General learning behavior identification method, system and device and storage medium

Abstract

The invention discloses a general learning behavior identification method, system and device and a storage medium. The method comprises the following steps: acquiring mobile phone signaling data and school AOI data, and preprocessing the mobile phone signaling data and the school AOI data; determining a fixed resident object based on the school and a type corresponding to the fixed resident object according to the mobile phone signaling data and the school AOI data; the type is a type corresponding to a geographic grid visited or resided by the object; and according to the type and the basic information of the object, based on a preset classification strategy, determining the crowd type of the object, and a starting point and an ending point of a general learning behavior. The method comprises the following steps: determining an object residence type in combination with large-scale mobile phone signaling data and school AOI data; and the crowd types and the general learning behaviors are finely divided, so that the fine degree of crowd identification can be improved. The method can be widely applied to the technical field of urban traffic planning.

Description

Technical Field

[0001] The present invention relates to the technical field of urban traffic planning, and in particular to a method, system, device and storage medium for identifying school commuting behavior. Background Art

[0002] With the development of big data and mobile communication technology, mobile phone signaling data has become an important resource for studying population mobility, urban activities and travel patterns. Due to its advantages such as wide coverage, strong real-time performance and relatively low cost, it is widely used in transportation planning, urban planning and other fields.

[0003] In the related technologies, some solutions have proposed methods for identifying people’s travel based on mobile phone signaling data, such as identifying unemployed people through users’ mobile phone signaling data, extracting travel chains of urban residents, identifying population residence migration, and describing the work-residence and travel chains of travelers. These methods usually involve steps such as data collection, feature extraction, and cluster analysis, and use machine learning and data mining techniques to process and analyze data. However, these technical solutions often focus on a single data source or a single application scenario, and lack the comprehensive use of multi-source data. In addition, in the solutions for school-residence identification, the existing technical solutions mainly use small data methods such as questionnaires for identification, which cannot perform large-scale and wide-range identification and analysis, and there is no detailed classification of school visitors. Summary of the invention

[0004] The purpose of the present invention is to provide a sophisticated method, system, device and storage medium for identifying school commuting behavior.

[0005] On the one hand, the present application provides a method for identifying school commuting behavior, the method comprising: obtaining mobile phone signaling data and school AOI data, and preprocessing the mobile phone signaling data and the school AOI data; determining fixed resident objects based on the school and the types corresponding to the fixed resident objects according to the mobile phone signaling data and the school AOI data; the types are types corresponding to the geographical grids visited or resided by the objects; according to the types and the basic information of the objects, based on a preset classification strategy, the crowd category of the objects, the starting point and the end point of the school commuting behavior are determined. The present application combines large-scale mobile phone signaling data and school AOI data to determine the resident type of the objects; and then finely divides the crowd categories and school commuting behaviors, which is conducive to improving the precision of crowd identification.

[0006] Optionally, determining the school-based fixed resident objects and their corresponding types according to the mobile phone signaling data and the school AOI data includes:

[0007] Setting a hierarchical buffer zone of the school; the hierarchical buffer zone is used to make the area of ​​the school larger than the extraction accuracy of the mobile phone signaling;

[0008] creating a geographic grid based on each of the schools and the grading buffers;

[0009] Traversing the mobile phone signaling data, mapping the signaling trajectory points to the geographic grid, and obtaining the visit data of each of the objects to the school;

[0010] The fixed resident object and its type are determined according to the access data.

[0011] Optionally, determining the fixed resident object and the type according to the access data includes:

[0012] According to the access data, within a preset time period, objects whose access and residence frequency to the school is greater than or equal to a preset frequency are screened out and regarded as fixed residence objects;

[0013] According to the access data of the fixed resident objects to the school, it is determined whether the first grid, the second grid and the third grid corresponding to each object are located in the school area; the first grid, the second grid and the third grid are the residence characteristics of the fixed resident objects on weekdays and non-working days.

[0014] Optionally, according to the type and basic information of the object, based on a preset classification strategy, determining the crowd category, the starting point and the end point of the commuting behavior of the object includes:

[0015] If the first grid and the second grid are the same, the first grid and the second grid both belong to the school area, and the age of the fixed resident object is greater than or equal to the first preset age, determining that the fixed resident object is a boarding student;

[0016] If the first grid belongs to the school area, the second grid does not belong to the school area, and the age of the fixed resident object is greater than or equal to a first preset age, determining that the fixed resident object is a day student;

[0017] If the first grid belongs to the school area, the fixed resident object uses at least one teacher-related application, and the age of the fixed resident object is greater than or equal to a second preset age, determining that the fixed resident object is a teacher;

[0018] If the first grid does not belong to the school area, the visit time of the fixed resident object to the school is within the preset time period and the age of the fixed resident object is greater than or equal to the second preset age, it is determined that the fixed resident object is a parent; the first grid is the grid where the fixed resident object stays the longest during the daytime on weekdays, and the second grid is the grid where the fixed resident object stays the longest at night on weekdays.

