Spatial correlation method, apparatus, electronic device, storage medium, and program product

Abstract

The present disclosure provides a spatial correlation method, device, electronic equipment, storage medium and program product. The spatial correlation method comprises: acquiring business characteristic data; at least based on the business characteristic data, acquiring location information corresponding to the business characteristic data; based on the business characteristic data and the location information, acquiring a spatial distribution characteristic of the business characteristic data; and based on the spatial distribution characteristic, determining a spatial correlation of the business characteristic data. The present disclosure combines the business characteristic data and the corresponding location information to acquire the spatial distribution characteristic of the business characteristic data, and determines the spatial correlation of the business characteristic data according to the spatial distribution characteristic, which can greatly reduce the influence of subjectivity on the analysis result, make the result more objective, and be suitable for analyzing the micro spatial scale.

Description

Technical Field

[0001] This disclosure relates to the field of communication technology, and in particular to a spatial correlation method, apparatus, electronic device, storage medium, and program product. Background Technology

[0002] In existing technologies, when analyzing whether business data is related to a certain geographic space, it generally relies on manual judgment. Moreover, manual judgment is usually based on a relatively large geographic spatial scale, which often results in qualitative results, i.e., related or unrelated.

[0003] However, this method of manual judgment is highly subjective and cannot be accurate to more detailed spatial scales. Summary of the Invention

[0004] This disclosure is made in view of the above-mentioned problems. This disclosure provides a method, apparatus, electronic device, computer-readable storage medium, and computer program product for determining the spatial correlation of communication service data.

[0005] According to one aspect of this disclosure, a method for determining the spatial correlation of communication service data is provided, comprising: acquiring service feature data; acquiring location information corresponding to the service feature data based at least on the service feature data; acquiring spatial distribution characteristics of the service feature data based on the service feature data and the location information; and determining the spatial correlation of the service feature data based on the spatial distribution characteristics.

[0006] Furthermore, according to one aspect of the method for determining the spatial correlation of communication service data, at least based on service feature data, location information corresponding to the service feature data is obtained, including: Obtain network parameter data corresponding to business feature data; match business feature data with network parameter data to obtain location information corresponding to business feature data.

[0007] Furthermore, according to one aspect of the method for determining the spatial correlation of communication service data, the service feature data is matched with network engineering parameter data to obtain location information corresponding to the service feature data, including: obtaining a cell identification code based on the service feature data; Based on the cell identification code, service feature data is matched with network engineering parameter data to obtain the location information corresponding to the service feature data.

[0008] Furthermore, according to one aspect of the present disclosure, a method for determining the spatial correlation of communication service data, based on service feature data and location information, obtains the spatial distribution characteristics of the service feature data, including: dividing the space corresponding to the location information into multiple regions based on the location information, wherein each region corresponds to one location information; determining the sum of service feature data corresponding to each region based on the service feature data and the multiple regions; determining the spatial adjacency relationship of the multiple regions based on the location information; and obtaining the spatial distribution characteristics of the service feature data based on the spatial adjacency relationship, the location information, and the sum of the service feature data.

[0009] Furthermore, according to another aspect of this disclosure, a method for determining the spatial correlation of communication service data, based on location information, determines the spatial adjacency relationship of multiple regions, including: obtaining a spatial adjacency matrix based on location information; determining the distance information between any two location information based on location information; and obtaining an inverse distance exponential function based on the distance information. Based on the spatial adjacency matrix and the inverse distance exponential function, the spatial adjacency relationships of multiple regions are determined.

[0010] Furthermore, an apparatus for determining the spatial correlation of communication service data according to another aspect of this disclosure includes: a data acquisition module configured to acquire service feature data; a location information acquisition module configured to acquire location information corresponding to the service feature data based at least on the service feature data; a spatial distribution characteristic acquisition module configured to acquire spatial distribution characteristics of the service feature data based on the service feature data and the location information; and a spatial correlation determination module configured to determine the spatial correlation of the service feature data based on the service feature data and the location information.

[0011] Furthermore, according to another aspect of this disclosure, in the apparatus for determining the spatial correlation of communication service data, the location information acquisition module is further configured to: acquire network engineering parameter data corresponding to the service feature data; match the service feature data with the network engineering parameter data to acquire location information corresponding to the service feature data.

[0012] According to another aspect of this disclosure, an electronic device is provided, comprising: a memory for storing computer-readable instructions; and a processor for executing the computer-readable instructions, causing the electronic device to perform the method for determining the spatial correlation of communication service data as described above.

