A method, system and terminal for visualizing spatiotemporal kernel density based on prefix matrix

Abstract

The present invention discloses a method, system and terminal for visualizing spatiotemporal kernel density based on prefix matrix, the method comprising: determining multiple timestamps according to limiting information input by a user, determining corresponding time axes, and dividing multiple time bandwidths on each time axis; obtaining a set of pixel data points in a target area, constructing a set of spatiotemporal data points corresponding to the timestamps, and constructing multiple prefix matrices; constructing a window matrix according to the prefix matrix to calculate the spatiotemporal kernel density of the target area; and coloring the pixel data point set to obtain a visualization result of the spatiotemporal kernel density. The present invention studies the problems of exploratory and traditional spatiotemporal kernel density visualization and bandwidth adjustment through prefix structure, obtains prefix matrices of different numbers, and performs coloring processing, thereby realizing the visualization of spatiotemporal kernel density, reducing the time complexity in the calculation process, while also ensuring considerable space complexity, and considering the time and space dimensions at the same time, improving the visualization efficiency of the map.

Description

Technical Field

[0001] The present invention relates to the field of geographic information science and technology, and in particular to a prefix matrix-based spatiotemporal kernel density visualization method, system, terminal and computer-readable storage medium. Background Art

[0002] Spatiotemporal kernel density visualization is a basic tool in geographic information systems. It has been used in applications such as traffic hotspot detection, traffic accident hotspot detection, and infectious disease hotspot detection, providing great convenience for information tracking.

[0003] However, spatiotemporal kernel density visualization is a very slow tool. The "sliding-window-based spatiotemporal kernel density visualization" method (SWS: Sliding-Window-based Solution) with the current optimal time complexity is still slow, and the efficiency of the spatiotemporal kernel density visualization method based on range query is relatively low. If multi-threaded parallel query is performed, the query speed of this method still cannot meet the existing needs.

[0004] Therefore, the prior art still needs to be improved and developed. Summary of the invention

[0005] The main purpose of the present invention is to provide a prefix matrix-based spatiotemporal kernel density visualization method, system, terminal and computer-readable storage medium, aiming to solve the problems of slow query speed and low efficiency of spatiotemporal kernel density visualization in the prior art.

[0006] To achieve the above object, the present invention provides a prefix matrix-based spatiotemporal kernel density visualization method, the prefix matrix-based spatiotemporal kernel density visualization method comprising the following steps:

[0007] Acquire limiting information input by a user, determine a first preset number of timestamps according to the limiting information, determine a corresponding time axis according to each of the timestamps, and divide a second preset number of time bandwidths on each of the time axes according to the limiting information;

[0008] Obtaining a pixel data point set corresponding to each time stamp in the target area, and constructing a plurality of prefix matrices according to each pixel data point set and all the time bandwidths on each time axis;

[0009] Constructing multiple window matrices according to the multiple prefix matrices, and calculating the spatiotemporal kernel density of the target area according to all the window matrices;

[0010] The pixel-time pairs in each pixel data point set are color-filled to obtain a spatiotemporal kernel density visualization result of the target area.

[0011] Optionally, the prefix matrix-based spatiotemporal kernel density visualization method, wherein the obtaining of limiting information input by a user, determining a first preset number of timestamps according to the limiting information, determining a corresponding time axis according to each of the timestamps, and dividing a second preset number of time bandwidths on each of the time axes according to the limiting information, specifically includes:

[0012] Acquire limiting information input by a user, wherein the limiting information is used to limit the number of timestamps in a target area, and the number of spatial bandwidths and time bandwidths at each timestamp;

[0013] Determine a first preset number of time stamps in the target area according to the limiting information, and determine a corresponding time axis according to each of the time stamps;

[0014] According to the limiting information, a second preset number of time bandwidths and a third preset number of space bandwidths are divided on each of the time axes.

[0015] Optionally, the prefix matrix-based spatiotemporal kernel density visualization method, wherein the step of dividing a second preset number of time bandwidths and a third preset number of space bandwidths on each of the time axes according to the limiting information, specifically includes:

[0016] Fixing the single spatial bandwidth, and determining a second preset number of time bandwidths on each of the time axes according to a second preset number of time bandwidths;

[0017] A fourth preset number of endpoints is determined according to all the time bandwidths.

