Method, apparatus and storage medium for separating mr data

Abstract

The application provides a measurement report MR data separation method and device and a storage medium, relates to the technical field of communication, and can effectively improve the speed and efficiency of MR data separation. The method comprises the following steps: determining the interval to which each MR data belongs based on the reference signal receiving power RSRP of each MR data in multiple measurement report MR data; the multiple MR data comprise outdoor MR data and indoor MR data; clustering multiple intervals based on the RSRP value of the interval midpoint of each interval and the proportion of MR data in each interval, and determining first MR data and second MR data; the first MR data and the second MR data each comprise at least one interval, and the RSRP of the first MR data is smaller than the RSRP of the second MR data; determining a distribution model of outdoor MR data based on the second MR data; and determining the outdoor MR data based on the distribution model of the outdoor MR data.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of communication technology, and in particular to a MR data separation method and device and storage medium. BACKGROUND

[0002] Measurement report (MR) analysis is an important tool for wireless communication network optimization, which can provide data support for the optimization of wireless communication network. However, MR analysis cannot determine whether the user is indoors or outdoors, and cannot exclude the interference of outdoor data in network coverage analysis. Therefore, it is necessary to separate indoor and outdoor MR data to improve the accuracy of network coverage analysis.

[0003] Currently, when separating indoor and outdoor MR data, a large amount of MR data and multiple field data are usually required, and the indoor and outdoor MR data are separated by processing a large amount of data. As a result, the existing technology has high complexity, long time and low efficiency. SUMMARY

[0004] The present application provides a measurement report MR data separation method and device and storage medium, which can effectively improve the speed and efficiency of MR data separation.

[0005] To achieve the above-mentioned purpose, the present application adopts the following technical solutions:

[0006] In a first aspect, the present application provides a MR data separation method, which comprises: determining the interval to which each MR data belongs based on the reference signal received power (RSRP) of each MR data in a plurality of measurement report (MR) data; the plurality of MR data includes outdoor MR data and indoor MR data; clustering the plurality of intervals based on the RSRP value of the interval midpoint of each interval and the proportion of MR data in each interval to determine first MR data and second MR data; the first MR data and the second MR data each include at least one interval, and the RSRP of the first MR data is less than the RSRP of the second MR data; determining the distribution model of outdoor MR data based on the second MR data; and determining the outdoor MR data based on the distribution model of the outdoor MR data.

[0007] In one possible implementation, multiple intervals are clustered based on the RSRP value of the midpoint of each interval and the proportion of MR data within each interval to determine the first MR data and the second MR data. This includes: Step 1: Selecting any two intervals from the multiple intervals as the first central intervals, and determining the distance between each interval and the first central interval based on the RSRP value of the midpoint of each interval and the proportion of MR data within each interval; Step 2: Assigning each interval to the nearest first central interval to form two first clusters; each first cluster is composed of at least one merged interval; Step 3: Re-determining the second central intervals for the first clusters, and re-assigning each interval to the nearest second central interval to determine two second clusters; each second cluster is composed of at least one merged interval; Step 4: Re-determining... Determine the third central interval of the second cluster and reassign each interval to the nearest third central interval to determine two third clusters; the third cluster is composed of at least one merged interval; Step 5: When the third central interval does not meet the preset conditions or does not reach the preset number of iterations, repeat step 4 until the third central interval meets the preset conditions or reaches the preset number of iterations; the preset conditions include at least one of the following: the third central interval is the same as the second central interval, or the distance between the third central interval and the second central interval is less than a preset distance; Step 6: When the third central interval meets the preset conditions or reaches the preset number of iterations, determine the two third clusters as the first MR data and the second MR data respectively; the RSRP of the first MR data is less than the RSRP of the second MR data; the second MR data includes at least two intervals.

[0008] In one possible implementation, based on the second MR data, a distribution model for the outdoor MR data is determined, including: establishing a mathematical programming model based on the RSRP value of the midpoint of each interval in the second MR data and the proportion of MR data within each interval.

[0009]

[0010]

[0011]

[0012] min≤μ≤max

[0013]

[0014] Among them, c y R is a constant and represents the adjustment factor for each level. y denoted as , where b represents the percentage of MR data within each interval of the second MR data set, and b represents the percentage of outdoor measurement points. It is a distribution model of outdoor MR data. Follows a normal distribution and satisfies y is the RSRP value of the interval midpoint of each interval in the second MR data; max and min are the upper and lower bounds of the interval corresponding to the maximum RSRP in the second MR data; and the distribution model of the outdoor MR data is determined based on the mathematical programming model.

[0015] In a possible implementation, after determining the outdoor MR data based on the distribution model of the outdoor MR data, the method further includes: determining the indoor MR data based on the outdoor MR data and the plurality of MR data.

[0016] In a possible implementation, the determining of the interval to which each MR data belongs based on the reference signal received power (RSRP) of each MR data in the plurality of MR data includes: obtaining the RSRP of each MR data in the plurality of MR data, and dividing the RSRP into a plurality of RSRP intervals based on a preset partitioning standard; determining a limited interval in the plurality of RSRP intervals; and determining the interval to which each MR data belongs based on the RSRP of each MR data and the plurality of RSRP intervals.

[0017] In a second aspect, the present application provides a MR data separation device, which includes: a processing unit; the processing unit is configured to determine the interval to which each MR data in a plurality of measurement report (MR) data belongs based on the reference signal received power (RSRP) of each MR data; the plurality of MR data includes outdoor MR data and indoor MR data; the processing unit is further configured to cluster a plurality of intervals based on the RSRP value of the interval midpoint of each interval and the proportion of MR data in each interval, and determine first MR data and second MR data; the first MR data and the second MR data each include at least one interval, and the RSRP of the first MR data is less than the RSRP of the second MR data; the processing unit is further configured to determine the distribution model of the outdoor MR data based on the second MR data; and the processing unit is further configured to determine the outdoor MR data based on the distribution model of the outdoor MR data.

