity period according to its time period; for each activity period, calculating the potential activity space using a weighted confidence ellipse method, wherein the weighted confidence ellipse method includes: calculating the center position of the potential activity space based on the spatial distribution and dwell time of all key activity dwell points within the activity period, the center position being determined by the weighted average position of all key activity positions within the activity period; calculating the corresponding covariance matrix based on the spatial distribution of all key activity points within the activity period, and calculating eigenvalues ​​and corresponding eigenvectors based on the covariance matrix; determining the length of the major semi-axis of the potential activity space using the confidence probability and the larger eigenvalue, and determining the length of the minor semi-axis of the potential activity space using the confidence probability and the smaller eigenvalue; and calculating the rotation angle of the potential activity space based on the eigenvector corresponding to the larger eigenvalue.

[0009] As an optional implementation of the first aspect of this application, the step of calculating the scale index and shape index of the potential activity space for different activity periods and extracting the overall evolution characteristics of the potential activity space of urban residents specifically includes: for each activity period, calculating the area of ​​the weighted confidence ellipse as the scale index of the potential activity space; for each activity period, calculating the eccentricity of the weighted confidence ellipse as the shape index of the potential activity space; and arranging the scale index and shape index of each activity period in ascending order of time to form a set of overall evolution characteristics of the potential activity space.

[0010] As an optional implementation of the first aspect of this application, the step of performing spatial overlay analysis on the potential activity spaces of adjacent activity periods to determine the retained region, lost region, and newly added region of the potential activity space between adjacent activity periods specifically includes: performing a spatial intersection operation on the potential activity spaces of the first activity period and the potential activity spaces of the second activity period to obtain the retained region; performing spatial fusion and spatial erasure operations on the potential activity spaces of the two adjacent activity periods, with the erased region being the potential activity space of the second activity period, to obtain the lost region; and performing spatial fusion and spatial erasure operations on the potential activity spaces of the two adjacent activity periods, with the erased region being the potential activity space of the first activity period, to obtain the newly added region.

[0011] As an optional implementation of the first aspect of this application, the step of extracting the process evolution characteristics of the potential activity space of urban residents further includes: calculating the area of ​​the preserved area, the area of ​​the lost area, and the area of ​​the newly added area respectively; subtracting the area of ​​the newly added area from the area of ​​the lost area to obtain the total area of ​​change; and forming a set of process evolution characteristics that includes the area of ​​the preserved area, the area of ​​the lost area, the area of ​​the newly added area, and the total area of ​​change.

[0012] As an optional implementation of the first aspect of this application, the step of deleting abnormal jump records specifically includes: sequentially calculating the speed between adjacent signaling records; setting a speed threshold; if the speed is greater than the speed threshold, deleting the next signaling record; and continuing to calculate the speed between the signaling record before deletion and the next signaling record after deletion, comparing it with the speed threshold; if it is less than the speed threshold, retaining it, otherwise continuing to delete; repeating the above process until all abnormal jump points are deleted.

[0013] Secondly, embodiments of this application provide a system for extracting the spatial evolution features of potential urban residents' activities, including: The data acquisition and preprocessing module is used to acquire raw mobile phone signaling data, preprocess the raw mobile phone signaling data to identify multiple key activity dwell points, and obtain a key activity dwell point trajectory queue. The potential activity space measurement module is used to divide the trajectory queue of the key activity dwell points into at least two activity periods based on the time period or event inflection point, and for each activity period, to construct a potential activity space measurement model based on the key activity dwell points in the activity period, and measure the potential activity space corresponding to the activity period. The overall evolution feature extraction module is used to calculate the scale and shape indicators of the potential activity space during different activity periods, and extract the overall evolution features of the potential activity space of urban residents. The process evolution feature extraction module is used to perform spatial overlay analysis on the potential activity space of adjacent activity periods, determine the retained area, lost area and newly added area of ​​potential activity space between adjacent activity periods, and extract the process evolution features of urban residents' potential activity space.

[0014] Thirdly, embodiments of this application provide an electronic device, which includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor. When the program or instructions are executed by the processor, they implement the steps of the method described in the first aspect.

[0015] Fourthly, embodiments of this application provide a readable storage medium on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described in the first aspect.

