A method for mining spatiotemporal objects, terminal device and storage medium

Abstract

The present invention relates to a method for mining spatiotemporal companion objects, a terminal device and a storage medium, the method comprising: receiving data for mining spatiotemporal companion objects, grouping all received data in pairs, calculating the comprehensive confidence that each group of data belongs to a spatiotemporal companion object, and determining the spatiotemporal companion object corresponding to each data according to the order of the comprehensive confidence. The present invention can better determine the reliability of the association by characterizing the spatiotemporal discreteness of the association, improve the accuracy of mining spatiotemporal companion objects, provide the most reliable clues for users, facilitate them to quickly track the latest multi-dimensional trends of the target, and also lay a good foundation for multi-dimensional fusion recommendation.

Description

Technical Field

[0001] The present invention relates to the field of data mining, and in particular to a method for mining spatiotemporal companion objects, a terminal device and a storage medium. Background Art

[0002] With the rapid development of wireless communications, mobile computing, and global positioning and navigation systems, spatiotemporal data has continued to increase, and a large number of algorithms for mining spatiotemporal companion objects have emerged. However, the following methods are generally used to mine companion objects:

[0003] The first one is the most basic one, which is to simply stack the credibility of the association based on the frequency by calculating the apriori similarity algorithm of the frequent set. This method not only takes up a lot of association storage, but also the value of the association mined is extremely low.

[0004] The second method is to combine the trajectory similarity of the geohash grid. Although this method does not simply look at the frequency, it ignores the temporal and spatial discreteness of the association, which will result in the same two associations occurring twice, and it is impossible to distinguish that the reliability of the two associations with a greater distance difference is higher. The actual scenario is as follows: A and B are associated twice at C1 and C2, 100 meters apart, respectively, and A and C are associated twice at C1 and C2, 3,000 meters apart, respectively; people will subjectively think that A and C are more reliable, and A and B may have met by chance, but the method of trajectory similarity alone cannot confirm who A is more closely related to.

[0005] Therefore, the existing spatiotemporal trajectory data association methods cannot reflect the spatiotemporal discreteness of the association. They only consider whether the data meet the basic spatiotemporal conditions and the frequency or similarity matching of the association. When the frequency is very low, the similarity matching will be distorted and it is impossible to recommend reliable associations more accurately. Summary of the invention

[0006] In order to solve the above problems, the present invention proposes a method for mining spatiotemporal companion objects, a terminal device and a storage medium.

[0007] The specific plan is as follows:

[0008] A method for mining spatiotemporal companion objects comprises: receiving data for mining spatiotemporal companion objects, grouping all received data in pairs, calculating the comprehensive confidence of each group of data that it belongs to the spatiotemporal companion object, and determining the spatiotemporal companion object corresponding to each data according to the order of the comprehensive confidence.

[0009] Furthermore, the comprehensive confidence is the weighted sum of the scores of four indicators: the number of valid associations, the number of valid association days, the maximum spatial dispersion, and the recent activity between the two data in each group.

[0010] Furthermore, the calculation method of the effective correlation number index between two data is:

[0011] S101: Calculate the number of associations between two data;

[0012] S102: After all the associations between the two data are sorted according to the association time, for any two connected associations, it is determined whether the two associations are time-space discrete. If not, the number of associations is reduced by 1. The number of associations obtained after all the two connected associations are determined is taken as the valid number of associations.

[0013] Furthermore, the calculation method of the number of associations between two data in step S101 is: if two data appear at a similar location at a similar time point, then the number of associations between the two data is set to be plus 1.

[0014] Furthermore, a method for determining that two data are at similar time points is that the time difference corresponding to the acquisition timestamps of the two data is less than a time difference threshold.

[0015] Furthermore, the method for determining whether two data are in close locations is as follows: the grid location corresponding to the collection location of one of the two data is within an M*M grid centered on the grid location corresponding to the collection location of the other data, where M represents the number of rows and columns of the M grid.

[0016] Furthermore, the method for judging whether the two associations in step S102 are space-time discrete is as follows: when the association time interval between the two associations is less than the time interval threshold, and the association location distance is less than the distance threshold, it is judged that the two associations are not space-time discrete; otherwise, it is judged that the two associations are space-time discrete.

[0017] Furthermore, the number of valid association days between two data is the total number of natural days of all associations occurring between the two data.

[0018] Furthermore, the maximum spatial dispersion between two data is calculated according to the minimum longitude and latitude and the maximum longitude and latitude of all associations between the two data.