[0018] In a possible implementation, the processing unit is further configured to: in step 1, select any two intervals as first center intervals from the plurality of intervals, determine the distance between each interval and the first center interval based on the RSRP value of the interval midpoint of each interval and the proportion of MR data in each interval; in step 2, assign each interval to the nearest first center interval to form two first-type clusters; the first-type cluster is composed of at least one interval merge; in step 3, re-determine the second center interval of the first-type cluster, and re-assign each interval to the nearest second center interval to determine two second-type clusters; the second-type cluster is composed of at least one interval merge; in step 4, re-determine the third center interval of the second-type cluster, and re-assign each interval to the nearest third center interval to determine two third-type clusters; the third-type cluster is composed of at least one interval merge; in step 5, when the third center interval does not satisfy the preset condition or does not reach the preset iteration number, re-execute step 4 until the third center interval satisfies the preset condition or reaches the preset iteration number; the preset condition includes at least one of the following: the third center interval is the same as the second center interval, and the distance between the third center interval and the second center interval is less than a preset distance; in step 6, when the third center interval satisfies the preset condition or reaches the preset iteration number, determine the two third-type clusters as the first MR data and the second MR data respectively; the RSRP of the first MR data is less than the RSRP of the second MR data; the second MR data includes at least two intervals.

[0019] In a possible implementation, the processing unit is specifically configured to: based on the RSRP value of the interval midpoint of each interval in the second MR data and the proportion of MR data in each interval, establish a mathematical programming model:

[0020]

[0021] s.t.

[0022]

[0023]

[0024] min≤μ≤max,

[0025]

[0026] wherein c y is a constant, R y is the proportion of MR data in each interval in the second MR data, b is the proportion of outdoor measurement points, is a distribution model of outdoor MR data, obeys normal distribution and satisfies y is the RSRP value of the interval midpoint of each interval in the second MR data; max and min are the upper and lower bounds of the interval corresponding to the maximum RSRP in the second MR data; based on the mathematical programming model, a distribution model of the outdoor MR data is determined.

[0027] In a possible implementation, after determining the outdoor MR data based on the distribution model of the outdoor MR data, the processing unit is further configured to determine the indoor MR data based on the outdoor MR data and the plurality of MR data.

[0028] In a possible implementation, the apparatus further includes an obtaining unit configured to obtain the RSRP of each MR data in the plurality of MR data; a processing unit configured to divide the RSRP into a plurality of RSRP intervals based on a preset partitioning criterion; the processing unit is further configured to determine a limited interval in the plurality of RSRP intervals; and the processing unit is further configured to determine an interval to which each MR data belongs based on the RSRP of each MR data and the plurality of RSRP intervals.

[0029] In a third aspect, the present application provides an MR data separation apparatus, which includes a processor and a communication interface; the communication interface is coupled to the processor, and the processor is configured to run a computer program or instructions to implement the MR data separation method described in the first aspect and any possible implementation of the first aspect.

[0030] In a fourth aspect, the present application provides a computer readable storage medium, which stores instructions, and when the instructions are run on a terminal, the terminal performs the MR data separation method described in the first aspect and any possible implementation of the first aspect.

[0031] In a fifth aspect, the present application provides a computer program product including instructions, and when the computer program product is run on an MR data separation apparatus, the MR data separation apparatus performs the MR data separation method described in the first aspect and any possible implementation of the first aspect.

[0032] In a sixth aspect, the present application provides a chip, which includes a processor and a communication interface; the communication interface is coupled to the processor, and the processor is configured to run a computer program or instructions to implement the MR data separation method described in the first aspect and any possible implementation of the first aspect.

[0033] Specifically, the chip provided in the present application further includes a memory configured to store the computer program or instructions.

[0034] In the MR data separation method provided by the embodiment of the application, the application does not need to process a large amount of data, only needs to obtain a reference signal receiving power RSRP of a measurement report MR data, divide an interval for the RSRP, separate the MR data into first MR data and second MR data, and separate outdoor MR data based on the second MR data. The application can obtain a separation result of MR data with sufficient precision only by using a small amount of statistical data, and effectively improves the speed and efficiency of MR data separation. BRIEF DESCRIPTION OF DRAWINGS

[0035] Figure 1 A structural schematic diagram of an MR data separation system provided by the embodiment of the application is shown in FIG. 1.

[0036] Figure 2 A structural schematic diagram of an MR data separation device provided by the embodiment of the application is shown in FIG. 2.

[0037] Figure 3 A flowchart of an MR data separation method provided by the embodiment of the application is shown in FIG. 3.

[0038] Figure 4 A flowchart of another MR data separation method provided by the embodiment of the application is shown in FIG. 4.

[0039] Figure 5 A flowchart of another MR data separation method provided by the embodiment of the application is shown in FIG. 5.

[0040] Figure 6 A flowchart of another MR data separation method provided by the embodiment of the application is shown in FIG. 6.

[0041] Figure 7 A flowchart of another MR data separation method provided by the embodiment of the application is shown in FIG. 7.

[0042] Figure 8 A flowchart of another MR data separation method provided by the embodiment of the application is shown in FIG. 8.

[0043] Figure 9 A structural schematic diagram of another MR data separation device provided by the embodiment of the application is shown in FIG. 9. DETAILED DESCRIPTION

[0044] The MR data separation method, device and storage medium provided by the embodiment of the application are described in detail below with reference to the accompanying drawings.

[0045] The term “and / or” in the present document is only used to describe the association relationship of the associated objects, and can represent three relationships, for example, A and / or B can represent three cases of existence of A alone, existence of A and B simultaneously, and existence of B alone.

[0046] The terms "first", "second", and the like in the description of the present application and in the claims of the present application are used for distinguishing between similar objects, or for distinguishing between different processing steps, and are not necessarily used to describe a particular sequential or chronological order. The terms "first", "second", and the like are used an identically intended purposes in the description of the present application and in the claims of the present application.

[0047] In addition, the terms "comprise", "comprising", "have", "having", "include", "including", "contain", "containing", and any variations thereof in the description and in the claims of the present application are intended to cover a non-exclusive inclusion. For example, a process, method, system, product, or apparatus that comprises a list of steps or units is not necessarily limited to the listed steps or units, but can optionally further include other steps or units not listed, or can optionally further include other steps or units inherent to such process, method, system, product, or apparatus.

[0048] It should be noted that in the embodiments of the present application, the words "exemplary" or "for example" are used to mean serving as an example, instance, or illustration. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of "exemplary" or "for example" is intended to present concepts in a concrete manner.

[0049] In the description of the present application, the meaning of "a plurality of" is two or more, unless otherwise specified.

[0050] In order to facilitate understanding, the terms involved in the present application are first explained.

[0051] 1. Rasterized MR: Rasterized MR is a process of processing MR data according to raster levels. In this process, the platform outputs information including the total number of MR points, the average reference signal receiving power (RSRP), the total number of indoor MR points, the average value of indoor RSRP, etc. in units of raster levels.

[0052] 2. Cell: A cell, also known as a cellular cell, refers to an area covered by a base station or a part (sector antenna) of a base station in a cellular mobile communication system. In this area, a mobile station can reliably communicate with the base station through a wireless channel.

