A method for calculating the degree of social space integration based on individual spatiotemporal co-occurrence

Abstract

The application relates to the technical field of data processing, in particular to a social space integration degree calculation method based on individual space-time co-occurrence, which identifies a user space-time co-occurrence residence pair, calculates a space-time co-occurrence duration, calculates an individual space-time co-occurrence weight, classifies the space-time co-occurrence, and analyzes the individual space-time co-occurrence identification result. The application only needs to calculate the space-time co-occurrence duration of adjacent residence records to measure the social space integration degree, does not need to traverse the space-time co-occurrences of various space-time slots, and improves the practicability of the social space integration degree.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a social space integration degree calculation method based on individual space-time co-occurrence. BACKGROUND

[0002] Minority group refers to a social group that does not occupy a dominant position in a particular society.

[0003] Space-time co-occurrence originates from computer science and refers to the frequent proximity of two individuals in time and space, that is, the spatial distance is less than a set threshold and the duration is greater than a set threshold, including the proximity in the process of staying and moving. It can be used to discover the relationship between different events, mine trajectories with high similarity, and construct a dynamic social relationship network in space-time.

[0004] In recent years, with the rapid development of space-time big data, the application of space-time co-occurrence technology has a wider foundation, and there are more applications in the fields of epidemic, crime prevention, user pushing, etc. Some studies have quantified the social space integration degree of minority groups by identifying the space-time co-occurrence of minority groups and mainstream groups in individual behavior. However, such technology needs to traverse each time slot and calculate the spatial distance between individual cases. The time of co-occurrence is not continuous. It cannot effectively quantify the social integration degree of minority groups based on the duration of co-occurrence.

[0005] The study of the integration degree of minority groups is applied to the research and analysis of urban social fields, including the spatial differentiation and social integration between minority groups and mainstream groups. The space-time co-occurrence of individuals in minority groups is calculated to provide decision support for formulating urban development policies. However, there is no method for calculating the social integration degree of residents using space-time co-occurrence. SUMMARY

[0006] In order to solve the above technical problems, the purpose of the present application is to provide a social space integration degree calculation method based on individual space-time co-occurrence, and the technical solution adopted is as follows:

[0007] Identifying space-time co-occurrence staying pairs and calculating space-time co-occurrence duration, including: extracting daily staying information of users, calculating user staying information duration and screening out staying records with duration greater than a preset duration; constructing user space co-occurrence staying pairs according to the space adjacency matrix; screening out space co-occurrence staying pairs with overlapping time and determining the corresponding co-occurrence time period start and end time; calculating the co-occurrence duration and screening out records greater than the preset duration;

[0008] Calculate the weight of individual space-time co-occurrence and classify the space-time co-occurrence, including: classifying the type of user space-time co-occurrence according to the label, splitting the cross-period space-time co-occurrence record according to the standard period, and converting the space-time co-occurrence staying duration according to the user summary space-time co-occurrence actual duration;

[0009] The spatiotemporal co-occurrence recognition result of the individual is analyzed, including: summarizing the spatiotemporal co-occurrence duration, vectorizing the co-occurrence record, and visualizing the spatial distribution, determining the spatial integration degree of the minority group according to the proportion of the cross-group co-occurrence duration in the minority group in all co-occurrence types under the random condition and the actual condition.

[0010] The embodiment of the application has at least the following beneficial effects:

[0011] The application has spatiotemporal dynamic continuity, has better frontiers for new social space research needs, and provides support for researches on social space differentiation, social isolation, and exploration of differentiation rules of urban social resident space.

[0012] The application reduces the computing power requirement, only needs to measure the social space integration degree by calculating the spatiotemporal co-occurrence duration of the adjacent residence record, and does not need to traverse the spatiotemporal co-occurrence of each spatiotemporal slot, and is more practical.