[0016] Compared with the prior art, the beneficial effects of the present invention include: (1) It utilizes the wide coverage, low collection cost, and strong time continuity of mobile signaling data to replace expensive and time-consuming manual questionnaire surveys. This makes it possible to conduct long-term and dynamic monitoring of the activity space of the entire city or a large-scale population, greatly reducing the cost of data acquisition and improving the efficiency and coverage of analysis.

[0017] (2) By deduplicating and de-anomalyizing the original signaling data (especially deleting abnormal jump points based on speed thresholds) and identifying key dwelling points based on spatiotemporal thresholds, high-quality dwelling point information that can truly reflect the residents' activity intentions can be effectively extracted from the massive, low-value-density original data. Noise data such as traffic transit points are filtered out, providing a solid data foundation for the accuracy of subsequent activity space measurement.

[0018] (3) The confidence ellipse method can not only locate the center of the activity space, but also quantitatively describe the activity space from two new dimensions, namely "how big" and "what shape", by calculating the area (scale index) and eccentricity (shape index) of the ellipse. Compared with the traditional one-dimensional indexes such as activity distance and frequency, this provides richer and more vivid spatial morphological information (for example, whether the activity space is a compact circle or a narrow elongated shape distributed along the traffic corridor), and realizes a high-dimensional characterization of the activity space.

[0019] (4) When constructing the confidence ellipse, the “duration of stay” of key activity points is used as the weight, so that activity points with longer stay times and higher importance (such as home and workplace) have a greater impact on the shape and central location of the final activity space. This weighting method is more reflective of the subjective importance distribution of residents’ activity space than undifferentiated trajectory point set analysis, making the measured potential activity space model closer to residents’ actual perception and behavior patterns.

[0020] (5) Through operations such as spatial intersection, spatial fusion, and spatial erasure, this invention decomposes the abstract "spatial change" into three specific and quantifiable spatial entities: the retained region, the lost region, and the newly added region. This allows the analysis to move beyond vague overall conclusions of "it has become larger" or "it has become smaller," and instead accurately answer procedural questions such as "which core regions remain unchanged," "which regions have become unreachable (lost)," and "which new regions have been developed (added)."

[0021] (6) Based on the calculation of the area of ​​retained, lost, and newly added areas, this invention can generate a series of process evolution characteristic indicators. For example, after extreme events such as rainstorms, by analyzing the distribution and scale of "lost areas," the extent of paralysis of urban transportation networks or public facilities can be quickly assessed; by analyzing "newly added areas," alternative activity centers formed by residents to cope with disasters can be discovered. This quantification of the evolution "process" provides unprecedentedly refined and traceable data support for urban emergency management, resilience assessment, and dynamic planning. Attached Figure Description

[0022] Figure 1 This is a flowchart of a method for extracting the potential activity space evolution characteristics of urban residents according to an embodiment of the present invention; Figure 2 This is a schematic diagram of travel activity trajectories based on key activity stay points in an embodiment of the present invention; Figure 3 This is a schematic diagram of the potential activity space across multiple time periods in an embodiment of the present invention; Figure 4 This is a schematic diagram of the potential activity space of different activity periods overlaid in an embodiment of the present invention; Figure 5This is a schematic diagram of the structure of a system for extracting the potential activity space evolution features of urban residents, provided in an embodiment of the present invention. Detailed Implementation

[0023] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0024] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0025] Example 1 Please see Figure 1 This is a flowchart illustrating a method for extracting the potential spatial evolution features of urban residents, provided by an embodiment of the present invention. The method may include the following steps: S1: Obtain raw mobile phone signaling data, preprocess the raw mobile phone signaling data to identify multiple key activity dwell points, and obtain a key activity dwell point trajectory queue.

[0026] Step S1 specifically includes: Step S11: Delete duplicate and abnormal records in the original mobile phone signaling data to generate a valid trajectory queue; the abnormal records include records with missing information and records with abnormal jumps.

[0027] (1) Delete duplicate records. Obtain the original mobile signaling data. Each user has a unique identifier code, and in traditional communication networks, there is usually only one record of interaction with the base station at any given time. The user's location is determined by the coordinates of the base station. When a user has multiple records of interaction with the base station at a certain time, it is considered a duplicate record. In this case, only the first record is retained, and the other duplicate records are deleted.