[0053] 3. Spatial scale: Spatial scale generally refers to the size of the space used to carry out research. According to the area, it is divided into partial area, local area and large area, and according to latitude, it is divided into subtropical or subtropical.

[0054] The above is a detailed explanation of the terms involved in the embodiments of the present application.

[0055] A method for separating indoor and outdoor MR data based on a statistical model is provided in the related art, which comprises: performing eigenvalue statistics of a received signal for MR sampling data of each cell of an outdoor macro station, including statistics of a main area level; performing separation and probability calculation of a mixed Gaussian distribution, and obtaining a corresponding indoor and outdoor separation result according to an indoor probability. And support combining multiple factors such as main area level, main neighbor level difference and neighbor area number, and outputting an indoor and outdoor determination result through a combination model; other angle judgment methods can also be integrated.

[0056] A method and device for separating indoor and outdoor MR data are also provided in the related art, which comprises: dividing MR data into M grids or N grids or M*N grids according to sub-items TA and AOA in the MR data, so that at least one attribute of MR data in each grid after division is the same; clustering and separating the MR data corresponding to each grid into two types of indoor and outdoor MR data according to the sub-item MR.LteScRSRP.

[0057] The related art also provides an indoor and outdoor separation method, device and medium, which comprises: receiving S1MME data and MR data reported by a user to obtain a first database; processing the MR data in the first database to screen outdoor users; removing the MR data of the outdoor users from the first database to obtain a second database; establishing an indoor user feature library, matching the MR data of the users in the second database with the indoor user feature library to screen indoor users; removing the MR data of the indoor users from the second database to obtain a third database; and screening outdoor users and indoor users in the third database based on base station positions and time period features.

[0058] The related art also provides a multi-dimensional measurement report indoor and outdoor separation method, which comprises: forming a multi-dimensional indoor and outdoor MR separation method for distinguishing indoor and outdoor MR data by a room division signal source separation method, an outdoor test feature separation method and a user mobility separation method, and then forming an indoor and outdoor MR grid for evaluating wireless network quality of indoor scenes such as residential buildings, office buildings and hotels and various outdoor road scenes.

[0059] However, the existing technology usually requires a large amount of MR data, and cannot be effective when there is only a small amount of MR data or only segmented statistical values of MR data. The existing technology requires multiple field data in MR data, and has high data integrity requirements. The algorithm complexity of the existing technology is high, the time consumption is long, and the efficiency is low.

[0060] Therefore, the embodiment of the present application provides a measurement report (MR) data separation method, which does not need to process a large amount of data, only needs to obtain the RSRP of the MR data, divides intervals for the RSRP, separates the MR data into first MR data and second MR data, and separates outdoor MR data based on the second MR data. The embodiment of the present application only needs a small amount of statistical data to obtain a separation result of the MR data with sufficient precision, and effectively improves the speed and efficiency of MR data separation.

[0061] The technical scheme provided by the embodiment of the present application can be applied to various communication systems, for example, a new radio (NR) communication system using a fifth generation mobile communication technology (5G), a future evolution system or a multi-communication fusion system, etc.

[0062] Exemplarily, as shown in Figure 1 , a structure schematic diagram of an MR data separation system 100 provided by the embodiment of the present application is shown. Figure 1 The MR data separation system 100 includes an MR data separation device 101 and a plurality of base stations. Figure 1 Taking an example that the MR data separation system 100 includes one MR data separation device 101 and two base stations (a base station 102 and a base station 103) for description.

[0063] The MR data separation device 101 is configured to separate indoor MR data and outdoor MR data in MR data.

[0064] The outdoor cells in the base station 102 and the base station 103 can upload the MR data in the grid smaller than the preset spatial scale to the MR data separation device 101. The grid with smaller spatial scale is convenient for more fine network planning and optimization.

[0065] Optionally, the specification of the grid can be 50*50 meters.

[0066] In an example, the MR data separation device 101 can be a server. The server can be a single server, or can also be a server cluster composed of a plurality of servers. In some embodiments, the server cluster can also be a distributed cluster.

[0067] Optionally, the base station 102 and the base station 103 can be a base station (base transceiver station, BTS) in a global system for mobile communication (GSM), a base station (node B) in a code division multiple access (CDMA), a base station (eNB) in a wideband code division multiple access (WCDMA), an internet of things (IoT) or a narrowband-internet of things (NB-IoT), a base station in a future 5th generation mobile communication technology (5G) mobile communication network or a future evolved public land mobile network (PLMN), and the present application does not make any limitation thereto.

[0068] In addition, the MR data separation system described in the embodiments of the present application is for more clearly illustrating the technical solutions of the embodiments of the present application, and does not constitute a limitation on the technical solutions provided by the embodiments of the present application. It can be known by those skilled in the art that, with the evolution of network architecture and the emergence of new MR data separation systems, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0069] In specific implementation, Figure 1 The devices in the embodiments of the present application can adopt the component structures shown in Figure 2 or include the components shown in Figure 2 . Figure 2 A component structure of an MR data separation apparatus 200 provided by the embodiments of the present application is shown in the figure. The MR data separation apparatus 200 can be the MR data separation device 101 or a chip or system on chip in the MR data separation device 101. As shown in Figure 2 , the MR data separation apparatus 200 can include a processor 201 and a communication line 202.

[0070] Further, the MR data separation apparatus 200 can further include a communication interface 203 and a memory 204. The processor 201, the memory 204 and the communication interface 203 can be connected through the communication line 202.

[0071] The processor 201 can be a CPU, a general-purpose processor, a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a programmable logic device (PLD), or any combination thereof. The processor 201 can also be other devices with processing capability, such as a circuit, a device, or a software module, without limitation.

[0072] The communication line 202 is configured to transmit information between components included in the MR data separation apparatus 200.

[0073] The communication interface 203 is configured to communicate with other devices or other communication networks. The other communication networks can be an Ethernet, a radio access network (RAN), a wireless local area network (WLAN), or the like. The communication interface 203 can be a module, a circuit, a communication interface, or any device capable of communication.

[0074] The memory 204 is configured to store instructions. The instructions can be a computer program.

[0075] The memory 204 can be a read-only memory (ROM) or other type of static storage device that can store static information and / or instructions, or can be a random access memory (RAM) or other type of dynamic storage device that can store information and / or instructions, or can be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disk storage, a magneto-optical disk, a magnetic disk storage medium, or other magnetic storage device, without limitation.

