Region classification method, apparatus, and storage medium
By acquiring simulation and measurement data, calculating the difference between received power and signal-to-noise ratio, and using cluster analysis to divide regions, the problems of high cost and low efficiency in existing technologies are solved, achieving low-cost, high-efficiency, and accurate region classification.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA UNITED NETWORK COMM GRP CO LTD
- Filing Date
- 2023-01-05
- Publication Date
- 2026-08-04
AI Technical Summary
Existing geographic scene classification technologies are costly and inefficient, relying mainly on manual experience for classification and the reading of 3D digital map data, resulting in high labor costs and low efficiency.
By acquiring simulation and measurement data, the difference between received power and signal-to-noise ratio is calculated, and cluster analysis is used to divide the region, thereby reducing costs and improving efficiency.
It achieves low-cost, efficient, and accurate regional classification, reduces reliance on manual experience-based classification, and lowers the cost of collecting 3D digital maps.
Smart Images
Figure CN116257774B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of communication technology, and in particular to a method, apparatus and storage medium for area classification. Background Technology
[0002] In wireless simulation technology, the geographical scene classification of base stations is a key fundamental parameter. A geographical scene refers to a regional complex with a specific structure and function, formed by the interconnection and interaction of various natural and human elements within a certain spatiotemporal range.
[0003] Existing geographic scene classification technologies primarily rely on manual experience and scene type data from 3D digital maps. Manual experience-based classification, in particular, involves personnel familiar with city-level and geographical environments classifying geographic scenes. This method suffers from high labor costs and low efficiency. Creating 3D maps from remote sensing images and processing scene type data from 3D digital maps requires 3D digital maps of all cities nationwide, which is costly to acquire. Summary of the Invention
[0004] This application provides a region classification method, apparatus, and storage medium, which solves the problems of high cost and low efficiency of existing region classification technologies, and can classify regions efficiently and at low cost.
[0005] To achieve the above objectives, this application adopts the following technical solution:
[0006] Firstly, this application provides a region classification method, which includes: acquiring N simulation data and N measurement data; the simulation data includes the simulated latitude and longitude, simulated received power, and simulated signal-to-noise ratio of the simulation region; the measurement data includes the measured latitude and longitude, measured received power, and measured signal-to-noise ratio of the measurement region; N is a positive integer; comparing the N simulation data and the N measurement data to obtain N target data; the target data includes the difference between the simulated received power and the measured received power corresponding to the target region, and the difference between the simulated signal-to-noise ratio and the measured signal-to-noise ratio; performing cluster analysis on the target data to obtain the region classification result for each simulation region; the region classification result is used to characterize the scene information of the simulation region.
[0007] The above solution offers at least the following advantages: Based on the above technical solution, the region classification method provided in this application first acquires N simulation data and N measurement data, and obtains N target data by comparing the N simulation data and N measurement data. Then, the region classification device performs cluster analysis on the target data to obtain the region classification result for each simulation region. Compared with existing technologies that rely on manual experience for division and reading scene type data from 3D digital maps, which are costly and inefficient, the above technical solution can divide regions in a low-cost, efficient, and accurate manner.
[0008] In conjunction with the first aspect mentioned above, in one possible implementation, the method further includes: acquiring base station data corresponding to each of the multiple first regions within the simulation area; determining simulation parameters of the simulation model; the simulation parameters include frequency point data, bandwidth data, and transmit power; and inputting the base station data corresponding to each first region within the simulation area into the simulation model to obtain simulation data.
[0009] In conjunction with the first aspect above, in one possible implementation, the method further includes: determining that the simulation area and the measurement area are the same target area when the simulated latitude and longitude of the simulation area are the same as the measured latitude and longitude of the measurement area; for N target areas, calculating the difference between the simulated received power of the simulation area and the measured received power of the measurement area corresponding to each target area; and for N target areas, calculating the difference between the simulated signal-to-noise ratio of the simulation area and the measured signal-to-noise ratio of the measurement area corresponding to each target area.
[0010] In conjunction with the first aspect mentioned above, in one possible implementation, the method further includes: determining K target data points out of N target data points as K first target centroids; K is less than or equal to N; clustering the N target data points based on the K first target centroids to obtain K target sets; wherein, a target set includes M target data points; M is a positive integer; M is less than or equal to N; determining the region classification result of the simulation area as the category of the corresponding target set; the category of the target set is used to characterize the scene information of the simulation area.