[0013] According to another aspect of this disclosure, a computer-readable storage medium is provided for storing computer-readable instructions that, when executed by a processor, cause the processor to perform the method for determining the spatial correlation of communication service data as described above.

[0014] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the method for determining the spatial correlation of communication service data as described above.

[0015] As will be described in detail below, the method, apparatus, electronic device, computer-readable storage medium, and computer program product for determining the spatial correlation of communication service data according to embodiments of the present disclosure, compared to relying entirely on manual judgment, obtain the spatial distribution characteristics of service feature data by combining service feature data with corresponding location information, and determine the spatial correlation of service feature data based on the spatial distribution characteristics. This can greatly reduce the influence of subjectivity on the analysis results, making the results more objective, and is applicable to the analysis at the microscale.

[0016] It should be understood that both the foregoing general description and the following detailed description are exemplary and intended to provide further illustration of the claimed technology. Attached Figure Description

[0017] The above and other objects, features, and advantages of this disclosure will become more apparent from the more detailed description of the embodiments thereof in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of this disclosure and form part of the specification. They are used together with the embodiments of this disclosure to explain the disclosure and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same components or steps.

[0018] Figure 1 This is a flowchart illustrating a method for determining the spatial correlation of communication service data according to an embodiment of the present disclosure.

[0019] Figure 2 This is a flowchart illustrating a method for determining the spatial correlation of communication service data according to an embodiment of the present disclosure.

[0020] Figure 3 This is a flowchart illustrating a method for determining the spatial correlation of communication service data according to an embodiment of the present disclosure.

[0021] Figure 4 This is an illustration of the adjacency relationship of different regions according to an embodiment of the present disclosure.

[0022] Figure 5 This is a functional block diagram illustrating an apparatus for determining the spatial correlation of communication service data according to an embodiment of the present disclosure.

[0023] Figure 6 This is a hardware block diagram illustrating an electronic device according to an embodiment of the present disclosure.

[0024] Figure 7This is a schematic diagram illustrating a computer-readable storage medium according to an embodiment of the present disclosure.

[0025] Figure 8 This is a schematic diagram illustrating a computer program according to an embodiment of the present disclosure. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of this disclosure more apparent, exemplary embodiments according to this disclosure will now be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this disclosure, and not all embodiments of this disclosure. It should be understood that this disclosure is not limited to the exemplary embodiments described herein.

[0027] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the present invention, and not all of the structures.

[0028] For ease of understanding, please refer to Figures 1 to 4 A method for determining the spatial correlation of communication service data according to embodiments of the present disclosure is described.

[0029] like Figure 1 As shown, Figure 1 This is a flowchart of a method for determining the spatial correlation of communication service data according to an embodiment of this disclosure.

[0030] In step S101, business feature data is obtained.

[0031] Business characteristic data is used to characterize multiple key attributes and features of business data. These features help network operators, service providers, and developers understand the behavior, needs, and performance of business data within the network.

[0032] In one embodiment of this disclosure, service characteristic data may refer to a service table in the wireless operator's general service database within the wireless operator's operational domain data warehouse. This service table includes data such as traffic and utilization. Specifically, this service table is obtained by sharing service tables from specific service databases within each operator's data warehouse.

[0033] In one embodiment of this disclosure, business feature data may also refer to data obtained by extracting key fields from the aforementioned business table and cleaning the included key fields. For example, as shown in Table 1 below, the field names and related business meanings included in the business table are as follows: Table 1:

[0034] Extract data containing the required key fields from the business table. These key fields include: cgi, sdate, pld_gb, and utility. Clean the extracted data. Specifically, filter records where the key fields cgi, sdate, and pld_gb are null. Clean non-numeric records of pld_gb and non-date records of sdate. The final data obtained is the business characteristic data.

[0035] In step S102, location information corresponding to the business feature data is obtained, at least based on the business feature data.

[0036] Understandably, location information can refer to absolute location, such as latitude and longitude. It can also refer to relative location, such as location based on other landmarks or reference points. For example, distance from a known location in meters or kilometers, or a distance in a certain direction. It can also refer to altitude, such as information describing the height of a location. Because wireless operators have extensive service coverage and their network infrastructure spans various regions, they can collect service data from different geographical locations. Each of these service data points corresponds to specific location information.

[0037] In one embodiment of this disclosure, after obtaining service characteristic data from the wireless operator's operating domain, location information corresponding to this service characteristic data can be further obtained to analyze the service characteristic data and understand its distribution. For example, if the service characteristic data is service traffic usage, the geographical distribution of traffic usage can be analyzed through the corresponding location information, thereby optimizing network resource allocation and improving network coverage and service quality.