[0076] It should be noted that the memory 204 can exist independently of the processor 201, or can be integrated with the processor 201. The memory 204 can be configured to store instructions or program codes or some data, etc. The memory 204 can be located in the MR data separation apparatus 200, or can be located outside the MR data separation apparatus 200, without limitation. The processor 201 is configured to execute the instructions stored in the memory 204, to implement the MR data separation method provided in the embodiments described below.

[0077] In an example, the processor 201 can include one or more CPUs, for example, CPU0 and CPU1.

[0078] As an optional implementation, the MR data separation apparatus 200 includes a plurality of processors.

[0079] As an optional implementation, the MR data separation apparatus 200 further includes an output device and an input device. Exemplarily, the output device is a display screen, a speaker, or the like, and the input device is a keyboard, a mouse, a microphone, or a joystick, or the like.

[0080] It should be noted that the MR data separation apparatus 200 can be a desktop computer, a portable computer, a network server, a mobile phone, a tablet computer, a wireless terminal, an embedded device, a chip system, or a device with a similar structure. In addition, Figure 2 the constituent structures shown in the foregoing Figure 2 do not constitute a limitation on the various devices in the foregoing Figure 1 and Figure 2 In addition to the components shown in the foregoing Figure 2 and Figure 1 the various devices in the foregoing Figure 2 may include more or fewer components than shown, or combine certain components, or have different arrangements of components.

[0081] In the embodiments of the present application, the chip system can be composed of a chip, or can include a chip and other discrete devices.

[0082] In addition, the actions, terms, and the like involved in the various embodiments of the present application can be mutually referred to and are not limited. The message name or parameter name in the message exchanged between the various devices in the embodiments of the present application is only an example, and other names can also be used in the specific implementation, which is not limited.

[0083] The MR data separation method provided by the embodiments of the present application will be described below in combination with the MR data separation system 100 shown in the foregoing Figure 1 . In the various embodiments of the present application, the actions, terms, and the like involved can be mutually referred to and are not limited. The message name or parameter name in the message exchanged between the various devices in the embodiments of the present application is only an example, and other names can also be used in the specific implementation, which is not limited. The actions involved in the various embodiments of the present application are only an example, and other names can also be used in the specific implementation, for example, “include in” in the embodiments of the present application can also be replaced by “carried in” or “carried in” and the like.

[0084] To solve the problems in the prior art, the embodiment of the application provides a MR data separation method for improving the speed and efficiency of MR data separation. Figure 3 As shown in the figure, the method comprises S301-S304.

[0085] S301, the MR data separation device determines the interval to which each MR data belongs based on the reference signal received power (RSRP) of each MR data in the plurality of measurement report (MR) data.

[0086] Among the plurality of MR data, there are outdoor MR data and indoor MR data.

[0087] In a possible implementation, the MR data separation device receives MR data from the grid of the base station cell and extracts the RSRP of all MR data in the grid. The MR data separation device can select a suitable partitioning standard, divide the RSRP into a plurality of RSRP intervals, and count the proportion (Rate) of MR data in each interval, and arrange the data in the format shown in Table 1.

[0088] In Table 1, when the RSRP is located in the interval [a1, a2), the proportion (Rate) is R1; when the RSRP is located in the interval [a2, a3), the proportion (Rate) is R2; when the RSRP is located in the interval [a n-1 , a n ), the proportion (Rate) is R n-1 ; when the RSRP is located in the interval [a n , a n+1 ), the proportion (Rate) is R n .

[0089] Table 1 Relationship table between RSRP interval and proportion (Rate)

[0090] RSRP [[a1,a2)] [[a2,a3)]]> … [[a n-1 ,a n )]]> [[a n ,a n+1 )]]> Rate [R1] [R2] … [R n-1 ]]> [R n ]]>

[0091] In a possible implementation, when the RSRP of the MR data in the grid has been segmented and counted, the MR data separation device only needs to arrange the MR data according to the above data format, and does not need to re-divide the intervals.

[0092] S302, the MR data separation device clusters the plurality of intervals based on the RSRP value of the interval midpoint of each interval and the proportion of MR data in each interval, and determines a first MR data and a second MR data.

[0093] The first MR data and the second MR data each comprise at least one interval, and the RSRP of the first MR data is less than the RSRP of the second MR data.

[0094] In a possible implementation, the MR data separation device calculates the RSRP value of the interval midpoint of each interval, and determines the proportion of MR data in each interval, and determines a two-dimensional array composed of the RSRP value of the interval midpoint Center and the proportion Rate, as shown in Table 2. In Table 2, when the interval midpoint Center is , the proportion Rate is R1; when the interval midpoint Center is , the proportion Rate is R2; when the interval midpoint Center is , the proportion Rate is R n-1 ; when the interval midpoint Center is , the proportion Rate is R n .

[0095] Table 1 Relationship table between interval midpoint Center and proportion Rate

[0096]

[0097] For example, the MR data separation device calculates the RSRP value of the interval midpoint of the interval [-120, -110) to be -115, and the proportion of MR data in the interval to be 0.1; the RSRP value of the interval midpoint of the interval [-110, 100) to be -105, and the proportion of MR data in the interval to be 0.1; the RSRP value of the interval midpoint of the interval [-80, -70) to be -75, and the proportion of MR data in the interval to be 0.2; and the RSRP value of the interval midpoint of the interval [-70, -60) to be -65, and the proportion of MR data in the interval to be 0.15. The MR data separation device determines a two-dimensional array composed of the RSRP value of the interval midpoint Center and the proportion Rate, as shown in Table 3:

[0098] Table 2 Relationship table between interval midpoint Center and proportion Rate

[0099] Center -115 -105 … -75 -65 Rate 0.1 0.1 … 0.2 0.15

[0100] It should be noted that the basic principle of the clustering algorithm is to determine the relationship between data by calculating the similarity or distance of data quality inspection, and to classify similar data into a class, so that the data points in the same class are as similar as possible, and the data points in different classes are as different as possible.

[0101] Optionally, the clustering algorithm can be at least one of a K-means algorithm, a K-modes algorithm, a K-prototypes algorithm, a K-medoids algorithm, a CLARA algorithm, a CLARANS algorithm, a Focused CLARAN algorithm, a PCM algorithm, a DBSCAN algorithm, and the like, and the present application does not limit the same.

[0102] In a possible implementation, the MR data separation device determines a plurality of first type clusters, each of which is composed of a zone of the plurality of zones. The MR data separation device determines distances between the first type clusters based on RSRP values of zone midpoints of each zone and proportions of MR data in each zone. The MR data separation device determines two second type clusters based on the distances between the plurality of first type clusters, determines one of the two second type clusters as a second type cluster A and the other as a second type cluster B, if the RSRP value of the one second type cluster is less than a preset RSRP value.