[0013] The data source of the application is convenient, only needs to use the existing mobile phone signaling data product to complete the identification of the user type, does not need to identify from the original data, and can be realized through simple algorithms such as data classification, grouping counting, and table connection, and deeply mines the value of the existing data. BRIEF DESCRIPTION OF DRAWINGS

[0014] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiment or the prior art description. Obviously, the drawings in the following description are only some embodiments of the application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0015] Figure 1 The method flowchart of the social space integration degree calculation method based on individual spatiotemporal co-occurrence provided by one embodiment of the application is shown in the figure.

[0016] Figure 2 The method flowchart of identifying the user spatiotemporal co-occurrence residence pair and calculating the spatiotemporal co-occurrence duration provided by one embodiment of the application is shown in the figure.

[0017] Figure 3 The space adjacency table construction schematic diagram provided by one embodiment of the application is shown in the figure.

[0018] Figure 4 The method flowchart of calculating the individual spatiotemporal co-occurrence weight and classifying the spatiotemporal co-occurrence provided by one embodiment of the application is shown in the figure.

[0019] Figure 5This is a flowchart of a method for analyzing the spatiotemporal co-occurrence identification results of individuals, provided as an embodiment of the present invention. Detailed Implementation

[0020] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a method for calculating the degree of social spatial integration based on the spatiotemporal co-occurrence of individuals proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0022] The following description, in conjunction with the accompanying drawings, details a specific scheme for calculating the degree of social spatial integration based on the spatiotemporal co-occurrence of individuals, provided by this invention.

[0023] Please see Figure 1 The diagram illustrates a flowchart of a method for calculating the degree of social spatial integration based on the spatiotemporal co-occurrence of individuals, according to an embodiment of the present invention. The method includes the following steps:

[0024] Step S100: Identify the user spatiotemporal co-occurrence dwell pair and calculate the spatiotemporal co-occurrence duration.

[0025] Daily user dwell time data with a duration of more than 30 minutes within the study area were selected. It should be noted that the original data had already been identified by dwell time points and activity types. A spatial adjacency matrix was established to determine whether user dwell times overlapped, identify spatiotemporal co-occurrence dwell pairs between users, and calculate the duration of spatiotemporal co-occurrence.

[0026] In some possible implementations, step S100 can be achieved through steps S110 to S170. Please refer to [link / reference]. Figure 2 , Figure 2 Flowchart of the method for identifying user spatiotemporal co-occurrence dwell pairs and calculating the duration of spatiotemporal co-occurrence:

[0027] Step S110: Extract user information from the user's daily residency information table.

[0028] Select the spatiotemporal scope of the analysis, determine the spatial range and time period of the analysis, extract user information from the daily user stay information table and summarize it into a table. The dataset includes user ID, stay point ID, stay point latitude and longitude information, and start and end time label information of stay activities.

[0029] Please refer to Table 1, which is a user daily stay original data set.

[0030] Table 1

[0031]

[0032] Step S120, calculate the user stay information duration and filter out the stay records with duration greater than the preset duration.

[0033] In the embodiment of the application, the preset duration is 30 minutes, and in other embodiments, the preset duration can be adjusted by the implementer according to the actual situation.

[0034] According to the user stay start and end time, the user stay duration is calculated, and the result is stored in the stay duration field. According to the duration of user activity stay, the records are filtered, and the records with stay duration greater than 30 minutes are filtered out, and the user stay duration data table is obtained. The output data set includes user number, stay point number, stay point latitude and longitude, stay start time, stay end time and stay duration.

[0035] Please refer to Table 2, which is a user stay duration data table.

[0036] Table 2

[0037]

[0038] Step S130, constructing a spatial adjacency table according to a spatial proximity threshold.

[0039] According to the selected spatial proximity threshold, a spatial adjacency matrix is constructed. Based on the Geohash7 algorithm, the optional spatial adjacency threshold includes about 200m, 335m, 420m, etc. The specific threshold varies with the latitude and longitude of the Geohash7 grid. The corresponding spatial adjacency matrix construction rules include considering only the Geohash7 grid itself, ROOK matrix and QUEEN matrix, etc. It can be generated by using the adjacent analysis tool of ArcGIS.