[0038] In one embodiment of this disclosure, location information can be obtained by acquiring network parameter data corresponding to service feature data, matching the service feature data with the network parameter data, and obtaining location information corresponding to the service feature data. Specifically, the network parameter data can refer to the local parameter data of the wireless operator, which must at least include longitude (lgt), latitude (ltt), and cell identifier (cgi).

[0039] In one embodiment of this disclosure, the location information can be obtained by acquiring a cell identification code based on service feature data, and then matching the service feature data with network parameter data based on the cell identification code. Specifically, the CGI of the service feature data is inner-joined with the CGI of the network parameter data, i.e.: datawarehouse.database.tablename inner join local_cfg on datawarehouse.database.tablename.cgi = local_cfg.cgi.

[0040] The acquired business feature data and corresponding location information are aggregated into a single data table named "source". This data table is then stored in the open-source database Postgrest for subsequent data analysis.

[0041] In step S103, the spatial distribution characteristics of the business feature data are obtained based on the business feature data and location information.

[0042] As can be understood, spatial distribution characteristics refer to the distribution state of things existing in a certain region or area, as well as the spatial relationships between these things. These characteristics usually involve the analysis and interpretation of the location, quantity, density, pattern, and interrelationships of various elements within a geographic space.

[0043] In one embodiment of this disclosure, obtaining the spatial distribution characteristics of business feature data based on business feature data and location information refers to combining business feature data and location information to analyze the distribution status of business feature data in different geographical areas and the interrelationships between them.

[0044] In one embodiment of this disclosure, spatial distribution characteristics can be analyzed using the Moran index. For example, based on business feature data and location information, the Moran index of the business feature data is determined, and then the spatial distribution characteristics of the business feature data are analyzed using the Moran index. That is, the spatial distribution characteristics of the business feature data are interpreted based on the analysis results of the Moran index.

[0045] In step S104, the spatial correlation of business feature data is determined based on spatial distribution characteristics.

[0046] Spatial correlation, as we understand it, refers to the strong correlation between nearby points in a geographically continuous distribution of phenomena, while the correlation between more distant points is weak or unrelated. It describes the degree of interdependence and correlation among geographical phenomena in their spatial distribution. Spatial correlation analysis can also distinguish between positive and negative correlation. Positive correlation indicates that nearby points have similar characteristics or attributes; that is, similar characteristics tend to cluster together spatially. Negative correlation, on the other hand, indicates that nearby points have opposite characteristics or attributes.

[0047] In one embodiment of this disclosure, "based on the spatial distribution characteristics of the acquired business feature data" refers to assessing whether there is a spatial dependence or correlation among these business features by analyzing their distribution in different geographical regions or locations.

[0048] Specifically, for example, using traffic volume data from telecommunications services as business characteristic data, this data is integrated with corresponding location information (such as latitude and longitude) to form a dataset containing geographical location and business data information. The spatial distribution characteristics of this integrated dataset are then analyzed. This includes determining the spatial distribution of the business data, such as which regions have concentrated business data, which regions have sparse data, and whether there are obvious spatial distribution patterns (such as clustering, dispersion, or banded distribution). After analyzing the spatial distribution characteristics, spatial analysis techniques can be used to measure the spatial correlation between business data. This allows for the determination of whether geographically adjacent or similar business data tend to have similar characteristics or trends.

[0049] Figure 2 This is a flowchart illustrating a method for determining the spatial correlation of communication service data according to an embodiment of the present disclosure.

[0050] like Figure 2 As shown, the method for determining the spatial correlation of communication service data according to an embodiment of this disclosure specifically includes the following steps.

[0051] Steps S201-S202 are the same as steps S101-S102, and will not be described again here.

[0052] In step S203, based on the location information, the space corresponding to the location information is divided into multiple regions, wherein each region corresponds to one location information.

[0053] In one embodiment of this disclosure, after obtaining all relevant location information of the business feature data.

[0054] Based on the needs of the analysis and the characteristics of the data, the space corresponding to the location information is divided. For example, the space can be divided into regular grid cells, such as square or hexagonal grids. Alternatively, based on the location information, the Thiessen polygon method can be used to divide the space corresponding to the location information into multiple regions. Each region corresponds to a specific location information.