[0103] The MR data separation device determines whether the first type clusters in the second type cluster B are greater than two. When the first type clusters in the second type cluster B are greater than two, the MR data separation device determines the second type cluster A as first MR data and the second type cluster B as second MR data. When the first type clusters in the second type cluster B are less than two, the MR data separation device resets the zoning criterion, re-zones the RSRP, and iteratively performs the above process.

[0104] S303, the MR data separation device determines a distribution model of outdoor MR data based on the second MR data.

[0105] It should be understood that, when the indoor user terminal receives the outdoor base station signal, the indoor user terminal will suffer more wall loss than the outdoor user terminal, and thus the average RSRP value of the indoor user terminal will be less than that of the outdoor user terminal, and it can be considered that the second MR data is mainly composed of outdoor users.

[0106] S304, the MR data separation device determines outdoor MR data based on the distribution model of the outdoor MR data.

[0107] In a possible implementation, the MR data separation device determines the outdoor MR data R out (i):

[0108]

[0109] The technical solutions provided by the above embodiments at least have the following beneficial effects: as can be seen from S301-S304, the present application does not need to process a large amount of data, only needs to obtain the RSRP of the MR data, zone the RSRP, and then separate the MR data into first MR data and second MR data, and separate the outdoor MR data based on the second MR data. The present application only needs a small amount of statistical data to obtain a separation result of the MR data with sufficient precision, and effectively improves the speed and efficiency of MR data separation.

[0110] In an optional embodiment, the MR data separation device is combined with a base station. Figure 3 For example,Figure 4 As shown, in S302, the process of clustering the plurality of intervals and determining the first MR data and the second MR data based on the RSRP value of the interval midpoint of each interval and the proportion of MR data in each interval can be implemented by the following S401-S406:

[0111] S401, the MR data separation device selects any two intervals from the plurality of intervals as first center intervals, and determines the distance of each interval from the first center interval based on the RSRP value of the interval midpoint of each interval and the proportion of MR data in each interval.

[0112] For example, the MR data separation device selects the interval [-120, -110) and the interval [-70, -60) as the first center intervals, and then determines the distance of each interval from the two first center intervals based on the RSRP value -115 of the interval midpoint of the interval [-120, -110) and the proportion 0.1, and the RSRP value -65 of the interval midpoint of the interval [-70, -60) and the proportion 0.15.

[0113] S402, the MR data separation device assigns each interval to the nearest first center interval to form two first clusters.

[0114] The first cluster is composed of at least one interval merge.

[0115] For example, the MR data separation device assigns the interval [-110, -100) to the first center interval [-120, -110) to form a first cluster, and assigns the interval [-80, -70) to the first center interval [-70, -60) to form a first cluster.

[0116] S403, the MR data separation device re-determines the second center interval of the first cluster, and re-assigns each interval to the nearest second center interval to determine two second clusters.

[0117] The second cluster is composed of at least one interval merge.

[0118] For example, the MR data separation device re-determines the second center interval [-110, -100) of the first cluster formed by the intervals [-110, -100), [-120, -110), and the second center interval [-70, -60) of the first cluster formed by the intervals [-80, -70), [-70, -60), and assigns the intervals [-120, -110), [-80, -70) to the center interval [-110, -100) to form a second cluster, and the interval [-70, -60) forms another second cluster.

[0119] S404, the MR data separation device re-determines third center intervals of the second type of clusters, and re-allocates each interval to the nearest third center interval, to determine two third type of clusters.

[0120] The third type of clusters are composed of at least one interval merging.

[0121] S405, when the third center intervals do not meet the preset condition or do not reach the preset iteration number, the MR data separation device re-executes S404 until the third center intervals meet the preset condition or reach the preset iteration number.

[0122] Optionally, the preset condition includes at least one of the following: the third center intervals are the same as the second center intervals, and the distance between the third center intervals and the second center intervals is less than a preset distance.

[0123] In one possible implementation, the MR data separation device determines whether the following condition is met: whether the third center intervals are the same as the second center intervals, or the third center intervals change little from the second center intervals, i.e., the distance between the third center intervals and the second center intervals is less than a preset distance or reaches a preset iteration number, and when the condition is not met, the MR data separation device re-selects the third center intervals until the condition is met.

[0124] S406, when the third center intervals meet the preset condition or reach the preset iteration number, the MR data separation device determines the two third type of clusters as first MR data and second MR data respectively.

[0125] The RSRP of the first MR data is less than the RSRP of the second MR data, and the second MR data includes at least two intervals.

[0126] In one possible implementation, the MR data separation device randomly selects two intervals from a plurality of intervals as two center intervals, and allocates each interval in the plurality of intervals to the nearest center interval to form two initial clusters. For each cluster, the MR data separation device re-calculates the center interval based on the RSRP value of the interval midpoint of each interval, and the proportion of MR data in each interval, and re-allocates each interval to the nearest center interval, and repeats the above steps until the center interval meets the preset condition. The MR data separation device outputs the two center intervals and the corresponding two clusters, and determines the cluster with smaller average RSRP value of each interval in the two clusters as the first MR data, and determines the cluster with smaller average RSRP value of each interval in the two clusters as the second MR data.

[0127] In a possible implementation, when the interval contained in the second MR data is less than two, the MR data separation device can re-divide the intervals according to the RSRP of the MR data, re-determine the interval to which each MR data belongs, and re-perform the above steps to determine the second MR data.

[0128] The technical solutions provided by the above embodiments at least bring the following beneficial effects: as can be seen from S401-S406, the MR data separation device in the application clusters multiple intervals based on the RSRP value of the interval midpoint of each interval and the proportion of MR data in each interval, and the MR data separation device in the application determines the distance between intervals by using the midpoint RSRP value of each interval and the proportion of MR data. This method can more accurately reflect the difference between intervals, accurately distinguish the first MR data and the second MR data, and help us to accurately cluster and analyze in terms of signal coverage and signal quality.

[0129] In an optional embodiment, in combination with Figure 3 As shown in Figure 5 , in S303, the process of determining the distribution model of the outdoor MR data based on the second MR data can be implemented by the following S501-S502:

[0130] S501, the MR data separation device establishes a mathematical programming model based on the RSRP value of the interval midpoint of each interval in the second MR data and the proportion of MR data in each interval:

[0131]

[0132] s.t.