[0040] More specifically: according to the selected spatial proximity threshold, a spatial adjacency matrix is constructed. Considering the stay records based on the Geohash7 algorithm, the alternative adjacency matrix includes considering only the stay grid itself, ROOK adjacency matrix and QUEEN adjacency matrix. The search radius of the grid center point can be set to 200m (ROOK matrix) or 250m (QUEEN matrix) to generate the adjacency matrix that meets the conditions by using the adjacent analysis tool of ArcGIS software, and the spatial unit adjacency table is obtained. Here, taking the QUEEN matrix as an example, the grid where the primary user A is located is regarded as the center grid, and the grid where the secondary user B is located is regarded as the edge grid.

[0041] Please refer to Figure 3 , Figure 3 for the construction of the spatial adjacency table; Figure 3 (a) in the table is only considering the grid itself spatial adjacency, namely when the user A's residence record and user B's residence record in the same geohash7 grid at the same time is determined as spatial neighbors. Figure 3 (b) in the table is the ROOK matrix, namely the grid with the same edge adjacency is considered as adjacent. When user A is in the center grid, user B is also determined as spatial neighbors when it is in the four grids with the same edge except the center grid. Figure 3 (c) in the table is the QUEEN adjacency matrix, when user A is in the center grid, user B is also determined as spatial neighbors when it is in the eight grids with the same edge and angle except the center grid. Using ROOK and QUEEN adjacency matrix can include the case of partial space-time co-occurrence on the grid edge, but it increases the spatial proximity threshold and reduces the spatial co-occurrence determination accuracy. The specific use needs to be balanced.

[0042] Please refer to Table 3, Table 3 is a spatial adjacency table;

[0043]

[0044] Step S140, constructing user spatial co-occurrence residence pairs according to the spatial adjacency matrix.

[0045] According to the spatial adjacency matrix and the rule of inconsistent user numbers, the user residence duration data table is self-connected to construct user residence records. The user spatial co-occurrence residence pair data is obtained, and the output data set includes one main and one vice two groups of user numbers, residence point numbers, residence start time and residence end time, a total of 8 fields.

[0046] Please refer to Table 4, Table 4 is a user spatial co-occurrence residence pair table.

[0047] Table 4

[0048]

[0049]

[0050]

[0051] Step S150, screening out spatial co-occurrence residence pairs with overlapping residence time.

[0052] According to the start time of any activity is earlier than the end time of another activity, the residence pairs with overlapping residence time are screened out, and the output data set includes one main and one vice two groups of user numbers, residence point numbers, residence start and end time points, a total of 8 fields.

[0053] Please refer to Table 5, which is a table of user space co-located residence pairs with time overlap.

[0054] Table 5

[0055]

[0056]

[0057] Step S160, calculate the co-occurrence time period start and end time of residence pairs with overlapping residence time.

[0058] Compare the time points of the two residence start times in the residence pair, and take the later time point as the starting time point of the co-occurrence time period. Compare the time points of the two residence end times in the residence pair, and take the earlier time point as the termination time point of the co-occurrence time period, to obtain the user space co-occurrence residence start and end time data. The output data set includes 6 fields of user space co-occurrence residence pair data, including main user number, main residence point number, secondary user number, secondary residence point number, co-occurrence start time and co-occurrence end time.

[0059] Please refer to Table 6, which is a table of user space co-located residence pairs with start and end time.

[0060] Table 6

[0061]

[0062] Step S170, calculate the co-occurrence duration of the residence pair and filter out records with co-occurrence duration greater than the preset duration.