[0018] Optionally, the spatiotemporal kernel density visualization method based on prefix matrix, wherein the step of obtaining a pixel data point set corresponding to each timestamp in the target area and constructing multiple prefix matrices according to each pixel data point set and all the time bandwidths on each time axis, specifically includes:

[0019] Obtain a pixel data point set corresponding to each timestamp in the target area, and extract all pixel points in each pixel data point set;

[0020] Constructing a plurality of pixel-time pairs according to all the pixel points and a fourth preset number of endpoints on each of the time axes;

[0021] According to all the pixel-time pairs, a prefix matrix corresponding to each of the endpoints is constructed:

[0022] ;

[0023] ;

[0024] in, represents the pixel position of the prefix matrix, represents the entire set of spatiotemporal data points, express A data point in Indicates The timestamps corresponding to the pixel-time pairs, Indicates the number of timestamps, represents a constant whose value is determined by the time kernel function. express of Power, Indicates The prefix matrix of timestamps, express location, express timestamp, represents the spatial kernel function, express A set of spatiotemporal data points.

[0025] Optionally, the spatiotemporal kernel density visualization method based on prefix matrices, wherein the step of constructing multiple window matrices based on multiple prefix matrices and calculating the spatiotemporal kernel density of the target area based on all the window matrices, specifically includes:

[0026] Construct multiple window matrices based on the fourth preset number of prefix matrices on each time axis:

[0027] ;

[0028] in, represents the window matrix used to calculate the spatiotemporal kernel density, represents a constant whose value is determined by the time kernel function. and They represent the time bandwidth respectively. Time The prefix matrix of the two endpoints in the timestamp represents the time bandwidth, Indicates The timestamp corresponding to the window matrix;

[0029] Calculate the spatiotemporal kernel density of the target area based on all the window matrices:

[0030] ;

[0031] in, Indicates The space-time kernel density of the timestamp, timestamps representing spatiotemporal data points, express and The Euclidean distance between represents the normalization constant, express The window matrix is ​​0, express A window matrix of 1, express A window matrix of 2.

[0032] Optionally, the prefix matrix-based spatiotemporal kernel density visualization method, wherein the step of constructing a plurality of window matrices according to the plurality of prefix matrices and calculating the spatiotemporal kernel density of the target area according to all the window matrices, further comprises:

[0033] Calculate the time complexity of the prefix matrix of each endpoint on the time axis to obtain a first time complexity;

[0034] Calculate the time complexity of multiple prefix matrices corresponding to each of the time axes to obtain a second time complexity;

[0035] The time complexity of multiple prefix matrices corresponding to each of the spatial bandwidths and each of the temporal bandwidths is calculated to obtain a third time complexity.

[0036] Optionally, the prefix matrix-based spatiotemporal kernel density visualization method, wherein the coloring process is performed on each pixel-time pair in the pixel data point set to obtain the spatiotemporal kernel density visualization result of the target area, specifically includes:

[0037] According to the multiple time bandwidths, two prefix matrices corresponding to each window matrix are determined;

[0038] Each pixel-time pair in the pixel data point set in each prefix matrix is ​​filled with colors to obtain a spatiotemporal kernel density visualization result of the target area.

[0039] In addition, to achieve the above purpose, the present invention also provides a prefix matrix-based spatiotemporal kernel density visualization system, wherein the prefix matrix-based spatiotemporal kernel density visualization system includes:

[0040] a bandwidth information determination module, configured to obtain limiting information input by a user, determine a first preset number of timestamps according to the limiting information, determine a corresponding time axis according to each of the timestamps, and divide a second preset number of time bandwidths on each of the time axes according to the limiting information;

[0041] A prefix matrix construction module, used to obtain a pixel data point set corresponding to each time stamp in the target area, and to construct a plurality of prefix matrices according to each pixel data point set and all the time bandwidths on each time axis;

[0042] A spatiotemporal kernel density calculation module, used to construct a plurality of window matrices according to the plurality of prefix matrices, and calculate the spatiotemporal kernel density of the target area according to all the window matrices;

[0043] The result visualization module is used to perform coloring processing on the pixel-time pairs in each pixel data point set to obtain a spatiotemporal kernel density visualization result of the target area.

[0044] In addition, to achieve the above-mentioned purpose, the present invention also provides a terminal, wherein the terminal includes: a memory, a processor, and a prefix matrix-based spatiotemporal kernel density visualization program stored in the memory and run on the processor, and when the prefix matrix-based spatiotemporal kernel density visualization program is executed by the processor, the steps of the prefix matrix-based spatiotemporal kernel density visualization method as described above are implemented.

[0045] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a prefix matrix-based spatiotemporal kernel density visualization program, and when the prefix matrix-based spatiotemporal kernel density visualization program is executed by a processor, the steps of the prefix matrix-based spatiotemporal kernel density visualization method as described above are implemented.

