WO2022242530A1 - 一种确定流量统计结果的方法及装置 - Google Patents

一种确定流量统计结果的方法及装置 Download PDF

Info

Publication number
WO2022242530A1
WO2022242530A1 PCT/CN2022/092285 CN2022092285W WO2022242530A1 WO 2022242530 A1 WO2022242530 A1 WO 2022242530A1 CN 2022092285 W CN2022092285 W CN 2022092285W WO 2022242530 A1 WO2022242530 A1 WO 2022242530A1
Authority
WO
WIPO (PCT)
Prior art keywords
grid
traffic
grids
beams
values
Prior art date
Application number
PCT/CN2022/092285
Other languages
English (en)
French (fr)
Inventor
王琪
闫琦
蒋瑞拓
王楠斌
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to EP22803852.7A priority Critical patent/EP4319245A1/en
Publication of WO2022242530A1 publication Critical patent/WO2022242530A1/zh
Priority to US18/513,811 priority patent/US20240098009A1/en

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • H04L43/0876—Network utilisation, e.g. volume of load or congestion level
    • H04L43/0882—Utilisation of link capacity
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/02—Arrangements for optimising operational condition
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/06—Generation of reports
    • H04L43/062—Generation of reports related to network traffic
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/08—Testing, supervising or monitoring using real traffic
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W28/00—Network traffic management; Network resource management
    • H04W28/02—Traffic management, e.g. flow control or congestion control
    • H04W28/06—Optimizing the usage of the radio link, e.g. header compression, information sizing, discarding information

Definitions

  • the embodiments of the present application relate to the field of mobile communications, and in particular to a method and device for determining traffic statistics results.
  • large-scale network optimization is the trend of future network optimization.
  • it is necessary to obtain the distribution of traffic statistics in time and space, that is, to obtain traffic statistics in a certain spatial area within a period of time.
  • Embodiments of the present application provide a method and device for determining traffic statistics results, so as to obtain the distribution of traffic statistics results in time and space.
  • the embodiment of the present application provides a method for determining traffic statistics results.
  • the method includes: the first server obtains the first data set, and the first data set is included in A plurality of data collected in a period of time, each data includes flow measurement values and level measurement values of n beams.
  • the flow measurement value includes an uplink flow measurement value and/or a downlink flow measurement value.
  • the first server determines the second data set associated with the first grid in the first data set according to the level measurement values of n beams of each data and the center coordinates of the first grid, and according to the first data set
  • the traffic measurement value included in each data in the two data sets determines the upstream traffic or downstream traffic corresponding to the first grid within the first time period.
  • the central coordinates of the first grid are represented by level values of n beams.
  • the first server determines the data associated with the first grid in the first data set, obtains the second data set, and then determines the Traffic statistics results corresponding to the first grid in the first time period.
  • the traffic statistical results determined by the above method are the traffic statistical results of grid-level time period granularity, which can provide a basis for subsequent traffic optimization.
  • the first server determines the n beams included in any data in the first data set If the distance between the level measurement value and the central coordinate of the first grid is less than or equal to the radius of the first grid, then the data is the data in the second data set. The distance between the level measurement values of the n beams included in any one of the data included in the second data set and the central coordinate of the first grid is less than or equal to the radius of the first grid.
  • the first server determines that the distance between the level measurement values of n beams included in any one of the first data sets and the central coordinate of the first grid is smaller than the distance between the level measurement values of the n beams and the If the distance between the center coordinates of grids other than the first grid among the plurality of grids, the data is the data in the second data set.
  • the distance between the level measurement values of n beams included in the second data set and the central coordinates of the first grid is smaller than the distance between the level measurement values of the n beams and the plurality of grids except the first The distance from the center coordinates of other grids other than the grid.
  • the data belonging to the second data set in the first data set can be determined by adopting the above design.
  • the distance between the level measurement values of the n beams included in any one of the data in the first data set and the central coordinate of the first grid is less than or equal to that of the first grid Radius, and the distance between the level measurement values of the n beams included in the data and the center coordinates of the second grid is less than or equal to the radius of the second grid, wherein the second grid is the plurality of grids A grid other than the first grid in the grid; the distance between the level measurement values of the n beams included in the data and the central coordinates of the first grid is smaller than that of the n beams included in the data
  • the data is determined to be the data in the second data set.
  • the data belonging to the second data set in the first data set can be determined by adopting the above design.
  • the method further includes: acquiring center coordinates and radii corresponding to respective grids of the plurality of grids in the n-dimensional beam space, the plurality of grids including the first grid.
  • the above method can be used to obtain the information of multiple grids in the n-dimensional beam space. It can be understood that the information of the multiple grids may be determined by the first server itself, or other devices may determine the information of the multiple grids and notify the first server, which is not limited in this embodiment of the present application.
  • a training data set when acquiring the center coordinates corresponding to the grids of the multiple grids in the n-dimensional beam space, a training data set is acquired, the training data set includes multiple samples, each The samples include level measurement values of n beams, and a distance set corresponding to the training data set is obtained according to the level measurement values of the n beams corresponding to each sample in the plurality of samples, and a distance set corresponding to the training data set is obtained according to the distance set corresponding to the training data set Determine samples corresponding to each grid in the plurality of grids, and determine center coordinates corresponding to each grid according to the samples corresponding to each grid.
  • the distance set corresponding to the training data set includes the distance between the level measurement values of any two groups of n beams in the level measurement values of n beams corresponding to each sample in the plurality of samples, and each raster The distance between the level measurement values of the n beams included in each sample of any two samples in the samples corresponding to the grid satisfies a preset distance condition.
  • the central coordinates of the first grid are determined according to the samples corresponding to the first grid. Using the above method, first determine the grid to which each sample in the training set belongs, and further determine the center coordinates of the grid according to the samples corresponding to each grid.
  • the traffic statistics results corresponding to each grid are convenient for subsequent traffic optimization based on the traffic statistics results.
  • a training data set when acquiring the center coordinates corresponding to the grids of the multiple grids in the n-dimensional beam space, a training data set is acquired, the training data set includes multiple samples, each The samples include flow measurement values and level measurement values of n beams, and a distance set corresponding to the training data set is obtained according to the level measurement values of n beams corresponding to each sample in the plurality of samples, and according to the training data set
  • the corresponding distance set determines the samples corresponding to each candidate grid in the plurality of candidate grids, and determines each of the plurality of candidate grids according to the flow measurement value included in each sample in the sample corresponding to each candidate grid.
  • the traffic statistical value corresponding to the candidate grid according to the traffic statistical value corresponding to each candidate grid in the plurality of candidate grids, determine the candidate grid that meets the preset traffic condition, and use the candidate grid that meets the preset traffic condition as For the plurality of grids in the n-dimensional beam space, determine the corresponding center coordinates of each grid according to the samples corresponding to each grid in the plurality of grids, wherein the center coordinates of the first grid are determined according to the samples corresponding to the first grid.
  • the distance set corresponding to the training data set includes the distance between the level measurement values of any two groups of n beams in the level measurement values of n beams corresponding to each sample in the plurality of samples, and each candidate grid The distance between the level measurement values of the n beams included in each sample in any two samples of the corresponding samples satisfies a preset distance condition.
  • first determine the candidate grid to which each sample in the training set belongs, and combine the flow measurement value included in each sample to screen the candidate grid, and determine the center of the corresponding grid according to the sample corresponding to the screened grid Coordinates can realize the traffic statistics corresponding to each grid when performing traffic statistics, which is convenient for subsequent traffic optimization based on the traffic statistics results, and can also reduce the complexity of subsequent large-scale data calculation, storage and transmission.
  • the flow measurement value in each sample includes an uplink flow measurement value and/or a downlink flow measurement value;
  • the flow statistical value corresponding to the first grid includes the uplink flow measurement value corresponding to the first grid Statistical values of traffic and/or statistical values of downlink traffic corresponding to the first grid;
  • the statistical values of uplink traffic corresponding to the first grid are based on samples that include measured values of uplink traffic in the samples corresponding to the first grid determined; and/or the statistical value of the downstream traffic corresponding to the first grid is determined according to the sample that includes the measured value of the downstream traffic in the samples corresponding to the first grid;
  • the first grid is the multi- Any one of the candidate grids satisfying the preset traffic condition among the candidate grids, the traffic statistical value corresponding to the first grid meets the preset traffic condition means that the upstream traffic statistics corresponding to the first grid
  • the value is greater than or equal to a preset uplink traffic threshold, and/or the statistical value of downlink traffic corresponding to the first grid is greater than or equal to a preset down
  • the above method can be used to delete some candidate grids with low traffic, but the final grid can still cover most of the traffic, which can reduce the complexity of subsequent calculation, storage and transmission of large amounts of data.
  • the multiple grids are the intersection of candidate grids corresponding to k1 uplink traffic statistics values and k2 candidate grids corresponding to downlink traffic statistics values respectively; wherein, the k1 uplink traffic statistics values The ratio of the sum of the traffic statistics to the total uplink traffic statistics is greater than or equal to a first threshold, the ratio of the sum of the k2 downlink traffic statistics to the total downlink traffic statistics is greater than or equal to a second threshold, and k1 and k2 are positive integers;
  • the k1 uplink traffic statistic values are determined from the uplink traffic statistic values corresponding to each candidate grid in the plurality of candidate grids according to the order from large to small, and the k2 downlink traffic statistic values are determined according to the order from large to small
  • the small order is determined from the statistical value of downlink traffic corresponding to each candidate grid in the plurality of candidate grids, the total uplink traffic refers to the sum of measured values of uplink traffic included in the plurality of samples, the The total downlink flow refers to the sum of
  • the above method can be used to delete some candidate grids with low traffic, but the final grid can still cover most of the traffic, which can reduce the complexity of subsequent calculation, storage and transmission of large amounts of data.
  • the plurality of grids is a union set of candidate grids corresponding to k1 uplink traffic statistics values and k2 candidate grids corresponding to downlink traffic statistics values respectively; wherein, the k1 The ratio of the sum of uplink traffic statistics to the total uplink traffic statistics is greater than or equal to the first threshold, the ratio of the sum of the k2 downlink traffic statistics to the total downlink traffic statistics is greater than or equal to the second threshold, k1 and k2 are positive integers ;
  • the k1 uplink traffic statistic values are determined from the uplink traffic statistic values corresponding to each candidate grid in the plurality of candidate grids according to the order from large to small, and the k2 downlink traffic statistic values are determined according to the sequence from large to small
  • the sequence from the smallest to the smallest is determined from the statistical value of downlink traffic corresponding to each candidate grid in the plurality of candidate grids, the total uplink traffic refers to the sum of measured values of uplink traffic included in the plurality of samples, so The total downstream flow refers
  • the above method can be used to delete some candidate grids with low traffic, but the final grid can still cover most of the traffic, which can reduce the complexity of subsequent calculation, storage and transmission of large amounts of data.
  • the central coordinates of the first grid are the n beams calculated according to the level measurement values of the n beams included in each sample in the sample corresponding to the first grid The average value of the level measurements.
  • the center coordinates of the first grid can be calculated by using the above method.
  • the radius of the first grid is the maximum distance in a radius set, and the radius set includes electrical signals of n beams included in any one of the samples corresponding to the first grid.
  • the above method can be used to calculate the radius of the first grid.
  • the upstream traffic corresponding to the first grid during the first time period is determined according to the data in the second data set including the measured value of upstream traffic;
  • the downlink traffic corresponding to the first grid in the time period is determined according to the data in the second data set including downlink traffic measurement values.
  • the first server may also send the uplink traffic or downlink traffic corresponding to the first grid within the first time period to other servers.
  • the traffic statistics result can be calculated by using the above method.
  • the embodiment of the present application provides a device for determining traffic statistics results
  • the device includes: a transceiver unit, configured to obtain a first data set, the first data set includes a plurality of data collected during the first time period Data, each data includes a flow measurement value and level measurement values of n beams, and the flow measurement value includes an uplink flow measurement value and/or a downlink flow measurement value; a processing unit is used for n beams according to each data
  • the level measurement value of the first grid and the center coordinates of the first grid determine the second data set associated with the first grid in the first data set, and the center coordinates of the first grid use the electrical Average value representation; determine the upstream flow or downstream flow corresponding to the first grid within the first time period according to the flow measurement value included in each data in the second data set.
  • the transceiver unit is further configured to obtain the center coordinates and radii corresponding to the grids of the multiple grids in the n-dimensional beam space, the multiple grids including the first a grid.
  • the processing unit when determining the second data set associated with the first grid in the first data set, is configured to determine any data included in the first data set If the distance between the level measurement values of the n beams and the central coordinate of the first grid is less than or equal to the radius of the first grid, then the data is the data in the second data set. Or determine that the distance between the level measurement values of the n beams included in any one of the first data sets and the central coordinate of the first grid is smaller than the distance between the level measurement values of the n beams and the plurality of grids If the distance between the center coordinates of other grids in the grid other than the first grid, the data is the data in the second data set.
  • the processing unit is configured to determine that the distance between the level measurement values of the n beams included in any one of the data in the first data set and the central coordinate of the first grid is less than or equal to The radius of the first grid, and the distance between the level measurement values of the n beams included in the data and the center coordinates of the second grid is less than or equal to the radius of the second grid, wherein the second grid
  • the grid is a grid other than the first grid in the plurality of grids; the distance between the level measurement values of the n beams included in the data and the central coordinates of the first grid is less than the When the distance between the level measurement values of the n beams included in the data and the central coordinate of the second grid is determined, the data is determined to be the data in the second data set.
  • the transceiving unit is configured to acquire a training data set when acquiring the central coordinates corresponding to each grid of the plurality of grids in the n-dimensional beam space, and the training data set It includes a plurality of samples, and each sample includes level measurement values of n beams; the processing unit is configured to obtain the corresponding training data set according to the level measurement values of n beams corresponding to each sample in the plurality of samples.
  • a distance set includes the distance between the level measurement values of any two groups of n beams in the level measurement values of n beams corresponding to each sample in the plurality of samples; according to The distance set corresponding to the training data set determines the samples corresponding to each grid in the plurality of grids, wherein the n beams included in each sample of any two samples in the samples corresponding to each grid The distance of the level measurement value satisfies the preset distance condition; according to the samples corresponding to each grid, the center coordinates corresponding to each grid are determined, wherein the center coordinates of the first grid are based on the first grid The corresponding samples are determined.
  • the transceiving unit is configured to acquire a training data set when acquiring the central coordinates corresponding to each grid of the plurality of grids in the n-dimensional beam space, and the training data set It includes a plurality of samples, each sample includes flow measurement values and level measurement values of n beams; the processing unit is configured to obtain according to the level measurement values of n beams corresponding to each sample in the plurality of samples A distance set corresponding to the training data set, the distance set corresponding to the training data set includes the level measurement values of any two groups of n beams in the level measurement values of n beams corresponding to each sample in the plurality of samples According to the distance set corresponding to the training data set, the samples corresponding to each candidate grid in a plurality of candidate grids are determined, wherein each sample in any two samples in the samples corresponding to each candidate grid includes The distances of the level measurement values of the n beams satisfy the preset distance condition; according to the flow measurement value included in each sample in the sample corresponding to each candidate grid
  • the flow measurement value in each sample includes an uplink flow measurement value and/or a downlink flow measurement value;
  • the flow statistical value corresponding to the first grid includes the uplink flow measurement value corresponding to the first grid Statistical values of traffic and/or statistical values of downlink traffic corresponding to the first grid;
  • the statistical values of uplink traffic corresponding to the first grid are based on samples that include measured values of uplink traffic in the samples corresponding to the first grid determined; and/or the statistical value of the downstream traffic corresponding to the first grid is determined according to the sample that includes the measured value of the downstream traffic in the samples corresponding to the first grid;
  • the first grid is the multi- Any one of the candidate grids satisfying the preset traffic condition among the candidate grids, the traffic statistical value corresponding to the first grid meets the preset traffic condition means that the upstream traffic statistics corresponding to the first grid
  • the value is greater than or equal to a preset uplink traffic threshold, and/or the statistical value of downlink traffic corresponding to the first grid is greater than or equal to a preset down
  • the multiple grids are the intersection of candidate grids corresponding to k1 uplink traffic statistics values and k2 candidate grids corresponding to downlink traffic statistics values respectively; wherein, the k1 uplink traffic statistics values The ratio of the sum of the traffic statistics to the total uplink traffic statistics is greater than or equal to a first threshold, the ratio of the sum of the k2 downlink traffic statistics to the total downlink traffic statistics is greater than or equal to a second threshold, and k1 and k2 are positive integers;
  • the k1 uplink traffic statistic values are determined from the uplink traffic statistic values corresponding to each candidate grid in the plurality of candidate grids according to the order from large to small, and the k2 downlink traffic statistic values are determined according to the order from large to small
  • the small order is determined from the statistical value of downlink traffic corresponding to each candidate grid in the plurality of candidate grids, the total uplink traffic refers to the sum of measured values of uplink traffic included in the plurality of samples, the The total downlink flow refers to the sum of
  • the plurality of grids is a union set of candidate grids corresponding to k1 uplink traffic statistics values and k2 candidate grids corresponding to downlink traffic statistics values respectively; wherein, the k1 The ratio of the sum of uplink traffic statistics to the total uplink traffic statistics is greater than or equal to the first threshold, the ratio of the sum of the k2 downlink traffic statistics to the total downlink traffic statistics is greater than or equal to the second threshold, k1 and k2 are positive integers ;
  • the k1 uplink traffic statistic values are determined from the uplink traffic statistic values corresponding to each candidate grid in the plurality of candidate grids according to the order from large to small, and the k2 downlink traffic statistic values are determined according to the sequence from large to small
  • the sequence from the smallest to the smallest is determined from the statistical value of downlink traffic corresponding to each candidate grid in the plurality of candidate grids, the total uplink traffic refers to the sum of measured values of uplink traffic included in the plurality of samples, so The total downstream flow refers
  • the central coordinates of the first grid are the n beams calculated according to the level measurement values of the n beams included in each sample in the sample corresponding to the first grid The average value of the level measurements.
  • the radius of the first grid is calculated according to the level measurement values of the n beams included in each sample in the samples corresponding to the first grid and the The coordinates of the center of the grid are determined.