[0063] Calculate the co-occurrence duration by subtracting the start time of the co-occurrence time period from the end time of the co-occurrence time period, and store the result value in the co-occurrence duration field. Filter out residence pairs with overlapping duration greater than the preset duration to obtain user space co-occurrence residence pair data. The preset duration is 30 minutes. The output data set includes 7 fields, including main user number, main residence point number, secondary user number, secondary residence point number, co-occurrence start time, co-occurrence end time and co-occurrence duration.

[0064] Please refer to Table 7, which is a table of user space co-occurrence residence pair data.

[0065] Table 7

[0066]

[0067] Step S200, calculate individual space-time co-occurrence weight and classify space-time co-occurrence.

[0068] The co-occurrence type of the spatio-temporal co-occurrence resident pair is classified according to the user identity label. A self-defined standard time period is divided, and the spatio-temporal co-occurrence record across the time period is split, and the co-occurrence time period of the spatio-temporal co-occurrence resident pair is classified according to the time period. The actual spatio-temporal co-occurrence total time length of each user per day is calculated, and each spatio-temporal co-occurrence record is time length converted by taking the spatio-temporal co-occurrence total time length of each user per day as 1.

[0069] In some possible implementations, i.e., the above step S200 can be implemented by the following steps S210 to S270, please refer to Figure 4 , Figure 4 The flow chart of the method for calculating individual spatio-temporal co-occurrence weight and classifying spatio-temporal co-occurrence is as follows:

[0070] Step S210, connecting the user identity label with the spatio-temporal co-occurrence resident pair data.

[0071] The user identity label is connected according to the user number in the user spatio-temporal co-occurrence resident pair data. The output data set includes the user number, the main resident point number, the main user identity label, the secondary user number, the secondary resident point number, the secondary user identity label, the co-occurrence start time, the co-occurrence end time, and the co-occurrence time length, i.e., the user spatio-temporal co-occurrence resident pair data of 9 fields.

[0072] Please refer to Table 8, which is the user spatio-temporal co-occurrence resident pair data table with user identity label.

[0073] Table 8

[0074]

[0075]

[0076] Step S220, distinguishing the user spatio-temporal co-occurrence type.

[0077] The type of the spatio-temporal co-occurrence is determined according to the identity labels of the two users. If both users are minority groups, it is a minority group co-occurrence. If both users are mainstream groups, it is a mainstream group co-occurrence. Otherwise, it is a cross-group co-occurrence. The determination result is recorded in the co-occurrence type field. The output data set includes the main user number, the main resident point number, the secondary user number, the secondary resident point number, the co-occurrence start time, the co-occurrence end time, the co-occurrence time length, and the co-occurrence type, i.e., the user spatio-temporal co-occurrence resident pair data of 8 fields.

[0078] Please refer to Table 9, which is a schematic table of the user spatio-temporal co-occurrence resident pair data with user identity label.

[0079] Table 9

[0080]

[0081] Step S230, generating standard time periods on demand.

[0082] According to the time range of all data, the standard time periods are generated on demand, the time period rule table is defined, and all standard time periods within the analysis time period are generated. It can be considered to divide into one time slot for 1 hour or 3 hours. Here, the day and night of weekdays and weekends are segmented as an example, and 0:00, 8:00, and 22:00 are taken as time period division points. The output data set includes 3 fields of standard time period, start time, and end time.

[0083] Please refer to Table 10, which is a schematic table of the standard time period data set.

[0084] Table 10

[0085]

[0086] Step S240, split the cross-time period spatiotemporal co-occurrence record.

[0087] Connect the spatiotemporal co-occurrence residence pair data with the standard time period, and the intersection of the spatiotemporal co-occurrence residence pair data and the standard time period. The time period intersection is similar to the spatiotemporal co-occurrence determination algorithm in the previous section. Here, 8:00 is taken as an example. If the spatiotemporal co-occurrence start time is earlier than 8:00, the spatiotemporal co-occurrence end time point is changed to 8:00 of the day, and a residence record from 8:00 to the spatiotemporal co-occurrence end time is generated. The spatiotemporal co-occurrence residence pair is split according to the standard time period.