[0133]

[0134]

[0135] min≤μ≤max,

[0136]

[0137] where c y is a constant, R y is the proportion of MR data in each interval in the second MR data, b is the proportion of outdoor measurement points, is the distribution model of the outdoor MR data, obeys normal distribution and satisfies y is the RSRP value of the interval midpoint of each interval in the second MR data; max and min are the upper and lower bounds of the interval corresponding to the maximum RSRP in the second MR data, respectively;

[0138] S502, the MR data separation device determines a distribution model of the outdoor MR data based on the mathematical programming model.

[0139] It should be understood that for the same location, multiple RSRP measurement results conform to a normal distribution, and the RSRP mean value is affected by spatial loss, that is, the blocking condition affects the RSRP mean value. In a grid smaller than the preset size, the spatial scale is much smaller than the base station coverage range, so it can be considered that the blocking conditions of outdoor users within the grid are the same, that is, the RSRP measurement results of all outdoor users conform to the same normal distribution. For indoor users, due to the complexity of the indoor environment, the indoor space size is smaller than the grid size, so it is not considered that the RSRP measurement results of all indoor users within the grid conform to a normal distribution.

[0140] In an implementable manner, since the second MR data is mainly composed of outdoor MR data, the second MR data conforms to a normal distribution The MR data separation device determines the distribution model of the outdoor MR data based on R y and y to establish the above mathematical programming model R y is the proportion of MR data in each interval in the second MR data, R y (i) = {R1, R2,..., R m}, and y is the RSRP value of the interval midpoint of each interval in the second MR data. For example, when the interval midpoint y is , the proportion R y is R1, and the specific relationship table is shown in Table 4:

[0141] Table 4 Interval midpoint y and proportion R y of each interval

[0142]

[0143] The MR data separation device inputs the proportion of MR data in each interval in the above second MR data and the RSRP value of the interval midpoint of each interval into the mathematical programming model to determine the distribution model of the outdoor MR data

[0144] The technical scheme provided by the above embodiment at least brings the following beneficial effects: as can be seen from S501-S502, the mathematical programming model can provide a systematic method to process and analyze a large amount of data, so that the data processing is more efficient and accurate, the actual problem can be converted into a mathematical problem, and the mathematical method is used to solve the problem, so that a more accurate result can be obtained, which is beneficial to improve the accuracy and reliability of the outdoor MR data distribution model.

[0145] In an optional embodiment, after the MR data separation device determines the outdoor MR data based on the distribution model of the outdoor MR data in S304,Figure 3 Based on the illustrated method embodiments, this embodiment provides a possible implementation method, combined with Figure 3 ,like Figure 6 As shown, this method can be determined by the following S601.

[0146] S601, the MR data separation device determines indoor MR data based on outdoor MR data and multiple MR data.

[0147] In one alternative implementation, the distribution model r of the MR data is:

[0148]

[0149] Among them, ξ and Distribution models for indoor and outdoor MR data are given, where a and b represent the proportions of indoor and outdoor measurement points in the raster, respectively. The outdoor MR data R is known. out Given MR data R(i) and MR data R(i), the MR data separation device can determine the indoor MR data R. in (i) is:

[0150]

[0151] The technical solution provided by the above embodiments brings at least the following beneficial effects: As can be seen from S601, the MR data separation device of this application can determine the indoor MR data after determining the outdoor MR data, which helps to reduce the uncertainty of the indoor MR data, improve the accuracy of the indoor MR data, and thus accurately separate the indoor and outdoor MR data, better understand the relationship between indoor and outdoor network coverage, so as to provide a basis for network optimization reminders.

[0152] In one alternative embodiment, combined with Figure 3 ,like Figure 7 As shown in S301, the process of determining the interval to which each MR data belongs based on the reference signal received power RSRP of each MR data in multiple measurement report MR data can be specifically implemented through the following S701-S703:

[0153] S701, the MR data separation device acquires the RSRP of each MR data in multiple MR data sets, and divides the RSRP into multiple RSRP intervals based on a preset partitioning standard.

[0154] For example, the MR data separation device extracts the RSRP of all MR data in the raster, selects the following segmentation criteria, divides the RSRP into multiple RSRP intervals, and calculates the percentage Rate of each interval. The statistical results are shown in Table 5.

[0155] In Table 5, when the RSRP is in the interval [-120, -110), the proportion Rate is 0.1; when the RSRP is in the interval [-110, -100), the proportion Rate is 0.1; when the RSRP is in the interval [-80, -70), the proportion Rate is 0.2; when the RSRP is in the interval [-70, -60), the proportion Rate is 0.15.

[0156] Table 2: Relationship between RSRP interval and proportion Rate

[0157] RSRP [-120，-110) [-110，-100) … [-80，-70) [-70，-60) Rate 0.1 0.1 … 0.2 0.15

[0158] S702, the MR data separation device determines a limited interval in the plurality of RSRP intervals.

[0159] In a possible implementation, the plurality of RSRP intervals determined by the MR data separation device are all limited intervals, that is, the interval endpoints are not equal to positive or negative infinity, and the MR data separation device can further remove intervals with low proportions at both ends of the interval, so that the sum of the proportions of all intervals is less than or equal to 1.

[0160] S703, the MR data separation device determines, based on the RSRP of each MR data and the plurality of RSRP intervals, an interval to which each MR data belongs.

[0161] For example, the MR data separation device determines, based on the RSRP of each MR data, an interval to which each MR data belongs. For example, if there is an MR data with an RSRP value of -115, the MR data belongs to the interval [-120, -110).

[0162] The technical solutions provided in the above embodiments at least have the following beneficial effects: as can be seen from S701-S703, in the present application, the MR data separation device can accurately separate indoor MR data and outdoor MR data by partitioning and clustering RSRP and then analyzing the RSRP of MR data, without needing to process too much MR data, without needing complete information of MR data, and only needing the RSRP field of MR data, thereby improving the efficiency of separating MR data.

[0163] Figure 8 is a flowchart of the MR data separation method in the present application, and the MR data separation method provided in the embodiments of the present application will be described below Figure 8 For example, the MR data separation method provided in the embodiments of the present application will be described below.

[0164] For example, the MR data separation method provided in the embodiments of the present application will be described below. Figure 8As shown, in the process of separating MR data, the input data needs to be sorted first, the MR data separation device extracts the RSRP of the MR data in the grid, selects a suitable partitioning standard, divides the RSRP into intervals, determines the proportion of MR data in each interval, and sorts the input data into a two-dimensional array data format of RSRP interval and the proportion of MR data in each interval.