[0011] In conjunction with the first aspect described above, in one possible implementation, the method further includes: repeatedly performing the first operation to ensure that all K first distances are less than a preset threshold, thereby determining K target sets; the first operation includes: for each target data in N target data, calculating the Euclidean distance between the target data and each first target centroid, obtaining K first Euclidean distances corresponding to the target data; for each target data in N target data, determining the second Euclidean distance with the smallest value among the K first Euclidean distances corresponding to the target data; determining K first data sets based on the second Euclidean distance of each target data; the K first data sets correspond one-to-one with the K first target centroids; the second Euclidean distance of any target data in the first data set is the Euclidean distance between the target data and the first target centroid corresponding to the first data set; for each of the K first data sets, taking the center point of the target data in the first data set as the second target centroid; for each of the K first data sets, calculating the distance between the first target centroid and the second target centroid corresponding to the first data set, obtaining K first distances; taking the second target centroid corresponding to the first data set as the first target centroid.
[0012] Secondly, this application provides a region classification device, which includes: a communication unit and a processing unit; the communication unit is used to acquire N simulation data and N measurement data; the simulation data includes the simulated latitude and longitude, simulated received power, and simulated signal-to-noise ratio of the simulated region; the measurement data includes the measured latitude and longitude, measured received power, and measured signal-to-noise ratio of the measured region; N is a positive integer; the processing unit is used to compare the N simulation data and the N measurement data to obtain N target data; the target data includes the difference between the simulated received power and the measured received power corresponding to the target region, and the difference between the simulated signal-to-noise ratio and the measured signal-to-noise ratio; the processing unit is further used to perform cluster analysis on the target data to obtain the region classification result of each simulation region; the region classification result is used to characterize the scene information of the simulation region.
[0013] In conjunction with the second aspect above, in one possible implementation, the communication unit is further configured to acquire base station data corresponding to each of the multiple first regions within the simulation area; the processing unit is further configured to determine the simulation parameters of the simulation model; the simulation parameters include frequency point data, bandwidth data, and transmission power; the processing unit is further configured to input the base station data corresponding to each first region within the simulation area into the simulation model to obtain simulation data.
[0014] In conjunction with the second aspect above, in one possible implementation, the processing unit is further configured to: determine that the simulation area and the measurement area are the same target area when the simulated latitude and longitude of the simulation area are the same as the measured latitude and longitude of the measurement area; calculate the difference between the simulated received power of the simulation area and the measured received power of the measurement area for each of the N target areas; and calculate the difference between the simulated signal-to-noise ratio of the simulation area and the measured signal-to-noise ratio of the measurement area for each of the N target areas.
[0015] In conjunction with the second aspect above, in one possible implementation, the processing unit is further configured to: determine K target data out of N target data as K first target centroids; K is less than or equal to N; based on the K first target centroids, cluster the N target data to obtain K target sets; wherein, a target set includes M target data; M is a positive integer; M is less than or equal to N; determine the region classification result of the simulation area as the category of the corresponding target set; the category of the target set is used to characterize the scene information of the simulation area.
[0016] In conjunction with the second aspect above, in one possible implementation, the processing unit is further configured to: repeatedly execute the first operation to ensure that all K first distances are less than a preset threshold, thereby determining K target sets; the first operation includes: for each target data in N target data, calculating the Euclidean distance between the target data and each first target centroid, obtaining K first Euclidean distances corresponding to the target data; for each target data in N target data, determining the second Euclidean distance with the smallest value among the K first Euclidean distances corresponding to the target data; determining K first data sets based on the second Euclidean distance of each target data; the K first data sets correspond one-to-one with the K first target centroids; the second Euclidean distance of any target data in the first data set is the Euclidean distance between the target data and the first target centroid corresponding to the first data set; for each of the K first data sets, taking the center point of the target data in the first data set as the second target centroid; for each of the K first data sets, calculating the distance between the first target centroid corresponding to the first data set and the second target centroid, obtaining K first distances; taking the second target centroid corresponding to the first data set as the first target centroid.
[0017] Thirdly, this application provides a region classification apparatus, which includes: a processor and a communication interface; the communication interface and the processor are coupled, and the processor is used to run computer programs or instructions to implement the region classification method as described in the first aspect and any possible implementation of the first aspect.
[0018] Fourthly, this application provides a computer-readable storage medium storing instructions that, when executed on a terminal, cause the terminal to perform the region classification method as described in the first aspect and any possible implementation thereof.
[0019] Fifthly, this application provides a computer program product containing instructions that, when run on a region classification device, cause the region classification device to perform the region classification method as described in the first aspect and any possible implementation thereof.
[0020] In a sixth aspect, this application provides a chip including a processor and a communication interface coupled to the processor. The processor is used to run computer programs or instructions to implement the region classification method as described in the first aspect and any possible implementation thereof.
[0021] Specifically, the chip provided in this application also includes a memory for storing computer programs or instructions.
[0022] It should be noted that the aforementioned computer instructions may be stored, in whole or in part, on a computer-readable storage medium. This computer-readable storage medium may be packaged together with the processor of the device, or it may be packaged separately from the processor of the device; this application does not impose any limitation on this.