[0088] Please refer to Table 11, which is a schematic table of the user spatiotemporal co-occurrence residence pair data after splitting according to the standard time period.

[0089] Table 11

[0090]

[0091] Step S250, classify the split spatiotemporal co-occurrence record and label the date and time period.

[0092] The split spatiotemporal co-occurrence residence pair data is classified according to the standard time period, and the date is labeled. The output data set includes 10 fields of main user number, main residence point number, secondary user number, secondary residence point number, co-occurrence start time, co-occurrence end time, co-occurrence duration, co-occurrence type, co-occurrence time period, and co-occurrence date.

[0093] Please refer to Table 12, which is a schematic table of the user spatiotemporal co-occurrence residence pair data by time period.

[0094] Table 12

[0095]

[0096]

[0097] Step S260, the user summary space-time co-occurrence actual length of time.

[0098] According to the user number and the date, the space-time co-occurrence residence time of each user each day is summarized, and a user daily space-time co-occurrence time length table is generated, which includes three fields of user number, co-occurrence date and actual co-occurrence total time length.

[0099] Please refer to Table 13, which is a schematic table of the standard time period data set;

[0100] Table 13

[0101]

[0102] Step S270, the space-time co-occurrence residence time is converted.

[0103] The space-time co-occurrence residence record is connected with the user daily space-time co-occurrence time length table according to the main user number. The ratio of the time length of each space-time co-occurrence residence record to the total space-time co-occurrence time length of the main user on the same day is taken as the converted co-occurrence time length, and is summarized according to the user number, co-occurrence location, co-occurrence type and time period. The individual space-time co-occurrence identification result data table is obtained. The output data set includes six fields of user number, co-occurrence location number, co-occurrence time length, co-occurrence type, co-occurrence time period and converted co-occurrence time length.

[0104] Please refer to Table 14, which is an individual space-time co-occurrence identification result data table.

[0105] Table 14

[0106]

[0107] Step S300, analyze the individual space-time co-occurrence identification result.

[0108] The spatial distribution of different classified space-time co-occurrence records is visualized. The proportion of completely random and actual cross-group space-time co-occurrence in all types of space-time co-occurrence of the minority group in different spatial units is calculated, and the spatial integration degree is quantified by the ratio.

[0109] In some possible implementations, i.e., the above-mentioned step S300 can be realized by the following steps S310 to S360, please refer to Figure 5 , Figure 5 The method flow chart for analyzing the individual space-time co-occurrence identification result is as follows:

[0110] Step S310, summarize the space-time co-occurrence time length according to the time period, classification and location.

[0111] The individual space-time co-occurrence duration is aggregated according to the same period, the same type and the same place to obtain a desensitized co-occurrence record sample containing the co-occurrence place number, the co-occurrence type, the co-occurrence period and the co-occurrence duration.

[0112] Referring to Table 15, Table 15 is a table of various types of space-time co-occurrence data aggregated by place;

[0113] Table 15

[0114]

[0115] Step S320, vectorizing the co-occurrence records.

[0116] According to the co-occurrence place number of the co-occurrence records, the co-occurrence records are connected with the residence point latitude and longitude table. The co-occurrence record sample space distribution data containing the co-occurrence place and latitude and longitude, the co-occurrence type, the co-occurrence period and the co-occurrence duration is obtained. In ArcGIS software, the co-occurrence record sample space distribution data is created as a point feature according to X and Y coordinates. In the case of existing vector points, the desensitized co-occurrence record sample can also be connected with the vector points according to the number.

[0117] Step S330, visualizing the co-occurrence record space distribution.

[0118] The co-occurrence records of different periods and different types are screened, and kernel density analysis in ArcGIS is used to visualize them respectively. Taking the period classification of weekdays and weekends, daytime and nighttime as an example, 12 kernel density maps of different periods and different types are generated.