[0019] Optionally, the identification method of the present application further includes:

[0020] Determine that the area where the third grid of the boarding student is located is the residence, the area where the second grid or the third grid of the day student is located is the residence, the area where the second grid or the third grid of the teacher is located is the residence, the area where the first grid of the parent is located is the workplace, and the area where the second grid or the third grid of the parent is located is the residence; the third grid is the grid where the fixed resident object stays the longest on non-working nights.

[0021] Optionally, the identification method of the present application further includes:

[0022] The schools are divided based on the school system, and the school commuting behaviors of the schools with different school systems are displayed according to the starting points and end points of the school commuting behaviors of all the subjects;

[0023] Alternatively, the schools are divided based on teaching quality, and the school commuting behaviors of the schools with different teaching qualities are displayed according to the starting points and end points of the school commuting behaviors of all the subjects.

[0024] Optionally, preprocessing the mobile phone signaling data and the school AOI data includes:

[0025] Acquire all the school AOI data and text data related to the school;

[0026] The text data is understood through natural language processing to determine basic information about the school.

[0027] On the other hand, an embodiment of the present invention provides a school commuting behavior recognition system, the system comprising:

[0028] The first model is used to obtain mobile phone signaling data and school AOI data, and pre-process the mobile phone signaling data and the school AOI data;

[0029] A second model is used to determine, based on the mobile phone signaling data and the school AOI data, a fixed resident object based on the school and its corresponding type; the type is a type corresponding to a geographical grid visited or resident by the object;

[0030] The third model is used to determine the population category, the starting point and the end point of the commuting behavior of the object based on the type and the basic information of the object and a preset classification strategy.

[0031] On the other hand, an embodiment of the present invention provides a device for identifying commuting behavior, the device comprising:

[0032] at least one processor;

[0033] at least one memory for storing at least one program;

[0034] When the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned method for identifying school commuting behavior.

[0035] On the other hand, an embodiment of the present invention provides a storage medium, in which a program executable by a processor is stored. When the program executable by the processor is executed by the processor, it is used to implement the above-mentioned method for identifying school commuting behavior.

[0036] The method provided by the embodiment of the present invention includes: obtaining mobile phone signaling data and school AOI data, and preprocessing the mobile phone signaling data and the school AOI data; determining the fixed resident objects based on the school and the types corresponding to the fixed resident objects according to the mobile phone signaling data and the school AOI data; the types are the types corresponding to the geographical grids visited or resided by the objects; according to the types and the basic information of the objects, based on the preset classification strategy, the crowd category of the objects, the starting point and the end point of the school commuting behavior are determined. The present application combines large-scale mobile phone signaling data and school AOI data to determine the resident type of the objects; and then finely divides the crowd categories and school commuting behaviors, which is conducive to improving the precision of crowd identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the embodiments of the present invention or the drawings of related technical solutions in the prior art are introduced below. It should be understood that the drawings introduced below are only for the convenience of clearly describing some embodiments of the technical solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0038] Figure 1 A schematic diagram of a flow chart of an embodiment of a method for identifying school commuting behavior provided by the present invention;

[0039] Figure 2 A schematic diagram of a flow chart of another embodiment of the method for identifying school commuting behavior provided by the present invention;

[0040] Figure 3 A schematic diagram of a flow chart of an embodiment of the crowd segmentation and school commuting behavior recognition provided by the present invention;

[0041] Figure 4 A schematic diagram of the structure of an embodiment of the school commuting behavior recognition system provided by the present invention;

[0042] Figure 5 This is a schematic diagram of the structure of an embodiment of the school commuting behavior recognition device provided by the present invention. DETAILED DESCRIPTION

[0043] The embodiments of the present invention are described in detail below, and examples of the embodiments 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 invention, and are not to be construed as limitations of the present invention. For the step numbers in the following embodiments, they are only provided for the convenience of explanation, and the order between the steps is not limited in any way, and the execution order of each step in the embodiment can be adaptively adjusted according to the understanding of those skilled in the art.