  • the radius of the first grid is the maximum distance in a radius set, and the radius set includes electrical signals of n beams included in any one of the samples corresponding to the first grid.
  • the upstream traffic corresponding to the first grid during the first time period is determined according to the data in the second data set including the measured value of upstream traffic;
  • the downlink traffic corresponding to the first grid in the time period is determined according to the data in the second data set including downlink traffic measurement values.
  • the transceiving unit is configured to send the uplink traffic or downlink traffic corresponding to the first grid within the first time period to the server.
  • the present application also provides a device.
  • the device can perform the method design described above.
  • the apparatus may be a chip or a circuit capable of performing the function corresponding to the above method, or a device including the chip or circuit.
  • the apparatus includes: a memory, configured to store computer executable program codes; and a processor, and the processor is coupled to the memory.
  • the program code stored in the memory includes instructions, and when the processor executes the instructions, the device or the device installed with the device executes the method in the above-mentioned first aspect or any possible design of the first aspect.
  • the device may further include a communication interface, which may be a transceiver, or, if the device is a chip or a circuit, the communication interface may be an input/output interface of the chip, such as an input/output pin.
  • a communication interface which may be a transceiver, or, if the device is a chip or a circuit, the communication interface may be an input/output interface of the chip, such as an input/output pin.
  • the device includes corresponding functional units for respectively implementing the steps in the above methods.
  • the functions may be implemented by hardware, or may be implemented by executing corresponding software through hardware.
  • Hardware or software includes one or more units corresponding to the functions described above.
  • the embodiment of the present application provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and when the computer program is run on the device, the first aspect or the first aspect are executed. Any one of the possible design methods.
  • the embodiment of the present application provides a computer program product, the computer program product includes a computer program, and when the computer program is run on the device, it executes any one of the possible functions of the first aspect or the first aspect. method in design.
  • FIG. 1 is one of the schematic diagrams of the beam space in the embodiment of the present application.
  • FIG. 2 is the second schematic diagram of the beam space in the embodiment of the present application.
  • Fig. 3 is the schematic diagram of MR structure in the embodiment of the present application.
  • FIG. 4 is an overview flowchart of a method for determining multiple grids in an n-dimensional beam space in an embodiment of the present application
  • FIG. 5 is an overview flowchart of a method for determining traffic statistics results in an embodiment of the present application
  • FIG. 6 is one of a schematic diagram of a communication structure in an embodiment of the present application.
  • FIG. 7 is a second schematic diagram of a communication structure in an embodiment of the present application.
  • FIG. 8 is a third schematic diagram of a communication structure in an embodiment of the present application.
  • FIG. 9 is one of the structural schematic diagrams of a device in the embodiment of the present application.
  • Fig. 10 is the second schematic diagram of a device structure in the embodiment of the present application.
  • Traffic refers to the data volume of the service flow transmitted by the user when performing data transmission services. Specifically, it may include uplink traffic and/or downlink traffic.
  • the uplink traffic refers to the sum of the size of uplink packets sent by the terminal device to the base station per unit time
  • the downlink traffic refers to the sum of the size of downlink packets sent by the base station to the terminal device per unit time.
  • the antennas of traditional MIMO are 2 antennas, 4 antennas or 8 antennas, while the number of channels of Massive MIMO reaches 64/128/256.
  • the actual signal moves in the horizontal direction in the coverage area and does not move in the vertical direction.
  • the Massive MIMO signal is introduced into the airspace of the vertical dimension on the basis of the horizontal dimension space for utilization.
  • Massive MIMO also has the advantages of providing rich spatial degrees of freedom, providing more possible arrival paths, and improving signal reliability.
  • terminal devices can use multiple beams (such as narrow beams) in the beam space to communicate during the interaction with the base station.
  • multiple beams such as narrow beams
  • the beam space may be defined based on multiple static beams.
  • Figure 1 is a schematic diagram of a possible beam space.
  • Static beams refer to beams formed using predefined weights during beamforming. For example, fixed beams are formed under a cell, where the number, width, and direction of the beams are all determined.
  • a beam carrying a sounding reference signal (sounding reference signal, SRS), or a beam carrying a synchronization signal block (synchronization signal and PBCH block, SSB) is a static beam, and its sending direction is determined by a physical radio frequency (radio frequency, RF ) parameter decision.
  • RF radio frequency
  • the n-dimensional beam space involved in the embodiment of the present application is defined based on n static beams.
  • the n-dimensional beam space is defined based on n beams carrying SRS.
  • the n beams are received by beam antennas
  • the number of beams, or the n-dimensional beam space is defined based on n beams carrying the SSB, where n beams are the number of beams received by the beam antenna.
  • the location of the terminal device can currently be determined in the following ways:
  • the beam ids corresponding to UE1 and UE3 are different, and the number of beams available to UE1 is different from the number of beams available to UE3, so the positions of UE1 and UE3 can be determined according to the above information.
  • the beam corresponding to UE1 refers to the beam used when UE1 communicates with the base station
  • the number of beams available to UE1 refers to the number of beams that UE1 can use when communicating with the base station.
  • the beam corresponding to UE3 refers to the number of beams used by UE3 and the base station.
  • the beams used for communication, the number of beams available to UE3 refers to the number of beams that UE3 can use when communicating with the base station.
  • Different level values corresponding to the same beam may also be used to indicate different positions in the beam space.
  • the beam id corresponding to UE1 is the same as the beam id corresponding to UE2, but because the distance between UE1 and the base station is different from the distance between UE2 and the base station, the level value corresponding to UE1 is different from the level value corresponding to UE2,
  • the location of UE1 and the location of UE2 may be indicated according to the above-mentioned beam id and level value.
  • the level value corresponding to UE1 may refer to the reference signal receiving power (reference signal receiving power) obtained by the base station measuring the SRS transmitted by UE1 using beam 1.
  • RSRP reference signal receiving power
  • the level value corresponding to UE2 may refer to the RSRP obtained by the base station measuring the SRS transmitted by UE2 using beam 1.
  • the position of the terminal device can be determined according to the horizontal direction angle of the main beam, the vertical direction angle of the main beam, and the path loss corresponding to the main beam.
  • Each beam corresponds to a horizontal direction angle and a vertical direction angle.
  • the path loss is proportional to the distance between the terminal device and the base station.
  • path loss refers to the loss caused by the propagation of electromagnetic waves in space, which is caused by the radiation diffusion of the transmitted power and the propagation characteristics of the channel, and reflects the change of the average value of the received signal power in the macroscopic range.
  • the solution for determining the position of the terminal device provided by way 3 is mainly applied to determine the position of the terminal device in an open scene.
  • signal transmission will be affected by obstructions in the environment, and using only information of one main beam to describe the location of terminal equipment has poor reliability and low resolution.
  • the above method 1 and method 2 can only determine the approximate location of the terminal device, while the solution provided by method 3 for determining the location of the terminal device uses the information of a single main beam, and its application scenarios are relatively limited.
  • information of multiple beams may be used to determine the position of the terminal device in the beam space.
  • the multi-beam information can more truly reflect the actual physical environment.
  • UE4 can receive the beam reflected by the building, and then determine the position of UE4 by not only using the information of beam 1 (ie, the main beam), but also using the information of beam 2 (ie, the reflected beam) at the same time. It can be understood that the accuracy of determining the position of UE4 by using the information of beam 1 and the information of beam 2 is higher than the accuracy of determining the position of UE4 by only using the information of beam 1 .
  • the multi-beam information may be determined through a measurement report (measurement report, MR).
  • MR can record the time when MR is generated, the level measurement value and flow measurement value of multiple beams, etc.
  • the level measurement value of a beam may be the RSRP obtained by the base station measuring the SRS sent by the terminal device using the beam, or the level measurement value of a beam may be the RSRP obtained by the terminal device measuring the SSB sent by the base station using the beam. Wherein, for the latter case, the terminal device needs to report the measured level measurement value of the beam to the base station.
  • CELLID refers to a cell ID.
  • the cell ID is the ID of the serving cell of the terminal device, and the MR is the MR for the terminal device.
  • TIME refers to the time when the MR was generated.
  • RSRP1 to RSRPn refer to level measurement values of n beams, or may also be referred to as n-dimensional beam level measurement values.
  • RSRP1 to RSRPn refer to the n RSRPs obtained by the base station measuring the SRS transmitted by the terminal equipment using n beams respectively, or the n RSRPs obtained by the terminal equipment measuring the SSB transmitted by the base station using n beams respectively.
  • n is the number of beams included in the beam space, for example, the value of n may be 32, or 64, etc. It can be understood that, taking RSRP1 as an example, RSRP1 is the average or cumulative value of the RSRP of the first beam measured within the time period determined by the generation time of the current MR and the generation time of the previous MR.
  • the MR may include level measurement values of n beams, or level measurement values of p beams, where p ⁇ n, and both p and n are positive integers.
  • the level measurement values of the p beams here refer to p effective level measurement values.
  • the terminal device or the base station may not be able to measure the level measurement values of all n beams, for example, the terminal device can only measure the level measurement values of p beams in the n beams, at this time, the terminal device may only Report the level measurement values of p beams.
  • the level measurement values of the p beams may be expressed as the level measurement values of the n beams, for example, the level measurement values of the other n-p beams except the p beams are set as default values.
  • ULTHP uplink throughput
  • DLTHP downlink throughput
  • ULTHP is the sum of the accumulated uplink packet size in the time period determined by the generation time of the current MR and the generation time of the previous MR
  • DLTHP is the size determined by the generation time of the current MR and the generation time of the previous MR The sum of the size of downlink packets accumulated in the time period.
  • An embodiment of the present application provides a method for determining multiple grids in an n-dimensional beam space.
  • a grid in the n-dimensional beam space refers to a beam space determined by taking the level values of a group of n beams as the center coordinates and taking R as the radius in the n-dimensional beam space.
  • the specific manner of determining the center coordinates and the radius R of each grid can refer to the following embodiments.
  • the first server is taken as the execution subject here as an example.
  • the first server may be any server or processor or cloud device or edge device, etc., which is not limited in this embodiment of the present application, as shown in FIG. 4 .
  • Step 401 the first server acquires a training data set, and the training data set includes M samples.
  • the training data set may include MRs collected within a preset time period, for example, the training data set may include MRs collected within one week or two weeks.
  • the base station may send the MR to the first server according to the subscription parameter.
  • the subscription parameters may include an MR reporting period (for example, several minutes or several hours or several seconds).
  • the specific form of MR can refer to FIG. 3 .
  • the training data set is MR collected for a cell within a preset time period. Therefore, the finally determined multiple grids in the n-dimensional beam space are multiple grids corresponding to the cell.
  • the training data set includes M samples, and each sample includes level measurement values of n beams.
  • the first server can determine the training data set shown in the level measurement value matrix L according to the M MRs. If an MR includes level measurement values of n beams (that is, RSRPs of n beams), the level measurement values of n beams are directly used as a row in the level measurement value matrix L. If an MR includes the level measurement values of p beams, it is necessary to write the level measurement values of p beams as the level measurement values of n beams. Specifically, the other n-p beams except p beams correspond to The measured level values of the beams are set to 0, and then the obtained measured level values of the n beams are used as a row in the level measured value matrix L.
  • each row in the level measurement value matrix L may correspond to the level measurement values of n beams in one MR, and the level measurement value matrix L indicates M groups of level measurement values.
  • the training data set includes M samples, and each sample includes flow measurement values and level measurement values of n beams, where the flow measurement values may include uplink flow measurements and/or downlink flow measurements value.
  • the first server may determine the training data set shown in the traffic matrix ThpMat according to the M MRs.
  • each row in the flow matrix ThpMat may correspond to a flow measurement value in one MR and level measurement values of n beams. If the MR only includes dlthp but not ulthp, then ulthp can be set to 0. Similarly, if the MR only includes ulthp but not dlthp, then dlthp can be set to 0.
  • the traffic matrix ThpMat can also include can also not include This embodiment of the present application does not limit this. It can be understood that the level measurement value matrix L can also be extracted through the flow matrix ThpMat.
  • the i-th row in the flow matrix ThpMat corresponds to the i-th MR
  • time i is the generation time of the i-th MR
  • rsrp i,n is the electric current of the n beams included in the i-th MR
  • ulthp i is the measured value of uplink traffic included in the i-th MR
  • dlthp i is the measured value of downlink traffic included in the i-th MR.
  • Step 402 The first server obtains a distance set corresponding to the training data set according to the training data set, and the distance set corresponding to the training data set includes distances between level measurement values of n beams of any two samples in the M samples.
  • the distance matrix R is calculated with the level measurement value matrix L or the flow matrix ThpMat as input (distance matrix R is M ⁇ M dimension), wherein,
  • the distance set corresponding to the training data set includes M(M ⁇ 1)/2 distances in total.
  • the above-mentioned distance matrix R is only a representation form of the distance set corresponding to the training data set, and the distance set corresponding to the training data set may also adopt other representation forms, which are not limited in this embodiment of the present application.
  • R ij represents the distance between the level measurement value of the n beams contained in the i-th sample in the level measurement value matrix L or the flow matrix ThpMat and the level measurement value of the n beams contained in the j-th sample, or it can be It is described as the distance between the beam space position corresponding to the i-th sample and the beam space position corresponding to the j-th sample.
  • the distance dist may be defined as the Euclidean distance or other distances in the beam space, which is not limited in this embodiment of the present application.
  • L i refers to the level measurement value of the n beams in the i-th row in the level measurement value matrix L, that is, ⁇ rsrp i,1 ,rsrp i,2 ,...,rsrp i,n ⁇ , L j, ⁇
  • L j refers to the level measurement values of the n beams in the j-th row in the level measurement value matrix L, that is, ⁇ rsrp j,1 , rsrp j,2 ,...,rsrp j,n ⁇ .
  • L i refers to the level measurement value of n beams in the i-th row in the flow matrix ThpMat, namely ⁇ rsrp i,1 ,rsrp i,2 ,...,rsrp i,n ⁇
  • L j Refers to the level measurement value of the n beams in the jth row of the flow matrix ThpMat, namely ⁇ rsrp j,1 ,rsrp j,2 ,...,rsrp j,n ⁇ .
  • the level measurement value matrix L includes 1000 rows
  • a distance is determined according to any two rows in the level measurement value matrix L
  • the distance matrix R is determined, and R has a dimension of 1000 ⁇ 1000.
  • Step 403 The first server determines the grid index corresponding to each sample in the M samples.
  • the grid index corresponding to each sample is determined by using a preset clustering algorithm according to the distance set corresponding to the training data set.
  • the preset clustering algorithm may refer to a distance clustering method (such as Kmeans, etc.), which is not limited in this embodiment of the present application.
  • the grid index corresponding to each sample can be determined by using a preset distance clustering algorithm according to the above distance matrix R. Specifically, it can be represented by the grid index matrix Label.
  • the grid index matrix Label can be a 1 ⁇ M matrix, label i refers to the grid index corresponding to the i-th sample, and the value of label i is an integer (1 ⁇ label i ⁇ m′), indicating the i-th sample Corresponding to the grid indicated by label i , where m' ⁇ M, the value of m' can be determined based on empirical values, or determined according to the size of the actual required grid range. It can be understood that the smaller the value of m', the larger the range of each grid, and the larger the value of m', the smaller the range of each grid.
  • the grid index matrix Label indicates the distribution of M samples in the m' grids.
  • the m' grids may be the finally determined multiple grids, that is, the number of the multiple grids may be m', or the m' grids may not be the final determined multiple grids.
  • the m' grids are m' candidate grids, which need to be further screened, and the number of finally determined multiple grids may be less than m'.
  • Step 404 The first server determines the center coordinates and radius of each grid.
  • the following describes how to determine the multiple grids included in the n-dimensional beam space, as well as the center coordinates and radius of each grid, in combination with Example 1 and Example 2 according to the specific content included in the training data set.
  • Example 1 If the training data set includes M samples, each sample includes level measurement values of n beams, excluding flow measurement values.
  • the m′ grids determined by using the preset distance clustering algorithm according to the distance matrix R are the multiple grids included in the finally determined n-dimensional beam space.
  • the central coordinates of each grid may be determined according to level measurement values of n beams included in each sample in the samples corresponding to the grid.
  • the level measurement values of n beams are calculated according to the level measurement values of n beams included in each sample in the sample corresponding to the grid index i Average value, the average value of the level measurement values of the n beams is recorded as the center coordinate of the i-th grid.
  • the raster index of the 2nd sample, the raster index of the 5th sample and the raster index of the 10th sample are the same, for example, the raster index of the 2nd sample, the raster index of the 5th sample, the raster index of the 10th sample
  • the grid indexes of the 10 samples are all 3, that is, the 2nd sample, the 5th sample, and the 10th sample belong to the 3rd grid, according to the 2nd sample, the 5th sample, and the 10th sample respectively
  • the level measurement values of the n included beams can determine the center coordinates of the grid whose grid index is 3 (that is, the third grid).
  • the 2nd sample, the 5th sample, the measured value of the level of the n beams that the 10th sample includes respectively:
  • the center coordinates of the third grid are determined as:
  • the radius of each grid can be a preset value, for example, the preset value can be determined according to empirical values. Alternatively, the radius of each grid may be determined according to the level measurement values of the n beams included in each sample corresponding to the grid and the center coordinates of the grid.
  • the radius of the i-th grid is determined according to the level measurement values of n beams included in each sample of the sample corresponding to the grid index i and the center coordinate of the i-th grid.
  • the radius of the i-th grid is determined according to the maximum distance in the radius set, which is the level measurement value of the n beams included in each sample in the sample corresponding to the grid index i The distance determined by the center coordinates of the i grids is formed.
  • the radius of the i-th grid is the maximum distance in the radius set, or the radius of the i-th grid is the sum of the maximum distance in the radius set and the preset distance, or the radius of the i-th grid is The difference between the largest distance in the set of radii and the preset distance.
  • the 2nd sample, the 5th sample, and the 10th sample belong to the grid whose grid index is 3, according to the electric
  • the flat measurement can determine the coordinates of the center of the third grid.