[0119] Step S340, calculating the proportion of cross-group space-time co-occurrence to all types of co-occurrence under random conditions.

[0120] The proportion of cross-group co-occurrence duration to all co-occurrence type durations of the minority group under the condition of complete randomness (each individual can co-occur with other individuals in space-time and the co-occurrence duration is the same) , the calculation formula is:

[0121] ;

[0122] Wherein, m is the number of minority groups in the research scope; n is the number of mainstream groups in the research scope; is the combination number calculation formula, which represents the number of all possible combinations of randomly selecting 2 from m samples.

[0123] Step S350, calculating the proportion of cross-group space-time co-occurrence to all types of co-occurrence under actual conditions.

[0124] The actual minority group co-occurrence time length, the cross-group co-occurrence time length are summarized by using the desensitization spatiotemporal co-occurrence identification result data table, and the proportion of the cross-group co-occurrence time length in the total co-occurrence time length of the minority group in the actual situation is calculated , and the calculation formula is

[0125] ;

[0126] Among them, is the cross-group co-occurrence time length of the i th person in the minority group in the research range; is the co-occurrence time length of the i th person in the minority group in the research range; and m is the number of people in the minority group in the research range.

[0127] In step S360, the spatial integration degree of the minority group is calculated.

[0128] The proportion of the cross-group co-occurrence time length in the total co-occurrence time length of the minority group in the actual situation is taken as the numerator, and the proportion of the cross-group co-occurrence time length in the total co-occurrence time length of the minority group in the completely random situation is taken as the denominator, and the ratio is taken as the spatial integration degree of the minority group.

[0129] The calculation formula of the spatial integration degree of the minority group is When the value is greater than 1, the integration degree is high, and the larger the value is, the higher the integration degree is; when the value is less than 1, the integration degree is low, and the smaller the value is, the lower the integration degree is.

[0130] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0131] Each embodiment in the specification is described in a progressive manner, and the same and similar parts between each embodiment can be referred to each other, and each embodiment mainly describes the difference from other embodiments.​​​

Claims

1. A method for calculating the degree of social spatial integration based on the spatiotemporal co-occurrence of individuals, characterized in that, The method includes the following steps: Identifying user spatiotemporal co-occurrence dwell pairs and calculating spatiotemporal co-occurrence duration includes: extracting daily user dwell information, calculating user dwell information duration, and filtering dwell records with durations greater than a preset duration; constructing user spatial co-occurrence dwell pairs based on a spatial adjacency matrix; filtering spatial co-occurrence dwell pairs with overlapping dwell times and determining the start and end times of the corresponding co-occurrence period; calculating co-occurrence duration and filtering records with durations greater than a preset duration. Calculate the spatiotemporal co-occurrence weight of individuals and classify spatiotemporal co-occurrence, including: classifying the spatiotemporal co-occurrence type of users according to the tags used, splitting cross-time period spatiotemporal co-occurrence records according to standard time periods, and converting the spatiotemporal co-occurrence dwell time according to the actual duration of the user's aggregated spatiotemporal co-occurrence; The method for obtaining the individual spatiotemporal co-occurrence weight is as follows: the ratio of the duration of each spatiotemporal co-occurrence dwell record to the total spatiotemporal co-occurrence duration of the main user on that day is used as the converted co-occurrence duration, and the converted co-occurrence duration is the individual spatiotemporal co-occurrence weight; the user's aggregated spatiotemporal co-occurrence actual duration is: the end time of the co-occurrence period minus the start time of the co-occurrence period; The analysis of individual spatiotemporal co-occurrence identification results includes: summarizing the spatiotemporal co-occurrence duration, vectorizing the co-occurrence records and visualizing their spatial distribution, and determining the spatial integration degree of the minority group based on the proportion of cross-group co-occurrence duration under random and actual conditions to the total co-occurrence duration of all co-occurrence types in the minority group.