[0044] With the development of big data and mobile communication technology, mobile phone signaling data has become an important resource for studying population mobility, urban activities and travel patterns. Due to its wide coverage, strong real-time performance and relatively low cost, it has been widely used in transportation planning, urban planning, socio-economic analysis and other fields. Among the existing technical solutions, some solutions have proposed crowd travel identification methods based on mobile phone signaling data, such as identifying unemployed people through user mobile phone signaling data, extracting the travel chain of urban residents, identifying population residence migration, and characterizing the work residence and travel chain of travelers. These methods usually involve steps such as data collection, feature extraction, and cluster analysis, and use machine learning and data mining techniques to process and analyze data. However, these technical solutions often focus on a single data source or a single application scenario, lacking the comprehensive use of multi-source data, such as vector geographic information data (AOI, POI), which limits the ability in refined identification. In the scheme for school-residence identification, the existing technical scheme mainly uses small data methods such as questionnaires for identification. There is no mature multi-source spatiotemporal big data method such as mobile phone signaling for large-scale and wide-range identification and analysis, nor is there a detailed classification of school visitors (such as teachers, parents of students, day / boarding students, etc.). Specifically, the relevant technology has the following problems:

[0045] (1) Single data source:

[0046] Existing technologies for crowd travel identification mainly rely on single mobile phone signaling data and fail to make full use of other data sources such as school AOI data, resulting in the inability to comprehensively and accurately identify the daily activities and off-campus living conditions of student groups.

[0047] (2) Insufficient spatial and temporal coverage:

[0048] Existing solutions for identifying student groups are mainly through field questionnaire surveys and other methods. The data obtained have a small coverage and poor timeliness, making it impossible to conduct large-scale and wide-ranging identification and analysis.

[0049] (3) Insufficient recognition accuracy:

[0050] The accurate identification methods for student groups, especially the students’ family residence and school locations, are still immature, and there is a lack of in-depth analysis of the characteristics of student groups.

[0051] (4) The classification is not detailed enough:

[0052] There is no detailed classification of school visitors, making it difficult to distinguish between people of different identities, such as teachers, parents, boarding students and day students, resulting in bias in the identification of student groups.

[0053] The present invention aims to make up for the shortcomings of the existing technology. By combining mobile phone signaling data and school AOI data, it can realize the accurate identification of students' family residence and place of study, as well as the refined classification of school visitors. This method not only improves the accuracy and real-time performance of identification, but also expands the scope of application, so that fields such as education management, urban planning and transportation planning can obtain more accurate data support. Compared with the existing technology, the present invention provides a more comprehensive and in-depth analysis method by integrating multi-source data, especially in the subdivision of school visitor types and the identification of student residences, achieving technological progress and innovation.

[0054] The following describes in detail a method and system for identifying commuting behavior according to an embodiment of the present invention with reference to the accompanying drawings. First, the method for identifying commuting behavior according to an embodiment of the present invention will be described with reference to the accompanying drawings.

[0055] Reference Figure 1 In an embodiment of the present invention, a method for identifying school commuting behavior is provided, and the method mainly comprises the following steps:

[0056] S100: obtaining mobile phone signaling data and school AOI data, and preprocessing the mobile phone signaling data and school AOI data;

[0057] S200: Determine the fixed resident objects based on the school and their corresponding types according to the mobile phone signaling data and the school AOI data; the type is the type corresponding to the geographical grid where the object visits or resides;

[0058] S300: According to the type and basic information of the object, based on a preset classification strategy, determine the population category of the object, the starting point and the end point of the school commuting behavior.

[0059] In some possible implementations, the present application screens and determines fixed resident objects based on each school based on mobile phone signaling data and school AOI data, and further determines the type corresponding to the geographical grid where the object visits or resides. The type can be the type corresponding to the grid where the object / user stays the longest within a preset time period. It is understandable that the preset classification strategy in the present application can be set according to the actual situation / characteristics of the school, and the present application does not make specific limitations. It should be noted that the objects in the present application can be terminal users or people related to visiting the school.

[0060] Optionally, according to the mobile phone signaling data and the school AOI data, the school-based fixed resident objects and their corresponding types are determined, including:

[0061] Set the school's hierarchical buffer zone; the hierarchical buffer zone is used to make the school's area larger than the extraction accuracy of mobile phone signaling;

[0062] Create a geographic grid based on individual schools and their grading buffers;

[0063] Traverse the mobile phone signaling data, map the signaling trajectory points to the geographic grid, and obtain the access data of each object to the school;

[0064] Based on the access data, the fixed resident objects and their types are determined.