  • the 2nd sample, the 5th sample, the measured value of the level of the n beams that the 10th sample includes respectively:
  • the center coordinates of the third grid are:
  • the radius set can be determined, and the radius set includes distance 1, distance 2 and distance 3, of which,
  • Distance 2 consists of ⁇ rsrp 5,1 ,rsrp 5,2 ,...,rsrp 5,n ⁇ and Sure,
  • the radius of the third grid is the largest distance among distance1, distance2 and distance3.
  • the center coordinates corresponding to the m' grids can be represented by the center coordinate matrix X', and m' represents the number of grids in the n-dimensional beam space.
  • the i-th row in the center coordinate matrix X' represents the center coordinates of the grid with the grid index i (that is, the i-th grid).
  • the third row in the center coordinate matrix X' indicates the center coordinates of the grid with grid index 3 (that is, the third grid).
  • the radii of the m' grids may be the same, for example, the radius of each grid may be a preset value, or the radii of the m' grids may be represented by a radius matrix d'.
  • m' represents the number of grids in the n-dimensional beam space.
  • the i-th row element represents the radius of the i-th grid.
  • the 3rd row element represents the radius of the 3rd grid.
  • X′(i, ) represents the i-th row in the center coordinate matrix X′, that is, the center coordinate of the i-th grid
  • the distances from the center coordinates of the i-th grid are respectively calculated, and the maximum distance among them is taken as the Radius of i grids.
  • the sample corresponding to the i-th grid includes s samples
  • s distances can be determined from the center coordinates of the i-th grid according to the level measurement values of the n beams respectively included in the s samples, and s The maximum distance among the distances is taken as the radius of the i-th grid.
  • the solution is simple and easy to implement.
  • the center coordinate of each grid is the average value of the level measurement values of multiple samples, the spatial position of the flow rate is represented by the center coordinate of the grid, which can reduce the influence of noise and measurement error on the space. Location is more statistically significant.
  • Example 2 If the training data set includes M samples, and each sample includes flow measurement values and level measurement values of n beams, after step 403, m′ determined by using a preset distance clustering algorithm according to the distance matrix R The grids are not the multiple grids included in the finally determined n-dimensional beam space.
  • the m' grids determined after step 403 are the m' candidate grids, and m ' Candidate grids are screened to obtain multiple grids included in the finally determined n-dimensional beam space.
  • the flow measurement value in each sample includes an uplink flow measurement value and/or a downlink flow measurement value.
  • the uplink flow statistical value of the i-th candidate grid is the sum of the uplink flow values of the samples that include uplink flow measurement values in the samples corresponding to the i-th candidate grid.
  • the statistical value of the downstream traffic of the i-th candidate grid is the sum of the downstream traffic values of the samples that include the measured value of the downstream traffic in the samples corresponding to the i-th candidate grid.
  • the uplink traffic statistic value of the i-th candidate grid is the average uplink traffic value corresponding to the sample corresponding to the i-th candidate grid.
  • the downlink traffic statistical value of the i-th candidate grid is the average downlink traffic value corresponding to the sample corresponding to the i-th candidate grid.
  • the fourth candidate grid includes 5 samples, where sample 1, sample 3, and sample 4 include measured values of downlink traffic, sample 2 includes measured values of uplink traffic, and sample 5 includes measured values of uplink traffic and downlink traffic, Then the statistical value of the uplink traffic of the fourth candidate grid is the sum of the measured value of uplink traffic included in sample 2 and the measured value of uplink traffic included in sample 5, and the statistical value of the downlink traffic of the fourth candidate grid is the downlink traffic included in sample 1 The sum of the flow measurement value, the downstream flow measurement value included in sample 3, the downstream flow measurement value included in sample 4, and the downstream flow measurement value included in sample 5.
  • the uplink traffic statistics value of the fourth candidate grid is divided by the sum of the uplink traffic measurement value included in sample 2 and the uplink traffic measurement value included in sample 5, and the downlink traffic statistic value of the fourth candidate grid is sample The sum of the downstream traffic measurement value included in 1, the downstream traffic measurement value included in sample 3, the downstream traffic measurement value included in sample 4, and the downstream traffic measurement value included in sample 5 is divided by 4.
  • the flow measurement values in the M samples are summarized according to the grid index matrix Label, and the flow statistics corresponding to the m' candidate grids are obtained.
  • the flow statistics of the m' candidate grids are respectively The value can be represented by the following uplink traffic statistic value ULTHP and/or downlink traffic statistic value DLTHP.
  • ulthp i and dlthp i respectively represent the statistical value of the upstream traffic of the ith candidate grid and the statistical value of the downstream traffic of the ith candidate grid.
  • the uplink traffic statistic value ULTHP includes m′ uplink traffic statistic values, that is, the uplink traffic statistic values corresponding to m′ candidate grids, and the downlink traffic statistic value DLTHP includes m′ downlink traffic statistic values, that is, m′ candidate grids corresponding uplink traffic statistics.
  • the m' candidate grids can be screened in the following manner, but not limited to, to obtain multiple grids included in the finally determined n-dimensional beam space:
  • Method 1 If the uplink traffic statistics of the i-th candidate grid meet the preset uplink traffic threshold, and/or the downlink traffic statistics of the i-th candidate grid meet the preset downlink traffic threshold, then the i-th candidate grid grid as the final grid.
  • the preset uplink traffic threshold and the preset downlink traffic threshold may be determined according to empirical values, or determined according to actual screening needs. For example, when it is necessary to filter out candidate grids with a larger statistical value of uplink traffic, the preset uplink traffic threshold may be increased.
  • Method 2 According to the descending order of the m' uplink traffic statistics, k1 uplink traffic statistics are selected from the m' uplink traffic statistics, and the m' downlink traffic statistics are ordered from large to small Selecting k2 downlink traffic statistics values from the m′ downlink traffic statistics values.
  • the ratio of the sum of k1 uplink traffic statistics to the total uplink traffic statistics is greater than or equal to the first threshold, the ratio of the sum of k2 downlink traffic statistics to the total downlink traffic statistics is greater than or equal to the second threshold, k1 and k2 are positive integers , the statistical value of the total upstream traffic refers to the sum of the upstream traffic values of the samples including the measured value of the upstream traffic in the M samples, and the statistical value of the total downstream traffic refers to the downstream traffic value of the samples including the measured value of the downstream traffic in the M samples
  • the i-th uplink traffic statistic value among the m′ uplink traffic statistic values is the sum of the uplink traffic values of the samples including the uplink flow measurement value in the sample corresponding to the i-th candidate grid.
  • the i th downlink traffic statistic value among the m′ downlink traffic statistic values is the sum of the downlink traffic values of the samples including the downlink traffic measurement values in the sample corresponding to the i th candidate grid.
  • the plurality of grids is an intersection of candidate grids corresponding to k1 uplink traffic statistics values and k2 candidate grids corresponding to downlink traffic statistics values respectively.
  • the k1 uplink traffic statistics include the uplink traffic statistics of the i-th candidate grid
  • the k2 downlink traffic statistics include the i-th candidate grid's downlink traffic statistics
  • the i-th candidate raster as the finalized raster.
  • the k1 upstream traffic statistics include the upstream traffic statistics of the i-th candidate grid
  • the k2 downlink traffic statistics do not include the i-th candidate grid's downstream traffic statistics, then the i-th candidate grid raster is not the finalized raster.
  • the plurality of grids is a union set of candidate grids corresponding to k1 uplink traffic statistics values and k2 candidate grids corresponding to downlink traffic statistics values respectively.
  • the k1 uplink traffic statistics include the uplink traffic statistics of the i-th candidate grid
  • the k2 downlink traffic statistics include the i-th candidate grid's downlink traffic statistics
  • the i-th candidate raster as the finalized raster.
  • the i-th candidate Raster is not a finalized raster.
  • the uplink traffic statistical value ULTHP is taken out from the largest to the smallest m u grids according to the element value, so that the sum of the uplink traffic statistics corresponding to the m u grids respectively accounts for the total uplink traffic statistics
  • the ratio of the ratio exceeds r u (0 ⁇ r u ⁇ 1, for example, r u takes 0.8 or more), and the index of these m u grids is recorded as:
  • the downlink traffic statistical value DLTHP is taken out of m d grids according to the element value from large to small, so that the sum of the downlink traffic statistics corresponding to the m d grids respectively accounts for the total downlink traffic
  • the ratio exceeds r d (0 ⁇ r d ⁇ 1, for example, r d is above 0.8), and the index of these m d grids is recorded as:
  • the uplink traffic statistics corresponding to the m′ candidate grids it is judged whether they belong to the k1 uplink traffic statistics, and at the same time, whether the downlink traffic statistics corresponding to the m′ candidate grids are respectively judged whether they belong to the k2 downlink traffic statistics to determine the multiple grids included in the final n-dimensional beam space.
  • the central coordinates of each grid can be determined according to the level measurement values of n beams included in each sample in the sample corresponding to the grid , for example, assuming that the i-th grid is the finally determined multiple grids, the n-beam level of n beams is calculated according to the level measurement values of n beams included in each sample in the sample corresponding to the i-th grid The average value of the level measurement values, the average value of the level measurement values of the n beams is recorded as the center coordinate of the i-th grid.
  • the radius of each grid can be a preset value, for example, the preset value can be determined according to empirical values.
  • the radius of each grid may be determined according to the level measurement values of the n beams included in each sample corresponding to the grid and the center coordinates of the grid.
  • the radius of the i-th grid is determined according to the level measurement values of n beams included in each sample in the sample corresponding to the grid index i and the center coordinates of the i-th grid.
  • the radius of the i-th grid is determined according to the maximum distance in the radius set, which is the level measurement value of the n beams included in each sample in the sample corresponding to the grid index i The distance determined by the center coordinates of the i grids is formed.
  • the radius of the i-th grid is the maximum distance in the radius set, or the radius of the i-th grid is the sum of the maximum distance in the radius set and the preset distance, or the radius of the i-th grid is The difference between the largest distance in the set of radii and the preset distance.
  • the center coordinates corresponding to the m' candidate grids can be represented by a center coordinate matrix X', where m' represents the number of candidate grids in the n-dimensional beam space.
  • the i-th row in the central coordinate matrix X' represents the central coordinates of the candidate grid of the grid index i (ie, the i-th candidate grid).
  • the third row in the center coordinate matrix X' represents the center coordinates of the candidate grid of grid index 3 (ie the third candidate grid), as shown in the above example.
  • the radii of the m' candidate grids may be the same, for example, the radius of each candidate grid may be a preset value, or the radii of the m' candidate grids may be represented by a radius matrix d'.
  • m' represents the number of candidate grids in the n-dimensional beam space.
  • the i-th row element represents the radius of the i-th candidate grid.
  • the 3rd row element represents the radius of the 3rd candidate grid.
  • X′(i, ⁇ ) represents the i-th row in the center coordinate matrix X′, that is, the center coordinates of the candidate grid (the i-th candidate grid) of the grid index i.
  • the distances from the center coordinates of the i-th candidate grid are calculated respectively, and the maximum distance as the radius of the i-th candidate raster.
  • the samples corresponding to the i-th candidate grid include s samples
  • s distances from the center coordinates of the i-th candidate grid can be determined according to the level measurement values of the n beams respectively included in the s samples, Determine the largest distance among the s distances as the radius of the i-th candidate grid.
  • the corresponding row is taken out from the center coordinate matrix X′, which is recorded as the center coordinate matrix X, and at the same time from the radius matrix d′ Take out the corresponding row, and record it as the radius matrix d.
  • the corresponding row is taken out from the center coordinate matrix X', which is recorded as the center coordinate matrix X, and the corresponding row is taken out from the radius matrix d' The row of is recorded as the radius matrix d.
  • the final output central coordinate matrix X is:
  • the final output radius matrix d is:
  • the candidate grids can be screened by the traffic measurement value included in each sample, and a part of grids with low traffic can be deleted.
  • the number of grids determined using the method shown in Example 2 above is reduced compared to the number of grids determined using the method shown in Example 1, but the determined grids can still cover most of the traffic. That is to say, under the premise that the final effect of traffic perception (that is, traffic statistics results) is not greatly affected, the complexity of subsequent big data calculation, storage, and transmission is reduced.
  • the determined multiple grids in the n-dimensional beam space can also be updated every preset time period, that is, step 401 to step 404 are performed regularly .
  • the multiple grids in the n-dimensional beam space are determined for the first time according to the collected MR, which can also be called the grid initialization process. It is not the first time to determine multiple grids in the n-dimensional beam space according to the collected MR, which can also be called the grid update process.
  • the grid associated with the first terminal device can be determined according to the level measurement values of the n beams corresponding to the first terminal device, and then the grid associated with the first terminal device can be determined by using The grid associated with the first terminal device characterizes the location of the terminal device.
  • the n beams corresponding to the center coordinates of a grid and the first terminal device can be sequentially calculated according to the order of the grid indexes of the m grids The distance of the level measurement.
  • the distance between the level measurement values of the n beams corresponding to the first terminal device and the center coordinate of the i-th grid is less than or equal to the radius of the i-th grid, it is determined that the first terminal device is associated with the i-th grid , at this time, there is no need to determine the distances between the center coordinates of other remaining grids after the i-th grid and the level measurement values of the n beams corresponding to the first terminal device.
  • the ratio of the center coordinates of a grid to the level measurement values of the n beams corresponding to the first terminal device can be sequentially calculated according to the order of the grid indexes of the 10 grids distance.
  • the distance between the level measurement values of the n beams corresponding to the first terminal device and the center coordinate of the first grid is greater than the radius of the first grid, it is determined that the first terminal device is not associated with the first grid , and continue to calculate the distances between the level measurement values of the n beams corresponding to the first terminal device and the center coordinates of the second grid.
  • the first terminal device is not associated with the second grid , and continue to calculate the distances between the level measurement values of the n beams corresponding to the first terminal device and the center coordinates of the third grid.
  • the distance between the level measurement values of the n beams corresponding to the first terminal device and the center coordinates of the third grid is less than or equal to the radius of the third grid, it is determined that the distance between the first terminal device and the third grid and stop calculating the distance between the level measurement values of the n beams corresponding to the first terminal device and the center coordinate of the fourth grid.
  • the level measurement values of the n beams corresponding to the first terminal device and the center coordinates of N grids in the m grids determine The distances are all smaller than the corresponding radius, 2 ⁇ N ⁇ n, and N is a positive integer, then select the grid corresponding to the minimum distance as the grid associated with the first terminal device, or select any grid from N grids as the grid associated with the first terminal device.
  • the grid associated with the first terminal device select the grid corresponding to the minimum distance as the grid associated with the first terminal device, or select any grid from N grids as the grid associated with the first terminal device.
  • the distance between the level measurement values of the n beams corresponding to the first terminal device and the center coordinates of the i-th grid is smaller than the radius of the i-th grid
  • the corresponding The distance between the level measurement values of the n beams and the center coordinate of the jth grid is smaller than the radius of the jth grid. If the first distance is smaller than the second distance, the grid associated with the first terminal device is the i-th grid.
  • the distance between the level measurement values of the n beams corresponding to the first terminal device and the center coordinate of the first grid is smaller than the radius of the first grid, and the n beams corresponding to the first terminal device
  • the distance between the level measurement value of the first beam and the center coordinate of the fifth grid is smaller than the radius of the fifth grid, and the level measurement value of the n beams corresponding to the first terminal device is the same as the 11th grid
  • the distance between the center coordinates of the first grid (denoted as distance 11) is less than the radius of the eleventh grid, wherein, among distance 1, distance 5 and distance 11, distance 11 is the smallest, then the grid associated with the first terminal device for the 11th grid.
  • the n-dimensional beam space includes m grids
  • the grid corresponding to the smallest distance among the m distances is the i-th grid, and then the i-th grid is used as the grid associated with the first terminal device.
  • the distribution of traffic statistics results in time and space may be further obtained based on the multiple grids.
  • An embodiment of the present application provides a method for determining traffic statistics results.
  • the first server is taken as the execution subject here.
  • the first server can be any server or processor or cloud device or edge device.
  • the embodiment of the application does not limit this. It can be understood that the execution subject of the embodiment shown in FIG. 4 may be the same as or different from the execution subject of the embodiment shown in FIG. 5 , which is not limited in this embodiment of the present application.
  • the method includes:
  • Step 501 the first server acquires a first data set, the first data set includes a plurality of data collected in a first time period, and each data includes flow measurement values and level measurement values of n beams.
  • the first data set may include MRs collected during a first time period.
  • the first data set may include MRs collected within one week or two weeks, or the first data set may include MRs collected within one day, or the first data set may include MRs collected within one hour, the first data set may include Includes MR collected from 7am to 10am.
  • the training data set may include MRs collected during a preset time period, and the first data set may include MRs collected during a first time period.
  • the first time period is later than the preset time period, and both the first data set and the training data set are MRs acquired for the same cell.
  • the base station may send the MR to the first server according to the subscription parameter.
  • the subscription parameters may include an MR reporting period (for example, several minutes or several hours or several seconds).
  • the first server can divide the collected data into data sets corresponding to multiple time periods according to the generation time in MR to obtain multiple data sets, and the first data set can be multiple data sets one of the.
  • the first data set is MR collected for a cell within the first time period, and the first data set may be identified by a cell identifier and the first time period.
  • the cell corresponding to the first data set is the same cell as the cells corresponding to the plurality of grids in the n-dimensional beam space, and any one of the plurality of grids may be identified by a cell identifier and a grid index.
  • the first data set includes K data.
  • the first data set can be shown as ThpMat 1 , and the level matrix L 1 can be extracted through ThpMat 1 .
  • each row in ThpMat 1 may correspond to the generation time, flow measurement value (uplink flow measurement value and/or downlink flow measurement value) and level measurement value of n beams included in one MR, and K is the first data set includes the number of data.
  • Each row of the level matrix L1 is the level measurement value of n beams.
  • time 1,1 ...time K,1 all belong to the first time period.
  • Step 502 The first server determines the second data set associated with the first grid in the first data set according to the level measurement values of n beams of each data and the center coordinates of the first grid, and the first grid The center coordinates of the grid are represented by the level values of n beams.
  • the first grid can be any one of the multiple grids in the n-dimensional beam space, or the first grid can be a specific one of the multiple grids in the n-dimensional beam space grid.
  • the first server may use, but not limited to, the following methods to determine the second data set associated with the first grid in the first data set:
  • Method 1 The first server determines that the distance between the level measurement values of n beams included in any data in the first data set and the center coordinates of the first grid is less than or equal to the radius of the first grid, then the data is the first The data in the second data set.