[0055] In one embodiment of this disclosure, the open-source database pg is used to load data from the data table source containing location information. After loading, the Thiessen polygon module of the open-source geographic information software QGIS is used to construct Thiessen polygons, thereby dividing the space corresponding to the location information into multiple regions, each region corresponding to a Thiessen polygon, and the center latitude and longitude of the Thiessen polygon is the location information corresponding to that region. Specifically, taking latitude and longitude as the location information, for example, the rounding function round is used to retain 5 decimal places in the latitude and longitude of source in pg: round(lgt,5)lgt, round(ltt,5)ltt. The underlying logic is that under the 1984 World Geodetic Coordinate System (WGS84 coordinate system), 5 decimal places of latitude and longitude are accurate to meters. After processing, duplicate data is removed. After removing duplicates, unique latitude and longitude are formed, and each latitude and longitude is assigned a different value to represent such a unique identifier ts_id. The unique latitude and longitude corresponding to each ts_id is used as the center latitude and longitude of the Thiessen polygon. The latitude and longitude of the center are processed using the PG point object conversion function `st_point(lgt,ltt)` to convert them into spatial point objects `point_geom`. The resulting point objects are then loaded into QGIS using a QGSI connection to the PG database, with the data table `source` loaded into the QGIS project. After loading the data, the Thiessen polygons are generated using the geometry tool under the vector module of QGIS.

[0056] In step S204, based on the business feature data and the multiple regions, the sum of business feature data corresponding to each region is determined.

[0057] In one embodiment of this disclosure, based on the obtained business feature data and multiple regions, the sum of business feature data corresponding to each region can be determined. That is, the sum of business feature data corresponding to each location information (e.g., latitude and longitude) is calculated. This helps to understand the overall situation of the business feature data for each location information.

[0058] In one embodiment of this disclosure, for example: the generated Thiessen polygons are imported from QGIS into the spatial database PG. The database schema used for import must be the same as the schema of the source table. The resulting geom is a spatial polygon object polygon_geom. At this point, the spatial function st_within is used in the PG database to group by ts_id, and the business volume in the source is associated with the Thiessen polygon myg_ts_panlong to calculate the sum of business volumes for each Thiessen polygon region. Specifically: Under the condition `source INNER JOIN myg_ts_panlong on st_within(source.geom, myg_ts_panlong.geom)`, `sum(pld_g)` will name the sum of the aggregated business feature data as `pld_g_s`.

[0059] In step S205, the spatial adjacency relationship of multiple regions is determined based on location information.

[0060] In one embodiment of this disclosure, each region corresponds to a location information, and the spatial adjacency relationship of multiple regions can be determined based on this location information. For example, taking latitude and longitude as the location information, each location information represents a region, and each region corresponds to a Thiessen polygon. Based on the Thiessen polygon, the spatial adjacency relationship of multiple regions can be determined, i.e., whether they are adjacent or not. This adjacency relationship can also be quantified into data, and the adjacency relationship between two different regions can be determined based on the data. Multiple regions can be represented by location information or by location point 1, location point 2... location point n.

[0061] In step S206, the spatial distribution characteristics of the business feature data are obtained based on the spatial adjacency relationship, location information, and the sum of business feature data.

[0062] In one embodiment of this disclosure, each region has corresponding location information (such as latitude and longitude). For each region, the sum of its corresponding business feature data has been calculated. The spatial adjacency relationships between regions have also been determined, i.e., which regions are adjacent. By combining the spatial adjacency relationships, location information, and the sum of business feature data, the spatial distribution characteristics of the business feature data can be obtained. That is, the distribution of business feature data across different regions. Based on these spatial distribution characteristics, it is possible to further analyze whether these business data exhibit spatial interdependence or correlation.

[0063] Figure 3 This is a flowchart illustrating a method for determining the spatial correlation of communication service data according to an embodiment of the present disclosure.

[0064] like Figure 3 As shown, this is a method for determining the spatial correlation of communication service data according to an embodiment of the present disclosure.

[0065] The steps involve determining the spatial adjacency relationships of multiple regions based on location information, specifically including the following steps.

[0066] In step S301, the spatial adjacency matrix is ​​obtained based on the location information.

[0067] In one embodiment of this disclosure, the latitude and longitude of the center of the Thiessen polygon correspond to the location information, and a matrix is ​​constructed based on the location information. O , O The record in the nth row is marked as O n Simultaneously, construct a matrix based on the location information. O ’ ,matrix O ’ The record in the nth row is marked as O ’ n Then the matrix O sum matrix O ’ The Cartesian product W is then the constructed spatial adjacency matrix. That is, constructing a identical matrix. O ’ , from the original matrix O Perform a full association to generate a Cartesian product W (note: this is not a simple multiplication, but a full record). Among these, O , O ’ W and W are represented as follows:

[0068]

[0069] in, O 1. O 2... O n This represents the position information of position point 1, position point 2, ..., position point n. O ’ 1. O ’ 2... O ’ n This represents the position information of position point 1, position point 2, ..., position point n.