[0065] In some possible implementations, the hierarchical buffer is used to prevent the school area from being too small and the mobile phone signaling trajectory from being accurately covered. This application screens the fixed resident objects whose residence times / durations meet the requirements based on the access data, and determines the type corresponding to each fixed resident object.

[0066] Optionally, according to the access data, the fixed resident object and its type are determined, including:

[0067] According to the access data, within the preset time period, select the objects whose access and residence frequency to the school is greater than or equal to the preset frequency, and regard them as fixed residence objects;

[0068] According to the access data of the fixed resident objects to the school, it is determined whether the first grid, the second grid and the third grid corresponding to each object are located in the school area; the first grid, the second grid and the third grid are the resident characteristics of the fixed resident objects on weekdays and non-workdays.

[0069] In some possible implementations, the preset duration may be one month, two months, or set according to actual needs, and the present application does not specifically limit this. The present application determines the types of the first grid, the second grid, and the third grid based on the access data. It is understandable that the first grid, the second grid, and the third grid are the number of grids corresponding to different situations of the types set by the present application based on general schools. Those skilled in the art can set the number of grids according to actual needs, and determine the school commuting behavior according to the type corresponding to the set grid.

[0070] Optionally, according to the type and basic information of the object, based on a preset classification strategy, the crowd category of the object, the starting point and the end point of the school commuting behavior are determined, including:

[0071] If the first grid and the second grid are the same, the first grid and the second grid both belong to the school area, and the age of the fixed resident object is greater than or equal to the first preset age, determining that the fixed resident object is a boarding student;

[0072] If the first grid belongs to the school area, the second grid does not belong to the school area, and the age of the fixed resident object is greater than or equal to the first preset age, it is determined that the fixed resident object is a day student;

[0073] If the first grid belongs to a school area, the fixed resident object uses at least one teacher-related application, and the age of the fixed resident object is greater than or equal to the second preset age, determining that the fixed resident object is a teacher;

[0074] If the first grid does not belong to the school area, the visit time of the fixed resident object to the school is within the preset time period and the age of the fixed resident object is greater than or equal to the second preset age, it is determined that the fixed resident object is a parent; the first grid is the grid where the fixed resident object stays the longest during the daytime on weekdays, the second grid is the grid where the fixed resident object stays the longest at night on weekdays, and the third grid is the grid where the fixed resident object stays the longest at night on non-working days.

[0075] In some possible implementations, the present application determines the crowd category of the fixed resident object through logical judgment of the first grid, the second grid, and the third grid. Of course, those skilled in the art can also classify the crowd category according to other preset classification strategies.

[0076] Optionally, the identification method of the present application further includes:

[0077] Determine the area where the third grid is located for boarding students as the place of residence, the area where the second grid or third grid is located for day students as the place of residence, the area where the second grid or third grid is located for teachers as the place of residence, the area where the first grid is located for parents as the place of work, and the area where the second grid or third grid is located for parents as the place of residence; the third grid is the grid where the fixed resident objects stay the longest on non-working nights.

[0078] In some possible implementations, different areas are identified based on the areas where the first grid, the second grid, and the third grid are located corresponding to different population categories. The understanding of determining that the area where the second grid or the third grid of a teacher is located is as follows: if the first grid and the second grid are the same, the third grid is confirmed as the place of residence, and the first grid and the second grid are the school; if the first grid and the second grid are different, the second grid and / or the third grid is confirmed as the place of residence, and the first grid is the school.

[0079] Optionally, the identification method of the present application further includes:

[0080] Schools are divided based on the school system, and the school commuting behavior of all subjects is displayed according to the starting and ending points of the school commuting behavior of schools with different school systems;

[0081] Alternatively, schools can be divided based on their teaching quality, and the school attendance behaviors of schools with different teaching qualities can be displayed according to the starting and ending points of the school attendance behaviors of all subjects.

[0082] In some possible implementations, after different groups of people and their corresponding commuting behaviors are identified, the commuting behaviors of different types of schools are displayed graphically, so that different types of schools can be compared intuitively. Of course, for the visualization interface, the user can set the displayed content, and the corresponding graphical interface is displayed based on the user's settings.

[0083] Optionally, the mobile phone signaling data and the school AOI data are pre-processed, including:

[0084] Get all school AOI data and text data related to the school;

[0085] Use natural language processing to understand text data and determine the basic information of the school.

[0086] In some possible implementations, the basic information of the school may include the school system, teaching quality, etc.

[0087] The following is a detailed description of the method for identifying school commuting behavior provided by the present application using a specific embodiment:

[0088] The purpose of the present invention is to provide a method for accurately identifying school commuting behavior based on mobile phone signaling and school AOI data.