[0028] (2) Delete abnormal records. Abnormal records mainly include two categories: First, some records have missing information, such as missing base station location or time information, which are abnormal records and should be deleted directly. Second, some records have abnormal jumps, which are also abnormal records and should be deleted directly. Calculate the speed between adjacent signaling records in sequence to identify abnormal jump points.

[0029] in, This represents the speed between the i-th and (i+1)-th signaling records. This represents the distance between the i-th and (i+1)-th signaling records. This represents the time difference between the i-th and (i+1)-th signaling records.

[0030] For example, setting a speed threshold ,like Greater than If the signaling record is not found to be true, then delete the (i+1)th signaling record. Continue to calculate the speed between the ith and (i+2)th signaling records and compare it with the speed threshold. In comparison, if less than If the signaling record is correct, then retain the (i+2)th signaling record; otherwise, delete it and continue the calculation. Repeat the above process, traversing all signaling records, until all jump points are deleted.

[0031] (3) Generate an effective trajectory queue. After deleting duplicate and abnormal records, sort the signaling records of each user in ascending order according to the time of interaction with the base station. Take the time of interaction of the next signaling record with the base station as the end time of the previous signaling record and calculate the dwell time of each trajectory point.

[0032] in, This represents the dwell time at the i-th trajectory point. This indicates the interaction time between the i-th signaling record and the base station. This indicates the interaction time between the (i+1)th signaling record and the base station.

[0033] Iterate through all signaling records for each user in turn to generate a valid trajectory queue.

[0034] in, This represents the trajectory queue of the k-th user. () represents the coordinates of the nth base station. This indicates the start time of the interaction between the nth trajectory point and the base station. This indicates the end time of the interaction between the nth trajectory point and the base station. This represents the dwell time of the nth trajectory point.

[0035] Step S12: Merge adjacent trajectory points in the effective trajectory queue based on the distance threshold to generate multiple candidate active dwell points.

[0036] Using each user trajectory queue generated in step S11, the distance between adjacent trajectory points is calculated sequentially. For example, setting a distance threshold. m, starting from the first trajectory point, iterates through the points. If the distance between adjacent trajectory points is... Less than If any of these points are not found in the original trajectory, they are merged into the same subset of trajectories, and this subset is replaced with a candidate active dwell point. This process is repeated for all trajectory points until all candidate active dwell points are generated. Each candidate active dwell point... The coordinates are the average coordinates of all trajectory points in the corresponding subset, the start time is the start time of the first trajectory point in the corresponding subset, the end time is the end time of the last trajectory point in the corresponding subset, and the dwell time is the sum of the dwell times of all trajectory points in the corresponding subset.

[0037] in,( , () indicates the candidate activity's location. coordinates Indicates the candidate activity's location Duration of stay, ( , () represents the coordinates of the j-th trajectory point in the i-th subset. This represents the dwell time of the j-th trajectory point in the i-th subset. This represents the number of trajectory points in the i-th subset.

[0038] Step S13: Filter the candidate activity dwell points based on the time threshold, identify the candidate activity dwell points with a dwell time greater than the time threshold as key activity dwell points, and generate the trajectory queue of the key activity dwell points.

[0039] For example, setting a time threshold min, if candidate activity dwell point Duration of stay Greater than The activity's rest point will be... Identify it as a key activity dwell point and add it to the queue of key activity dwell points for the user. Otherwise, it is considered a waypoint and discarded. Repeatedly iterate through all candidate activity dwell points for each user, filter out all key activity dwell points, and generate a key activity dwell point trajectory queue.

[0040] in, This represents the key activity dwell point trajectory queue for the k-th user. () represents the coordinates of the nth critical activity's location. This indicates the start time of the nth critical activity's dwell point. This indicates the termination time of the nth critical activity's dwell point. This represents the duration of stay at the nth key activity location.

[0041] In summary, based on distance and time thresholds, by merging nearby trajectory points and removing waypoints, key activity dwell points are identified. All key activity dwell points for each user are then filtered out, generating a key activity dwell point trajectory queue, such as... Figure 2 As shown.

[0042] S2: Based on the time cycle or event inflection point, the trajectory queue of the key activity dwell points is divided into at least two activity periods. For each activity period, a potential activity space measurement model is constructed based on the key activity dwell points within the activity period to measure the potential activity space corresponding to the activity period.