[0023] In a seventh aspect, this application provides a regional classification system, comprising: a regional classification device and a data server, wherein the regional classification device is used to perform the regional classification method as described in the first aspect and any possible implementation thereof.
[0024] The descriptions of aspects two through seven in this application can be referenced to the detailed description of aspect one; and the beneficial effects of the descriptions of aspects two through seven can be referenced to the analysis of the beneficial effects of aspect one, which will not be repeated here.
[0025] In this application, the names of the aforementioned area classification devices do not limit the devices or functional modules themselves. In actual implementation, these devices or functional modules may appear under other names. As long as the functions of each device or functional module are similar to those in this application, they fall within the scope of the claims of this application and their equivalents.
[0026] These or other aspects of this application will become more readily apparent in the following description. Attached Figure Description
[0027] Figure 1 This is a schematic diagram of the architecture of a region classification system provided in an embodiment of this application;
[0028] Figure 2A flowchart illustrating a region classification method provided in this application embodiment;
[0029] Figure 3 A flowchart illustrating another region classification method provided in this application embodiment;
[0030] Figure 4 This is a schematic diagram of the structure of a region classification device provided in an embodiment of this application;
[0031] Figure 5 This is a schematic diagram of another region classification device provided in an embodiment of this application. Detailed Implementation
[0032] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0033] In this article, the term "and / or" is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.
[0034] The terms "first" and "second," etc., used in the specification and drawings of this application are used to distinguish different objects or to distinguish different treatments of the same object, rather than to describe a specific order of objects.
[0035] Furthermore, the terms "comprising" and "having," and any variations thereof, used in the description of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the steps or units listed, but may optionally include other steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus.
[0036] It should be noted that in the embodiments of this application, the words "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.
[0037] In the description of this application, unless otherwise stated, "a plurality of" means two or more.
[0038] In wireless simulation technology, the geographical scene classification of base stations is a key fundamental parameter. A geographical scene refers to a regional complex with a specific structure and function, formed by the interconnection and interaction of various natural and human elements within a certain spatiotemporal range.
[0039] Existing geographic scene classification technologies primarily rely on manual experience and scene type data from 3D digital maps. Manual experience-based classification, in particular, involves personnel familiar with city-level and geographical environments classifying geographic scenes. This method suffers from high labor costs and low efficiency. Creating 3D maps from remote sensing images and processing scene type data from 3D digital maps requires 3D digital maps of all cities nationwide, which is costly to acquire.
[0040] Based on this, this application proposes a region classification method. The region classification device first acquires N simulation data points and N measurement data points, and obtains N target data points by comparing the N simulation data points and the N measurement data points. Then, the region classification device performs cluster analysis on the target data points to obtain the region classification result for each simulation region. Compared to existing technologies that rely on manual experience for region classification and read scene type data from 3D digital maps, which are costly and inefficient, the above technical solution can classify regions in a low-cost, efficient, and accurate manner.
[0041] The embodiments of this application will now be described in detail with reference to the accompanying drawings.
[0042] Figure 1 This is an architecture diagram of a region classification system 10 provided in an embodiment of this application. Figure 1 As shown, the regional classification system 10 includes: a regional classification device 101 and a data server 102.
[0043] The region classification device 101 and the data server 102 can be one or more, for ease of understanding. Figure 1 Only one is shown in the image.
[0044] The area classification device 101 and the data server 102 are connected via a communication link. This communication link can be a wired communication link or a wireless communication link, and this application does not limit it in this way.
[0045] The aforementioned area classification device 101 and data server 102 include:
[0046] The processor can be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of the program in this application.
[0047] A transceiver can be any type of transceiver used to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area network (WLAN), etc.
[0048] Memory can be read-only memory (ROM) or other types of static storage devices capable of storing static information and instructions, random access memory (RAM) or other types of dynamic storage devices capable of storing information and instructions, electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed discs, laser discs, optical discs, universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto. Memory can exist independently and be connected to the processor via communication lines. Memory can also be integrated with the processor.
[0049] One possible implementation is that the region classification device 101 performs network simulation based on base station data for each first region to obtain simulation data, and compares the simulation results with the measurement data provided by the data server 102 to obtain a comparison result. Then, the region classification device 101 performs cluster analysis on the difference between the comparison results to obtain the region classification result.
[0050] In one possible implementation, the data server 102 is used to provide measurement data and base station data for each of the multiple first regions to the region classification device 101.
[0051] For example, data server 102 stores measurement report (MR) data provided by the operator and base station data for each first area in its memory. Data server 102 sends the MR data and base station data to area classification device 101 for area classification.
[0052] It should be noted that the various embodiments of this application can be referenced or learned from each other. For example, the same or similar steps, method embodiments, system embodiments and device embodiments can be referenced from each other without limitation.
[0053] Figure 2 A flowchart illustrating a region classification method provided in an embodiment of this application. Figure 2 As shown, the method includes the following steps:
[0054] S201, The regional classification device acquires N simulation data and N measurement data.