[0089] The present invention adopts a large sample of mobile phone signaling data from the entire region at the city scale, and comprehensively uses methods such as data cleaning, topology correction and geographic informatics, combined with school AOI data and the residence distribution, user attributes and travel behavior characteristics in the mobile phone signaling sampling process, to accurately identify the user's population category and school-residence information.

[0090] To achieve the above objectives, the present invention proposes a method for accurately identifying school commuting behavior based on mobile phone signaling and school AOI data, including: preprocessing of mobile phone signaling and school AOI data, identification of school fixed resident users, classification of commuting population, and school-residence discrimination.

[0091] Reference Figure 2 As shown, the basic steps of the present invention are as follows:

[0092] S1. Preprocessing of mobile phone signaling and school AOI data: including matching of basic information of mobile phone signaling users and classification and sorting of attributes of school AOI data;

[0093] S11. Prioritize obtaining mobile phone signaling data within the study area, and then obtain the basic attribute information of the corresponding mobile phone users from the operator, including user daily residence, monthly residence, travel behavior, age, number location, app usage, etc. (see the mobile phone signaling data classification description table shown in Table 1). The original data of mobile phone users obtained do not contain any personal privacy information.

[0094] S12. Use web crawler tools to collect AOI data of all schools in the study area from Baidu Maps, collect text data about schools from relevant websites, school official websites, online comments (such as relevant forums, social apps, sharing apps, etc.), use natural language processing to build a sentiment analysis model, process and understand text data, and classify and organize the basic attributes of AOI of different schools, including school name, school stage, school quality, and school nature. The details are as follows:

[0095] (1) Educational stage: divided into five categories: primary school, junior high school, senior high school, nine-year system, and twelve-year system;

[0096] (2) School quality: divided into four categories: top, good, average, and poor;

[0097] (3) Nature of school: divided into two categories: public and private.

[0098] Among them, the text records of attributes such as school name, grade and school nature are relatively intuitive and can be directly extracted through fixed vocabulary search, while the vocabulary expressions related to school quality evaluation are relatively vague and obscure, and need to be further analyzed through natural language processing models, and then corrected in combination with the reputation ranking of private parents. The specific steps are as follows:

[0099] S111. School name correction: Combined with the government school list in the study area, the school names in the school AOI data are compared and corrected, and the AOIs that do not exist in the government school list are removed;

[0100] S112. Text data collection: Take the school name as the keyword, conduct batch search on government websites, school official websites and other online platforms, and select text data that meet the requested keywords to form a text database that corresponds to the school name one by one;

[0101] S113. Text preprocessing: Clean and organize the collected text data, including screening of key semantic information, removal of stop words and word segmentation. The details are as follows:

[0102] (1) Determine whether each text data item in the text database contains key semantic information describing basic attributes such as school stage, school quality, and school nature. If so, retain the text data; if not, remove it;

[0103] (2) Processing the sentences in each text data by removing stop words to reduce some meaningless sentences and reduce the complexity of subsequent model training. The specific method of removing stop words is a public technology and will not be described in detail in this invention;

[0104] (3) Use the "Jieba" Chinese word segmentation tool to segment text sentences and split longer text sentences into shorter phrases.

[0105] S114. Feature extraction and word vector construction: Since the sentiment analysis model cannot directly process raw text data, the text needs to be converted into a numerical vector for model processing. The present invention uses the open source model GloVe developed by Stanford University to train text sentences to obtain the final dictionary and word vectors, including positive sentiment words, negative sentiment words, and neutral words. The training process of GloVe is also a public technology, and the present invention will not go into details;

[0106] S115. Sentiment analysis model selection and training: The present invention uses the LSTM deep network learning model as the sentiment analysis model for sentiment analysis. The model can capture the long-term dependencies in the text, thereby improving the accuracy of the model. The word vector constructed in the previous step is input into the LSTM model. The LSTM model processes the data through its neural network layer and finally outputs the sentiment classification, including positive evaluation, negative evaluation and neutral evaluation of the school quality. Similarly, sentiment analysis based on the LSTM model is a public mature technology, and the present invention will not be elaborated in detail here;

[0107] S116. Model result evaluation and correction: Combine online comments and private parent word-of-mouth rankings to correct and improve the school quality evaluation results output by the sentiment analysis model; then extract and record the attributes of the school stage and school nature through keywords, and combine the school official website and Baidu Encyclopedia introduction to supplement the schools that lack the attributes of the school stage and school nature;

[0108] S117. Match the basic attribute information recorded in the above steps to the school AOI data to form a complete school AOI geospatial dataset that includes the school stage, school quality and school nature.