[0165] After sorting the input data, the MR data separation device determines the RSRP value of the interval midpoint of each interval, and uses a clustering algorithm to cluster multiple intervals to determine the first MR data and the second MR data. The first MR data and the second MR data each include at least one interval, and the RSRP of the first MR data is less than the RSRP of the second MR data.

[0166] In order to ensure the accuracy of MR data separation, the MR data separation device judges whether the interval in the second MR data is greater than two intervals. When the interval in the second MR data is not greater than two, the MR data separation device needs to reselect the partitioning standard to divide the interval. When the interval in the second MR data is greater than two, the indoor and outdoor MR data are separated by a mathematical programming model.

[0167] It can be understood that the above-mentioned MR data separation method can be realized by the MR data separation device. In order to realize the above-mentioned functions, the MR data separation device includes the hardware structure and / or software module corresponding to each function. Those skilled in the art should easily realize that, in combination with the modules and algorithm steps of each example described in the embodiments disclosed in the present application, the embodiments disclosed in the present application can be realized in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed by hardware or computer software driven hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments disclosed in the present application.

[0168] The MR data separation device generated according to the above-mentioned method examples can be divided into functional modules according to the embodiments disclosed in the present application. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above-mentioned integrated module can be realized in the form of hardware or software functional module. It should be noted that the division of modules in the embodiments disclosed in the present application is illustrative, and is only a logical functional division. When actually implemented, there can be another division method.

[0169] Figure 9 A structural schematic diagram of an MR data separation device provided by the embodiments of the present application is shown in FIG. 9. Figure 9 As shown, the MR data separation device 90 can be used to executeFigures 3-8 The MR data separation method is shown. The MR data separation device 90 comprises a processing unit 901.

[0170] The processing unit 901 is configured to determine an interval to which each MR data belongs based on a reference signal received power (RSRP) of each MR data in the plurality of measurement report (MR) data; the plurality of MR data comprises outdoor MR data and indoor MR data.

[0171] The processing unit 901 is further configured to cluster the plurality of intervals based on an RSRP value of an interval midpoint of each interval and a proportion of MR data in each interval, and determine first MR data and second MR data; the first MR data and the second MR data each comprise at least one interval, and an RSRP of the first MR data is less than an RSRP of the second MR data.

[0172] The processing unit 901 is further configured to determine a distribution model of the outdoor MR data based on the second MR data.

[0173] The processing unit 901 is further configured to determine the outdoor MR data based on the distribution model of the outdoor MR data.

[0174] In a possible implementation, the processing unit 901 is specifically configured to: in step 1, select any two intervals as first center intervals from the plurality of intervals, and determine a distance between each interval and the first center interval based on an RSRP value of an interval midpoint of each interval and a proportion of MR data in each interval; in step 2, assign each interval to the nearest first center interval to form two first clusters; the first cluster is composed of at least one interval; in step 3, re-determine second center intervals of the first clusters, and re-assign each interval to the nearest second center interval to determine two second clusters; the second cluster is composed of at least one interval; in step 4, re-determine third center intervals of the second clusters, and re-assign each interval to the nearest third center interval to determine two third clusters; the third cluster is composed of at least one interval; in step 5, when the third center interval does not satisfy a preset condition or does not reach a preset iteration number, re-execute step 4 until the third center interval satisfies the preset condition or reaches the preset iteration number; the preset condition comprises at least one of the following: the third center interval is the same as the second center interval, or a distance between the third center interval and the second center interval is less than a preset distance; in step 6, when the third center interval satisfies the preset condition or reaches the preset iteration number, determine the two third clusters as the first MR data and the second MR data respectively; an RSRP of the first MR data is less than an RSRP of the second MR data; and the second MR data comprises at least two intervals.

[0175] In a possible implementation, the processing unit 901 is specifically configured to: based on RSRP values of interval midpoints of each interval in the second MR data and proportions of MR data in each interval, establish a mathematical programming model:

[0176]

[0177] s.t.

[0178]

[0179]

[0180] min≤μ≤max,

[0181]

[0182] wherein c y is a constant, R y is the proportion of MR data in each interval in the second MR data, b is the proportion of outdoor measurement points, is a distribution model of outdoor MR data, obeys normal distribution and satisfies y is the RSRP value of the interval midpoint of each interval in the second MR data; max and min are respectively the upper and lower boundaries of the interval corresponding to the maximum RSRP in the second MR data; based on the mathematical programming model, the distribution model of the outdoor MR data is determined.

[0183] In a possible implementation, after the outdoor MR data is determined based on the distribution model of the outdoor MR data, the processing unit 901 is further configured to: determine indoor MR data based on the outdoor MR data and the plurality of MR data.

[0184] In a possible implementation, the apparatus further includes an acquisition unit 902; the acquisition unit 902 is configured to acquire RSRP of each MR data in the plurality of MR data; the processing unit 901 is configured to divide the RSRP into a plurality of RSRP intervals based on a preset partitioning standard; the processing unit 901 is further configured to determine a limited interval in the plurality of RSRP intervals; and the processing unit 901 is further configured to determine an interval to which each MR data belongs based on the RSRP of each MR data and the plurality of RSRP intervals.

[0185] Those skilled in the art can clearly understand the above-mentioned technical solutions from the description of the above-mentioned embodiments. For the convenience and brevity of description, only the division of the above-mentioned functional modules is exemplified. In actual application, the above-mentioned functions can be completed by different functional modules according to needs, that is, the internal structure of the device is 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 refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0186] The present disclosure also provides a computer-readable storage medium having instructions stored thereon, which, when executed by a processor of an electronic device, enable the electronic device to perform the MR data separation method provided in the embodiments of the present disclosure.

[0187] The embodiments of the present disclosure also provide a computer program product containing instructions, which, when running on an electronic device, enable the electronic device to perform the MR data separation method provided in the embodiments of the present disclosure.