[0046] In the present invention, the limiting information input by the user is obtained, a first preset number of timestamps are determined according to the limiting information, a corresponding time axis is determined according to each of the timestamps, and a second preset number of time bandwidths are divided on each of the time axes according to the limiting information; a pixel data point set corresponding to each timestamp in the target area is obtained, and multiple prefix matrices are constructed according to each of the pixel data point sets and all of the time bandwidths on each of the time axes; multiple window matrices are constructed according to the multiple prefix matrices, and the spatiotemporal kernel density of the target area is calculated according to all of the window matrices; the pixel-time pairs in each of the pixel data point sets are color-filled to obtain the spatiotemporal kernel density visualization result of the target area. The present invention studies the problems of exploratory and traditional spatiotemporal kernel density visualization and bandwidth adjustment through prefix structures, obtains different numbers of prefix matrices, and performs color-filling processing, thereby realizing the visualization of spatiotemporal kernel density, reducing the time complexity in the calculation process, while also ensuring considerable space complexity, and considering the time and space dimensions at the same time, improving the visualization efficiency of the map. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1It is a flow chart of a preferred embodiment of the spatiotemporal kernel density visualization method based on prefix matrix of the present invention;

[0048] Figure 2 It is a structural schematic diagram of a prefix matrix in a preferred embodiment of the spatiotemporal kernel density visualization method based on a prefix matrix of the present invention;

[0049] Figure 3 It is a schematic diagram of exploratory spatiotemporal kernel density visualization based on prefix matrix processing according to a preferred embodiment of the spatiotemporal kernel density visualization method based on prefix matrix of the present invention;

[0050] Figure 4 It is a schematic diagram of the total response time of the exploratory spatiotemporal kernel density visualization of a preferred embodiment of the spatiotemporal kernel density visualization method based on prefix matrix of the present invention;

[0051] Figure 5 It is a schematic diagram of the spatiotemporal kernel density visualization results based on three timestamps of a preferred embodiment of the spatiotemporal kernel density visualization method based on prefix matrix of the present invention;

[0052] Figure 6 It is a schematic diagram of processing traditional spatiotemporal kernel density visualization based on prefix matrix in a preferred embodiment of the spatiotemporal kernel density visualization method based on prefix matrix of the present invention;

[0053] Figure 7 It is a schematic diagram of the total response time of the traditional spatiotemporal kernel density visualization of the preferred embodiment of the spatiotemporal kernel density visualization method based on prefix matrix of the present invention;

[0054] Figure 8 It is a schematic diagram of spatiotemporal kernel density visualization based on prefix matrix processing fixed timestamps in a preferred embodiment of the spatiotemporal kernel density visualization method based on prefix matrix of the present invention;

[0055] Fig. 9 It is a schematic diagram of spatiotemporal kernel density visualization based on prefix matrix processing multiple time bandwidths according to a preferred embodiment of the spatiotemporal kernel density visualization method based on prefix matrix of the present invention;

[0056] Fig.10 It is a schematic diagram of the total response time of spatiotemporal kernel density visualization of multiple time bandwidths calculated by a fixed spatial bandwidth according to a preferred embodiment of the spatiotemporal kernel density visualization method based on prefix matrix of the present invention;

[0057] Fig.11 It is a schematic diagram of the spatial overhead of exploratory spatiotemporal kernel density visualization of a preferred embodiment of the spatiotemporal kernel density visualization method based on prefix matrix of the present invention;

[0058] Fig.12It is a schematic diagram of the space cost of traditional spatiotemporal kernel density visualization of a preferred embodiment of the spatiotemporal kernel density visualization method based on prefix matrix of the present invention;

[0059] Fig.13 It is a structural diagram of a preferred embodiment of the spatiotemporal kernel density visualization system based on prefix matrix of the present invention;

[0060] Fig.14 FIG. 1 is a structural diagram of a preferred embodiment of the terminal of the present invention. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solution and advantages of the present invention clearer and more specific, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0062] The spatiotemporal kernel density visualization method based on prefix matrix described in the preferred embodiment of the present invention is as follows: Figure 1 As shown, the spatiotemporal kernel density visualization method based on prefix matrix includes the following steps:

[0063] Step S10, obtaining the limitation information input by the user, determining a first preset number of timestamps according to the limitation information, determining a corresponding time axis according to each of the timestamps, and dividing a second preset number of time bandwidths on each of the time axes according to the limitation information.