[0109]

[0110]

[0111] Table 1

[0112] S2. Identification of fixed resident users in schools (ie, fixed resident objects in this application, objects of this application may be users, user corresponding terminal devices, etc., and this application is not specifically limited) based on large-scale mobile signaling data;

[0113] S21. Set up school hierarchical buffers. Considering that the extraction accuracy of mobile phone signaling data is limited (about 250m×250m), the area of ​​some schools is smaller than the extraction accuracy. Therefore, it is necessary to set up hierarchical buffers for school AOI data to ensure that the sum of the area of ​​the school and the buffer is greater than the extraction accuracy.

[0114] S22. Create geographic grid. Use the "Create Fishnet" tool of GIS software to grid the study area, map all signaling trajectory points into the grid, and form a large-scale geographic data set with basic attribute information of all users;

[0115] S23. Filter fixed resident users. Traverse the data set, count the users' visits and residence frequencies to the school AOI and its buffer grid, and filter out users whose visit and residence frequencies in the school buffer AOI are ≥ 8 (i.e., the preset frequency in this application) within one month (i.e., the preset duration in this application). In this step, if the trajectory point only moves within the same AOI area, it is not considered a new trip and is still in the residence process;

[0116] S24. Identify the user's residence type. Based on the fixed resident users selected in the previous step, combined with the fields such as the weekday daytime residence time, weekday night residence time, and weekend night residence time in the user's monthly residence table in the mobile phone signaling data, the longest weekday daytime residence grid, the longest weekday night residence grid, and the longest weekend night residence grid of each user are selected, and they are defined as three types: A, B, and C (i.e., the first grid, the second grid, and the third grid in this application).

[0117] S3. Classification of students: Figure 3 As shown, the fixed resident users in the previous step are finely divided into population categories according to their location, age and app usage;

[0118] S31. Determine whether the Class A grid belongs to the school buffer zone;

[0119] S32. Record the user's app usage type and age attributes;

[0120] S33. Classify the crowd. The classification results are as follows:

[0121] (1) Boarding students: A = B, that is, A and B belong to the same grid and are both within the school buffer zone, and the user's age is ≥ 6 years old (i.e., the first preset age in this application);

[0122] (2) Day students: A≠B, that is, A is within the school buffer zone but B is not, and the user is ≥6 years old;

[0123] (3) Teachers: A belongs to the school buffer zone, and the user uses at least one teacher app (such as Class Optimizer, Teacher Training, Teacher Recruitment, etc.) and is ≥18 years old (the second preset age in this application);

[0124] (4) Parents: A is not within the school buffer zone, and these users’ access to the school buffer zone occurs during the school and after-school hours on weekdays (6:30-9:00, 16:00-19:00, i.e., the preset time periods in this application), and they are ≥18 years old;

[0125] (5) Other visitor groups: Exclude visitors based on the start time of their visit (not during school hours, such as 10 a.m.), duration of their visit (less than 2 hours), and frequency of their visit (less than 8 times per month).

[0126] S4. School-residence identification: Combined with the above analysis steps, the school and residence of the mobile phone user are further identified to form an accurate school OD that includes different stages of study, school quality and school nature.

[0127] S41. Based on the mobility characteristics of four groups of people, identify the school-residence grid. The details are as follows:

[0128] (1) For boarding students: The place where this group of people spend the longest time during the day and at night on weekdays is the school. They may return to their residence on weekends. Therefore, the grid where they spend the longest time during the day on weekdays (A) and the grid where they spend the longest time at night on weekdays (B) are determined as the school location, and the grid where they spend the longest time at night on weekends (C) is determined as the residence;

[0129] (2) For day students: The place where this group of people spend the longest time on weekdays is the school, and they return to their residence on weekday nights and weekends. Therefore, the grid where they spend the longest time on weekdays (A) is determined as the school location, and the grid where they spend the longest time on weekday nights (B) and weekend nights (C) are determined as their residence;

[0130] (3) For teachers: The place where this group of people stays the longest during the day on weekdays is the school. In most cases, the school will provide teachers with dormitories for the group of teachers. Therefore, it is necessary to further determine whether the grid where the teachers stay the longest during the day on weekdays (A) and the grid where they stay the longest at night on weekdays (B) are the same. If they are the same, similar to day students, A and B are determined as the school location, and the grid where they stay the longest at weekend nights (C) is determined as the residence location; if they are different, A is determined as the school location, and B and C are determined as the residence location;

[0131] (4) For parents: This group of people's visits to the school are mainly concentrated during the school and after school hours on weekdays (6:30-9:00, 16:00-19:00), the frequency of stay is greater than 8 times per month, and the longest stay point during the day on weekdays is not at the school, and they will return to their residence at night on weekdays. Therefore, the grid with the longest stay during the day on weekdays (A) is determined as the place of work, and the grid with the longest stay at night on weekdays (B) and the grid with the longest stay at night on weekends (C) are determined as the place of residence.