[0043] Step S2 specifically includes: Step S21: Assign each key activity dwell point to the corresponding activity time period based on its time period, such as... Figure 3 As shown.

[0044] Based on time cycles, such as daily, weekly, or monthly cycles, or event inflection points, such as the start and end times of a rainstorm event, the research time is divided into multiple activity periods.

[0045] in, Indicates the overall research period. This represents the nth activity period. This indicates the start time of the nth activity period. This indicates the end time of the nth activity period. This represents the duration of the nth activity period, where n represents the number of activity periods.

[0046] For each key activity location Calculate the dwell points of key activities The intersection with multiple activity time periods. Specifically, if its time period falls entirely within the i-th activity time period. ,Right now and This will directly identify the key activity locations. Included in the activity period If key activity locations The time period is part of the i-th activity period. ,Right now and ,or and This will be the key activity location. Part of the time period or Included in the activity period If key activity locations The time period covers the i-th activity period. ,Right now and This will be the key activity location. Activity duration Modified to Then it will be included in the activity period. .

[0047] Iterate through all critical activity dwell points and assign them to their corresponding activity time periods to generate a critical activity dwell point queue covering each activity time period of the event process.

[0048] in, This represents the k-th user activity period. All key activity locations within the area, ( () indicates the activity period The coordinates of the nth key activity's location within the area. Indicates the activity period Duration of stay at the nth key activity location, where n represents the activity period. The number of key activity sites within the country.

[0049] Step S22: For each activity period, calculate the potential activity space using the weighted confidence ellipse method.

[0050] For each activity period, utilize the key activity dwell point queue generated in step S21. According to the activity period The spatial distribution and duration of stay at all key activity locations within the area are analyzed to construct a potential activity space measurement model. Generally, the weighted confidence ellipse method is used to calculate the potential activity space, specifically including: (1) Calculate the central location of the potential activity space based on the spatial distribution and dwell time of all key activity points during the activity period. The central location is determined by the activity period. The weighted average position of all key activity locations within the organization is determined.

[0051] in,( , () indicates the activity period The central location of the potential activity space, ( () indicates the activity period The coordinates of the j-th critical activity's location. Indicates the activity period The duration of stay at the j-th key activity location, where n represents the activity time period. The number of key activity sites within the country.

[0052] (2) Calculate the activity period The covariance matrix corresponding to the spatial distribution of all key activity points within the potential activity space is calculated, and eigenvalues ​​and corresponding eigenvectors are calculated based on the covariance matrix. Then, the length of the major semi-axis of the potential activity space is determined by using the confidence probability and the larger eigenvalue, and the length of the minor semi-axis of the potential activity space is determined by using the confidence probability and the smaller eigenvalue.

[0053] in, Indicates the activity period The covariance matrix generated from the spatial distribution of all key activity points within the area, () indicates the activity period The coordinates of the j-th critical activity's location. Indicates the activity period The duration of stay at the j-th key activity location, where n represents the activity time period. The number of key activity sites within the country, Indicates the activity period The set of eigenvalues, Indicates the activity period The set of feature vectors, This represents a function that calculates eigenvalues ​​and eigenvectors based on the covariance matrix. Indicates the activity period The length of the major semi-axis of the potential activity space. Indicates the activity period The length of the short semi-axis of the potential activity space. This represents the chi-square value corresponding to the confidence probability, which is usually set to 95%. =5.991.

[0054] (3) Calculate the rotation angle (intersection with the X-axis) of the potential activity space based on the eigenvector corresponding to the larger eigenvalue.

[0055] in, Indicates the activity period Potential activity space rotation angle (angle with the X-axis), _ _ [0], _ _ [1] indicates the activity period The eigenvector corresponding to the larger eigenvalue takes the value of .

[0056] Specifically, during the event period When the number of critical activity dwell points is 1, the potential activity space is defined as a circular area centered on that critical activity dwell point, with a radius of [value missing]. m; during the activity period When the number of critical activity dwell points is 2, the potential activity space is defined as the union of circular ranges centered at each of the two critical activity dwell points, with the radius taking a value of [value missing]. m; during the activity period When the number of critical activity dwelling points within the area is greater than or equal to 3, the potential activity space is calculated using the method described above.