[0064] Among them, for a data point set on a map (i.e., the target area) provided by the user, for a certain time point on the map (i.e., a timestamp, such as a certain year, month, and day), the target image of the target area (including Pixel points, that is, a pixel point set, where Indicates the number of horizontal pixels, Represents the number of vertical pixels), a corresponding time axis is obtained based on this timestamp (the changes in the data point set within a certain year, month and day), and a spatial kernel function bandwidth value (spatial bandwidth) and a temporal kernel function bandwidth value (temporal bandwidth) are introduced into the time axis. The spatiotemporal kernel density visualization of the target image can be calculated. This process is exploratory spatiotemporal and density visualization.

[0065] Furthermore, if the changes in the target area are observed for a long time, multiple (for example, As the target image changes, each timestamp can get a target image, and these timestamps can correspond to multiple time axes. At this time, for the changes of all time axes in the target area, a spatial bandwidth and a temporal bandwidth can be introduced to calculate the spatiotemporal kernel density visualization of the target image. This process is the traditional spatiotemporal and density visualization.

[0066] Specifically, obtain the limitation information input by the user, wherein the limitation information is used to limit the number of timestamps in the target area, and the number of spatial bandwidths and time bandwidths on each timestamp; determine a first preset number of timestamps in the target area according to the limitation information, and determine a corresponding time axis according to each of the timestamps; and divide a second preset number of time bandwidths and a third preset number of spatial bandwidths on each of the time axes according to the limitation information.

[0067] Furthermore, a single spatial bandwidth is fixed, and according to a second preset number of time bandwidths, a second preset number of time bandwidths on each of the time axes is determined; and according to all the time bandwidths, a fourth preset number of endpoints is determined.

[0068] Among them, obtain the limited information input by the user, and according to the limited information, determine (third preset number) of spatial bandwidths and The second preset number) of time bandwidths, based on the above steps, first fix a spatial bandwidth, for Time bandwidth exists Therefore, according to the limited information input by the user, it can be determined that when a spatial bandwidth is fixed, there is a certain time axis (corresponding to a certain timestamp) in the monitoring target area. endpoints, and then the corresponding prefix matrix can be constructed based on each endpoint (that is, Prefix matrices), through this parallel calculation method, the efficiency of calculating the visualization of the spatiotemporal kernel density function can be effectively improved.

[0069] Step S20: Obtain a pixel data point set corresponding to each time stamp in the target area, and construct a plurality of prefix matrices according to each pixel data point set and all the time bandwidths on each time axis.

[0070] Specifically, a pixel data point set corresponding to each timestamp in the target area is obtained, and all pixel points in each pixel data point set are extracted; a plurality of pixel-time pairs are constructed according to all the pixel points and a fourth preset number of endpoints on each time axis; a prefix matrix corresponding to each endpoint is constructed according to all the pixel-time pairs:

[0071] ;

[0072] ;

[0073] ;

[0074] in, represents the pixel position of the prefix matrix, represents the entire set of spatiotemporal data points (i.e., the set of data points in the entire spatiotemporal dimension within the target area), express A data point in Indicates The timestamps corresponding to the pixel-time pairs, Indicates the number of timestamps, represents a constant whose value is determined by the time kernel function. express of Power, Indicates The prefix matrix of timestamps, express location, express timestamp, represents the spatial kernel function, express A set of spatiotemporal data points, Indicates the standard spatial bandwidth value.

[0075] Among them, the pixel data point set in the target area at a certain timestamp (that is, the data point set mentioned above) is obtained, and according to the spatial bandwidth and time bandwidth corresponding to this timestamp (according to the limited information entered by the user, and a fixed spatial bandwidth, it can be determined that this timestamp in the current calculation process corresponds to a spatial bandwidth and Time bandwidth), the corresponding pixel-time pair can be constructed for each element in the pixel data point set, thereby constructing the prefix matrix corresponding to this timestamp (such as Figure 2 shown), there is timestamp, corresponding to the build prefix matrix, since there is space bandwidth, so the above steps need to be repeated Second-rate.