[0132] S42. Visualization of OD flow of commuting to school under different attributes. Combining the basic attributes of the school and the results of school-residence discrimination, the residential grid is defined as the starting point O of commuting to school, and the school grid is defined as the end point D of commuting to school, and the commuting behavior under different attributes is visualized.

[0133] In summary, the method provided by the embodiment of the present application includes: obtaining mobile phone signaling data and school AOI data, and preprocessing the mobile phone signaling data and school AOI data; determining the fixed resident objects based on the school and the types corresponding to the fixed resident objects according to the mobile phone signaling data and school AOI data; the type is the type corresponding to the geographical grid visited or resided by the object; according to the basic information of the type and the object, based on the preset classification strategy, determine the crowd category of the object, the starting point and end point of the school commuting behavior. The present application combines large-scale mobile phone signaling data and school AOI data to determine the resident type of the object; and then finely divides the crowd category and school commuting behavior, which is conducive to improving the precision of crowd identification.

[0134] Secondly, refer to the attached Figure 4 A system for identifying school commuting behavior according to an embodiment of the present invention is described, and the system specifically includes:

[0135] The first model 310 is used to obtain mobile phone signaling data and school AOI data, and pre-process the mobile phone signaling data and school AOI data;

[0136] The second model 320 is used to determine the school-based fixed resident objects and the types corresponding to the fixed resident objects according to the mobile phone signaling data and the school AOI data; the type is the type corresponding to the geographical grid visited or resided by the object;

[0137] The third model 330 is used to determine the population category of the object, the starting point and the end point of the school commuting behavior based on the type and basic information of the object and a preset classification strategy.

[0138] Optionally, the identification system provided by the present application further includes a fourth module, which is used to:

[0139] Schools are divided based on the school system, and the school commuting behavior of all subjects is displayed according to the starting and ending points of the school commuting behavior of schools with different school systems;

[0140] Alternatively, schools can be divided based on their teaching quality, and the school attendance behaviors of schools with different teaching qualities can be displayed according to the starting and ending points of the school attendance behaviors of all subjects.

[0141] It can be seen that the contents of the above method embodiments are all applicable to the present system embodiments, the functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0142] Reference Figure 5 , an embodiment of the present invention provides a device for identifying commuting behavior, the device comprising:

[0143] at least one processor 410;

[0144] At least one memory 420, used to store at least one program;

[0145] When the at least one program is executed by the at least one processor 410, the at least one processor 410 implements the school commuting behavior identification method.

[0146] Similarly, the contents of the above method embodiments are all applicable to the present device embodiments. The functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0147] An embodiment of the present invention further provides a computer-readable storage medium, in which a program executable by a processor is stored. When the program executable by the processor is executed by the processor, it is used to execute the above-mentioned method for identifying school commuting behavior.

[0148] Similarly, the contents of the above method embodiments are all applicable to the present storage medium embodiments. The functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0149] In some selectable embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operation and logic flow presented herein. Selectable embodiments are expected, wherein the order of various operations is changed and the sub-operation of a part for which is described as a larger operation is performed independently.

[0150] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise specified, one or more of the functions and / or features can be integrated into a single physical device and / or software module, or one or more functions and / or features can be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present invention. More specifically, in view of the properties, functions and internal relationships of the various functional modules in the device disclosed herein, the actual implementation of the module will be understood within the conventional skills of the engineer. Therefore, those skilled in the art can implement the present invention set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0151] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several programs to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0152] The logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable programs for implementing the logical functions, and may be embodied in any computer-readable medium for use by a program execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch and execute a program from a program execution system, device or apparatus), or in conjunction with such program execution systems, devices or apparatuses. For purposes of this specification, a "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by a program execution system, device or apparatus, or in conjunction with such program execution systems, devices or apparatuses.

[0153] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0154] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable program execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0155] In the above description of this specification, the description with reference to the terms "one embodiment / example", "another embodiment / example" or "certain embodiments / examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0156] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

[0157] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present invention.