  • the first server may sequentially calculate the center coordinate of a grid and the first The data includes the distance of the level measurements of the n beams.
  • the distance between the level measurement values of the n beams included in the first data and the central coordinate of the first grid is less than or equal to the radius of the i-th grid, it is determined that the first data is associated with the first grid, and at this time The distances between the center coordinates of other grids before the first grid and the level measurement values of the n beams included in the first data are greater than the corresponding radius.
  • the distance between the center coordinates of a grid and the level measurement values of the n beams included in the first data can be calculated sequentially according to the order of the grid indexes of the 10 grids .
  • the distance between the level measurement values of the n beams included in the first data and the center coordinates of the first grid is greater than the radius of the first grid, it is determined that the first data is not associated with the first grid, and Continue to calculate the distance between the level measurement values of the n beams included in the first data and the center coordinate of the second grid.
  • the distance between the level measurement values of the n beams included in the first data and the center coordinates of the second grid is greater than the radius of the second grid, it is determined that the first data is not associated with the second grid, and Continue to calculate the distance between the level measurement values of the n beams included in the first data and the center coordinate of the third grid.
  • the distance between the level measurement values of the n beams included in the first data and the center coordinates of the third grid is less than or equal to the radius of the third grid, it is determined that the first data is associated with the third grid, And stop continuing to calculate the distance between the level measurement values of the n beams included in the first data and the center coordinate of the fourth grid.
  • the first server can select any one of the N grids as the grid associated with the first data.
  • the distance between the level measurement values of the n beams included in the first data and the center coordinate of the first grid is smaller than the radius of the first grid, the n beams included in the first data
  • the distance between the level measurement value and the center coordinate of the fifth grid is smaller than the radius of the fifth grid, and the level measurement values of the n beams included in the first data are different from those of the eleventh grid
  • the distance between the center coordinates is less than the radius of the 11th grid, where any one of the 1st grid, the 5th grid and the 11th grid is selected as the grid with the first data The associated raster.
  • the first server determines the distance (denoted as distance Set 1), the first data is the data in the first data set, and the distance set 2 is determined according to the respective radii and distance set 1 of each of the plurality of grids, and the minimum distance in the distance set 2 is the first grid If the distance between the grid and the level measurement values of the n beams included in the first data is determined, then it is determined that the second data set includes the first data. Wherein, any distance in the distance set 2 is smaller than the radius of the grid corresponding to the distance.
  • the distances between the level measurement values of the n beams included in the first data and the central coordinates of N grids in the m grids are all smaller than the corresponding radius, 2 ⁇ N ⁇ n, and N is a positive integer, then the grid corresponding to the minimum distance is selected as the grid associated with the first data.
  • the distance between the level measurement values of the n beams included in the first data and the center coordinate of the first grid is smaller than the radius of the first grid
  • the n beams included in the first data The distance between the level measurement value and the center coordinate of the fifth grid (denoted as distance 5) is smaller than the radius of the fifth grid, and the level measurement values of the n beams included in the first data are different from those of the eleventh grid
  • the distance of the center coordinates (denoted as distance 11) is less than the radius of the eleventh grid, among which, among distance 1, distance 5 and distance 11, distance 11 is the smallest, then the eleventh grid is the grid associated with the first data grid.
  • Mode 2 The first server determines that the distance between the level measurement values of n beams included in any one of the data sets in the first data set and the center coordinate of the first grid is smaller than the distance between the level measurement values of the n beams and multiple grids If the distance between the center coordinates of grids other than the first grid, the data is the data in the second data set.
  • the first data set includes the first data
  • the first server calculates the level measurement values of the n beams included in the first data and each grid in the m grids
  • the distances of the center coordinates of the grid are obtained to obtain m distances, and the grid corresponding to the smallest distance among the m distances is used as the grid associated with the first data.
  • the grid corresponding to the smallest distance among the m distances is the i-th grid, and then the i-th grid is used as the grid associated with the first data.
  • Step 503 The first server determines the upstream traffic or downstream traffic corresponding to the first grid within the first time period according to the traffic measurement value included in each data in the second data set.
  • the flow measurement value in each data includes an uplink flow measurement value and/or a downlink flow measurement value.
  • the uplink traffic is determined according to the data including the uplink traffic measurement value in the second data set, and the downlink traffic is determined according to the data including the downlink traffic measurement value in the second data set.
  • the first server may sum up the uplink traffic measurement values included in the second data set as the uplink traffic statistics result corresponding to the first grid within the first time period.
  • the first server may sum up the downlink traffic measurement values included in the second data set as the downlink traffic statistics result corresponding to the first grid within the first time period.
  • the data associated with each of the plurality of grids in the first data set can be determined, and the flow rate at the first time can be determined according to the flow measurement value included in the data associated with each grid.
  • the traffic statistics result corresponding to the grid in the period, and then the traffic statistics result corresponding to each of the multiple grids in the first time period is obtained.
  • the multiple grids in the n-dimensional beam space are determined according to the method in Example 2 above, and the cells corresponding to the multiple grids in the n-dimensional beam space are the same as the cells corresponding to the first data set. According to the distance determined between L 1 (i, ⁇ ) in the level matrix L 1 and each row in the central coordinate matrix X determined in Example 2 above, a distance set s i is obtained.
  • L 1 (i, ⁇ ) is the i-th row in the level matrix L 1 , that is, the level measurement values of the n beams included in the i-th data in the first data set.
  • X(j, ⁇ ) is the jth row in the center coordinate matrix X, that is, the center coordinate of the jth grid in the n-dimensional beam space.
  • s i,j represents the distance between the level measurement value of the n beams included in the i-th data and the center coordinate of the j-th grid.
  • s i,1 is smaller than d 1
  • s i,2 is smaller than d 2
  • s i,1 ⁇ s i,2 the i-th data belongs to the first grid, or is described as the i-th grid Data is associated with the 1st raster.
  • the grid index of the belonging grid is recorded as -1, that is, the i-th data indicates that there is no belonging grid.
  • A1 can be a 1 ⁇ K matrix.
  • a i represents the grid to which the i-th data in the first data set belongs.
  • the i-th row of V u represents the statistical value of the upstream traffic corresponding to the i-th grid in the first time period
  • the i-th row of V d represents the statistical value of the downstream traffic corresponding to the i-th grid in the first time period.
  • the first server after determining the grid to which each data in the first data set belongs, divides ThpMat 1 into Z time ranges according to the generation time and the preset duration, for example, the preset duration for T.
  • TimeRange i is the ith sub-time period in the first time period
  • the duration of the i-th sub-time period is T.
  • the first server can follow A 1 to add The generation time belongs to the sub-time period and the flow measurement values belonging to the same grid are summed to obtain the following flow statistics:
  • T Z [TimeRange 1 ,TimeRange 2 ,...,TimeRange Z ]
  • T Z is the segmentation result of dividing the first preset time period into Z time ranges with a preset duration
  • the i-th row of V u represents the uplink traffic corresponding to the i-th grid in Z time ranges
  • the i-th row of V d represents the statistical value of the downlink traffic corresponding to the i-th grid in the Z time range.
  • the jth column of V u represents the uplink traffic statistics corresponding to the m grids in the jth sub-time period
  • the i-th row of V d represents the downlink traffic statistics corresponding to the m grids in the jth sub-time period value.
  • the traffic statistical results of user traffic determined by the above method are traffic statistical results of grid-level time period granularity, which can reduce the cost of data calculation, storage and transmission under the premise of maintaining the key spatio-temporal statistical characteristics of traffic.
  • the embodiment of the present application also provides a device that executes the method provided in the embodiment of the present application.
  • the device can be deployed independently, for example, on a server, or deployed on an edge node (such as a centralized unit (CU) Or mobile edge computing (mobile edge computing, MEC)).
  • CU centralized unit
  • MEC mobile edge computing
  • the device may be the first server or a chip or a functional module in the first server.
  • the first server may receive MRs from multiple base stations and obtain multiple MRs.
  • the first server may take multiple MRs as input, and output traffic distribution results determined based on the multiple MRs. Further, the first server may save the traffic distribution result for use by the first server, or the first server may send the traffic distribution result to the second server. Wherein, each base station may send multiple MRs to the first server.
  • the edge node when the device can also be deployed on an edge node, if the edge node is connected to multiple base stations, the edge node can subscribe to the MRs of the multiple base stations connected. The edge node can take the subscribed MR as input and output the traffic distribution result determined based on the subscribed MR. Among them, the traffic distribution results determined by subscription-based MR can be saved in edge nodes for use by edge nodes, and can also be sent back to the central cloud operation support systems (OSS) system to support network-wide traffic analysis or network optimization.
  • OSS central cloud operation support systems
  • the server of the MEC is connected to the edge sensing node (Edge Sensing Node, ESN).
  • ESN Edge Sensing Node
  • the connection between the ESN and the MEC is not necessarily cross-hardware, and the ESN can be directly deployed on the server of the MEC.
  • ESN can be embodied in the form of APP or process.
  • the ESN is responsible for MR collection, and determines the traffic distribution result based on the collected MR, and uploads it to the central cloud OSS.
  • the traffic distribution results here may include the traffic statistical results corresponding to the first grid in the first time period, or the traffic statistical results corresponding to multiple grids in the first time period, or the first grid in multiple The traffic statistics results corresponding to the time periods, or the traffic statistics results corresponding to multiple grids in multiple time periods, etc.
  • the specific content of the traffic distribution result may be determined according to specific requirements.
  • the embodiment of the present application further provides an apparatus for realizing the foregoing method.
  • the device may include a hardware structure and/or a software module, and realize the above-mentioned functions in the form of a hardware structure, a software module, or a hardware structure plus a software module. Whether one of the above-mentioned functions is executed in the form of a hardware structure, a software module, or a hardware structure plus a software module depends on the specific application and design constraints of the technical solution.
  • the apparatus provided in the embodiment of the present application may be a chip or a circuit capable of performing the functions corresponding to the above method, and the chip or circuit may be set in a processor or other device. Furthermore, the apparatus provided in the embodiments of the present application can also be implemented in hardware or a combination of hardware and computer software. Whether a certain function is executed by hardware or computer software drives hardware depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be regarded as exceeding the scope of the embodiments of the present application.
  • the device provided in the embodiment of the present application can divide functional modules, for example, each functional module can be divided corresponding to each function, or two or more functions can be integrated into one processing module.
  • the above-mentioned integrated modules can be implemented in the form of hardware or in the form of software function modules. It should be noted that the division of modules in the embodiment of the present application is schematic, and is only a logical function division, and there may be other division methods in actual implementation.
  • FIG. 9 a schematic structural diagram of an apparatus for determining a flow statistics result is provided for this embodiment of the present application.
  • the device may be a processor, or a device in a processor.
  • the apparatus 900 may include: a processing module 91 and a communication module 92 .
  • the device 900 may also include other modules, which are not limited in this embodiment of the present application, and only main functional modules are shown.
  • the communication module 92 is used to obtain a first data set, the first data set includes a plurality of data collected in the first time period, each data includes flow measurement values and level measurement values of n beams, and the processing module 91 is used to The second data set associated with the first grid in the first data set is determined according to the level measurement values of the n beams of each data and the center coordinates of the first grid, and according to each data included in the second data set
  • the traffic measurement value determines the traffic statistical result corresponding to the first grid within the first time period.
  • the second data set includes the data associated with the first grid in the n-dimensional beam space in the first data set, and the level measurement values of n beams included in any one of the second data sets are consistent with the first grid
  • the distance between the central coordinates of the grid is less than or equal to the radius of the first grid, and the central coordinates of the first grid are represented by the level values of n beams.
  • the processing module 91 in the device 900 can support the device 900 to execute the actions of the first server in the above method examples, for example, it can support the device 900 to execute steps 402, 403, 404 in FIG. 4, and step 502 in FIG. 5, Step 503.
  • the communication module 92 may support communication between the apparatus 900 and equipment (eg, a base station or other server), for example, the communication module 92 may support the apparatus 900 to execute step 401 in FIG. 4 and step 501 in FIG. 5 .
  • equipment eg, a base station or other server
  • the processing module 91 in the embodiment of the present application may be implemented by a processor or processor-related circuit components
  • the communication module 92 may be implemented by a communication interface or a communication interface-related circuit component or a communication interface.
  • the communication interface may include, for example, a transmitter and a receiver, and the processor, the transmitter, and the receiver are coupled to each other, wherein the transmitter and the receiver are implemented, for example, by an antenna, a feeder, and a codec, or if the device
  • the transmitter and receiver are, for example, the communication interface in the chip, which is connected to the radio frequency transceiver component in the device, so as to realize information transmission and reception through the radio frequency transceiver component.
  • FIG. 10 is an apparatus 1000 provided in the embodiment of the present application, and the apparatus shown in FIG. 10 may be a hardware circuit implementation manner of the apparatus shown in FIG. 9 .
  • the device can be used to execute the function of the first server in the flowchart shown in FIG. 5 .
  • FIG. 10 For ease of illustration, only the main components of the device are shown in FIG. 10 .
  • the apparatus shown in FIG. 10 may be a chip or a circuit capable of performing the functions corresponding to the above method, or may be a device including the above chip or circuit, which is not limited in this embodiment of the present application.
  • the apparatus 1000 shown in FIG. 10 includes at least one processor 1020 configured to implement the function of the first server in FIG. 5 provided by the embodiment of the present application.
  • Apparatus 1000 may also include at least one memory 1030 for storing program instructions and/or data.
  • the memory 1030 is coupled to the processor 1020 .
  • the coupling in the embodiments of the present application is an indirect coupling or a communication connection between devices, units or modules, which may be in electrical, mechanical or other forms, and is used for information exchange between devices, units or modules.
  • Processor 1020 may cooperate with memory 1030 .
  • Processor 1020 may execute program instructions stored in memory 1030 . At least one of the at least one memory may be included in the processor.
  • the device 1000 may not include a memory 1030, and the processor 1020 may read instructions (programs or codes) in the memory outside the chip or circuit to realize the The function of the first server provided by the embodiment.
  • the apparatus 1000 may also include a communication interface 1010 for communicating with other devices through a transmission medium, so that the devices used in the apparatus 1000 can communicate with other devices.
  • the communication interface may be a transceiver, a circuit, a bus, a module, or other types of communication interfaces.
  • the transceiver may be an independent receiver, an independent transmitter, a transceiver integrating transceiver functions, or an interface circuit.
  • the processor 1020 uses the communication interface 1010 to send and receive data, and is used to implement the function of the first server in the embodiment shown in FIG. 5 . For details, reference may be made to the foregoing description, and details will not be repeated here.
  • Apparatus 1000 may also include a communication bus 1040 .
  • the communication interface 1010, the processor 1020 and the memory 1030 can be connected to each other through the communication bus 1040;
  • the communication bus 1040 can be a peripheral component interconnect standard (peripheral component interconnect, referred to as PCI) bus or an extended industry standard architecture (extended industry standard architecture , referred to as EISA) bus and so on.
  • PCI peripheral component interconnect
  • EISA extended industry standard architecture
  • the communication bus 1040 can be divided into address bus, data bus, control bus and so on. For ease of representation, only one thick line is used in FIG. 10 , but it does not mean that there is only one bus or one type of bus.
  • the apparatus provided in the embodiment of the present application when implemented using software, it may be implemented in the form of a computer program product in whole or in part.
  • the computer program product includes one or more computer instructions.
  • the computer program instructions When the computer program instructions are loaded and executed on the computer, the processes or functions described in the embodiments of the present application are realized in whole or in part.
  • the computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable devices.
  • the computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website, computer, server or data center Transmission to another website site, computer, server or data center by wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.).
  • the computer-readable storage medium may be any available medium that can be accessed by a computer, or a data storage device such as a server or a data center integrated with one or more available media.
  • the available medium may be a magnetic medium (such as a floppy disk, a hard disk, or a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (solid state disk, SSD)), etc.
  • the processor included in the above-mentioned device for executing the method provided by the embodiment of the present application may be a central processing unit (central processing unit, CPU), a general purpose processor, a digital signal processor (digital signal processor, DSP), application-specific integrated circuit (ASIC), field programmable gate array (field programmable gate array, FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It can implement or execute the various illustrative logical blocks, modules and circuits described in connection with the present disclosure.
  • the processor may also be a combination of computing functions, for example, a combination of one or more microprocessors, a combination of DSP and a microprocessor, and so on.
  • the steps of the methods or algorithms described in conjunction with the embodiments of the present application may be implemented in hardware, or may be implemented in a manner in which a processor executes software instructions.
  • the software instructions can be composed of corresponding software modules, and the software modules can be stored in random access memory (random access memory, RAM), flash memory, read-only memory (read-only memory, ROM) memory, erasable programmable read-only Memory (erasable programmable read-only memory, EPROM), electrically erasable programmable read-only memory (electrically erasable programmable read-only memory, EEPROM), registers, hard disk, mobile hard disk, compact disc read-only memory , CD-ROM) or any other form of storage medium known in the art.
  • An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium.
  • the storage medium may also be a component of the processor.
  • the processor and storage medium can be located in the ASIC.
  • the ASIC may be located in a radar device or a detection device in which a radar device is installed.
  • the processor and the storage medium may also exist as discrete components in the radar device or the detection equipment in which the radar device is installed.
  • Figs. 9-10 only show a simplified design of the device.
  • the device provided by the embodiments of the present application may include any number of transmitters, receivers, processors, controllers, memories and other possible components.
  • the embodiment of the present application also provides a chip, the chip is connected to the memory, and is used to read and execute the software program stored in the memory, and when the software program is run on the chip, the chip realizes Functions of the first server in Fig. 5 .
  • the embodiment of the present application also provides a computer-readable storage medium, including instructions, and when the instructions are executed on a computer, the computer is made to realize the function of the first server in FIG. 5 .