[0076] Among them, if the exploratory spatiotemporal kernel density visualization is calculated based on the data structure of the prefix matrix, such as Figure 3 and Figure 4 As shown, the obtained regions are different ( Figure 4 (a) A, (b) B, (c) C, (d) D, and (e) E represent different regions), changing the resolution Generate a timestamp when the size The total response time of the exploratory spatiotemporal kernel density visualization of ; if we further calculate the spatiotemporal kernel density corresponding to a prefix matrix at a certain timestamp and color the pixel-time pairs in the prefix matrix, we can get the following Figure 5 The visualization results shown are Figure 5 (a) in the equation represents a set of spatiotemporal data points at a certain location. Figure 5 (b) the first time, Figure 5 (c) The second time and Figure 5 The third time (d) in the formula represents the change of the pixel points in the spatial-temporal data point set at different time stamps. If we further calculate the time complexity and space complexity of the exploratory spatial-temporal kernel density visualization, that is, calculate the time complexity of the prefix matrix at each of the timestamps (since the first research question only sets one time bandwidth and one space bandwidth, we only need to construct two prefix matrices, corresponding to one window matrix), and get the first time complexity, we can get the time complexity calculated based on the data structure of the prefix matrix as (The first time complexity, where represents the number of spatiotemporal data points), and the time complexity calculated by the SWS (Sliding-Window-based Solution, spatiotemporal kernel density visualization based on sliding windows) method in the prior art is , and the space complexity of the two is the same, both Therefore, the calculation process based on the prefix matrix takes both time and space dimensions into consideration, achieving the effect of efficiency optimization.

[0077] Step S30: construct multiple window matrices based on the multiple prefix matrices, and calculate the spatiotemporal kernel density of the target area based on all the window matrices.

[0078] Specifically, a plurality of window matrices are constructed according to a fourth preset number of prefix matrices on each time axis:

[0079] ;

[0080] in, represents the window matrix used to calculate the spatiotemporal kernel density, represents a constant whose value is determined by the time kernel function. and They represent the time bandwidth respectively. Time The prefix matrix of the two endpoints in the timestamp, represents the time bandwidth, Indicates The timestamp corresponding to the window matrix;

[0081] Calculate the spatiotemporal kernel density of the target area based on all the window matrices:

[0082] ;

[0083] in, Indicates The space-time kernel density of the timestamp, Represents the timestamp of a spatiotemporal data point (i.e., a pixel in a pixel data point set), express and The Euclidean distance between represents the normalization constant, express The window matrix is ​​0, express A window matrix of 1, express A window matrix of 2.

[0084] Among them, each prefix matrix has a corresponding endpoint on a time axis, and according to a certain time bandwidth, a window matrix can be constructed between the two endpoints, and the window matrix can be used to calculate the current time axis. The space-time kernel density corresponding to the time bandwidth.

[0085] Furthermore, when the time kernel function (time bandwidth) is greater than 0, the spatiotemporal kernel density change results on this time axis in the target area can be calculated for each time axis. This process is the traditional spatiotemporal kernel density visualization:

[0086] ;

[0087] in, represents the time kernel function, Indicates The timestamp corresponding to the window matrix, express and The Euclidean distance between Indicates the standard time bandwidth value.

[0088] Among them, Figure 6 As shown, the same color represents the two endpoints of building a window matrix, and the resulting regions are different (such as Figure 7 The (a) A, (b) B, (c) C, (d) D, and (e) E correspond to Figure 4 (a) A, (b) B, (c) C, (d) D, and (e) E), changing the resolution Generate a timestamp when the size The total response time of the traditional spatiotemporal kernel density visualization; if we further calculate the time complexity and space complexity of the traditional spatiotemporal kernel density visualization, that is, calculate the time complexity of the prefix matrix corresponding to each of the time axes (or each timestamp) (this process is to repeatedly calculate the exploratory spatiotemporal kernel density visualization problem for the number of timestamps), we can get the second time complexity, and the time complexity calculated based on the data structure of the prefix matrix can be obtained as (Second time complexity), while the time complexity calculated by the SWS method (sliding window method) in the prior art is , and the space complexity of the two is the same, both Therefore, the calculation process based on the prefix matrix takes both time and space dimensions into consideration, achieving the effect of efficiency optimization.

[0089] Furthermore, if Figure 8 As shown, according to the limited information input by the user, and first fix a spatial bandwidth, calculate All prefix matrices corresponding to the time bandwidth (including each timestamp ), further as Fig. 9 As shown, multiple timestamps ( ) to expand, then you only need to create The prefix matrix ( The timestamp includes prefix matrix), and then The total response time of the spatiotemporal kernel density visualization with fixed spatial bandwidth is calculated for different spatial bandwidths (e.g. Fig.10 As shown, Fig.10 The (a) A, (b) B, (c) C, (d) D, and (e) E correspond to Figure 4 (a) Place A, (b) Place B, (c) Place C, (d) Place D and (e) Place E) (Among them, Figure 8 express Fig. 9 So when a fixed spatial bandwidth The time complexity of generating these matrices is , then based on these matrices, the time complexity of calculating the space-time kernel density is For the calculation process of each spatial bandwidth, the time complexity of multiple prefix matrices corresponding to each spatial bandwidth and each temporal bandwidth is calculated, and the third time complexity is obtained, and the total time complexity can be obtained. (The third time complexity); and the total time complexity calculated using the SWS method is , and the space complexity calculated by the two methods is .