Claims

1. A method for identifying school commuting behavior, characterized in that: The method comprises the following steps: Acquire mobile phone signaling data and school AOI data of the subject, and pre-process the mobile phone signaling data and the school AOI data; Determine, according to the mobile phone signaling data and the school AOI data, a fixed resident object based on the school and a type corresponding to the fixed resident object; the type is a type corresponding to a geographical grid visited or resident by the object; According to the type and basic information of the object, based on a preset classification strategy, the population category of the object, the starting point and the end point of the school commuting behavior are determined.

2. The method for identifying school commuting behavior according to claim 1, characterized in that: Determining school-based fixed resident objects and their corresponding types according to the mobile phone signaling data and the school AOI data, including: Setting a hierarchical buffer zone of the school; the hierarchical buffer zone is used to make the area of ​​the school larger than the extraction accuracy of the mobile phone signaling; creating a geographic grid based on each of the schools and the grading buffers; Traversing the mobile phone signaling data, mapping the signaling trajectory points to the geographic grid, and obtaining the visit data of each of the objects to the school; The fixed resident object and its type are determined according to the access data.

3. The method for identifying school commuting behavior according to claim 2, characterized in that: Determining the fixed resident object and its type according to the access data includes: According to the access data, within a preset time period, objects whose access and residence frequency to the school is greater than or equal to a preset frequency are screened out and regarded as fixed residence objects; According to the access data of the fixed resident objects to the school, it is determined whether the first grid, the second grid and the third grid corresponding to each object are located in the school area; the first grid, the second grid and the third grid are the residence characteristics of the fixed resident objects on weekdays and non-working days.

4. The method for identifying school commuting behavior according to claim 1, characterized in that: According to the type and the basic information of the object, based on a preset classification strategy, the crowd category, the starting point and the end point of the commuting behavior of the object are determined, including: If the first grid and the second grid are the same, the first grid and the second grid both belong to the school area, and the age of the fixed resident object is greater than or equal to the first preset age, determining that the fixed resident object is a boarding student; If the first grid belongs to the school area, the second grid does not belong to the school area, and the age of the fixed resident object is greater than or equal to a first preset age, determining that the fixed resident object is a day student; If the first grid belongs to the school area, the fixed resident object uses at least one teacher-related application, and the age of the fixed resident object is greater than or equal to a second preset age, determining that the fixed resident object is a teacher; If the first grid does not belong to the school area, the visit time of the fixed resident object to the school is within the preset time period and the age of the fixed resident object is greater than or equal to the second preset age, it is determined that the fixed resident object is a parent; the first grid is the grid where the fixed resident object stays the longest during the daytime on weekdays, and the second grid is the grid where the fixed resident object stays the longest at night on weekdays.

5. The method for identifying school commuting behavior according to claim 4, characterized in that: The method further comprises: Determine that the area where the third grid of the boarding student is located is the residence, the area where the second grid or the third grid of the day student is located is the residence, the area where the second grid or the third grid of the teacher is located is the residence, the area where the first grid of the parent is located is the workplace, and the area where the second grid or the third grid of the parent is located is the residence; the third grid is the grid where the fixed resident object stays the longest on non-working nights.

6. The method for identifying school commuting behavior according to claim 1, characterized in that: The method further comprises: The schools are divided based on the school system, and the school commuting behaviors of the schools with different school systems are displayed according to the starting points and end points of the school commuting behaviors of all the subjects; Alternatively, the schools are divided based on teaching quality, and the school commuting behaviors of the schools with different teaching qualities are displayed according to the starting points and end points of the school commuting behaviors of all the subjects.

7. The method for identifying school commuting behavior according to claim 1, characterized in that: Preprocessing the mobile phone signaling data and the school AOI data includes: Acquire all the school AOI data and text data related to the school; The text data is understood through natural language processing to determine basic information of the school.

8. A system for identifying school commuting behavior, characterized in that: The system comprises: The first model is used to obtain mobile phone signaling data and school AOI data, and pre-process the mobile phone signaling data and school AOI data; A second model is used to determine, based on the mobile phone signaling data and the school AOI data, a fixed resident object based on the school and a type corresponding to the fixed resident object; the type is a type corresponding to a geographical grid visited or resided by the object; The third model is used to determine the population category, the starting point and the end point of the commuting behavior of the object based on the type and the basic information of the object and a preset classification strategy.

9. A device for identifying school commuting behavior, characterized in that: The device comprises: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the school commuting behavior recognition method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a program executable by a processor, characterized in that: The program executable by the processor is used to implement the school commuting behavior recognition method according to any one of claims 1 to 7 when executed by the processor.

Images