[0057] Step S23: Calculate the potential activity space for different activity periods. For each activity period... Utilizing different time periods Internal key activity station queue Calculate the potential activity space They are then sorted in ascending order according to the activity period to form a queue of potential activity spaces for each period.

[0058] in, This represents the queue of potential activity space for user k at different time periods. Indicates the activity period The potential activity space, where n represents the number of activity periods.

[0059] S3: Calculate the scale and shape indicators of the potential activity space during different activity periods, and extract the overall evolution characteristics of the potential activity space of urban residents.

[0060] Step S3 specifically includes: Step S31: For each activity period, calculate the area of ​​the weighted confidence ellipse as a size index of the potential activity space; for each activity period, calculate the eccentricity of the weighted confidence ellipse as a shape index of the potential activity space, such as... Figure 4 As shown.

[0061] From an overall perspective, the area and eccentricity of the weighted confidence ellipse for each activity period are calculated to characterize the scale and shape of the potential activity space for each activity period.

[0062] in, Indicates the activity period The potential activity space size, Indicates the activity period Potential activity space form, Indicates the activity period The length of the major semi-axis of the potential activity space. Indicates the activity period The length of the short semi-axis of the potential activity space.

[0063] Specifically, during the event period When the number of key activity dwelling points within the area is 1, the potential activity space size index is... The area of ​​a single circular region is equal to 0.19625 km². 2 morphology index It is 0.

[0064] During the activity period When the number of key activity dwelling points within the space is 2, the morphological index of the potential activity space is... The scale index is 1. Let be the area of ​​the union of the two circular regions, with a value between 0.19625 km. 2 up to 0.3925 km 2 The distance between two key activity outposts can be used to determine this. Simplify calculations. When When m, then km 2 ;when m, using Estimated size index .

[0065] in, Indicates the activity period The distance between the two key activity bases within the area, This represents the radius of the circular region, which is 250m.

[0066] Step S32: Arrange the scale indicators and shape indicators of each activity period in ascending order of time to form a set of overall evolution characteristics of potential activity space.

[0067] in, This represents the set of overall evolutionary features of the potential activity space of user k. Indicates the activity period The potential activity space size and form, where n represents the number of activity periods.

[0068] S4: Perform spatial overlay analysis on the potential activity spaces of adjacent activity periods to determine the retained, lost, and newly added areas of potential activity spaces between adjacent activity periods, and extract the process evolution characteristics of urban residents' potential activity spaces.

[0069] Step S4 specifically includes: Step S41: Perform a spatial intersection operation on the potential activity space of the first activity period and the potential activity space of the second activity period to obtain the retained area; perform spatial fusion and spatial erasure operations on the potential activity spaces of the two adjacent activity periods, with the erased area being the potential activity space of the second activity period, to obtain the lost area; perform spatial fusion and spatial erasure operations on the potential activity spaces of the two adjacent activity periods, with the erased area being the potential activity space of the first activity period, to obtain the newly added area; in, , and These represent the activity periods. and The retention, loss, and addition of areas between them and These represent the activity periods. and Potential activity space, This represents the spatial intersection operation. This indicates a space erasure operation.

[0070] By sequentially overlaying and analyzing the potential activity spaces of the same resident during adjacent activity periods, a queue of areas where potential activity spaces are retained, lost, and newly added is formed in each activity period.

[0071] in, A queue representing the region where user k's potential activity space evolves between activity periods. Indicates the activity period and The regions to be retained, lost, and added, where n represents the number of activity periods.

[0072] Step S42: Calculate the area of ​​the retained region, the area of ​​the lost region, and the area of ​​the newly added region respectively; subtract the area of ​​the lost region from the area of ​​the newly added region to obtain the total area of ​​change; form a set of process evolution features that includes the area of ​​the retained region, the area of ​​the lost region, the area of ​​the newly added region, and the total area of ​​change.

[0073] in, Indicates the area to be reserved. Indicates the lost area. This indicates the newly added area. The area representing the overall change. A function that calculates area.

[0074] The area of ​​the retained, lost, and newly added areas of potential activity space during each activity period is calculated sequentially, as well as the area that changes, to form a set of process evolution characteristics of the potential activity space of urban residents.