[0019] Furthermore, the calculation formula for the maximum spatial discreteness distance between two data is:

[0020] radLat1=latitude min *π / 180.0

[0021] radLat2=latitude max *π / 180.0

[0022] radLon1=longitudemin *π / 180.0

[0023] radLon2=longitude max *π / 180.0

[0024] a=radLat1-radLat2

[0025] b=radLon1-radLon2

[0026] s=2*Math.asin(Math.sqrt(Math.pow(Math.sin(a / 2),2)+Math.cos(radLat1)*

[0027] Math.cos(radLat2)*Math.pow(Math.sin(b / 2),2)))

[0028] distance=1000*Math.round(s*EARTH_RADIUS*10000) / 10000

[0029] Among them, latitude min Indicates the minimum latitude, latitude max Indicates the maximum latitude, longitude min Indicates the minimum longitude, longitude max Represents the maximum longitude, Math.asin represents the inverse sine operation, Math.sqrt represents the square root operation, Math.sin represents the sine operation, Math.cos represents the cosine operation, Math.round represents the integer operation, Math.pow is used to return the first parameter to the power of the second parameter, EARTH_RADIUS represents the radius of the earth, radLat1 represents the minimum latitude radian value, radLat2 represents the maximum latitude radian value, radLon1 represents the minimum longitude radian value, radLon2 represents the minimum longitude radian value, a represents the difference in latitude radian values, b represents the difference in longitude radian values, s represents the difference in longitude and latitude distance, and π represents pi.

[0030] Furthermore, the recent activity between two data is the time difference between the last associated association time and the current time.

[0031] A spatiotemporal companion object mining terminal device comprises a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned method of the embodiment of the present invention are implemented.

[0032] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described above in an embodiment of the present invention are implemented.

[0033] The present invention adopts the above technical solution, which can better determine the reliability of the association by characterizing the spatiotemporal discreteness of the association, improve the accuracy of mining spatiotemporal accompanying objects, provide users with the most reliable clues, and facilitate them to quickly track the latest multi-dimensional trends of the target, while also laying a good foundation for multi-dimensional fusion recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 Shown is a flow chart of Embodiment 1 of the present invention.

[0035] Figure 2 Shown is a schematic diagram of the spatial region where the association occurs in this embodiment. DETAILED DESCRIPTION

[0036] To further illustrate various embodiments, the present invention provides drawings. These drawings are part of the disclosure of the present invention, which are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, ordinary technicians in this field should be able to understand other possible implementations and advantages of the present invention.

[0037] The present invention will now be further described with reference to the accompanying drawings and specific implementation methods.

[0038] Embodiment 1:

[0039] The embodiment of the present invention provides a method for mining spatiotemporal companion objects, which is used for mining spatiotemporal companion objects in the security field, such as Figure 1 As shown, the method includes: receiving data for spatiotemporal companion object mining, and grouping all received data in pairs, calculating the comprehensive confidence of each group of data that it belongs to the spatiotemporal companion object, and determining the spatiotemporal companion object corresponding to each data according to the order of the comprehensive confidence.

[0040] The data received in this embodiment is multi-dimensional data related to the object, including personal ID number, license plate number, base station IoT information, etc. In other embodiments, those skilled in the art can set the type of received data according to actual business needs, which is not limited here.

[0041] In this embodiment, the comprehensive confidence is the weighted sum of the four index scores of the number of valid associations between two data in each group, the number of valid association days, the maximum spatial dispersion and the recent activity. That is: Confidence = w1*scountScore+w2*dcountScore+w3*distanceScore+w4*daydiffScore

[0042] Among them, scountScore, dcountScore, distanceScore, and daydiffScore are the scores of the four indicators: the number of valid associations scount, the number of valid association days dcount, the maximum spatial dispersion distance, and the recent activity daydiff. w1, w2, w3, and w4 all represent the corresponding weights, and Confidence represents the comprehensive confidence.

[0043] The following are the calculation methods for the above four indicators between two data.

[0044] (1) Number of valid associations

[0045] The calculation method of the effective correlation number index between two data is:

[0046] S101: Calculate the number of associations between two data;

[0047] S102: After all the associations between the two data are sorted according to the association time, for any two connected associations, it is determined whether the two associations are time-space discrete. If not, the number of associations is reduced by 1. The number of associations obtained after all the two connected associations are determined is taken as the valid number of associations.

[0048] If the number of associations between two data calculated in step S101 is 10, and there are 3 connected associations in step S102 that do not have a spatiotemporal discrete type, then the final effective number of associations obtained is 10-3=7.