[0070] After the above steps, the required spatial adjacency matrix W is formed, and because... O’ It is itself O The number of elements is exactly the same, but full cross-calculation is required, so the spatial adjacency matrix is ​​also a spatial adjacency square matrix.

[0071] See Figure 4 As shown in the figure, the numbers in the white area and the surrounding gray area are unique identifiers ts_id. The relationship between the ts_id in the white area and all the surrounding ts_ids needs to be fully analyzed in order to observe its position in space and its adjacent spatial positions.

[0072] In step S302, the distance information between any two location information is determined based on the location information.

[0073] In one embodiment of this disclosure, taking latitude and longitude as the location information as an example, the distance between any two location information can be calculated using Euclidean distance.

[0074] Specifically, input any two coordinates (lgt1,ltt1) and (lgt2,ltt2); Where (lgt1,ltt1) are the coordinates of latitude and longitude 1, and (lgt2,ltt2) are the coordinates of latitude and longitude 2. The distance d between latitude and longitude 1 and latitude and longitude 2 is obtained in meters.

[0075] earth_radius number := 6378.137; The Earth's radius is assigned 6378.137; radLat1 number := rad(ltt1); Latitude to radians 1; radLat2 number := rad(ltt2); Latitude to radians 2; a number := radLat1-radLat2; constructs the latitude arc difference a; radLat1 number := rad(lgt1); Longitude to radians 1; radLat2 number := rad(lgt2); Longitude to radians 2; b number := rad(lgt1)-rad(lgt2); Constructs the longitude arc difference b; calculate: i)

[0076] ii) s':= s * earth_radius; iii)d := Round(s'* 1000); The calculated result is the Euclidean distance d between latitude and longitude 1 (lgt1,ltt1) and latitude and longitude 2 (lgt2,ltt2), in meters.

[0077] The Euclidean distance d obtained above is the distance between any two locations.

[0078] In step S303, the inverse distance exponential function is obtained based on the distance information.

[0079] In one embodiment of this disclosure, the inverse distance exponential function is obtained based on distance information in order to describe Figure 4 The relationship between the white area and all surrounding gray areas based on distance needs to be expressed numerically: the closer a pair of white and gray areas is, the higher its importance; the farther apart they are, the lower their importance. In economics, the inverse distance function is used to describe the importance of one region's GDP to another region's GDP. (where d is the distance between the two regions), and its range in the first quadrant of the coordinate axis is (0, +∞). Considering that in economics, the distance is between the two regions (d=0), the value can be 0, so in economics, the range would be modified to [0, +∞). However, this disclosure studies distances at both large and microscales, so the inverse distance function in economics cannot be directly applied. Therefore, a number needs to be constructed so that it is distributed in the closed interval [0,1]. The closer the distance, the closer it is to 1, and the farther the distance, the closer it is to 0. This proposal uses an exponential function. The reason for selection is:

[0080] The above exponential function This is the inverse distance exponential function.

[0081] In step S304, the spatial adjacency relationships of multiple regions are determined based on the spatial adjacency matrix and the inverse distance exponential function.

[0082] In one embodiment of this disclosure, the spatial adjacency matrix and the inverse distance exponential function are combined to determine the spatial adjacency relationships of multiple regions.

[0083] Specifically, by substituting the distance information d between any two positions obtained above, along with the inverse distance exponential function, into matrix W, we can obtain the full matrix. Its element values ​​are as follows:

[0084] Where n represents the number of rows or columns of the matrix, that is, the position point n; the above matrix This represents the spatial adjacency relationship for multiple regions, where each element of the matrix represents a spatial adjacency relationship (weight) between a pair of regions.

[0085] At this point, we can draw three small conclusions: a) Matrix O Elements and matrices O ’ When the elements are identical, the calculated distance is 0, and the result of the inverse distance exponential function is 1. Therefore, the matrix formed by these elements will have all 1s on its main diagonal.

[0086] b) Considering distance: the result of the inverse distance exponential function between the i-th element and the j-th element is the same as the result of the inverse distance exponential function between the j-th element and the i-th element.

[0087] c) The sum of all element values ​​of the entire matrix converges.