  • the embodiments of the present application may be provided as methods, systems, or computer program products. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
  • computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to operate in a specific manner, such that the instructions stored in the computer-readable memory produce an article of manufacture comprising instruction means, the instructions
  • the device realizes the function specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Environmental & Geological Engineering (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

一种确定流量统计结果的方法及装置，该方法包括：第一服务器获取第一数据集合，第一数据集合包括在第一时间段被采集的多个数据，每个数据包括流量测量值和n个波束的电平测量值。第一服务器根据每个数据的n个波束的电平测量值和第一栅格的中心坐标确定第一数据集合中与第一栅格关联的第二数据集合，根据第二数据集合中每个数据包括的流量测量值确定在第一时间段内对应第一栅格的上行流量或下行流量。其中，第一栅格的中心坐标用n个波束的电平值表示。采用上述方法确定的用户流量的流量统计结果为栅格级时间段粒度的流量统计结果。

Description

一种确定流量统计结果的方法及装置
相关申请的交叉引用
本申请要求在2021年05月18日提交中国专利局、申请号为202110541055.3、申请名称为“一种确定流量统计结果的方法及装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请实施例涉及移动通信领域，尤其涉及一种确定流量统计结果的方法及装置。
背景技术
随着5G无线网络的初步建设完成，5G移动用户体验保障的重要性日益增加。由于网络结构与网络新特性更加复杂，用户分布不均现象更为明显，业务类型更加多样化，很难通过局部网络优化最优地保障用户体验。
当前，大规模网络优化是未来网络优化的趋势，而为了支撑大规模无线网络优化方案，需要获得流量统计结果在时空的分布情况，即需要获得在一段时间内在一定空间区域的流量统计结果。
发明内容
本申请实施例提供一种确定流量统计结果的方法及装置，用以实现获得流量统计结果在时空的分布情况。
第一方面，本申请实施例提供一种确定流量统计结果的方法，以第一服务器为执行主体为例，该方法包括：第一服务器获取第一数据集合，所述第一数据集合包括在第一时间段被采集的多个数据，每个数据包括流量测量值和n个波束的电平测量值。其中，流量测量值包括上行流量测量值和/或下行流量测量值。第一服务器根据每个数据的n个波束的电平测量值和第一栅格的中心坐标确定所述第一数据集合中与所述第一栅格关联的第二数据集合，根据所述第二数据集合中每个数据包括的流量测量值确定在所述第一时间段内对应所述第一栅格的上行流量或下行流量。所述第一栅格的中心坐标用n个波束的电平值表示。
采用上述实施例，第一服务器确定第一数据集合中与第一栅格关联的数据，得到第二数据集合，然后根据第二数据集合中每个第二数据集合包括的电平测量值确定在第一时间段内对应第一栅格的流量统计结果。采用上述方法确定的流量统计结果为栅格级时间段粒度的流量统计结果，进而可以为后续进行流量优化提供基础。
在一种可能的设计中，在确定第一数据集合中与所述第一栅格关联的第二数据集合时，第一服务器确定所述第一数据集合中任意一个数据包括的n个波束的电平测量值与所述第一栅格的中心坐标的距离小于或等于所述第一栅格的半径，则该数据为所述第二数据集合中的数据。第二数据集合包括的任意一个数据包括的n个波束的电平测量值与第一栅格的中心坐标的距离小于或等于第一栅格的半径。或第一服务器确定所述第一数据集合中任意 一个数据包括的n个波束的电平测量值与所述第一栅格的中心坐标的距离小于该n个波束的电平测量值与所述多个栅格中除所述第一栅格之外的其它栅格的中心坐标的距离，则该数据为所述第二数据集合中的数据。第二数据集合包括的任意一个数据包括的n个波束的电平测量值与第一栅格的中心坐标的距离小于该n个波束的电平测量值与多个栅格中除所述第一栅格之外的其它栅格的中心坐标的距离。
采用上述设计可以确定第一数据集合中属于第二数据集合的数据。
在一种可能的设计中，确定所述第一数据集合中任意一个数据包括的n个波束的电平测量值与所述第一栅格的中心坐标的距离小于等于所述第一栅格的半径，且该数据包括的n个波束的电平测量值与第二栅格的中心坐标的距离小于等于所述第二栅格的半径，其中，所述第二栅格为所述多个栅格中除所述第一栅格之外的一个栅格；在该数据包括的n个波束的电平测量值与所述第一栅格的中心坐标的距离小于该数据包括的n个波束的电平测量值与所述第二栅格的中心坐标的距离时，确定该数据为所述第二数据集合中数据。
采用上述设计可以确定第一数据集合中属于第二数据集合的数据。
在一种可能的设计中，还包括：获取所述n维波束空间中的多个栅格的各栅格分别对应的中心坐标和半径，所述多个栅格包括所述第一栅格。采用上述方法可以实现获取n维波束空间的多个栅格的信息。可以理解的是，多个栅格的信息可以由第一服务器自己确定，或者由其他设备确定多个栅格的信息通知给第一服务器，本申请实施例对此不做限定。
在一种可能的设计中，在获取所述n维波束空间中的多个栅格的各栅格分别对应的中心坐标时，获取训练数据集合，所述训练数据集合包括多个样本，每个样本包括n个波束的电平测量值，根据所述多个样本中每个样本对应的n个波束的电平测量值获得训练数据集合对应的距离集合，根据所述训练数据集合对应的距离集合确定所述多个栅格中的各栅格分别对应的样本，根据每个栅格对应的样本确定各栅格分别对应的中心坐标。其中，所述训练数据集合对应的距离集合包括所述多个样本中每个样本对应的n个波束的电平测量值中的任意两组n个波束的电平测量值的距离，每个栅格对应的样本中的任意两个样本中的各样本包括的n个波束的电平测量值的距离满足预设距离条件。所述第一栅格的中心坐标是根据所述第一栅格对应的样本确定的。采用上述方法，首先确定训练集合中每个样本所属的栅格，进一步可以根据每个栅格对应的样本确定该栅格的中心坐标，方案简便容易实现，还可以实现在进行流量统计时得到每个栅格对应的流量统计结果，便于后续根据流量统计结果进行流量优化。
在一种可能的设计中，在获取所述n维波束空间中的多个栅格的各栅格分别对应的中心坐标时，获取训练数据集合，所述训练数据集合包括多个样本，每个样本包括流量测量值和n个波束的电平测量值，根据所述多个样本中每个样本对应的n个波束的电平测量值获得训练数据集合对应的距离集合，根据所述训练数据集合对应的距离集合确定多个候选栅格中各候选栅格分别对应的样本，根据每个候选栅格对应的样本中每个样本包括的流量测量值，确定所述多个候选栅格中每个候选栅格对应的流量统计值；根据所述多个候选栅格中每个候选栅格对应的流量统计值确定满足预设流量条件的候选栅格，将满足预设流量条件的候选栅格作为所述n维波束空间中的多个栅格，根据所述多个栅格中每个栅格对应的样本确定各栅格分别对应的中心坐标，其中，所述第一栅格的中心坐标是根据所述第一栅格对应的样本确定的。所述训练数据集合对应的距离集合包括所述多个样本中每个样本对应的n个波束的电平测量值中的任意两组n个波束的电平测量值的距离，每个候选栅格 对应的样本中的任意两个样本中的各样本包括的n个波束的电平测量值的距离满足预设距离条件。
采用上述方法，首先确定训练集合中每个样本所属的候选栅格，并结合每个样本包括的流量测量值对候选栅格进行筛选，根据筛选出的栅格对应的样本确定相应栅格的中心坐标，可以实现在进行流量统计时得到每个栅格对应的流量统计结果，便于后续根据流量统计结果进行流量优化，还可以实现减小后续大量数据计算、存储和传输的复杂度。
在一种可能的设计中，每个样本中的流量测量值包括上行流量测量值和/或下行流量测量值；所述第一栅格对应的流量统计值包括所述第一栅格对应的上行流量统计值和/或所述第一栅格对应的下行流量统计值；所述第一栅格对应的上行流量统计值是根据所述第一栅格对应的样本中包括上行流量测量值的样本确定的；和/或所述第一栅格对应的下行流量统计值是根据所述第一栅格对应的样本中包括下行流量测量值的样本确定的；所述第一栅格为所述多个候选栅格中满足预设流量条件的候选栅格中的任一栅格，所述第一栅格对应的流量统计值满足预设流量条件是指所述第一栅格对应的上行流量统计值大于等于预设上行流量阈值，和/或所述第一栅格对应的下行流量统计值大于等于预设下行流量阈值。
采用上述方法可以实现删除一部分流量较小的候选栅格，但最终确定的栅格仍能覆盖大部分流量，进而可以减小后续大量数据计算、存储和传输的复杂度。
在一种可能的设计中，所述多个栅格为k1个上行流量统计值分别对应的候选栅格和k2个下行流量统计值分别对应的候选栅格的交集；其中，所述k1个上行流量统计值之和与上行总流量统计值的比值大于等于第一阈值，所述k2个下行流量统计值之和与下行总流量统计值的比值大于等于第二阈值，k1和k2为正整数；所述k1个上行流量统计值根据从大到小的顺序从所述多个候选栅格中每个候选栅格对应的上行流量统计值中确定，所述k2个下行流量统计值根据从大到小的顺序从所述多个候选栅格中每个候选栅格对应的下行流量统计值中确定，所述上行总流量是指所述多个样本中包括的上行流量测量值之和，所述下行总流量是指所述多个样本中包括的下行流量测量值之和；所述第一栅格为所述多个候选栅格中满足预设流量条件的候选栅格中的任一栅格，所述第一栅格对应的流量统计值满足预设流量条件是指所述第一栅格对应的上行流量统计值为所述k1个上行流量统计值中的一个，且所述第一栅格对应的下行流量统计值为所述k2个下行流量统计值中的一个；其中，所述第一栅格对应的上行流量统计值是指所述第一栅格对应的样本中包括的上行流量测量值之和；所述第一栅格对应的下行流量统计值是指所述第一栅格对应的样本中包括的下行流量值之和。
采用上述方法可以实现删除一部分流量较小的候选栅格，但最终确定的栅格仍能覆盖大部分流量，进而可以减小后续大量数据计算、存储和传输的复杂度。
在一种可能的设计中，所述多个栅格为k1个上行流量统计值分别对应的候选栅格和k2个下行流量统计值分别对应的候选栅格的并集；其中，所述k1个上行流量统计值之和与上行总流量统计值的比值大于等于第一阈值，所述k2个下行流量统计值之和与下行总流量统计值的比值大于等于第二阈值，k1和k2为正整数；所述k1个上行流量统计值根据从大到小的顺序从所述多个候选栅格中每个候选栅格对应的上行流量统计值中确定，所述k2个下行流量统计值根据从大到小的顺序从所述多个候选栅格中每个候选栅格对应的下行流量统计值中确定，所述上行总流量是指所述多个样本中包括的上行流量测量值之和，所述下行总流量是指所述多个样本中包括的下行流量测量值之和；所述第一栅格为所述多 个候选栅格中满足预设流量条件的候选栅格中的任一栅格，所述第一栅格对应的流量统计值满足预设流量条件是指所述第一栅格对应的上行流量统计值为所述k1个上行流量统计值中的一个，或所述第一栅格对应的下行流量统计值为所述k2个下行流量统计值中的一个；其中，所述第一栅格对应的上行流量统计值是指所述第一栅格对应的样本中包括的上行流量值之和；所述第一栅格对应的下行流量统计值是指所述第一栅格对应的样本中包括的下行流量值之和。
采用上述方法可以实现删除一部分流量较小的候选栅格，但最终确定的栅格仍能覆盖大部分流量，进而可以减小后续大量数据计算、存储和传输的复杂度。
在一种可能的设计中，所述第一栅格的中心坐标为根据所述第一栅格对应的样本中的每个样本包括的n个波束的电平测量值计算的所述n个波束的电平测量值的平均值。
采用上述方法可以计算第一栅格的中心坐标。
在一种可能的设计中，所述第一栅格的半径为半径集合中的最大距离，所述半径集合包括所述第一栅格对应的样本中的任意一个样本包括的n个波束的电平测量值与所述第一栅格的中心坐标的距离。
采用上述方法可以计算第一栅格的半径。
在一种可能的设计中，在所述第一时间段内对应所述第一栅格的上行流量是根据所述第二数据集合中包括上行流量测量值的数据确定的；在所述第一时间段内对应所述第一栅格的下行流量是根据所述第二数据集合中包括下行流量测量值的数据确定的。
在一种可能的设计中，第一服务器还可以向其他服务器发送在所述第一时间段内对应所述第一栅格的上行流量或下行流量。
采用上述方法可以计算流量统计结果。
第二方面，本申请实施例提供一种确定流量统计结果的装置，该装置包括：收发单元，用于获取第一数据集合，所述第一数据集合包括在第一时间段被采集的多个数据，每个数据包括流量测量值和n个波束的电平测量值，所述流量测量值包括上行流量测量值和/或下行流量测量值；处理单元，用于根据每个数据的n个波束的电平测量值和第一栅格的中心坐标确定所述第一数据集合中与所述第一栅格关联的第二数据集合，所述第一栅格的中心坐标用n个波束的电平值表示；根据所述第二数据集合中每个数据包括的流量测量值确定在所述第一时间段内对应所述第一栅格的上行流量或下行流量。
在一种可能的设计中，所述收发单元还用于获取所述n维波束空间中的多个栅格的各栅格分别对应的中心坐标和半径，所述多个栅格包括所述第一栅格。
在一种可能的设计中，在确定第一数据集合中与所述第一栅格关联的第二数据集合时，所述处理单元，用于确定所述第一数据集合中任意一个数据包括的n个波束的电平测量值与所述第一栅格的中心坐标的距离小于或等于所述第一栅格的半径，则该数据为所述第二数据集合中的数据。或确定所述第一数据集合中任意一个数据包括的n个波束的电平测量值与所述第一栅格的中心坐标的距离小于该n个波束的电平测量值与所述多个栅格中除所述第一栅格之外的其它栅格的中心坐标的距离，则该数据为所述第二数据集合中的数据。
在一种可能的设计中，所述处理单元，用于确定所述第一数据集合中任意一个数据包括的n个波束的电平测量值与所述第一栅格的中心坐标的距离小于等于所述第一栅格的半径，且该数据包括的n个波束的电平测量值与第二栅格的中心坐标的距离小于等于所述第二栅格的半径，其中，所述第二栅格为所述多个栅格中除所述第一栅格之外的一个栅格； 在该数据包括的n个波束的电平测量值与所述第一栅格的中心坐标的距离小于该数据包括的n个波束的电平测量值与所述第二栅格的中心坐标的距离时，确定该数据为所述第二数据集合中数据。
在一种可能的设计中，所述收发单元，用于在获取所述n维波束空间中的多个栅格的各栅格分别对应的中心坐标时，获取训练数据集合，所述训练数据集合包括多个样本，每个样本包括n个波束的电平测量值；所述处理单元，用于根据所述多个样本中每个样本对应的n个波束的电平测量值获得训练数据集合对应的距离集合，所述训练数据集合对应的距离集合包括所述多个样本中每个样本对应的n个波束的电平测量值中的任意两组n个波束的电平测量值的距离；根据所述训练数据集合对应的距离集合确定所述多个栅格中的各栅格分别对应的样本，其中，每个栅格对应的样本中的任意两个样本中的各样本包括的n个波束的电平测量值的距离满足预设距离条件；根据每个栅格对应的样本确定各栅格分别对应的中心坐标，其中，所述第一栅格的中心坐标是根据所述第一栅格对应的样本确定的。
在一种可能的设计中，所述收发单元，用于在获取所述n维波束空间中的多个栅格的各栅格分别对应的中心坐标时，获取训练数据集合，所述训练数据集合包括多个样本，每个样本包括流量测量值和n个波束的电平测量值；所述处理单元，用于根据所述多个样本中每个样本对应的n个波束的电平测量值获得训练数据集合对应的距离集合，所述训练数据集合对应的距离集合包括所述多个样本中每个样本对应的n个波束的电平测量值中的任意两组n个波束的电平测量值的距离；根据所述训练数据集合对应的距离集合确定多个候选栅格中各候选栅格分别对应的样本，其中，每个候选栅格对应的样本中的任意两个样本中的各样本包括的n个波束的电平测量值的距离满足预设距离条件；根据每个候选栅格对应的样本中每个样本包括的流量测量值，确定所述多个候选栅格中每个候选栅格对应的流量统计值；根据所述多个候选栅格中每个候选栅格对应的流量统计值确定满足预设流量条件的候选栅格，将满足预设流量条件的候选栅格作为所述n维波束空间中的多个栅格；根据所述多个栅格中每个栅格对应的样本确定各栅格分别对应的中心坐标，其中，所述第一栅格的中心坐标是根据所述第一栅格对应的样本确定的。
在一种可能的设计中，每个样本中的流量测量值包括上行流量测量值和/或下行流量测量值；所述第一栅格对应的流量统计值包括所述第一栅格对应的上行流量统计值和/或所述第一栅格对应的下行流量统计值；所述第一栅格对应的上行流量统计值是根据所述第一栅格对应的样本中包括上行流量测量值的样本确定的；和/或所述第一栅格对应的下行流量统计值是根据所述第一栅格对应的样本中包括下行流量测量值的样本确定的；所述第一栅格为所述多个候选栅格中满足预设流量条件的候选栅格中的任一栅格，所述第一栅格对应的流量统计值满足预设流量条件是指所述第一栅格对应的上行流量统计值大于等于预设上行流量阈值，和/或所述第一栅格对应的下行流量统计值大于等于预设下行流量阈值。