[0055] The simulation data includes the simulated latitude and longitude, simulated received power, and simulated signal-to-noise ratio of the simulated area, while the measurement data includes the measured latitude and longitude, measured received power, and measured signal-to-noise ratio of the measured area. N is a positive integer.
[0056] One possible implementation is that the region classification device in S201 can acquire N simulation data through the following S2011-S2013.
[0057] S2011. For each of the multiple first regions within the simulation area, obtain the base station data corresponding to the first region.
[0058] For example, as shown in Table 1, the regional classification device acquires core basic data such as longitude, latitude, orientation angle, downtilt angle, and mounting height of the base stations of each cell within the simulation area, as well as range parameters such as province, city, and administrative region.
[0059] Among them, the cell is the configuration corresponding to the most logical cells in the urban network, such as 5G, 4G or 3G.
[0060] Table 1 Cell Base Station Parameter Table
[0061]
[0062] S2012, The regional classification device determines the simulation parameters of the simulation model.
[0063] The simulation parameters include frequency data, bandwidth data, and transmit power.
[0064] One possible implementation is that the region classification device sets the transmission power in the simulation model based on the frequency point data, bandwidth data, and transmission power corresponding to the link budget.
[0065] For example, the area classification device models the frequency band / frequency point to be used based on the frequency point and subcarrier bandwidth corresponding to the link budget, sets the subcarrier bandwidth and primary synchronization signal (PSS) transmit power for the cell base station parameters, and sets the PSS transmit power in the simulation model.
[0066] S2013. The regional classification device inputs the base station data corresponding to each first region within the simulation area into the simulation model to obtain simulation data.
[0067] For example, the regional classification device inputs core basic data such as longitude, latitude, azimuth, downtilt angle, and mounting height of base stations in each cell within the simulation area, as well as range parameters such as province, city, and administrative region, into the simulation model for simulation calculation, resulting in simulation data with a size of 50m×50m grid processing. As shown in Table 2, the simulation data includes three simulation areas, and the simulation data includes data such as province, city, center longitude, center latitude, average received power, and average signal-to-noise ratio for each grid in the simulation area.
[0068] Table 2 Summary of Simulation Data
[0069]
[0070] One possible implementation involves a region classification device acquiring measurement data of the target size.
[0071] For example, consider N measurement data points as MR data. The area classification device acquires MR data provided by the operator, which is rasterized to a size of 50m × 50m. As shown in Table 3, the data includes measurement data from three measurement areas. Each measurement data point includes information such as the province, city, center longitude, center latitude, average received power, and average signal-to-noise ratio for each grid cell in the measurement area.
[0072] Table 3 Summary of Measurement Data
[0073]
[0074] S202. The regional classification device compares N simulation data and N measurement data to obtain N target data.
[0075] The target data includes the difference between the simulated received power and the measured received power corresponding to the target area, as well as the difference between the simulated signal-to-noise ratio and the measured signal-to-noise ratio.
[0076] One possible implementation is that the above-mentioned region classification device compares N simulation data and N measurement data to obtain N target data, which can be achieved through the following S2021-S2023.
[0077] S2021. When the simulated latitude and longitude of the simulated area are the same as the measured latitude and longitude of the measured area, the area classification device determines that the simulated area and the measured area are the same target area.
[0078] One possible implementation involves a region classification device comparing the simulated latitude and longitude of N simulated regions with the measured latitude and longitude of N measured regions. If the simulated latitude and longitude of the simulated regions are the same as the measured latitude and longitude of the measured regions, the region classification device determines that the simulated regions and the measured regions are the same target region.
[0079] For example, the region classification device compares the center longitude and center latitude of the simulated grid 1, the center longitude and center latitude of the simulated grid 2, and the center longitude and center latitude of the simulated grid 3 with the center longitude and center latitude of the measured grid 1, the measured grid 2, and the measured grid 3.
[0080] For example, the center longitude and center latitude of the simulated grid 1 are 115.7464 and 33.7999, respectively. The center longitude and center latitude of the measured grid 1 are also 115.7464 and 33.7999, respectively. Therefore, the region classification device determines that the simulated grid 1 and the measured grid 1 belong to the same target region.
[0081] S2022. For N target areas, the area classification device calculates the difference between the simulated received power of the simulated area and the measured received power of the measured area for each target area.
[0082] For example, taking N target regions as 3 target regions, with simulated received power of -96.6045 for simulated grid 1, -110.324 for simulated grid 2, -83.2164 for measured grid 1, and -98.2496 for measured grid 2, the region classification device calculates the difference between the simulated received power of simulated grid 1 and the measured received power of measured grid 1 corresponding to target region 1 as -13.3881. The region classification device calculates the difference between the simulated received power of simulated grid 2 and the measured received power of measured grid 2 corresponding to target region 2 as -12.0744.