[0090] For example, in this embodiment, when five large-scale data (up to 5 million data points) are tested, the prefix matrix-based calculation method is 115 to 1906 times faster than the more advanced SWS method in the prior art (reference Figure 4 , Figure 7 and Fig.10 ), and the space overhead is only 1.067 to 1.92 times more than SWS (reference Fig.11 and Fig.12 , Fig.11 (a) in the figure shows the spatial overhead of exploratory spatiotemporal kernel density visualization in the first region. Fig.11 (b) shows the spatial overhead of exploratory spatiotemporal kernel density visualization in the second region. Fig.12 (a) in the figure shows the spatial overhead of the traditional spatiotemporal kernel density visualization in the first region. Fig.12 (b) in the figure shows the spatial overhead of the traditional spatiotemporal kernel density visualization in the second region); when the resolution is , and when the data points reach millions, The value of can reach one trillion. Therefore, the technical features of this solution can simultaneously support high-resolution spatiotemporal kernel density visualization and large-scale data sets, significantly improving the computational efficiency of spatiotemporal kernel density.

[0091] Step S40: Fill in the pixel-time pairs in each pixel data point set to obtain a spatiotemporal kernel density visualization result of the target area.

[0092] Among them, a coloring process is performed for the pixel-time pairs in each prefix matrix, and the spatiotemporal kernel density of the target area is calculated, so that the spatiotemporal kernel density of the target area can be visualized.

[0093] Specifically, two prefix matrices corresponding to each window matrix are determined according to a plurality of time bandwidths; each pixel-time pair in the pixel data point set in each prefix matrix is ​​color-filled to obtain a spatiotemporal kernel density visualization result of the target area.

[0094] Among them, the spatial-temporal kernel density visualization is a very slow tool. When the data points are 1.67 million, it takes at least three hours to generate the resolution using the fastest SWS algorithm. The timestamp is Therefore, this application uses the prefix matrix structure to not only significantly improve the visualization efficiency and speed, but also effectively support the bandwidth adjustment of space-time kernel density visualization, find the optimal time bandwidth and space bandwidth, and significantly improve the performance of space-time kernel density visualization.

[0095] The present invention studies the problems of exploratory and traditional spatiotemporal kernel density visualization and bandwidth adjustment through prefix structure, obtains prefix matrices of different numbers, and performs coloring processing, thereby realizing the visualization of spatiotemporal kernel density, reducing the time complexity of the calculation process, while ensuring a considerable space complexity, and considering both time and space dimensions, thereby improving the visualization efficiency of the map.

[0096] Furthermore, if Fig.13 As shown, based on the above-mentioned prefix matrix-based spatiotemporal kernel density visualization method, the present invention also provides a prefix matrix-based spatiotemporal kernel density visualization system, wherein the prefix matrix-based spatiotemporal kernel density visualization system includes:

[0097] The bandwidth information determination module 51 is used to obtain the limiting information input by the user, determine a first preset number of timestamps according to the limiting information, determine a corresponding time axis according to each of the timestamps, and divide a second preset number of time bandwidths on each of the time axes according to the limiting information;

[0098] A prefix matrix construction module 52 is used to obtain a pixel data point set corresponding to each time stamp in the target area, and construct a plurality of prefix matrices according to each pixel data point set and all the time bandwidths on each time axis;

[0099] A spatiotemporal kernel density calculation module 53, configured to construct a plurality of window matrices according to the plurality of prefix matrices, and calculate the spatiotemporal kernel density of the target area according to all the window matrices;

[0100] The result visualization module 54 is used to perform coloring processing on the pixel-time pairs in each pixel data point set to obtain a spatiotemporal kernel density visualization result of the target area.

[0101] Furthermore, if Fig.14 As shown, based on the above prefix matrix-based spatiotemporal kernel density visualization method and system, the present invention also provides a terminal accordingly, and the terminal includes a processor 10, a memory 20 and a display 30. Fig.14 Only some components of the terminal are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0102] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard disk or memory of the terminal. In other embodiments, the memory 20 may also be an external storage device of the terminal, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the terminal. Further, the memory 20 may also include both an internal storage unit of the terminal and an external storage device. The memory 20 is used to store application software and various types of data installed on the terminal, such as the program code of the installation terminal. The memory 20 may also be used to temporarily store data that has been output or is to be output. In one embodiment, a spatiotemporal kernel density visualization program 40 based on a prefix matrix is ​​stored on the memory 20, and the spatiotemporal kernel density visualization program 40 based on a prefix matrix can be executed by the processor 10, thereby realizing the spatiotemporal kernel density visualization method based on a prefix matrix in the present application.