[0075] = in, This represents the set of process evolution characteristics of the potential activity space of urban residents for user k. Indicates the activity period and The process evolution characteristics of the potential activity space between them, where n represents the number of activity periods.

[0076] Example 2 Please see Figure 5 The diagram shown is a schematic representation of a system for extracting the potential spatial evolution features of urban residents according to a second embodiment of this application. The system includes the following key modules: The data acquisition and preprocessing module 100 is used to acquire raw mobile phone signaling data, preprocess the raw mobile phone signaling data to identify multiple key activity dwell points, and obtain a key activity dwell point trajectory queue. The potential activity space measurement module 200 is used to divide the trajectory queue of the key activity dwell points into at least two activity periods according to the time period or the event inflection point, and for each activity period, construct a potential activity space measurement model based on the key activity dwell points in the activity period to measure the potential activity space corresponding to the activity period. The overall evolution feature extraction module 300 is used to calculate the scale and shape indicators of the potential activity space during different activity periods and extract the overall evolution features of the potential activity space of urban residents. The process evolution feature extraction module 400 is used to perform spatial overlay analysis on the potential activity space of adjacent activity periods, determine the retained area, lost area and newly added area of ​​potential activity space between adjacent activity periods, and extract the process evolution features of potential activity space of urban residents.

[0077] The system for extracting the potential activity space evolution features of urban residents in this application embodiment can be a device, or a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. For example, mobile electronic devices can be mobile phones, tablets, laptops, PDAs, in-vehicle electronic devices, wearable devices, ultra-mobile personal computers (UMPCs), netbooks, or personal digital assistants (PDAs), etc., while non-mobile electronic devices can be servers, network attached storage (NAS), personal computers (PCs), etc., and this application embodiment does not specifically limit the scope.

[0078] The system for extracting the potential activity space evolution features of urban residents in this application embodiment can be a device with an operating system. This operating system can be Android, iOS, or other possible operating systems; this application embodiment does not specifically limit it.

[0079] This application provides a system for extracting the evolution features of potential activity spaces of urban residents, which can achieve... Figure 1 The various processes implemented by the method embodiment of the method for extracting the potential activity space evolution features of urban residents will not be described in detail here to avoid repetition.

[0080] Optionally, embodiments of this application also provide an electronic device, including a processor, a memory, and a program or instructions stored in the memory and executable on the processor. When the program or instructions are executed by the processor, they implement the various processes of the above-described embodiment of the method for extracting potential activity space evolution features of urban residents, and can achieve the same technical effect. To avoid repetition, they will not be described again here.

[0081] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described embodiment of the method for extracting the potential activity space evolution features of urban residents, and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0082] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0083] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0084] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0085] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A method for extracting the evolutionary characteristics of potential activity spaces of urban residents, characterized in that, Includes the following steps: The original mobile phone signaling data is acquired and preprocessed to identify multiple key activity dwell points, thereby obtaining a key activity dwell point trajectory queue. Based on time cycles or event inflection points, the trajectory queue of key activity dwell points is divided into at least two activity periods. For each activity period, a potential activity space measurement model is constructed based on the key activity dwell points within that activity period to measure the potential activity space corresponding to that activity period. Specifically, this includes: assigning each key activity dwell point to the corresponding activity period according to its time period; for each activity period, calculating the potential activity space using a weighted confidence ellipse method, which includes: calculating the center position of the potential activity space based on the spatial distribution and dwell time of all key activity dwell points within the activity period, wherein the center position is determined by the weighted average position of all key activity positions within the activity period; calculating the covariance matrix corresponding to the spatial distribution of all key activity points within the activity period, and calculating eigenvalues ​​and corresponding eigenvectors based on the covariance matrix; determining the length of the major semi-axis of the potential activity space using confidence probabilities and the larger eigenvalue, and determining the length of the minor semi-axis of the potential activity space using the confidence probabilities and the smaller eigenvalue; and calculating the rotation angle of the potential activity space based on the eigenvector corresponding to the larger eigenvalue. Calculate the scale and shape indices of the potential activity space during different activity periods, and extract the overall evolution characteristics of the potential activity space of urban residents; Spatial overlay analysis is performed on the potential activity spaces of adjacent activity periods to determine the retained, lost, and newly added areas of potential activity spaces between adjacent activity periods, and to extract the process evolution characteristics of urban residents' potential activity spaces. Specifically, this includes: performing a spatial intersection operation on the potential activity spaces of the first activity period and the second activity period to obtain the retained area; performing spatial fusion and spatial erasure operations on the potential activity spaces of the two adjacent activity periods, with the erased area being the potential activity space of the second activity period, to obtain the lost area; and performing spatial fusion and spatial erasure operations on the potential activity spaces of the two adjacent activity periods, with the erased area being the potential activity space of the first activity period, to obtain the newly added area.