在一种可能的设计中，所述多个栅格为k1个上行流量统计值分别对应的候选栅格和k2个下行流量统计值分别对应的候选栅格的交集；其中，所述k1个上行流量统计值之和与上行总流量统计值的比值大于等于第一阈值，所述k2个下行流量统计值之和与下行总流量统计值的比值大于等于第二阈值，k1和k2为正整数；所述k1个上行流量统计值根据从大到小的顺序从所述多个候选栅格中每个候选栅格对应的上行流量统计值中确定，所述k2个下行流量统计值根据从大到小的顺序从所述多个候选栅格中每个候选栅格对应的下行流量统计值中确定，所述上行总流量是指所述多个样本中包括的上行流量测量值之和， 所述下行总流量是指所述多个样本中包括的下行流量测量值之和；所述第一栅格为所述多个候选栅格中满足预设流量条件的候选栅格中的任一栅格，所述第一栅格对应的流量统计值满足预设流量条件是指所述第一栅格对应的上行流量统计值为所述k1个上行流量统计值中的一个，且所述第一栅格对应的下行流量统计值为所述k2个下行流量统计值中的一个；其中，所述第一栅格对应的上行流量统计值是指所述第一栅格对应的样本中包括的上行流量测量值之和；所述第一栅格对应的下行流量统计值是指所述第一栅格对应的样本中包括的下行流量值之和。
在一种可能的设计中，所述多个栅格为k1个上行流量统计值分别对应的候选栅格和k2个下行流量统计值分别对应的候选栅格的并集；其中，所述k1个上行流量统计值之和与上行总流量统计值的比值大于等于第一阈值，所述k2个下行流量统计值之和与下行总流量统计值的比值大于等于第二阈值，k1和k2为正整数；所述k1个上行流量统计值根据从大到小的顺序从所述多个候选栅格中每个候选栅格对应的上行流量统计值中确定，所述k2个下行流量统计值根据从大到小的顺序从所述多个候选栅格中每个候选栅格对应的下行流量统计值中确定，所述上行总流量是指所述多个样本中包括的上行流量测量值之和，所述下行总流量是指所述多个样本中包括的下行流量测量值之和；所述第一栅格为所述多个候选栅格中满足预设流量条件的候选栅格中的任一栅格，所述第一栅格对应的流量统计值满足预设流量条件是指所述第一栅格对应的上行流量统计值为所述k1个上行流量统计值中的一个，或所述第一栅格对应的下行流量统计值为所述k2个下行流量统计值中的一个；其中，所述第一栅格对应的上行流量统计值是指所述第一栅格对应的样本中包括的上行流量值之和；所述第一栅格对应的下行流量统计值是指所述第一栅格对应的样本中包括的下行流量值之和。
在一种可能的设计中，所述第一栅格的中心坐标为根据所述第一栅格对应的样本中的每个样本包括的n个波束的电平测量值计算的所述n个波束的电平测量值的平均值。
在一种可能的设计中，所述第一栅格的半径是根据所述第一栅格对应的样本中的每个样本包括的所述n个波束的电平测量值与所述第一栅格的中心坐标确定的。
在一种可能的设计中，所述第一栅格的半径为半径集合中的最大距离，所述半径集合包括所述第一栅格对应的样本中的任意一个样本包括的n个波束的电平测量值与所述第一栅格的中心坐标的距离。
在一种可能的设计中，在所述第一时间段内对应所述第一栅格的上行流量是根据所述第二数据集合中包括上行流量测量值的数据确定的；在所述第一时间段内对应所述第一栅格的下行流量是根据所述第二数据集合中包括下行流量测量值的数据确定的。
在一种可能的设计中，所述收发单元，用于向服务器发送在所述第一时间段内对应所述第一栅格的上行流量或下行流量。
其中，第二方面中的各个设计的技术效果可以参考第一方面中的相应设计的技术效果，重复之处不再赘述。
第三方面，本申请还提供一种装置。该装置可以执行上述方法设计。该装置可以是能够执行上述方法对应的功能的芯片或电路，或者是包括该芯片或电路的设备。
在一种可能的实现方式中，该装置包括：存储器，用于存储计算机可执行程序代码；以及处理器，处理器与存储器耦合。其中存储器所存储的程序代码包括指令，当处理器执行所述指令时，使该装置或者安装有该装置的设备执行上述第一方面或第一方面的任意一 种可能的设计中的方法。
其中，该装置还可以包括通信接口，该通信接口可以是收发器，或者，如果该装置为芯片或电路，则通信接口可以是该芯片的输入/输出接口，例如输入/输出管脚等。
在一种可能的设计中，该装置包括相应的功能单元，分别用于实现以上方法中的步骤。功能可以通过硬件实现，也可以通过硬件执行相应的软件实现。硬件或软件包括一个或多个与上述功能相对应的单元。
第四方面，本申请实施例提供一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，当所述计算机程序在装置上运行时，执行如第一方面或第一方面的任意一种可能的设计中的方法。
第五方面，本申请实施例提供一种计算机程序产品，所述计算机程序产品包括计算机程序，当所述计算机程序在装置上运行时，执行如第一方面或第一方面的任意一种可能的设计中的方法。
附图说明
图1为本申请的实施例中波束空间的示意图之一；
图2为本申请的实施例中波束空间的示意图之二；
图3为本申请的实施例中MR结构示意图；
图4为本申请的实施例中一种确定n维波束空间中的多个栅格的方法的概述流程图；
图5为本申请的实施例中一种确定流量统计结果的方法的概述流程图；
图6为本申请的实施例中一种通信结构示意图之一；
图7为本申请的实施例中一种通信结构示意图之二；
图8为本申请的实施例中一种通信结构示意图之三；
图9为本申请的实施例中一种装置结构示意图之一；
图10为本申请的实施例中一种装置结构示意图之二。
具体实施方式
以下首先对本申请实施例涉及的技术概念进行解释说明。
1.流量是指用户进行数据传输业务时传输的业务流的数据量。具体可以包括上行流量和/或下行流量。例如，上行流量是指单位时间内终端设备向基站发送的上行报文大小之和，下行流量是指单位时间内基站向终端设备发送的下行报文大小之和。
2.大规模多输入多输出(massive multiple input multiple output，MIMO)
传统的MIMO的天线为2天线、4天线或8天线，而Massive MIMO的通道数达到64/128/256个。传统的MIMO，以8天线为例，实际信号在覆盖范围在水平方向移动，在垂直方向上不动。而Massive MIMO的信号在水平维度空间的基础上引入垂直维度的空域进行利用。此外，Massive MIMO还具有提供丰富的空间自由度，提供更多可能的到达路径，以及提升信号的可靠性等优点。
对于基于Massive MIMO技术的无线网络(例如，4.5G与5G等)，终端设备在与基站交互的过程中可以采用波束空间中的多个波束(比如窄波束)进行通信。
其中，波束空间可以基于多个静态波束定义。如图1所示为一种可能的波束空间的示 意图。静态波束是指波束赋形时采用预定义的权值形成的波束。例如，在小区下形成固定的波束，其中，波束的数目、宽度、方向都是确定的。
示例性地，承载探测参考信号(sounding reference signal，SRS)的波束，或承载同步信号块(synchronization signal and PBCH block，SSB)的波束都是静态波束，其发送方向由物理射频(radio frequency，RF)参数决定。当物理RF参数确定时，可以基于多个承载SRS的静态波束或承载SSB的静态波束定义波束空间。
本申请实施例中所涉及的n维波束空间是基于n个静态波束定义的，示例性地，n维波束空间是基于n个承载SRS的波束定义的，此时n个波束为波束天线接收的波束的数量，或者，n维波束空间是基于n个承载SSB的波束定义的，此时n个波束为波束天线接收的波束的数量。
3.基于波束空间指示终端设备的位置
如图2所示的波束空间，当前可以采用以下方式确定终端设备的位置：
方式1：不同的波束可以用来区分在波束空间中的不同位置。例如，UE1与UE3分别对应的波束id不同，且UE1可用的波束数量与UE3可用的波束数量不同，进而可以根据上述信息确定UE1的位置和UE3的位置。其中，UE1对应的波束是指UE1与基站进行通信时采用的波束，UE1可用的波束数量是指UE1与基站进行通信时可以采用的波束的数量，同理，UE3对应的波束是指UE3与基站进行通信时采用的波束，UE3可用的波束数量是指UE3与基站进行通信时可以采用的波束的数量。
方式2：对于相同波束对应的不同电平值也可以用来指示在波束空间中的不同位置。例如，UE1对应的波束id与UE2对应的波束id相同，但由于UE1与基站之间的距离与UE2与基站之间的距离不同，因此UE1对应的电平值与UE2对应的电平值不同，进而可以根据上述波束id和电平值指示UE1的位置和UE2的位置。示例性地，假设UE1对应的波束为波束1，UE2对应的波束为波束1，UE1对应的电平值可以是指基站测量UE1采用波束1发送的SRS获得的参考信号接收功率(reference signal receiving power，RSRP)，UE2对应的电平值可以是指基站测量UE2采用波束1发送的SRS获得的RSRP。
方式3：根据主波束的水平方向角、主波束的垂直方向角及主波束对应的路损可以确定终端设备的位置。其中，每条波束对应一个水平方向角与一个垂直方向角，在终端设备与基站之间无遮挡物时，路径损耗的大小与终端设备与基站之间的距离成正比。其中，路径损耗(简称路损)是指电磁波在空间传播所产生的损耗，是由发射功率的辐射扩散及信道的传播特性造成的，反映宏观范围内接收信号功率均值的变化。
可以理解的是，方式3提供的确定终端设备的位置的方案主要应用于在空旷场景下确定终端设备的位置。但是，在实际环境中，信号传输会受到环境中遮挡物的影响，仅利用一条主波束的信息描述终端设备的位置可靠性较差、分辨率较低。例如，很容易出现直达径对应的主波束相同，路损相同，但实际物理位置不同的情况。因此，此方案在非空旷的场景下无法精确表示终端设备的位置。
综上，上述方式1和方式2仅能确定终端设备的大概位置，而方式3提供的确定终端设备的位置的方案利用单个主波束的信息，应用场景比较受限。
本申请实施例可以采用多波束的信息确定终端设备在波束空间的位置。其中，多波束的信息能够更加真实地反映实际物理环境的情况。如图2所示，UE4可以接收经建筑物反 射的波束，进而确定UE4的位置可以不仅利用波束1(即主波束)的信息，也可以同时利用波束2(即反射波束)的信息。可以理解的是，采用波束1的信息和波束2的信息确定UE4的位置的准确性高于仅采用波束1的信息确定UE4的位置的准确性。
示例性地，多波束的信息可以通过测量报告(measurement report，MR)确定。其中，MR可以记录MR生成的时间，多个波束的电平测量值与流量测量值等。其中，一个波束的电平测量值可以是基站测量终端设备采用该波束发送的SRS获得的RSRP，或者一个波束的电平测量值可以是终端设备测量基站采用该波束发送的SSB获得的RSRP。其中，针对后一种情况，终端设备需要将测得的该波束的电平测量值上报至基站。
如图3所示为一种可能的MR结构示意图。其中，CELLID是指小区ID。其中，小区ID为终端设备的服务小区的ID，MR为针对该终端设备的MR。TIME是指该MR生成的时间。RSRP1至RSRPn是指n个波束的电平测量值，或者又可称为n维波束电平测量值。RSRP1至RSRPn是指基站测量终端设备采用n个波束分别发送的SRS获得的n个RSRP，或者终端设备测量基站采用n个波束分别发送的SSB获得的n个RSRP。其中，n为波束空间包括的波束数目，例如n的取值可以为32，或64等。可以理解的是，以RSRP1为例，RSRP1为在当前MR的生成时间与前一个MR的生成时间所确定的时间段内测量得到的第1个波束的RSRP平均值或累计值。
此外，需要说明的是，MR可以包括n个波束的电平测量值，或者p个波束的电平测量值，p＜n，p和n均为正整数。其中，这里的p个波束的电平测量值是指p个有效的电平测量值。可以理解的是，终端设备或基站可能无法测量全部n个波束的电平测量值，例如，终端设备仅能测量n个波束中的p个波束的电平测量值，此时，终端设备可以仅上报p个波束的电平测量值。为了方便后续使用，可以将p个波束的电平测量值表示为n个波束的电平测量值，例如，将除p个波束外的其他n-p个波束的电平测量值置为默认值。
ULTHP(uplink throughput)表示上行流量测量值，DLTHP(downlink throughput)表示下行流量测量值。可以理解的是，MR中可以仅包括ULTHP或DLTHP。其中，ULTHP为在当前MR的生成时间与前一个MR的生成时间所确定的时间段内累计的上行报文大小之和，DLTHP为在当前MR的生成时间与前一个MR的生成时间所确定的时间段内累计的下行报文大小之和。
本申请实施例提供一种确定n维波束空间中的多个栅格的方法。其中，n维波束空间中一个栅格是指n维波束空间中以一组n个波束的电平值为中心坐标，以R为半径所确定的波束空间。其中，每个栅格的中心坐标和半径R的具体确定方式可以参考下述实施例。
示例性地，此处以第一服务器为例作为执行主体，例如，第一服务器可以为任意服务器或者处理器或者云端设备或边缘设备等，本申请实施例对此不做限定，如图4所示。
步骤401：第一服务器获取训练数据集合，训练数据集合包括M个样本。
示例性地，训练数据集合可以包括预设时间段内收集的MR，例如，训练数据集合可以包括一周或两周内收集的MR。在一些实施例中，基站可以根据订阅参数向第一服务器发送MR。例如，订阅参数可以包括MR上报周期(例如，若干分钟或若干小时或者若干秒)。其中，MR的具体形式可以参考图3。
需要说明的是，训练数据集合为预设时间段内针对一个小区收集的MR。因此，最终确定的n维波束空间中的多个栅格为与该小区对应的多个栅格。
在一种可能的设计中，训练数据集合包括M个样本，每个样本包括n个波束的电平测量值。例如，第一服务器根据M个MR可以确定如电平测量值矩阵L所示的训练数据集合。若一个MR包括n个波束的电平测量值(即n个波束的RSRP)，则直接将该n个波束的电平测量值作为电平测量值矩阵L中的一行。若一个MR包括p个波束的电平测量值，则需要将p个波束的电平测量值写成n个波束的电平测量值，具体的，将除p个波束外的其他n-p个波束分别对应的电平测量值置为0，然后将获得的n个波束的电平测量值作为电平测量值矩阵L中的一行。
Figure PCTCN2022092285-appb-000001
其中，电平测量值矩阵L中的每一行可以对应一个MR中的n个波束的电平测量值，电平测量值矩阵L指示M组电平测量值。
在一种可能的设计中，训练数据集合包括M个样本，每个样本包括流量测量值和n个波束的电平测量值，其中，流量测量值可以包括上行流量测量值和/或下行流量测量值。例如，第一服务器根据M个MR可以确定如流量矩阵ThpMat所示的训练数据集合。
Figure PCTCN2022092285-appb-000002
其中，流量矩阵ThpMat中的每一行可以对应一个MR中的流量测量值和n个波束的电平测量值。若MR仅包括dlthp,未包括ulthp,则可以将ulthp置为0，同理，若MR仅包括ulthp,未包括dlthp,则可以将dlthp置为0。流量矩阵ThpMat还可以包括
Figure PCTCN2022092285-appb-000003
也可以不包括
Figure PCTCN2022092285-appb-000004
本申请实施例对此不做限定。可以理解的是，通过流量矩阵ThpMat还可以提取出电平测量值矩阵L。
示例性地，流量矩阵ThpMat中的第i行对应第i个MR，time i为第i个MR的生成时间，rsrp i,1…rsrp i,n为第i个MR包括的n个波束的电平测量值，ulthp i为第i个MR包括的上行流量测量值，dlthp i为第i个MR包括的下行流量测量值。
步骤402：第一服务器根据训练数据集合获得训练数据集合对应的距离集合，训练数据集合对应的距离集合包括M个样本中任意两个样本的n个波束的电平测量值的距离。
示例性地，以电平测量值矩阵L或流量矩阵ThpMat作为输入计算距离矩阵R(距离矩阵R为M×M维),其中，
R ij＝dist(L i,·,L j,·),
可以理解的是，训练数据集合对应的距离集合共包括M(M-1)/2个距离。上述距离矩阵R仅为训练数据集合对应的距离集合的一种表现形式，训练数据集合对应的距离集合还可以采用其他表现形式，本申请实施例对此不做限定。其中，距离矩阵R中包括一些重复的元素，例如，R ij＝R ji，还包括一些由相同样本确定的距离，例如，R ii＝0。R ij表示电平测量值矩阵L或流量矩阵ThpMat中的第i个样本包含的n个波束的电平测量值和第j个 样本包含的n个波束的电平测量值的距离，或者又可以描述为第i条样本对应的波束空间位置与第j条样本对应的波束空间位置之间的距离。其中，距离dist可以定义为波束空间的欧式距离或其他距离，本申请实施例对此不做限定。
L i,·是指电平测量值矩阵L中的第i行的n个波束的电平测量值，即{rsrp i,1,rsrp i,2,…,rsrp i,n}，L j,·是指电平测量值矩阵L中的第j行的n个波束的电平测量值，即{rsrp j,1,rsrp j,2,…,rsrp j,n}。或者，L i,·是指流量矩阵ThpMat中的第i行的n个波束的电平测量值，即{rsrp i,1,rsrp i,2,…,rsrp i,n}，L j,·是指流量矩阵ThpMat中的第j行的n个波束的电平测量值，即{rsrp j,1,rsrp j,2,…,rsrp j,n}。
例如，假设M＝1000，电平测量值矩阵L包括1000行，根据电平测量值矩阵L中的任意两行确定一个距离，确定距离矩阵R，R为1000×1000维。
步骤403：第一服务器确定M个样本中每个样本对应的栅格索引。
在一些实施例中，根据训练数据集合对应的距离集合采用预设聚类算法确定每个样本对应的栅格索引。示例性地，预设聚类算法可以是指距离型聚类方法(如Kmeans等)，本申请实施例对此不做限定。
具体的，根据上述距离矩阵R采用预设距离聚类算法可以确定每个样本对应的栅格索引。具体可以由栅格索引矩阵Label表示。栅格索引矩阵Label可以为一个1×M为矩阵，label i是指第i个样本对应的栅格索引，label i的取值为整数(1≤label i≤m′)，表示第i个样本对应label i指示的栅格，其中，m′＜M，m′的取值可以根据经验值确定，或者根据实际所需的栅格范围大小确定。可以理解的是，m′的取值越小，则每个栅格的范围越大，m′的取值越大，则每个栅格的范围越小。