[0088] The proof is as follows:

[0089] Since n is the number of latitude and longitude coordinates of the center of the Thiessen polygon, which is exhaustive, it is bounded, with a lower bound of 0 and an upper bound of . Since the function is monotonically decreasing on [0, +∞), it can be concluded that a monotonically decreasing sequence must have a limit. Its convergence is within its limit value.

[0090] Once this element value is calculated, the coefficients of the spatial adjacency matrix are complete, and the coefficient values ​​are the calculated matrix element values.

[0091] In step S305, the spatial distribution characteristics of the business feature data are obtained based on the spatial adjacency relationship, location information, and the sum of business feature data.

[0092] In one embodiment of this disclosure, the spatial distribution characteristics of the business feature data can be obtained by summing the spatial adjacency relationships, location information, and business feature data of multiple regions as described above. For example, the spatial adjacency relationships of multiple regions are represented by a spatial adjacency matrix. Based on the location information, an inverse distance exponential function can be obtained, thereby determining the spatial adjacency matrix. Combining the spatial adjacency relationships, location information, and the sum of business feature data allows for the acquisition of the spatial distribution characteristics of the business feature data.

[0093] Specifically, the Moran's index is calculated to represent the spatial distribution characteristics of the business feature data. The Moran's index typically ranges from -1 to 1, where a positive value indicates that the business feature data are spatially positively correlated (i.e., similar values ​​cluster together), a negative value indicates that they are negatively correlated (i.e., different values ​​cluster together), and a value close to 0 indicates that the data are spatially randomly distributed.

[0094] Specifically, the formula for the Moran index system is as follows: Global Moran Index:

[0095] Local Moran Index:

[0096] The meanings of the parameters in the Moran index system formula are shown in Table 2 below: Table 2:

[0097] in: calculate: = ,when i=j At that time, assign a value =1, and = , Also known as spatial adjacency matrix coefficients.

[0098] a) Calculation In the special case where i=j, the value is directly assigned to 1.

[0099] b) Assignment = The forward calculation is performed, and at this point only the one-way assignment process is calculated.

[0100] c) Assignment When element index i and j When swapping the order, make its value equal to that in step b). The value of .

[0101] Standardize business characteristic data: In wireless communication data, due to the specific meaning of the service, it often contains units of measurement. For example, the service characteristic data used is traffic data, whose unit of measurement is gigabytes (GB). Data with units of measurement in mathematics needs to be standardized; otherwise, directly calculating with units of measurement will widen the gap between large data sets, leading to inaccurate calculation results. The specific processing is as follows: The business value corresponding to the i-th element (position i) ,minus As molecules; all elements to The maximum value, minus As the denominator. Final calculation: This is the dimensionless result. Where n represents the number of elements (the number of latitude and longitude coordinates at the center of the Thiessen polygon).

[0102] Calculation: After obtaining each Standardized value The arithmetic mean of all standardized elements is then obtained: .

[0103] Observe the left side of the product of the global Moran exponent formula Based on the full matrix, we know that it converges. The right side of its product... ,because Since there are extrema, it also converges.

[0104] In the above description, the standardized result of the actual business value corresponding to the i-th element of the spatial adjacency matrix is ​​the sum of business feature data corresponding to the i-th region (location point i). As can be seen from the Moran index system formula above, both the global and local Moran indices are determined by combining spatial adjacency relationships, location information, and the sum of business feature data.

[0105] The spatial distribution characteristics of business feature data are determined by calculating the global Moran index and the local Moran index.

[0106] Furthermore, the spatial correlation of business feature data is determined based on the spatial distribution characteristics of the business feature data.

[0107] In one embodiment of this disclosure, Moran's I ranges from -1 to 1 and is used to quantify the spatial autocorrelation of geographical phenomena. When the global Moran's I is close to 1, it indicates that the data has strong positive spatial autocorrelation, that is, similar values ​​tend to cluster together; when it is close to -1, it indicates strong negative spatial autocorrelation, that is, different values ​​tend to cluster together; when it is close to 0, it indicates that the data is spatially randomly distributed and has no significant spatial autocorrelation.

[0108] For example, when the global Moran's index value is between 0.23 and 0.25, and mostly around 0.25, it does indicate positive spatial autocorrelation. Specifically, within the study area, regions with similar business characteristics tend to cluster together. As another example, analysis of the local Moran's index shows that when the index is negative, it indicates an increase in business volume in that region, accompanied by a decrease in surrounding regions. The index itself also decreases, suggesting a situation where surrounding areas attract business flow.