[0103] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run the program code or process data stored in the memory 20, such as executing the prefix matrix-based spatiotemporal kernel density visualization method.

[0104] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 30 is used to display information on the terminal and to display a visual user interface. The components of the terminal communicate with each other via a system bus.

[0105] In one embodiment, when the processor 10 executes the prefix matrix-based spatiotemporal kernel density visualization program 40 in the memory 20 , the steps of the prefix matrix-based spatiotemporal kernel density visualization method described above are implemented.

[0106] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a prefix matrix-based spatiotemporal kernel density visualization program, and when the prefix matrix-based spatiotemporal kernel density visualization program is executed by a processor, the steps of the prefix matrix-based spatiotemporal kernel density visualization method as described above are implemented.

[0107] In summary, the present invention provides a spatiotemporal kernel density visualization method based on prefix matrix and related equipment, the method comprising: obtaining the limiting information input by the user, determining a first preset number of timestamps according to the limiting information, determining the corresponding time axis according to each of the timestamps, and dividing a second preset number of time bandwidths on each of the time axes according to the limiting information; obtaining the pixel data point set corresponding to each timestamp in the target area, constructing multiple prefix matrices according to each of the pixel data point sets and all of the time bandwidths on each of the time axes; constructing multiple window matrices according to the multiple prefix matrices, and calculating the spatiotemporal kernel density of the target area according to all of the window matrices; coloring the pixel-time pairs in each of the pixel data point sets to obtain the spatiotemporal kernel density visualization result of the target area. The present invention studies the problems of exploratory, traditional spatiotemporal kernel density visualization and bandwidth adjustment through prefix structure, obtains different numbers of prefix matrices, and performs coloring, realizes the visualization of spatiotemporal kernel density, reduces the time complexity in the calculation process, and also ensures considerable space complexity, while considering the time and space dimensions, and improves the visualization efficiency of the map.

[0108] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or terminal including the element.

[0109] Of course, those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the program can be stored in a computer-readable storage medium that can be read by a computer, and the program can include the processes of the above-mentioned method embodiments when executed. The computer-readable storage medium can be a memory, a disk, an optical disk, etc.

[0110] It should be understood that the application of the present invention is not limited to the above examples. For ordinary technicians in this field, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to the present invention.

Claims

1. A spatiotemporal kernel density visualization method based on prefix matrix, characterized in that: The prefix matrix-based spatiotemporal kernel density visualization method includes: Acquire limiting information input by a user, determine a first preset number of timestamps according to the limiting information, determine a corresponding time axis according to each of the timestamps, and divide a second preset number of time bandwidths on each of the time axes according to the limiting information; Obtaining a pixel data point set corresponding to each time stamp in the target area, and constructing a plurality of prefix matrices according to each pixel data point set and all the time bandwidths on each time axis; The step of obtaining a pixel data point set corresponding to each time stamp in the target area and constructing a plurality of prefix matrices according to each pixel data point set and all the time bandwidths on each time axis specifically includes: Obtain a pixel data point set corresponding to each timestamp in the target area, and extract all pixel points in each pixel data point set; Constructing a plurality of pixel-time pairs according to all pixel points and a fourth preset number of endpoints on each time axis; According to all the pixel-time pairs, a prefix matrix corresponding to each of the endpoints is constructed: ； ； in, represents the pixel position of the prefix matrix, represents the entire set of spatiotemporal data points, express A data point in Indicates The timestamps corresponding to the pixel-time pairs, Indicates the number of timestamps, represents a constant whose value is determined by the time kernel function. express of Power, Indicates The prefix matrix of timestamps, express location, express timestamp, represents the spatial kernel function, express A set of spatiotemporal data points; Constructing multiple window matrices according to the multiple prefix matrices, and calculating the spatiotemporal kernel density of the target area according to all the window matrices; The pixel-time pairs in each pixel data point set are color-filled to obtain a spatiotemporal kernel density visualization result of the target area.