Figure PCTCN2022092285-appb-000005
其中，具有相同栅格索引的样本归属于同一个栅格，例如，第2个样本，第5个样本，第10个样本分别对应的label 2、label 5、label 10取值相同，假设label 2＝label 5＝label 10＝3，则第2个样本，第5个样本，第10个样本归属于栅格索引为3的栅格(即第3个栅格)。
可以理解的是，经过步骤403，由于1≤label i≤m′，因此，栅格索引矩阵Label指示了M个样本在m′个栅格中的分布情况。需要说明的是，m′个栅格可以为最终确定的多个栅格，即多个栅格的数目可以为m′，或者，m′个栅格可以不是最终确定的多个栅格，此时，m′个栅格为m′个候选栅格，还需要进一步地筛选，最终确定的多个栅格的数目可以小于m′。下文将对这两种情况分别进行介绍(具体可以参阅下文中的示例1和示例2)，此处不再赘述。
步骤404：第一服务器确定每个栅格的中心坐标和半径。
以下根据训练数据集合包括的具体内容不同，结合示例1和示例2说明如何确定n维波束空间包括的多个栅格，以及每个栅格的中心坐标和半径。
示例1：若训练数据集合包括M个样本，每个样本包括n个波束的电平测量值，不包括流量测量值。在步骤403之后，根据距离矩阵R采用预设距离聚类算法确定的m′个栅格即为最终确定的n维波束空间包括的多个栅格。
每个栅格的中心坐标可以根据该栅格对应的样本中的每个样本包括的n个波束的电平测量值确定。示例性地，以栅格索引i对应的栅格为例，根据栅格索引i对应的样本中的 每个样本包括的n个波束的电平测量值计算一个n个波束的电平测量值的平均值，该n个波束的电平测量值的平均值记为第i个栅格的中心坐标。
假设第2个样本的栅格索引，第5个样本的栅格索引和第10个样本的栅格索引相同，例如，第2个样本的栅格索引，第5个样本的栅格索引，第10个样本的栅格索引均为3，即第2个样本，第5个样本，第10个样本归属于第3个栅格，根据第2个样本，第5个样本，第10个样本分别包括的n个波束的电平测量值可以确定栅格索引为3的栅格(即第3个栅格)的中心坐标。其中，第2个样本，第5个样本，第10个样本分别包括的n个波束的电平测量值为:
{rsrp 2,1,rsrp 2,2,…,rsrp 2,n},{rsrp 5,1,rsrp 5,2,…,rsrp 5,n},{rsrp 10,1,rsrp 10,2,…,rsrp 10,n},
则根据上述三组n个波束的电平测量值确定第3个栅格的中心坐标为：
Figure PCTCN2022092285-appb-000006
对应下述中心坐标矩阵X′中的第3行。
每个栅格的半径可以为预设数值，例如，该预设数值可以根据经验值确定。或者，每个栅格的半径可以根据该栅格对应的样本中的每个样本包括的n个波束的电平测量值与该栅格的中心坐标确定的。
示例性地，第i个栅格的半径是根据栅格索引i对应的样本中的每个样本包括的n个波束的电平测量值与第i个栅格的中心坐标确定的。示例性地，第i个栅格的半径是根据半径集合中的最大距离确定的，半径集合是由栅格索引i对应的样本中的每个样本包括的n个波束的电平测量值与第i个栅格的中心坐标确定的距离构成的。例如，第i个栅格的半径为半径集合中的最大距离，或者，第i个栅格的半径为半径集合中的最大距离与预设距离之和，或者，第i个栅格的半径为半径集合中的最大距离与预设距离之差。
例如，第2个样本，第5个样本，第10个样本归属于栅格索引为3的栅格，根据第2个样本，第5个样本，第10个样本分别包括的n个波束的电平测量值可以确定第3个栅格的中心坐标。其中，第2个样本，第5个样本，第10个样本分别包括的n个波束的电平测量值为:
{rsrp 2,1,rsrp 2,2,…,rsrp 2,n},{rsrp 5,1,rsrp 5,2,…,rsrp 5,n},{rsrp 10,1,rsrp 10,2,…,rsrp 10,n},
第3个栅格的中心坐标为：
Figure PCTCN2022092285-appb-000007
根据第2个样本，第5个样本，第10个样本分别包括的n个波束的电平测量值和第3个栅格的中心坐标可以确定半径集合，半径集合包括距离1、距离2和距离3，其中，
距离1：由{rsrp 2,1,rsrp 2,2,…,rsrp 2,n}和
Figure PCTCN2022092285-appb-000008
确定；
距离2由{rsrp 5,1,rsrp 5,2,…,rsrp 5,n}和
Figure PCTCN2022092285-appb-000009
确定，
距离3，由{rsrp 10,1,rsrp 10,2,…,rsrp 10,n}和
Figure PCTCN2022092285-appb-000010
确定。
第3个栅格的半径为距离1、距离2和距离3中的最大距离。
示例性地，m′个栅格分别对应的中心坐标可以用中心坐标矩阵X′表示，m′表示n维波 束空间中的栅格数目。
Figure PCTCN2022092285-appb-000011
其中，中心坐标矩阵X′中的第i行表示栅格索引i的栅格(即第i个栅格)的中心坐标。例如，中心坐标矩阵X′中的第3行表示栅格索引3的栅格(即第3个栅格)的中心坐标。
Figure PCTCN2022092285-appb-000012
其中，
Figure PCTCN2022092285-appb-000013
为根据栅格索引i对应的样本中的每个样本包括的n个波束的电平测量值中的第j个波束的电平测量值确定的平均值。label k＝i表示第k个样本对应的栅格索引为i。
m′个栅格的半径可以相同，例如，每个栅格的半径可以为预设数值，或者，m′个栅格的半径可以采用半径矩阵d′表示。
Figure PCTCN2022092285-appb-000014
其中，m′表示n维波束空间中的栅格数目。第i行元素表示第i个栅格的半径。例如，第3行元素表示第3个栅格的半径。
Figure PCTCN2022092285-appb-000015
其中，d i是指满足label k＝i的样本(即栅格索引i对应的样本或第i个栅格对应的样本)中，与X′(i,·)距离最远的元素与X′(i,·)的距离。其中，X′(i,·)表示中心坐标矩阵X′中的第i行，即第i个栅格的中心坐标，L k表示满足label k＝i的样本中任意一个样本。具体的，根据第i个栅格对应的样本中的每个样本包括的n个波束的电平测量值，分别求取与第i个栅格的中心坐标的距离，将其中的最大距离作为第i个栅格的半径。例如，假设第i个栅格对应的样本包括s个样本，则可以根据s个样本分别包括的n个波束的电平测量值，与第i个栅格的中心坐标确定s个距离，将s个距离中的最大距离作为第i个栅格的半径。
采用上述示例1所示的方法确定的n维波束空间包括的多个栅格，以及每个栅格的中心坐标和半径，方案简便容易实现。其中，由于每个栅格的中心坐标是多条样本的电平测量值的平均值，将流量的空间位置用栅格的中心坐标表示，可以减少噪声与测量误差对空间的影响，流量的空间位置更具有统计意义。
示例2：若训练数据集合包括M个样本，每个样本包括流量测量值和n个波束的电平测量值，在步骤403后，根据距离矩阵R采用预设距离聚类算法确定的m′个栅格不是最终确定的n维波束空间包括的多个栅格，在步骤403后确定的m′个栅格为m′个候选栅格，还需根据每个样本中包括的流量测量值对m′个候选栅格进行筛选，得到最终确定的n维波束空间包括的多个栅格。
其中，每个样本中的流量测量值包括上行流量测量值和/或下行流量测量值。第i个候选栅格的上行流量统计值为第i个候选栅格对应的样本中包括上行流量测量值的样本的上行流量值之和。第i个候选栅格的下行流量统计值为第i个候选栅格对应的样本中包括下行流量测量值的样本的下行流量值之和。或者，第i个候选栅格的上行流量统计值为第i个候选栅格对应的样本对应的上行流量平均值。第i个候选栅格的下行流量统计值为第i个候选栅格对应的样本对应的下行流量平均值。
例如，第4个候选栅格包括5个样本，其中，样本1、样本3和样本4包括下行流量测量值，样本2包括上行流量测量值，样本5包括上行流量测量值和下行流量测量值，则第4个候选栅格的上行流量统计值为样本2包括的上行流量测量值与样本5包括的上行流量测量值之和，第4个候选栅格的下行流量统计值为样本1包括的下行流量测量值、样本3包括的下行流量测量值、样本4包括的下行流量测量值与样本5包括的下行流量测量值之和。或者，第4个候选栅格的上行流量统计值为样本2包括的上行流量测量值与样本5包括的上行流量测量值之和除以2，第4个候选栅格的下行流量统计值为样本1包括的下行流量测量值、样本3包括的下行流量测量值、样本4包括的下行流量测量值与样本5包括的下行流量测量值之和除以4。
示例性地，将M个样本中的流量测量值按照栅格索引矩阵Label进行汇总，得到m′个候选栅格分别对应的流量统计值，示例性地，m′个候选栅格分别的流量统计值可以采用下述上行流量统计值ULTHP和/或下行流量统计值DLTHP表示。
Figure PCTCN2022092285-appb-000016
其中，ulthp i、dlthp i分别代表第i个候选栅格的上行流量统计值、第i个候选栅格的下行流量统计值。
上行流量统计值ULTHP包括m′个上行流量统计值，即m′个候选栅格分别对应的上行流量统计值，下行流量统计值DLTHP包括m′个下行流量统计值，即m′个候选栅格分别对应的上行流量统计值。
具体的，可以采用但不限于以下方式对m′个候选栅格进行筛选，得到最终确定的n维波束空间包括的多个栅格：
方式1：若第i个候选栅格的上行流量统计值满足预设上行流量阈值，和/或第i个候选栅格的下行流量统计值满足预设下行流量阈值，则将第i个候选栅格作为最终确定的栅格。
其中，预设上行流量阈值和预设下行流量阈值可以根据经验值确定，或者根据实际筛选需要确定。例如，当需要筛选出具有较大上行流量统计值的候选栅格时，可以提高预设上行流量阈值。
因此，针对m′个候选栅格分别对应的上行流量统计值和/下行流量统计值分别与对应的阈值进行判断，确定最终n维波束空间包括的多个栅格。
方式2：根据m′个上行流量统计值从大到小的顺序，从m′个上行流量统计值中筛选k1个上行流量统计值，根据m′个下行流量统计值从大到小的顺序从m′个下行流量统计值中筛选k2个下行流量统计值。k1个上行流量统计值之和与上行总流量统计值的比值大于等于第一阈值，k2个下行流量统计值之和与下行总流量统计值的比值大于等于第二阈值，k1 和k2为正整数，上行总流量统计值是指M个样本中包括上行流量测量值的样本的上行流量值之和，其中，下行总流量统计值是指M个样本中包括下行流量测量值的样本的下行流量值之和，第一阈值可以与第二阈值相同或不同，例如，第一阈值＝第二阈值＝0.8。m′个上行流量统计值中的第i个上行流量统计值为第i个候选栅格对应的样本中包括上行流量测量值的样本的上行流量值之和。m′个下行流量统计值中的第i个下行流量统计值为第i个候选栅格对应的样本中包括下行流量测量值的样本的下行流量值之和。
在一些实施例中，多个栅格为k1个上行流量统计值分别对应的候选栅格与k2个下行流量统计值分别对应的候选栅格的交集。示例性地，若k1个上行流量统计值包括第i个候选栅格的上行流量统计值，且k2个下行流量统计值包括第i个候选栅格的下行流量统计值，则将第i个候选栅格作为最终确定的栅格。示例性地，若k1个上行流量统计值包括第i个候选栅格的上行流量统计值，k2个下行流量统计值不包括第i个候选栅格的下行流量统计值，则第i个候选栅格不是最终确定的栅格。
在一些实施例中，多个栅格为k1个上行流量统计值分别对应的候选栅格与k2个下行流量统计值分别对应的候选栅格的并集。示例性地，若k1个上行流量统计值包括第i个候选栅格的上行流量统计值，或k2个下行流量统计值包括第i个候选栅格的下行流量统计值，则将第i个候选栅格作为最终确定的栅格。示例性地，若k1个上行流量统计值不包括第i个候选栅格的上行流量统计值，k2个下行流量统计值不包括第i个候选栅格的下行流量统计值，则第i个候选栅格不是最终确定的栅格。
示例性地，将上行流量统计值ULTHP按元素值从大到小取出m u个栅格，使得m u个栅格分别对应的上行流量统计值之和占总上行流量统计值
Figure PCTCN2022092285-appb-000017
的比例超过r u(0<r u<1,例如，r u取0.8以上)，将这m u个栅格的索引记为:
Figure PCTCN2022092285-appb-000018
同理，将下行流量统计值DLTHP按元素值从大到小取出m d个栅格，使得m d个栅格分别对应的下行流量统计值之和占下行总流量
Figure PCTCN2022092285-appb-000019
比例超过r d(0<r d<1,例如，r d取0.8以上)，将这m d个栅格的索引记为:
Figure PCTCN2022092285-appb-000020
取I＝I u∪I d，记I的元素个数为m1，即最终确定的栅格的数目为m1。或者，取I＝I u∩I d，记I的元素个数为m2，即最终确定的栅格的数目为m2。
因此，针对m′个候选栅格分别对应的上行流量统计值分别判断其是否属于k1个上行流量统计值，同时，针对m′个候选栅格分别对应的下行流量统计值分别判断其是否属于k2个下行流量统计值，确定最终n维波束空间包括的多个栅格。
与示例1类似，在最终n维波束空间包括的多个栅格之后，每个栅格的中心坐标可以根据该栅格对应的样本中的每个样本包括的n个波束的电平测量值确定，示例性地，假设第i个栅格为最终确定的多个栅格，根据第i个栅格对应的样本中的每个样本包括的n个波束的电平测量值计算一个n个波束的电平测量值的平均值，该n个波束的电平测量值的平均值记为第i个栅格的中心坐标。
每个栅格的半径可以为预设数值，例如，该预设数值可以根据经验值确定。或者，每个栅格的半径可以根据该栅格对应的样本中的每个样本包括的n个波束的电平测量值与该栅格的中心坐标确定的。示例性地，第i个栅格的半径是根据栅格索引i对应的样本中的 每个样本包括的n个波束的电平测量值与第i个栅格的中心坐标确定的。示例性地，第i个栅格的半径是根据半径集合中的最大距离确定的，半径集合是由栅格索引i对应的样本中的每个样本包括的n个波束的电平测量值与第i个栅格的中心坐标确定的距离构成的。例如，第i个栅格的半径为半径集合中的最大距离，或者，第i个栅格的半径为半径集合中的最大距离与预设距离之和，或者，第i个栅格的半径为半径集合中的最大距离与预设距离之差。
示例性地，m′个候选栅格分别对应的中心坐标可以用中心坐标矩阵X′表示，m′表示n维波束空间中的候选栅格数目。
Figure PCTCN2022092285-appb-000021
其中，中心坐标矩阵X′中的第i行表示栅格索引i的候选栅格(即第i个候选栅格)的中心坐标。中心坐标矩阵X′中的第3行表示栅格索引3的候选栅格(即第3个候选栅格)的中心坐标，如上述举例所示。
Figure PCTCN2022092285-appb-000022
其中，
Figure PCTCN2022092285-appb-000023
为根据栅格索引i对应的样本中的每个样本包括的n个波束的电平测量值中的第j维电平测量值确定的平均值。
m′个候选栅格的半径可以相同，例如，每个候选栅格的半径可以为预设数值，或者，m′个候选栅格的半径可以采用半径矩阵d′表示。
Figure PCTCN2022092285-appb-000024
其中，m′表示n维波束空间中的候选栅格数目。第i行元素表示第i个候选栅格的半径。例如，第3行元素表示第3个候选栅格的半径。其中，
Figure PCTCN2022092285-appb-000025
其中，d i是指在label k＝i的样本(即栅格索引i对应的样本或第i个候选栅格对应的样本)里，与X′(i,·)的距离最远的元素与X′(i,·)的距离。其中，X′(i,·)表示中心坐标矩阵X′中的第i行，即栅格索引i的候选栅格(第i个候选栅格)的中心坐标。具体的，根据第i个候选栅格对应的样本中的每个样本包括的n个波束的电平测量值，分别求取与第i个候选栅格的中心坐标的距离，将其中的最大距离作为第i个候选栅格的半径。例如，假设第i个候选栅格对应的样本包括s个样本，则可以根据s个样本分别包括的n个波束的电平测量值，与第i个候选栅格的中心坐标确定s个距离，确定s个距离中的最大距离作为第i个候选栅格的半径。
结合上述方式1，根据上行流量统计值满足预设上行流量阈值的候选栅格的栅格索引，从中心坐标矩阵X′中取出对应的行，记为中心坐标矩阵X，同时从半径矩阵d′中取出对应 的行，记为半径矩阵d。或者，根据下行流量统计值满足预设下行流量阈值的候选栅格的栅格索引，从中心坐标矩阵X′中取出对应的行，记为中心坐标矩阵X，同时从半径矩阵d′中取出对应的行，记为半径矩阵d。或者，根据上行流量统计值满足预设上行流量阈值的候选栅格的栅格索引与下行流量统计值满足预设下行流量阈值的候选栅格的栅格索引的交集或并集，从中心坐标矩阵X′中取出对应的行，记为中心坐标矩阵X，同时从半径矩阵d′中取出对应的行，记为半径矩阵d。
结合上述方式2，按照I中元素的取值取出中心坐标矩阵X′中对应的行，记为中心坐标矩阵X，具体的，若i∈I，保留X′中第i行，否则删除第i行，同时按照I中元素的取值取出半径矩阵d′中取出对应的行，记为半径矩阵d。
示例性地，最终输出的中心坐标矩阵X为：
Figure PCTCN2022092285-appb-000026
最终输出的半径矩阵d为：
Figure PCTCN2022092285-appb-000027
其中，由上述中心坐标矩阵X和中心坐标矩阵d可知，最终确定的n维波束空间包括的多个栅格的数目为m，m≤m′。