[0109] The above describes a method for determining the spatial correlation of communication service data according to embodiments of this disclosure. The following is based on… Figure 5 An apparatus for determining the spatial correlation of communication service data using the present disclosure is described.

[0110] like Figure 5As shown, the apparatus 500 for determining the spatial correlation of communication service data according to an embodiment of the present disclosure includes a data acquisition module 501, a location information acquisition module 502, a spatial distribution characteristic acquisition module 503, and a spatial correlation determination module 504.

[0111] Specifically, the data acquisition module 501 is configured to acquire business characteristic data.

[0112] Specifically, the location information acquisition module 502 is configured to acquire location information corresponding to the business feature data, at least based on the business feature data.

[0113] Specifically, the spatial distribution characteristic acquisition module 503 is configured to acquire the spatial distribution characteristics of the business characteristic data based on the business characteristic data and the location information.

[0114] Specifically, the spatial correlation determination module 504 is configured to determine the spatial correlation of the business feature data based on the business feature data and the location information.

[0115] Furthermore, the location information acquisition module 502 is also configured to acquire network engineering parameter data corresponding to the service feature data; match the service feature data with the network engineering parameter data to acquire location information corresponding to the service feature data.

[0116] Figure 6 This is a hardware block diagram illustrating an electronic device 600 according to an embodiment of the present disclosure. The electronic device according to an embodiment of the present disclosure includes at least a processor and a memory for storing computer-readable instructions. When the computer-readable instructions are loaded and executed by the processor, the processor performs the spatial correlation determination method for communication service data as described above.

[0117] Figure 6 The illustrated electronic device 600 specifically includes a central processing unit (CPU) 601, a graphics processing unit (GPU) 602, and a main memory 603. These units are interconnected via a bus 604. The CPU 601 and / or GPU 602 can function as the aforementioned processors, and the main memory 603 can function as the aforementioned memory storing computer-readable instructions. Furthermore, the electronic device 600 may also include a communication unit 605, a storage unit 606, an output unit 607, an input unit 608, and an external device 609, all of which are also connected to the bus 604.

[0118] Figure 7 This is a schematic diagram illustrating a computer-readable storage medium according to an embodiment of the present disclosure. Figure 7As shown, a computer-readable storage medium 700 according to an embodiment of the present disclosure stores computer-readable instructions 701 thereon. When the computer-readable instructions 701 are executed by a processor, the method for determining the spatial correlation of communication service data according to an embodiment of the present disclosure, as described with reference to the above figures, is performed. The computer-readable storage medium includes, but is not limited to, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, optical disk, magnetic disk, etc.

[0119] Figure 8 This is a schematic diagram illustrating a computer program product according to an embodiment of the present disclosure. Figure 8 As shown, a computer program product 800 according to an embodiment of this disclosure stores a computer program 801 thereon. When the computer program is executed by a processor, it implements the method for determining the spatial correlation of communication service data as described above. The computer program product includes, but is not limited to, system software, application software, and games. System software is the basic software of a computer, responsible for managing the computer's hardware and applications, including operating systems, device drivers, etc. Application software is software designed to meet specific needs, such as office software, image processing software, etc. Games are software used for entertainment, providing various gaming experiences. In addition, the computer program product may also include embedded software, firmware, etc., for controlling and operating various hardware devices.

[0120] The above description, with reference to the accompanying drawings, outlines a method, apparatus, electronic device, computer-readable storage medium, and computer program product for determining the spatial correlation of communication service data according to embodiments of this disclosure. Compared to relying entirely on manual judgment, this disclosure obtains the Moran index of the service feature data by combining the service feature data with the corresponding location information, and determines the spatial correlation of the service feature data based on the Moran index. This can greatly reduce the influence of subjectivity on the analysis results, making the results more objective, and is applicable to the analysis at the microscale.

[0121] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.

[0122] The basic principles of this disclosure have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this disclosure are merely examples and not limitations, and should not be considered as essential features of each embodiment of this disclosure. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the scope of this disclosure to the necessity of employing the aforementioned specific details for implementation.

[0123] The block diagrams of devices, apparatuses, devices, and systems disclosed herein are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0124] Additionally, as used herein, the "or" used in a list of items beginning with "at least one" indicates a separate list, such that a list of, for example, "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not imply that the described example is preferred or better than other examples.

[0125] It should also be noted that in the systems and methods of this disclosure, the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered as equivalent solutions to this disclosure.