[0049] The calculation method of the number of associations between two data in step S101 is: if two data appear at similar locations at similar time points, then the number of associations between the two data is set to be plus 1. Specifically, the method for determining that two data are at similar time points is: the time difference corresponding to the acquisition timestamps of the two data is less than the time difference threshold; the method for determining that two data are at similar locations is: the grid location corresponding to the acquisition location of one of the two data is within an M*M grid centered on the grid location corresponding to the acquisition location of the other data, where M represents the number of rows and columns of the M grid. The time difference threshold and the size of M can be set by those skilled in the art according to their needs, and are not limited here.

[0050] In step S102, the method for determining whether the two associations have time-space discreteness is as follows: when the association time interval between the two associations is less than the time interval threshold, and the distance between the association locations is less than the distance threshold, it is determined that the two associations do not have time-space discreteness; otherwise, it is determined that the two associations have time-space discreteness. That is, only two associations with time-space discreteness are considered two valid associations, and two associations without time-space discreteness can only be considered one valid association. The time interval threshold and the distance threshold can be set by those skilled in the art according to their needs, and are not limited here.

[0051] (2) Valid association days

[0052] The number of valid association days between two data is the total number of natural days of all associations between the two data. For example, if associations occurred on June 1, 2019 and June 10, 2019, respectively, the number of valid association days is 2 days; if N associations occurred only today, June 1, 2019, the number of valid association days is only 1 day.

[0053] (3) Maximum spatial discreteness

[0054] In this embodiment, the maximum spatial dispersion between two data is calculated based on the minimum longitude and latitude and the maximum longitude and latitude in all associations between the two data, such as Figure 2 As shown, ready to use Figure 2 The rectangle formed by the four points in represents the spatial area where the correlation occurs.

[0055] The calculation formula of the maximum spatial discreteness distance in this embodiment is:

[0056] radLat1=latitude min *π / 180.0

[0057] radLat2=latitude max *π / 180.0

[0058] radLon1=longitude min *π / 180.0

[0059] radLon2=longitude max *π / 180.0

[0060] a=radLat1-radLat2

[0061] b=radLon1-radLon2

[0062] s=2*Math.asin(Math.sqrt(Math.pow(Math.sin(a / 2),2)+Math.cos(radLat1)*

[0063] Math.cos(radLat2)*Math.pow(Math.sin(b / 2),2)))

[0064] distance=1000*Math.round(s*EARTH_RADIUS*10000) / 10000

[0065] Among them, latitude min Indicates the minimum latitude, latitude max Indicates the maximum latitude, longitude min Indicates the minimum longitude, longitude max Indicates the maximum longitude, Math.asin indicates inverse sine operation, Math.sqrt indicates square root operation, Math.sin indicates sine operation, Math.cos indicates cosine operation, Math.round indicates integer operation, Math.pow is used to return the first parameter to the power of the second parameter, EARTH_RADIUS indicates the radius of the earth, radLat1 indicates the minimum latitude radian value, radLat2 indicates the maximum latitude radian value, radLon1 indicates the minimum longitude radian value, radLon2 indicates the minimum longitude radian value, a indicates the difference in latitude radian value, b indicates the difference in longitude radian value, s indicates the difference in longitude and latitude distance, π indicates pi, and the number type of 10000 in the distance calculation formula is double.

[0066] (4) Recent activity

[0067] The recent activity between two data is the time difference between the last associated association time and the current time.

[0068] After the values ​​of the four indicators are calculated by the above method, they are normalized to obtain the scores corresponding to each indicator, and the scores corresponding to each indicator are weighted and calculated to obtain the comprehensive confidence.

[0069] After sorting according to the size of the comprehensive confidence, each data obtains multiple data groups with different sizes of comprehensive confidence, and another data in the data group with the maximum comprehensive confidence is used as the spatiotemporal companion object of the data.

[0070] The embodiment of the present invention provides a method for quantifying the spatiotemporal discreteness and activity of associations, and calculates the comprehensive confidence index between each pair according to each quantitative index to quantify the reliability of the association, and then recommend more reliable associations. This embodiment is applicable to any pairwise associations between any dimension of any spatiotemporal perception data.

[0071] Embodiment 2:

[0072] The present invention also provides a spatiotemporal companion object mining terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in the above-mentioned method embodiment of the first embodiment of the present invention when executing the computer program.