[0083] S2023. For N target regions, the region classification device calculates the difference between the simulated signal-to-noise ratio of the simulated region and the measured signal-to-noise ratio of the measured region for each target region.
[0084] For example, taking N target regions as 3 target regions, with the simulated signal-to-noise ratio (SNR) of simulated grid 1 being 2.5412, simulated grid 2 being 3.1756, measured grid 1 being 1.8764, and measured grid 2 being 0.2451, the region classification device calculates the difference between the simulated SNR of simulated grid 1 and the measured SNR of measured grid 1 corresponding to target region 1 as 0.6648. The region classification device calculates the difference between the simulated SNR of simulated grid 2 and the measured SNR of measured grid 2 corresponding to target region 2 as 2.9305.
[0085] S203. The region classification device performs cluster analysis on the target data to obtain the region classification results for each simulated region.
[0086] Among them, the region classification results are used to characterize the scene information of the simulation region.
[0087] One possible implementation involves the region classification device performing cluster analysis on N target data using the k-means clustering algorithm to obtain K categories of target data. The region classification device then uses the category of the target set corresponding to each target data point as the region classification result.
[0088] One possible implementation is that the region classification device performs cluster analysis on the target data to obtain the region classification result for each simulated region, which can be achieved through the following S2031-S2033.
[0089] S2031, The region classification device determines K target data out of N target data as K first target centroids.
[0090] Where K is less than or equal to N.
[0091] For example, the region classification device randomly selects K target data from N target data as K first target centroids based on the K value determined by the user.
[0092] S2032. The region classification device clusters N target data based on K first target centroids to obtain a set of K targets.
[0093] A target set includes M target data points, where M is a positive integer and M is less than or equal to N.
[0094] For example, based on K first target centroids, the region classification device clusters N target data into a set of K targets using the K-means clustering algorithm.
[0095] S2033, The region classification device determines the region classification result of the simulation region as the category of the corresponding target set.
[0096] The categories of the target set are used to characterize the scene information of the simulation area.
[0097] One possible implementation is that the region classification device determines the region classification result of the target data as the category of the target set to which the target data belongs.
[0098] For example, taking a user-defined K value of 3, the three target sets correspond to type 1, type 2, and type 3, respectively. The region classification result of the M target data in target set 1 is type 1. The region classification result of the M target data in target set 2 is type 2. The region classification result of the M target data in target set 3 is type 3.
[0099] For example, as shown in Table 4, the target data corresponding to raster number 1 is data in target set 1; therefore, the region classification result for the target data corresponding to raster number 1 is type 1. The target data corresponding to raster number 2 is data in target set 2; therefore, the region classification result for the target data corresponding to raster number 2 is type 2. The target data corresponding to raster number 3 is data in target set 3; therefore, the region classification result for the target data corresponding to raster number 3 is type 3.
[0100] Table 4 Summary of Regional Classification Results
[0101] XX XX 1 115.7464 33.7999 Type 1 XX XX 2 118.3725 31.31351 Type 2 XX XX 3 115.7245 33.8424 Type 3
[0102] Based on the above technical solution, the region classification device first acquires N simulation data points and N measurement data points, and obtains N target data points by comparing the N simulation data points and N measurement data points. Then, the region classification device performs cluster analysis on the target data to obtain the region classification result for each simulation region. Compared to existing technologies that rely on manual experience for region division and reading scene type data from 3D digital maps, which are costly and inefficient, the above technical solution can divide regions in a low-cost, efficient, and accurate manner.
[0103] As one possible embodiment of this application, such as Figure 3 As shown, the above-mentioned region classification device clusters N target data based on K first target centroids to obtain a set of K targets, which can be achieved through the following S301.
[0104] S301, The region classification device repeatedly performs the first operation to ensure that all K first distances are less than a preset threshold, thereby determining a set of K targets.
[0105] One possible implementation is that the region classification device repeatedly performs the first operation, calculating K first distances. If all K first distances are less than a preset threshold, a set of K targets is determined.
[0106] For example, with K = 4, K first distances being 1.5, 2.2, 2, and 0.4 respectively, and a preset threshold of 3, the region classification device determines that all four first distances are less than the preset threshold, thus identifying four target sets.
[0107] One possible implementation is that the first operation can be implemented through the following S302-S306.
[0108] S302. For each of the N target data, the region classification device calculates the Euclidean distance between the target data and each first target centroid, and obtains the K first Euclidean distances corresponding to the target data.
[0109] For example, taking a K value of 3, the region classification device calculates the Euclidean distance between each of the N target data points and the centroid of each first target, obtaining three first Euclidean distances corresponding to the target data. The formula for calculating the Euclidean distance is as follows:
[0110]
[0111] Where D is the Euclidean distance, R i R is the received power of the target data. c S is the received power of the first target centroid. i S represents the signal-to-noise ratio of the target data. c The signal-to-noise ratio for the first target centroid.