2. The prefix matrix-based spatiotemporal kernel density visualization method according to claim 1, characterized in that: The obtaining of the limiting information input by the user, determining a first preset number of timestamps according to the limiting information, determining a corresponding time axis according to each of the timestamps, and dividing a second preset number of time bandwidths on each of the time axes according to the limiting information, specifically includes: Acquire limiting information input by a user, wherein the limiting information is used to limit the number of timestamps in a target area, and the number of spatial bandwidths and time bandwidths at each timestamp; Determine a first preset number of time stamps in the target area according to the limiting information, and determine a corresponding time axis according to each of the time stamps; According to the limiting information, a second preset number of time bandwidths and a third preset number of space bandwidths are divided on each of the time axes.

3. The prefix matrix-based spatiotemporal kernel density visualization method according to claim 2, characterized in that: The dividing, on each of the time axes, of a second preset number of time bandwidths and a third preset number of space bandwidths according to the limiting information specifically includes: Fixing the single spatial bandwidth, and determining a second preset number of time bandwidths on each of the time axes according to a second preset number of time bandwidths; A fourth preset number of endpoints is determined according to all the time bandwidths.

4. The spatiotemporal kernel density visualization method based on prefix matrix according to claim 1, characterized in that: The step of constructing a plurality of window matrices according to the plurality of prefix matrices and calculating the spatiotemporal kernel density of the target area according to all the window matrices specifically includes: Construct multiple window matrices based on the fourth preset number of prefix matrices on each time axis: ； in, represents the window matrix used to calculate the spatiotemporal kernel density, represents a constant whose value is determined by the time kernel function. and They represent the time bandwidth respectively. Time The prefix matrix of the two endpoints in the timestamp, represents the time bandwidth, Indicates The timestamp corresponding to the window matrix; Calculate the spatiotemporal kernel density of the target area based on all the window matrices: ； in, Indicates The space-time kernel density of the timestamp, timestamps representing spatiotemporal data points, express and The Euclidean distance between represents the normalization constant, express The window matrix is ​​0, express A window matrix of 1, express A window matrix of 2.

5. The prefix matrix-based spatiotemporal kernel density visualization method according to claim 2, characterized in that: The step of constructing a plurality of window matrices according to the plurality of prefix matrices and calculating the spatiotemporal kernel density of the target area according to all the window matrices further includes: Calculate the time complexity of the prefix matrix of each endpoint on the time axis to obtain a first time complexity; Calculate the time complexity of multiple prefix matrices corresponding to each of the time axes to obtain a second time complexity; The time complexity of multiple prefix matrices corresponding to each of the spatial bandwidths and each of the temporal bandwidths is calculated to obtain a third time complexity.

6. The prefix matrix-based spatiotemporal kernel density visualization method according to claim 4, characterized in that: The coloring of the pixel-time pairs in each pixel data point set to obtain the spatiotemporal kernel density visualization result of the target area specifically includes: According to the multiple time bandwidths, two prefix matrices corresponding to each window matrix are determined; Each pixel-time pair in the pixel data point set in each prefix matrix is ​​filled with colors to obtain a spatiotemporal kernel density visualization result of the target area.

7. A spatiotemporal kernel density visualization system based on prefix matrix, characterized in that: The prefix matrix-based spatiotemporal kernel density visualization system is applied to the prefix matrix-based spatiotemporal kernel density visualization method according to any one of claims 1 to 6, and the prefix matrix-based spatiotemporal kernel density visualization system includes: a bandwidth information determination module, configured to obtain limiting information input by a user, determine a first preset number of timestamps according to the limiting information, determine a corresponding time axis according to each of the timestamps, and divide a second preset number of time bandwidths on each of the time axes according to the limiting information; A prefix matrix construction module is used to obtain a pixel data point set in a target area, construct a spatiotemporal data point set corresponding to each time stamp according to the pixel data point set and all the time bandwidths on each time axis, and construct a plurality of prefix matrices according to the spatiotemporal data point set; A spatiotemporal kernel density calculation module, used to construct a plurality of window matrices according to the plurality of prefix matrices, and calculate the spatiotemporal kernel density of the target area according to all the window matrices; The result visualization module is used to perform coloring processing on the pixel-time pairs in each pixel data point set to obtain a spatiotemporal kernel density visualization result of the target area.

8. A terminal, characterized in that: The terminal includes: a memory, a processor, and a prefix matrix-based spatiotemporal kernel density visualization program stored in the memory and executable on the processor. When the prefix matrix-based spatiotemporal kernel density visualization program is executed by the processor, the steps of the prefix matrix-based spatiotemporal kernel density visualization method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a prefix matrix-based spatiotemporal kernel density visualization program, which, when executed by a processor, implements the steps of the prefix matrix-based spatiotemporal kernel density visualization method as described in any one of claims 1 to 6.

Images