2. The method for calculating the degree of social spatial integration based on the spatiotemporal co-occurrence of individuals according to claim 1, characterized in that, The construction of user space co-resident pairs based on the spatial adjacency matrix includes: Based on the spatial adjacency matrix and the rule of inconsistent user IDs, a self-join is performed on the user dwell time data table to construct user dwell record pairs.

3. The method for calculating the degree of social spatial integration based on the spatiotemporal co-occurrence of individuals according to claim 1, characterized in that, The calculation of the co-occurrence duration and the filtering of records longer than a preset duration includes: Calculate the co-occurrence duration, store the result in the co-occurrence duration field, filter out the dwell pairs with an overlap duration greater than the preset duration, and obtain the user spatiotemporal co-occurrence dwell pair data.

4. The method for calculating the degree of social spatial integration based on the spatiotemporal co-occurrence of individuals according to claim 1, characterized in that, The classification of user spatiotemporal co-occurrence types based on tags includes: The spatiotemporal co-occurrence type is determined based on the identity tags of the two users. If both users belong to minority groups, it is minority group co-occurrence; if both users belong to mainstream groups, it is mainstream group co-occurrence; otherwise, it is cross-group co-occurrence.

5. The method for calculating the degree of social spatial integration based on the spatiotemporal co-occurrence of individuals according to claim 1, characterized in that, The calculation of the spatiotemporal co-occurrence dwell time based on the actual duration of spatiotemporal co-occurrence summarized by the user includes: Connect the spatiotemporal co-occurrence resident data to the user's daily spatiotemporal co-occurrence duration table according to the main user number.

6. The method for calculating the degree of social spatial integration based on the spatiotemporal co-occurrence of individuals according to claim 1, characterized in that, The formula for calculating the proportion of cross-group co-occurrence duration to the total duration of all co-occurrence types in a minority group under random conditions is as follows: ； in, is the proportion of cross-group co-occurrence duration under random conditions to the total co-occurrence duration of all co-occurrence types in the minority group; m is the number of people in the minority group within the study scope; n is the number of people in the mainstream group within the study scope; The formula for calculating the number of combinations represents the number of all possible combinations of randomly selecting 2 items from m samples.

7. The method for calculating the degree of social spatial integration based on the spatiotemporal co-occurrence of individuals according to claim 1, characterized in that, The formula for calculating the proportion of cross-group co-occurrence duration to the total duration of all co-occurrence types in a minority group in actual practice is as follows: ； in, This refers to the proportion of cross-group co-occurrence duration in actual circumstances to the total duration of all co-occurrence types in a minority group. The cross-group co-occurrence duration of the i-th individual within the minority group studied; Let m be the co-occurrence duration within the minority group corresponding to the i-th person in the minority group within the research scope; m is the number of people in the minority group within the research scope.

8. The method for calculating the degree of social spatial integration based on the spatiotemporal co-occurrence of individuals according to claim 1, characterized in that, The method for determining the spatial integration level of minority groups is as follows: The ratio of cross-group co-occurrence duration under random conditions to the total duration of all co-occurrence types in the minority group is used as the denominator, and the ratio of cross-group co-occurrence duration under actual conditions to the total duration of all co-occurrence types in the minority group is used as the numerator. This ratio is then used as the degree of spatial integration of the minority group.

9. The method for calculating the degree of social spatial integration based on the spatiotemporal co-occurrence of individuals according to claim 1, characterized in that, The calculation of user dwell time and filtering of dwell records with a dwell time longer than a preset time includes: Calculate the user's dwell time based on the start and end times of the dwell time, subtract the start time from the end time of dwell time, and store the result in the dwell time field. Records are filtered based on the duration of user activity, with records showing a duration longer than a preset duration being selected.

10. The method for calculating the degree of social spatial integration based on the spatiotemporal co-occurrence of individuals according to claim 1, characterized in that, The spatial adjacency matrix is ​​obtained by constructing a spatial adjacency matrix based on a self-selected spatial proximity threshold.

Images