[0112] S303, For each of the N target data, the region classification device determines the second Euclidean distance with the smallest value among the K first Euclidean distances corresponding to the target data.
[0113] For example, with K = 3 and the three first Euclidean distances being 30, 32, and 35 respectively, for each of the N target data, the region classification device determines the first Euclidean distance with the smallest value (30) from the three first Euclidean distances of the target data as the second Euclidean distance.
[0114] S304. The region classification device determines K first data sets based on the second Euclidean distance of each target data.
[0115] Among them, K first data sets correspond one-to-one with K first target centroids, and the second Euclidean distance of any target data in the first data set is the Euclidean distance between the target data and the first target centroid corresponding to the first data set.
[0116] For example, based on the second Euclidean distance of the target data, the region classification device classifies the target data to the first target centroid corresponding to the second Euclidean distance, and determines the M target data corresponding to each first target centroid as a first data set.
[0117] S305. For each of the K first data sets, the region classification device takes the center point of the target data in the first data set as the second target centroid.
[0118] S306. For each of the K first data sets, the region classification device calculates the distance between the first target centroid and the second target centroid corresponding to the first data set, obtains K first distances, and takes the second target centroid corresponding to the first data set as the first target centroid.
[0119] For example, taking the position of the first target centroid corresponding to the first data set as (1, 2, 3) and the position of the second target centroid corresponding to the first data set as (3, 2, 3), the region classification device calculates the distance between the position of the first target centroid corresponding to the first data set and the position of the second target centroid corresponding to the first data set as 2.
[0120] Based on the above technical solution, the region classification device repeatedly performs the first operation to ensure that all K first distances are less than a preset threshold, thereby determining K target sets. Furthermore, for each of the N target data sets, the region classification device calculates the Euclidean distance between the target data and each first target centroid, obtaining K first Euclidean distances corresponding to the target data. For each of the N target data sets, it determines the second Euclidean distance with the smallest value among the K first Euclidean distances. Then, based on the second Euclidean distance of each target data, the region classification device determines K first data sets. For each of the K first data sets, the center point of the target data in the first data set is taken as the second target centroid. For each of the K first data sets, the distance between the first target centroid and the second target centroid corresponding to the first data set is calculated, obtaining K first distances. The second target centroid corresponding to the first data set is taken as the first target centroid. Therefore, the region classification device in the above technical solution can efficiently and accurately determine K target sets by using a K-means iterative algorithm.
[0121] This application embodiment can divide the region classification device into functional modules or functional units according to the above method example. For example, each function can be divided into a separate functional module or functional unit, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or in software functional modules or functional units. The module or unit division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.
[0122] like Figure 4 The diagram shown is a structural schematic of a region classification device 40 provided in an embodiment of this application. The region classification device 40 includes a communication unit 401 and a processing unit 402.
[0123] The communication unit 401 is used to acquire N simulation data and N measurement data; the simulation data includes the simulated latitude and longitude of the simulation area, the simulated received power, and the simulated signal-to-noise ratio; the measurement data includes the measured latitude and longitude of the measurement area, the measured received power, and the measured signal-to-noise ratio; N is a positive integer.
[0124] The processing unit 402 is used to compare N simulation data and N measurement data to obtain N target data; the target data includes the difference between the simulated received power and the measured received power corresponding to the target area, and the difference between the simulated signal-to-noise ratio and the measured signal-to-noise ratio.
[0125] The processing unit 402 is also used to perform cluster analysis on the target data to obtain the region classification results for each simulation region; the region classification results are used to characterize the scene information of the simulation region.
[0126] The communication unit 401 is also used to acquire base station data corresponding to each of the multiple first regions within the simulation area.
[0127] The processing unit 402 is also used to determine the simulation parameters of the simulation model; the simulation parameters include frequency point data, bandwidth data and transmit power.
[0128] The processing unit 402 is also used to input the base station data corresponding to each first area within the simulation area into the simulation model to obtain simulation data.
[0129] The processing unit 402 is further configured to determine that the simulation area and the measurement area are the same target area when the simulated latitude and longitude of the simulation area are the same as the measured latitude and longitude of the measurement area; for N target areas, calculate the difference between the simulated received power of the simulation area and the measured received power of the measurement area corresponding to each target area; and for N target areas, calculate the difference between the simulated signal-to-noise ratio of the simulation area and the measured signal-to-noise ratio of the measurement area corresponding to each target area.
[0130] The processing unit 402 is further configured to determine K target data out of N target data as K first target centroids; K is less than or equal to N; based on the K first target centroids, cluster the N target data to obtain K target sets; wherein, a target set includes M target data; M is a positive integer; M is less than or equal to N; determine the region classification result of the simulation area as the category of the corresponding target set; the category of the target set is used to characterize the scene information of the simulation area.