[0188] The computer-readable storage medium may, for example, be, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or apparatus, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a register, a hard disk, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing, or any other form of computer-readable storage medium known in the art. An exemplary storage medium is coupled to the processor such that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can be part of the processor. The processor and the storage medium can be located in an application-specific integrated circuit (ASIC). In the embodiments of the present disclosure, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0189] The above merely provides the specific implementation of the present application, but the protection scope of the present application is not limited to this. Any change or replacement within the technical scope disclosed by the present application should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for separating MR data in a measurement report, characterized in that, include: Based on the reference signal received power (RSRP) of each MR data in multiple measurement reports, the interval to which each MR data belongs is determined; The multiple MR data include outdoor MR data and indoor MR data; Based on the RSRP value of the midpoint of each interval and the proportion of MR data in each interval, multiple intervals are clustered to determine the first MR data and the second MR data; both the first MR data and the second MR data include at least one interval, and the RSRP of the first MR data is less than the RSRP of the second MR data. Based on the second MR data, determine the distribution model of the outdoor MR data; Based on the distribution model of the outdoor MR data, the outdoor MR data is determined; The method of clustering multiple intervals based on the RSRP value of the midpoint of each interval and the proportion of MR data within each interval to determine the first MR data and the second MR data includes: Step 1: Select any two intervals from the plurality of intervals as the first central interval. Based on the RSRP value of the midpoint of each interval and the proportion of MR data in each interval, determine the distance between each interval and the first central interval. Step 2: Assign each of the intervals to the nearest first central interval to form two first clusters; the first clusters are composed of at least one of the intervals merged. Step 3: Redetermine the second central interval of the first cluster and reassign each interval to the nearest second central interval to determine two second clusters; the second cluster is composed of at least one of the intervals merged. Step 4: Redetermine the third center interval of the second type of cluster, and reassign each interval to the nearest third center interval to determine two third type of clusters; each third type of cluster is composed of at least one of the merged intervals; Step 5: When the third central interval does not meet the preset conditions or does not reach the preset number of iterations, repeat step 4 until the third central interval meets the preset conditions or reaches the preset number of iterations; the preset conditions include at least one of the following: the third central interval is the same as the second central interval, or the distance between the third central interval and the second central interval is less than a preset distance; Step 6: When the third central interval meets the preset conditions or reaches the preset number of iterations, the two third clusters are respectively determined as the first MR data and the second MR data; the RSRP of the first MR data is less than the RSRP of the second MR data; the second MR data includes at least two of the intervals. The step of determining the distribution model of outdoor MR data based on the second MR data includes: Based on the RSRP value of the midpoint of each interval in the second MR data, and the proportion of MR data in each interval, a mathematical programming model is established: ， ； in, is a constant, and is the adjustment factor for each level. denoted as , where b represents the percentage of MR data within each interval of the second MR data set, and b represents the percentage of outdoor measurement points. It is a distribution model of outdoor MR data. Follows a normal distribution and satisfies , is the RSRP value of the midpoint of each interval in the second MR data; max and min are the upper and lower bounds of the interval corresponding to the maximum RSRP in the second MR data, respectively; Based on the mathematical programming model, the distribution model of outdoor MR data is determined.

2. The data separation method according to claim 1, characterized in that, After determining the outdoor MR data based on the distribution model of the outdoor MR data, the method further includes: Indoor MR data are determined based on the outdoor MR data and the plurality of MR data.

3. The data separation method according to claim 1, characterized in that, The determination of the interval to which each MR data belongs based on the Reference Signal Received Power (RSRP) of each MR data in multiple measurement reports includes: The RSRP of each MR data in multiple MR data is obtained, and the RSRP is divided into multiple RSRP intervals based on a preset partitioning standard; Determine a finite interval among the plurality of RSRP intervals; Based on the RSRP of each MR data and the plurality of RSRP intervals, the interval to which each MR data belongs is determined.

4. An MR data separation device, characterized in that, The device includes: a processing unit; The processing unit is used to determine the interval to which each MR data belongs based on the Reference Signal Received Power (RSRP) of each MR data in multiple measurement report MR data; the multiple MR data include outdoor MR data and indoor MR data; The processing unit is further configured to cluster multiple intervals based on the RSRP value of the midpoint of each interval and the proportion of MR data in each interval to determine first MR data and second MR data; the first MR data and second MR data both include at least one interval, and the RSRP of the first MR data is less than the RSRP of the second MR data. The processing unit is further configured to determine the distribution model of outdoor MR data based on the second MR data; The processing unit is also used to determine the outdoor MR data based on the distribution model of the outdoor MR data; The processing unit is specifically used for: Step 1: Select any two intervals from the plurality of intervals as the first central interval. Based on the RSRP value of the midpoint of each interval and the proportion of MR data in each interval, determine the distance between each interval and the first central interval. Step 2: Assign each of the intervals to the nearest first central interval to form two first clusters; the first clusters are composed of at least one of the intervals merged. Step 3: Redetermine the second central interval of the first cluster and reassign each interval to the nearest second central interval to determine two second clusters; the second cluster is composed of at least one of the intervals merged. Step 4: Redetermine the third center interval of the second type of cluster, and reassign each interval to the nearest third center interval to determine two third type of clusters; each third type of cluster is composed of at least one of the merged intervals; Step 5: When the third central interval does not meet the preset conditions or does not reach the preset number of iterations, repeat step 4 until the third central interval meets the preset conditions or reaches the preset number of iterations; the preset conditions include at least one of the following: the third central interval is the same as the second central interval, or the distance between the third central interval and the second central interval is less than a preset distance; Step 6: When the third central interval meets the preset conditions or reaches the preset number of iterations, the two third clusters are respectively determined as the first MR data and the second MR data; the RSRP of the first MR data is less than the RSRP of the second MR data; the second MR data includes at least two of the intervals. The step of determining the distribution model of outdoor MR data based on the second MR data includes: Based on the RSRP value of the midpoint of each interval in the second MR data, and the proportion of MR data in each interval, a mathematical programming model is established: ， ； in, is a constant, and is the adjustment factor for each level. denoted as , where b represents the percentage of MR data within each interval of the second MR data set, and b represents the percentage of outdoor measurement points. It is a distribution model of outdoor MR data. Follows a normal distribution and satisfies , is the RSRP value of the midpoint of each interval in the second MR data; max and min are the upper and lower bounds of the interval corresponding to the maximum RSRP in the second MR data, respectively; Based on the mathematical programming model, the distribution model of outdoor MR data is determined.

5. The apparatus according to claim 4, characterized in that, The device further includes: an acquisition unit; The acquisition unit is used to acquire the RSRP of each MR data in multiple MR data; The processing unit is used to divide the RSRP into multiple RSRP intervals based on a preset partitioning standard; The processing unit is further configured to determine a finite interval among the plurality of RSRP intervals; The processing unit is further configured to determine the interval to which each MR data belongs based on the RSRP of each MR data and the plurality of RSRP intervals.

6. An MR data separation 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 MR data separation method as described in any one of claims 1-3.

7. A computer-readable storage medium storing instructions, characterized in that, When the computer executes the instruction, the computer performs the MR data separation method as described in any one of claims 1-3.

Images