[0126] Various changes, substitutions, and modifications can be made to the technology herein without departing from the teachings defined by the appended claims. Furthermore, the scope of the claims of this disclosure is not limited to the specific aspects of the processes, machines, manufactures, events, means, methods, and actions described above. Currently existing or later-developed processes, machines, manufactures, events, means, methods, or actions that perform substantially the same function or achieve substantially the same result as the corresponding aspects herein can be utilized. Therefore, the appended claims include such processes, machines, manufactures, events, means, methods, or actions within their scope.

[0127] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of this disclosure. Therefore, this disclosure is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0128] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this disclosure to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.

Claims

1. A method for determining the spatial correlation of communication service data, characterized in that, include: Obtain business characteristic data; At least based on the business feature data, obtain the location information corresponding to the business feature data; Based on the business feature data and the location information, the spatial distribution characteristics of the business feature data are obtained. This process includes: Based on the location information, the space corresponding to the location information is divided into multiple regions, wherein each region corresponds to one location information. Based on the business feature data and the multiple regions, determine the sum of business feature data corresponding to each region; Based on the location information, the spatial adjacency relationship of the multiple regions is determined, wherein determining the spatial adjacency relationship of the multiple regions based on the location information includes: Based on the location information, obtain the spatial adjacency matrix; Based on the location information, determine the distance information between any two locations; Based on the distance information, obtain the inverse distance exponential function; Based on the spatial adjacency matrix and the inverse distance exponential function, the spatial adjacency relationships of the multiple regions are determined; Based on the spatial adjacency relationship, the location information, and the sum of the business feature data, the spatial distribution characteristics of the business feature data are obtained; Based on the spatial distribution characteristics, the spatial correlation of the business feature data is determined.

2. The method for determining the spatial correlation of communication service data according to claim 1, characterized in that, The step of obtaining location information corresponding to the business feature data, at least based on the business feature data, includes: Obtain the network engineering parameter data corresponding to the business characteristic data; The service feature data is matched with the network parameter data to obtain the location information corresponding to the service feature data.

3. The method for determining the spatial correlation of communication service data according to claim 2, characterized in that, The step of matching the service feature data with the network parameter data to obtain the location information corresponding to the service feature data includes: Based on the aforementioned service characteristic data, obtain the cell identification code; Based on the cell identification code, the service feature data is matched with the network engineering parameter data to obtain the location information corresponding to the service feature data.

4. An apparatus for determining the spatial correlation of communication service data, characterized in that, include: The data acquisition module is configured to acquire business characteristic data; The location information acquisition module is configured to acquire location information corresponding to the business feature data, at least based on the business feature data. The spatial distribution characteristic acquisition module is configured to acquire the spatial distribution characteristics of the business feature data based on the business feature data and the location information. The acquisition of the spatial distribution characteristics of the business feature data based on the business feature data and the location information includes: Based on the location information, the space corresponding to the location information is divided into multiple regions, wherein each region corresponds to one location information. Based on the business feature data and the multiple regions, determine the sum of business feature data corresponding to each region; Based on the location information, the spatial adjacency relationship of the multiple regions is determined, wherein determining the spatial adjacency relationship of the multiple regions based on the location information includes: Based on the location information, obtain the spatial adjacency matrix; Based on the location information, determine the distance information between any two locations; Based on the distance information, obtain the inverse distance exponential function; Based on the spatial adjacency matrix and the inverse distance exponential function, the spatial adjacency relationships of the multiple regions are determined; Based on the spatial adjacency relationship, the location information, and the sum of the business feature data, the spatial distribution characteristics of the business feature data are obtained; The spatial correlation determination module is configured to determine the spatial correlation of the business feature data based on the spatial distribution characteristics.

5. The apparatus for determining the spatial correlation of communication service data according to claim 4, characterized in that, The location information acquisition module is further configured to: Obtain the network engineering parameter data corresponding to the business characteristic data; The service feature data is matched with the network parameter data to obtain the location information corresponding to the service feature data.

6. An electronic device, characterized in that, include: Memory, used to store computer-readable instructions; as well as A processor for executing the computer-readable instructions, causing the electronic device to perform the method for determining the spatial correlation of communication service data as described in any one of claims 1 to 3.

7. A computer-readable storage medium for storing computer-readable instructions, characterized in that, When the computer-readable instructions are executed by a processor, the processor performs the method for determining the spatial correlation of communication service data as described in any one of claims 1 to 3.

8. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the method for determining the spatial correlation of communication service data as described in any one of claims 1 to 3.

Images