[0131] The processing unit 402 is further configured to repeatedly execute the first operation to ensure that all K first distances are less than a preset threshold, thereby determining K target sets. The first operation includes: for each target data in N target data, calculating the Euclidean distance between the target data and each first target centroid to obtain K first Euclidean distances corresponding to the target data; for each target data in N target data, determining the second Euclidean distance with the smallest value among the K first Euclidean distances corresponding to the target data; determining K first data sets based on the second Euclidean distance of each target data; the K first data sets correspond one-to-one with the K first target centroids; the second Euclidean distance of any target data in the first data set is the Euclidean distance between the target data and the first target centroid corresponding to the first data set; for each of the K first data sets, taking the center point of the target data in the first data set as the second target centroid; for each of the K first data sets, calculating the distance between the first target centroid and the second target centroid corresponding to the first data set to obtain K first distances; and taking the second target centroid corresponding to the first data set as the first target centroid.
[0132] In one possible implementation, the region classification device 40 may further include a storage unit 403. Figure 4 (shown in dashed box) The storage unit 403 stores a program or instruction. When the processing unit 402 executes the program or instruction, the region classification device 40 can perform the region classification method described in the above method embodiment.
[0133] When implemented in hardware, the communication unit 401 in this embodiment can be integrated onto the communication interface, and the processing unit 402 can be integrated onto the processor. Specific implementation methods are as follows: Figure 5 As shown.
[0134] Figure 5A schematic diagram of another possible structure of the region classification device involved in the above embodiments is shown. The region classification device includes a processor 502 and a communication interface 501. The processor 502 is used to control and manage the operation of the region classification device, for example, executing the steps performed by the processing unit 402, and / or performing other processes of the technology described herein. The communication interface 501 is used to support communication between the region classification device and other network entities, for example, executing the steps performed by the communication unit 401. The region classification device may also include a memory 503 and a bus 504, the memory 503 being used to store the program code and data of the region classification device.
[0135] The memory 503 may be a memory in a region classification device, and the memory may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as read-only memory, flash memory, hard disk or solid-state drive; the memory may also include a combination of the above types of memory.
[0136] The processor 502 described above can implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor can be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements computing functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.
[0137] Bus 504 can be an Extended Industry Standard Architecture (EISA) bus, etc. Bus 504 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 5 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.
[0138] Figure 5 The region classification device in the chip can also be a chip. The chip includes one or more processors 502 and a communication interface 501.
[0139] In some embodiments, the chip further includes a memory 503, which may include read-only memory and random access memory, and provides operation instructions and data to the processor 502. A portion of the memory 503 may also include non-volatile random access memory (NVRAM).
[0140] In some implementations, memory 503 stores elements such as execution modules or data structures, or subsets thereof, or extended sets thereof.
[0141] In this embodiment of the application, the corresponding operation is executed by calling the operation instructions stored in the memory 503 (the operation instructions may be stored in the operating system).
[0142] Through the above description of the embodiments, those skilled in the art will clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.
[0143] This application provides a computer program product containing instructions that, when run on a computer, cause the computer to execute the region classification method described in the above method embodiments.
[0144] This application also provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the region classification method in the method flow shown in the above method embodiments.
[0145] The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: electrical connections having one or more wires; portable computer disks; hard disks; random access memory (RAM); read-only memory (ROM); erasable programmable read-only memory (EPROM); registers; hard disks; optical fibers; portable compact disc read-only memory (CD-ROM); optical storage devices; magnetic storage devices; or any suitable combination thereof; or any other form of computer-readable storage medium known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium may also be a component of the processor. The processor and the storage medium may reside in an application-specific integrated circuit (ASIC). In the embodiments of this application, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
[0146] Since the region classification device, computer-readable storage medium, and computer program product in the embodiments of this application can be applied to the above method, the technical effects that can be obtained can also be referred to the above method embodiments. The embodiments of this application will not be repeated here.
[0147] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.
[0148] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0149] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.