2. The method according to claim 1, characterized in that, The steps of acquiring raw mobile phone signaling data, preprocessing the raw mobile phone signaling data to identify multiple key activity dwell points, and obtaining a key activity dwell point trajectory queue specifically include: Delete duplicate and abnormal records from the original mobile signaling data to generate a valid trajectory queue; the abnormal records include records with missing information and records with abnormal jumps; Based on a distance threshold, adjacent trajectory points in the effective trajectory queue are merged to generate multiple candidate active dwell points; Candidate activity dwell points are filtered based on a time threshold. Candidate activity dwell points with a dwell time greater than the time threshold are identified as key activity dwell points, and a trajectory queue of the key activity dwell points is generated.

3. The method according to claim 1, characterized in that, The steps of calculating the scale and shape indices of the potential activity space during different activity periods and extracting the overall evolution characteristics of the potential activity space of urban residents specifically include: For each activity period, the area of ​​the weighted confidence ellipse is calculated as a size index of the potential activity space; For each activity period, the eccentricity of the weighted confidence ellipse is calculated as a shape index of the potential activity space; The scale and shape indicators for each activity period are arranged in ascending order of time to form a set of overall evolutionary characteristics of the potential activity space.

4. The method according to claim 1, characterized in that, The step of extracting the process evolution characteristics of potential activity spaces of urban residents also includes: Calculate the area of ​​the retained region, the area of ​​the lost region, and the area of ​​the newly added region, respectively. Subtract the area of ​​the newly added region from the area of ​​the lost region to obtain the total area of ​​change; A set of procedural evolutionary features is formed, comprising the area of ​​the retained region, the area of ​​the lost region, the area of ​​the newly added region, and the area of ​​the overall change.

5. The method according to claim 2, characterized in that, The step of deleting records with abnormal jumps specifically includes: Calculate the rate between adjacent signaling records sequentially; Set a speed threshold; if the speed exceeds the speed threshold, delete the next signaling record. The system continues to calculate the speed between the signaling record before deletion and the next signaling record after deletion, and compares it with the speed threshold. If the speed is less than the speed threshold, the record is retained; otherwise, deletion continues. Repeat the above process until all abnormal jump points are deleted.

6. A system for extracting the potential spatial evolution characteristics of urban residents' activities, characterized in that, include: The data acquisition and preprocessing module is used to acquire raw mobile phone signaling data, preprocess the raw mobile phone signaling data to identify multiple key activity dwell points, and obtain a key activity dwell point trajectory queue. The potential activity space measurement module is used to divide the trajectory queue of the key activity dwell points into at least two activity periods based on the time period or event inflection point, and for each activity period, to construct a potential activity space measurement model based on the key activity dwell points in the activity period, and measure the potential activity space corresponding to the activity period. The overall evolution feature extraction module is used to calculate the scale and shape indicators of the potential activity space during different activity periods, and extract the overall evolution features of the potential activity space of urban residents. The process evolution feature extraction module is used to perform spatial overlay analysis on the potential activity space of adjacent activity periods, determine the retained area, lost area and newly added area of ​​potential activity space between adjacent activity periods, and extract the process evolution features of urban residents' potential activity space.

7. An electronic device, characterized in that, It includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor. When the program or instructions are executed by the processor, they implement the steps of the method for extracting the potential spatial evolution characteristics of urban residents as described in any one of claims 1-5.

8. A readable storage medium, characterized in that, The program or instructions are stored on the readable storage medium, and when the program or instructions are executed by the processor, they implement the steps of the method for extracting the potential activity space evolution characteristics of urban residents as described in any one of claims 1-5.

Images