[0073] Further, as an executable solution, the spatiotemporal companion object mining terminal device can be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The spatiotemporal companion object mining terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the composition structure of the spatiotemporal companion object mining terminal device is only an example of the spatiotemporal companion object mining terminal device, and does not constitute a limitation on the spatiotemporal companion object mining terminal device. It may include more or less components than the above, or combine certain components, or different components. For example, the spatiotemporal companion object mining terminal device may also include input and output devices, network access devices, buses, etc., which are not limited in the embodiments of the present invention.

[0074] Further, as an executable solution, the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the spatiotemporal companion object mining terminal device, and uses various interfaces and lines to connect various parts of the entire spatiotemporal companion object mining terminal device.

[0075] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the spatiotemporal companion object mining terminal device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system and at least one application required for a function; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0076] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above method in the embodiment of the present invention are implemented.

[0077] If the module / unit integrated in the spatiotemporal companion object mining terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory) and software distribution medium, etc.

[0078] Although the present invention has been specifically shown and described in conjunction with the preferred embodiments, it should be understood by those skilled in the art that various changes may be made to the present invention in form and details without departing from the spirit and scope of the present invention as defined by the appended claims, all of which are within the scope of protection of the present invention.

Claims

1. A method for mining spatiotemporal companion objects, characterized in that: include: Receive data for spatiotemporal companion object mining, and group all received data in pairs. For each group of data, calculate the comprehensive confidence that it belongs to the spatiotemporal companion object, and determine the spatiotemporal companion object corresponding to each data according to the ranking of the comprehensive confidence. The comprehensive confidence is the weighted sum of the scores of the four indicators of the number of valid associations, the number of valid association days, the maximum spatial dispersion, and the recent activity between the two data in each group. The calculation method of the effective correlation number index between two data is: S101: Calculate the number of associations between two data; S102: After all the associations between the two data are sorted according to the association time, for any two connected associations, determine whether the two associations are of time-space discrete type. If not, reduce the number of associations by 1, and take the number of associations obtained after all the two connected associations are determined as the effective number of associations; the method for determining whether the two associations are of time-space discrete type is as follows: when the association time interval between the two associations is less than the time interval threshold, and the distance between the association locations is less than the distance threshold, determine that the two associations are not of time-space discrete type; otherwise, determine that the two associations are of time-space discrete type; The number of effective association days between two data is the total number of natural days of all associations between the two data; The calculation formula for the maximum spatial discreteness distance between two data is: radLat1=latitude min *π / 180.0 radLat2=latitude max *π / 180.0 workLon1=longitude min *π / 180.0 radLon2=longitude max *π / 180.0 a=radLat1-radLat2 b=radLon1-radLon2 s=2*Math.asin(Math.sqrt(Math.pow(Math.sin(a / 2),2)+Math.cos(radLat1)*Math.cos(radLat2)*Math.pow(Math.sin(b / 2),2))) distance=1000*Math.round(s*EARTH_RADIUS*10000) / 10000 Among them, latitude min Indicates the minimum latitude, latitude max Indicates the maximum latitude, longitude min Indicates the minimum longitude, longitude max Indicates the maximum longitude, Math.asin indicates the arc sine operation, Math.sqrt indicates the square root operation, Math.sin indicates the sine operation, Math.cos indicates the cosine operation, Math.round indicates the integer operation, Math.pow is used to return the first parameter to the power of the second parameter, EARTH_RADIUS indicates the radius of the earth, radLat1 indicates the minimum latitude radian value, radLat2 indicates the maximum latitude radian value, radLon1 indicates the minimum longitude radian value, radLon2 indicates the minimum longitude radian value, a indicates the difference in latitude radian values, b indicates the difference in longitude radian values, s indicates the difference in longitude and latitude distance, and π indicates the ratio of pi; The recent activity between two data is the time difference between the last associated association time and the current time.

2. The method for mining spatiotemporal companion objects according to claim 1, characterized in that: The method for calculating the number of associations between two data in step S101 is: if two data appear at a similar location at a similar time point, the number of associations between the two data is set to be plus 1.

3. The method for mining spatiotemporal companion objects according to claim 2, characterized in that: The method for determining that two data are at similar time points is: the time difference corresponding to the acquisition timestamps of the two data is less than the time difference threshold.

4. The method for mining spatiotemporal companion objects according to claim 2, characterized in that: The method for determining whether two data are in close locations is as follows: the grid location corresponding to the collection location of one of the two data is within an M*M grid centered on the grid location corresponding to the collection location of the other data, where M represents the number of rows and columns of the M grid.

5. A time-space companion object mining terminal device, characterized in that: The method comprises a processor, a memory and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 4 when executing the computer program.

6. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images