[0150] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
Claims
1. A method of classifying regions, characterized by, The method includes: For each of the multiple first regions within the simulation area, obtain the base station data corresponding to the first region; Determine the simulation parameters of the simulation model; the simulation parameters include frequency point data, bandwidth data, and transmit power; The base station data corresponding to each first region within the simulation area is input into the simulation model to obtain simulation data; Obtain N simulation data points and N measurement data points; the simulation data points include the simulated latitude and longitude, simulated received power, and simulated signal-to-noise ratio of the simulation area; the measurement data points include the measured latitude and longitude, measured received power, and measured signal-to-noise ratio of the measurement area; N is a positive integer; By comparing the N simulation data and the N measurement data, N target data are obtained; the target data includes the difference between the simulated received power and the measured received power corresponding to the target area, and the difference between the simulated signal-to-noise ratio and the measured signal-to-noise ratio. K out of N target data points are identified as K first target centroids; K is less than or equal to N. Repeat the first operation to ensure that all K first distances are less than a preset threshold, and determine the K target sets; The first operation includes: For each of the N target data, calculate the Euclidean distance between the target data and each of the first target centroids to obtain K first Euclidean distances corresponding to the target data; For each of the N target data, determine the second Euclidean distance that is the smallest among the K first Euclidean distances corresponding to the target data; Based on the second Euclidean distance of each target data, K first data sets are determined; the K first data sets correspond one-to-one with the K first target centroids; the second Euclidean distance of any target data in the first data set is the Euclidean distance between the target data and the first target centroid corresponding to the first data set; For each of the K first data sets, the center point of the target data in the first data set is taken as the second target centroid; For each of the K first data sets, calculate the distance between the first target centroid and the second target centroid corresponding to the first data set to obtain K first distances; and take the second target centroid corresponding to the first data set as the first target centroid. Wherein, one of the target sets includes M target data; M is a positive integer; M is less than or equal to N; The region classification result of the simulation region is determined as the category of the corresponding target set; the category of the target set is used to characterize the scene information of the simulation region; the region classification result is used to characterize the scene information of the simulation region.
2. The method of claim 1, wherein, The comparison of the N simulation data and the N measurement data yields N target data, including: If the simulated latitude and longitude of the simulated area are the same as the measured latitude and longitude of the measured area, then the simulated area and the measured area are determined to be the same target area. For each of the N target regions, calculate the difference between the simulated received power of the simulated region and the measured received power of the measured region corresponding to each target region; For each of the N target regions, calculate the difference between the simulated signal-to-noise ratio of the simulated region and the measured signal-to-noise ratio of the measured region corresponding to each target region.
3. A region classification device, characterized in that, The device includes: a communication unit and a processing unit; The communication unit is used to acquire base station data corresponding to each of the multiple first regions within the simulation area; The processing unit is used to determine the simulation parameters of the simulation model; the simulation parameters include frequency point data, bandwidth data, and transmit power. The processing unit is further configured to input base station data corresponding to each first region within the simulation area into the simulation model to obtain simulation data; The communication unit is also used to acquire N simulation data and N measurement data; the simulation data includes the simulated latitude and longitude, simulated received power, and simulated signal-to-noise ratio of the simulation area; the measurement data includes the measured latitude and longitude, measured received power, and measured signal-to-noise ratio of the measurement area; N is a positive integer; The processing unit is further configured to compare the N simulation data and the N measurement data to obtain N target data; the target data includes the difference between the simulated received power and the measured received power corresponding to the target area, and the difference between the simulated signal-to-noise ratio and the measured signal-to-noise ratio; The processing unit is further configured to: determine K target data points out of N target data points as K first target centroids; K is less than or equal to N; repeatedly perform the first operation to ensure that all K first distances are less than a preset threshold, thereby determining K target sets; the first operation includes: for each target data point out of the N target data points, calculating the Euclidean distance between the target data point and each first target centroid, obtaining K first Euclidean distances corresponding to the target data point; for each target data point out of the N target data points, determining the second Euclidean distance with the smallest value among the K first Euclidean distances corresponding to the target data point; determining K first data sets based on the second Euclidean distance of each target data point; the K first data sets correspond one-to-one with the K first target centroids; the second Euclidean distance of any target data point in the first data set... The Euclidean distance between the target data and the first target centroid corresponding to the first data set is defined as follows: For each of the K first data sets, the center point of the target data in the first data set is taken as the second target centroid; For each of the K first data sets, the distance between the first target centroid and the second target centroid corresponding to the first data set is calculated to obtain K first distances; The second target centroid corresponding to the first data set is taken as the first target centroid; Wherein, a target set includes M target data; M is a positive integer; M is less than or equal to N; The region classification result of the simulation area is determined as the category of the corresponding target set; The category of the target set is used to characterize the scene information of the simulation area; The region classification result is used to characterize the scene information of the simulation area.
4. The apparatus according to claim 3, characterized in that, The processing unit is also used for: If the simulated latitude and longitude of the simulated area are the same as the measured latitude and longitude of the measured area, then the simulated area and the measured area are determined to be the same target area. For each of the N target regions, calculate the difference between the simulated received power of the simulated region and the measured received power of the measured region corresponding to each target region; For each of the N target regions, calculate the difference between the simulated signal-to-noise ratio of the simulated region and the measured signal-to-noise ratio of the measured region corresponding to each target region.
5. A region classification device, characterized in that, include: A processor and a communication interface; the communication interface is coupled to the processor, the processor being used to run computer programs or instructions to implement the region classification method as described in claim 1 or 2.
6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed by a computer, perform the region classification method as described in claim 1 or 2.