采用上述示例2所示的方法能够通过每个样本中包括的流量测量值对候选栅格进行筛选，进而可以删除一部分流量较小的栅格。采用上述示例2所示的方法确定的栅格数目相较于采用示例1所示的方法确定的栅格数目减少，但确定的栅格仍能覆盖大部分流量。也就是说，在对流量感知的最终效果(即流量统计结果)影响不大的前提下，减小了后续大数据计算、存储、传输的复杂度。
此外，可以理解的是，在完成确定n维波束空间中的多个栅格之后，还可以每隔预设时间段对已确定的多个栅格进行更新，即定时执行一次步骤401至步骤404。其中，首次根据收集到的MR确定n维波束空间中的多个栅格，又可称为栅格初始化过程。非首次根据收集到的MR确定n维波束空间中的多个栅格，又可称为栅格更新过程。
进一步地，结合上述方法在确定n维波束空间中的多个栅格之后，根据第一终端设备对应的n个波束的电平测量值可以确定与第一终端设备关联的栅格，进而可以利用与第一终端设备关联的栅格表征终端设备的位置。
在一种可能的设计中，假设n维波束空间包括m个栅格，则可以根据m个栅格的栅格索引的顺序依次计算一个栅格的中心坐标与第一终端设备对应的n个波束的电平测量值的距离。当第一终端设备对应的n个波束的电平测量值与第i个栅格的中心坐标的距离小于等于第i个栅格的半径时，则确定第一终端设备与第i个栅格关联，此时可以不需要再确定第i个栅格之后的其他剩余栅格的中心坐标与第一终端设备对应的n个波束的电平测量值的距离。
例如，假设n维波束空间包括10个栅格，则可以根据10个栅格的栅格索引的顺序依次计算一个栅格的中心坐标与第一终端设备对应的n个波束的电平测量值的距离。当第一终端设备对应的n个波束的电平测量值与第1个栅格的中心坐标的距离大于第1个栅格的半径时，则确定第一终端设备不与第1个栅格关联，并继续计算第一终端设备对应的n个波束的电平测量值与第2个栅格的中心坐标的距离。当第一终端设备对应的n个波束的电平测量值与第2个栅格的中心坐标的距离大于第2个栅格的半径时，则确定第一终端设备不与第2个栅格关联，并继续计算第一终端设备对应的n个波束的电平测量值与第3个栅格的中心坐标的距离。当第一终端设备对应的n个波束的电平测量值与第3个栅格的中心坐标的距离小于或等于第3个栅格的半径时，则确定第一终端设备与第3个栅格关联，并停止继续计算第一终端设备对应的n个波束的电平测量值与第4个栅格的中心坐标的距离。
在一种可能的设计中，假设n维波束空间包括m个栅格，第一终端设备对应的n个波束的电平测量值与m个栅格中的N个栅格的中心坐标所确定的距离均小于对应的半径，2≤N＜n，N为正整数，则选择最小距离对应的栅格作为与第一终端设备关联的栅格，或者从N个栅格中选择任意一个栅格作为与第一终端设备关联的栅格。
例如，第一终端设备对应的n个波束的电平测量值与第i个栅格的中心坐标的距离(记为第一距离)小于第i个栅格的半径，且第一终端设备对应的n个波束的电平测量值与第j个栅格的中心坐标的距离(记为第二距离)小于第j个栅格的半径。若第一距离小于第二距离，则与第一终端设备关联的栅格为第i个栅格。
又例如，第一终端设备对应的n个波束的电平测量值与第1个栅格的中心坐标的距离(记为距离1)小于第1个栅格的半径，第一终端设备对应的n个波束的电平测量值与第5个栅格的中心坐标的距离(记为距离5)小于第5个栅格的半径，第一终端设备对应的n个波束的电平测量值与第11个栅格的中心坐标的距离(记为距离11)小于第11个栅格的半径，其中，在距离1、距离5和距离11中，距离11最小，则与第一终端设备关联的栅格为第11个栅格。或者，在第1个栅格、第5个栅格和第11个栅格中选择任意一个栅格作为与第一数据关联的栅格。
在一种可能的设计中，假设n维波束空间包括m个栅格示例性地，计算第一终端设备对应的n个波束的电平测量值与m个栅格中的各栅格的中心坐标的距离，得到m个距离，将m个距离中的最小距离所对应的栅格作为与第一终端设备关联的栅格。例如，m个距离中的最小距离所对应的栅格为第i个栅格，则第i个栅格作为与第一终端设备关联的栅格。
基于通过上述实施例确定的n维波束空间中多个栅格，可以进一步基于上述多个栅格获得流量统计结果在时空的分布情况。
本申请实施例提供一种确定流量统计结果的方法，示例性地，此处以第一服务器为例作为执行主体，例如，第一服务器可以为任意服务器或者处理器或者云端设备或边缘设备等，本申请实施例对此不做限定。可以理解的是，图4所示实施例的执行主体与图5所示实施例的执行主体可以相同，也可以不同，本申请实施例对此不做限定。
如图5所示，该方法包括：
步骤501：第一服务器获取第一数据集合，第一数据集合包括在第一时间段被采集的多个数据，每个数据包括流量测量值和n个波束的电平测量值。
示例性地，第一数据集合可以包括在第一时间段内收集的MR。例如，第一数据集合 可以包括一周或两周内收集的MR，或者，第一数据集合可以包括一天内收集的MR，或者第一数据集合可以包括一个小时内收集的MR，第一数据集合可以包括早上7点至10点收集的MR。
其中，第一数据集合与上述训练数据集合不同。训练数据集合可以包括预设时间段内收集的MR，第一数据集合可以包括在第一时间段内收集的MR。其中，第一时间段晚于预设时间段，且第一数据集合和训练数据集合均是针对同一个小区获取的MR。
示例性地，基站可以根据订阅参数向第一服务器发送MR。例如，订阅参数可以包括MR上报周期(例如，若干分钟或若干小时或者若干秒)。其中，可以理解的是，第一服务器可以根据MR中的生成时间将收集到的数据划分为多个时间段分别对应的数据集合，得到多个数据集，第一数据集合可以为多个数据集合中的一个。此外，需要说明的是，第一数据集合为在第一时间段内针对一个小区收集的MR，第一数据集合可以用小区标识和第一时间段标识。第一数据集合对应的小区与上述n维波束空间中的多个栅格所对应的小区为同一个小区，多个栅格中的任意一个栅格可以用小区标识和栅格索引标识。
示例性地，第一数据集合包括K个数据。第一数据集合可以如ThpMat 1所示，通过ThpMat 1电可以提取电平矩阵L 1。
Figure PCTCN2022092285-appb-000028
Figure PCTCN2022092285-appb-000029
其中，ThpMat 1中的每一行可以对应一个MR包括的生成时间、流量测量值(上行流量测量值和/或下行流量测量值)和n个波束的电平测量值，K为第一数据集合包括的数据数目。电平矩阵L 1的每一行即为n个波束的电平测量值。其中，time 1,1…time K,1均属于第一时间段。
步骤502：第一服务器根据每个数据的n个波束的电平测量值和第一栅格的中心坐标确定所述第一数据集合中与第一栅格关联的第二数据集合，第一栅格的中心坐标用n个波束的电平值表示。
可以理解的是，第一栅格可以为n维波束空间中的多个栅格中的任意一个栅格，或者，第一栅格可以为n维波束空间中的多个栅格中的一个特定的栅格。
示例性地，第一服务器确定所述第一数据集合中与第一栅格关联的第二数据集合可以采用但不限于以下方式：
方式1：第一服务器确定第一数据集合中任意一个数据包括的n个波束的电平测量值与第一栅格的中心坐标的距离小于或等于第一栅格的半径，则该数据为第二数据集合中的数据。
示例性地，假设n维波束空间包括m个栅格，第一数据集合包括第一数据，第一服务器可以根据m个栅格的栅格索引的顺序依次计算一个栅格的中心坐标与第一数据包括的n个波束的电平测量值的距离。当第一数据包括的n个波束的电平测量值与第一栅格的中心坐标的距离小于或者等于第i个栅格的半径时，则确定第一数据与第一栅格关联，此时第 一栅格之前的其他栅格的中心坐标与第一数据包括的n个波束的电平测量值的距离均大于相应的半径。例如，假设n维波束空间包括10个栅格，则可以根据10个栅格的栅格索引的顺序依次计算一个栅格的中心坐标与第一数据包括的n个波束的电平测量值的距离。当第一数据包括的n个波束的电平测量值与第1个栅格的中心坐标的距离大于第1个栅格的半径时，则确定第一数据不与第1个栅格关联，并继续计算第一数据包括的n个波束的电平测量值与第2个栅格的中心坐标的距离。当第一数据包括的n个波束的电平测量值与第2个栅格的中心坐标的距离大于第2个栅格的半径时，则确定第一数据不与第2个栅格关联，并继续计算第一数据包括的n个波束的电平测量值与第3个栅格的中心坐标的距离。当第一数据包括的n个波束的电平测量值与第3个栅格的中心坐标的距离小于或等于第3个栅格的半径时，则确定第一数据与第3个栅格关联，并停止继续计算第一数据包括的n个波束的电平测量值与第4个栅格的中心坐标的距离。
示例性地，假设n维波束空间包括m个栅格，第一数据集合包括第一数据，第一数据包括的n个波束的电平测量值与m个栅格中的N个栅格的中心坐标所确定的距离均小于对应的半径，2≤N＜n，N为正整数，则第一服务器可以从N个栅格中选择任意一个栅格作为与第一数据关联的栅格。例如，第一数据包括的n个波束的电平测量值与第1个栅格的中心坐标的距离(记为距离1)小于第1个栅格的半径，第一数据包括的n个波束的电平测量值与第5个栅格的中心坐标的距离(记为距离5)小于第5个栅格的半径，第一数据包括的n个波束的电平测量值与第11个栅格的中心坐标的距离(记为距离11)小于第11个栅格的半径，其中，在第1个栅格、第5个栅格和第11个栅格中选择任意一个栅格作为与第一数据关联的栅格。
示例性地，第一服务器确定多个栅格的各栅格分别对应的中心坐标中的任意一个栅格的中心坐标与第一数据包括的n个波束的电平测量值的距离(记为距离集合1)，第一数据为第一数据集合中的数据，根据多个栅格的各栅格分别对应的半径和距离集合1确定距离集合2，在距离集合2中的最小距离为第一栅格与第一数据包括的n个波束的电平测量值的距离的情况下，则确定第二数据集合包括第一数据。其中，距离集合2中的任意一个距离小于该距离对应的栅格的半径。
示例性地，假设n维波束空间包括m个栅格，第一数据包括的n个波束的电平测量值与m个栅格中的N个栅格的中心坐标所确定的距离均小于对应的半径，2≤N＜n，N为正整数，则选择最小距离对应的栅格作为与第一数据关联的栅格。例如，第一数据包括的n个波束的电平测量值与第1个栅格的中心坐标的距离(记为距离1)小于第1个栅格的半径，第一数据包括的n个波束的电平测量值与第5个栅格的中心坐标的距离(记为距离5)小于第5个栅格的半径，第一数据包括的n个波束的电平测量值与第11个栅格的中心坐标的距离(记为距离11)小于第11个栅格的半径，其中，在距离1、距离5和距离11中，距离11最小，则第11个栅格为与第一数据关联的栅格。
方式2：第一服务器确定第一数据集合中任意一个数据包括的n个波束的电平测量值与第一栅格的中心坐标的距离小于该n个波束的电平测量值与多个栅格中除第一栅格之外的其它栅格的中心坐标的距离，则该数据为第二数据集合中的数据。
示例性地，假设n维波束空间包括m个栅格，第一数据集合包括第一数据，第一服务器计算第一数据包括的n个波束的电平测量值与m个栅格中的各栅格的中心坐标的距离，得到m个距离，将m个距离中的最小距离所对应的栅格作为与第一数据关联的栅格。例 如，m个距离中的最小距离所对应的栅格为第i个栅格，则第i个栅格作为与第一数据关联的栅格。
步骤503：第一服务器根据第二数据集合中每个数据包括的流量测量值确定在第一时间段内对应于第一栅格的上行流量或下行流量。
每个数据中的流量测量值包括上行流量测量值和/或下行流量测量值。上行流量是根据第二数据集合中包括上行流量测量值的数据确定的，下行流量是根据第二数据集合中包括下行流量测量值的数据确定的。
示例性地，第一服务器可以将第二数据集合中包括的上行流量测量值求和作为在第一时间段内对应于第一栅格的上行流量统计结果。第一服务器可以将第二数据集合中包括的下行流量测量值求和作为在第一时间段内对应于第一栅格的下行流量统计结果。
进一步地，基于相同的实现方式，可以确定第一数据集合中与多个栅格中每个栅格关联的数据，并根据与每个栅格关联的数据包括的流量测量值确定在第一时间段内对应该栅格的流量统计结果，进而获得第一时间段内对应多个栅格中的每个栅格的流量统计结果。
示例性地，假设n维波束空间中的多个栅格是根据上述示例2的方法确定，n维波束空间中的多个栅格对应的小区与第一数据集合对应的小区相同。根据电平矩阵L 1中的L 1(i,·)与上述示例2确定的中心坐标矩阵X中的每行确定的距离，得到距离集合s i。
s i＝[s i,1,s i,2,…,s i,m]
其中，L 1(i,·)为电平矩阵L 1中的第i行，即第一数据集合中的第i个数据包括的n个波束的电平测量值。X(j,·)为中心坐标矩阵X中的第j行，即n维波束空间中的第j个栅格的中心坐标。s i,j表示第i个数据包括的n个波束的电平测量值与第j个栅格的中心坐标的距离。
比较距离集合s i中的每个元素与上述示例2中确定的半径矩阵d中对应的元素，具体的，比较s i,1与d 1，比较s i,2与d 2，……，比较s i,m与d m，确定第i个数据归属的栅格索引。其中，满足s i,j≤d j的j中对应s i,j最小的索引为第i个数据归属的栅格索引，即L 1(i,·)归属的栅格的索引。示例性地，s i,1小于d 1，s i,2小于d 2，若s i,1＜s i,2，则第i个数据归属于第1个栅格，或描述为第i个数据与第1个栅格关联。
如果对于所有j都满足s i,j>d j，记归属栅格的栅格索引为-1，即第i个数据表示没有归属栅格。
因此，采用上述方法可以确定对于L 1中的每一行归属的栅格，即每个数据归属的栅格，如A1所示。A1可以为一个1×K为矩阵。
Figure PCTCN2022092285-appb-000030
其中，a i代表第一数据集合中的第i条数据归属的栅格。a i的取值范围为0<a i<m，或者a i＝-1。
进一步地，可以首先删除A 1中的-1以及ThpMat 1中对应的行，不失一般性，仍记为A 1和ThpMat 1，则确定第一时间段内的上行流量统计结果V u和下行流量统计结果V d为：
Figure PCTCN2022092285-appb-000031
V u的第i行代表在第一时间段内对应第i个栅格的上行流量统计值，V d的第i行代表在第一时间段内对应第i个栅格的下行流量统计值。例如，ULTHP 1是根据A1中a i的取值为1的数据包括的上行流量测量值确定的，假设第1个数据、第3个数据，第6个数据归属于第1个栅格(即第1个数据、第3个数据，第6个数据与第1个栅格关联)，a 1＝a 3＝a 6＝1，第1个数据、第3个数据，第6个数据包括的上行流量测量值分别为ulthp 1，ulthp 3，ulthp 6，则ULTHP 1＝ulthp 1+ulthp 3+ulthp 6。
可以理解的是，此处仅以采用示例2所示的方法确定的n维波束空间中的多个栅格为例进行说明在第一时间段内对应每个栅格的流量统计结果。上述中心坐标矩阵X和栅格半径矩阵d还可以替换为中心坐标矩阵X′，栅格半径矩阵d′。
此外，在一些实施例中，在确定第一数据集合中的每个数据归属的栅格后，第一服务器将ThpMat 1按照生成时间以预设时长分割成Z个时间范围，例如，预设时长为T。TimeRange i为第一时间段中的第i个子时间段，第i个子时间段的时长为T。针对任意一个子时间段，在删除A 1中的-1以及ThpMat 1中对应的行(不失一般性，仍记为A 1和ThpMat 1)之后，第一服务器可以按照A 1将ThpMat 1中生成时间属于该子时间段且归属于同一栅格的流量测量值求和，得到如下流量统计结果：
T Z＝[TimeRange 1,TimeRange 2,…,TimeRange Z]
Figure PCTCN2022092285-appb-000032
Figure PCTCN2022092285-appb-000033
其中，T Z为将第一预设时间段以预设时长分割成Z个时间范围的分段结果，V u的第i行代表对应第i个栅格在Z个时间范围分别对应的上行流量统计值，V d的第i行代表对应第i个栅格在Z个时间范围分别对应的下行流量统计值。其中，V u的第j列代表第j个子时间段在m个栅格分别对应的上行流量统计值，V d的第i行代表第j个子时间段在m个栅格分别对应的下行流量统计值。
因此，采用上述方法确定的用户流量的流量统计结果为栅格级时间段粒度的流量统计结果，在保持流量的关键时空统计特征的前提下，能够实现降低数据计算、存储与传输的成本。
上述主要从方法流程的角度对本申请实施例提供的方案进行了介绍。下面结合附图介绍本申请实施例中用来实现上述方法的装置。因此，上文中的内容均可以用于后续实施例中，重复的内容不再赘述。
本申请实施例还提供一种装置，所述装置执行本申请实施例提供的方法，该装置可以单独部署，例如部署在一个服务器上，或者部署在边缘节点(如集中单元(centralized unit，CU)或移动边缘计算(mobile edge computing，MEC)上)。
如图6所示，该装置可以为第一服务器或第一服务器中的芯片或功能模块。第一服务器可以接收来自于多个基站的MR，获得多个MR。第一服务器可以以多个MR作为输入，输出基于多个MR确定的流量分布结果。进一步地，第一服务器可以保存该流量分布结果 供第一服务器使用，或者，第一服务器可以向第二服务器发送该流量分布结果。其中，每个基站可以发送多个MR至第一服务器。
在一示例中，如图7所示，当该装置还可以部署在边缘节点时，若边缘节点与多个基站进行连接，边缘节点可以订阅所连接的多个基站的MR。边缘节点可以以订阅的MR为输入，输出基于订阅的MR确定的流量分布结果。其中，基于订阅的MR确定的流量分布结果可以保存在边缘节点供边缘节点使用，也可以回传至中心云操作支持系统(operation support systems，OSS)系统支撑全网流量分析或网络优化。
在另一示例中，如图8所示，MEC的服务器与边缘感应节点(Edge Sensing Node,ESN)连接，ESN与MEC的连接不一定是跨硬件的，ESN可以是直接部署在MEC的服务器上，ESN可以以APP或进程形式体现。其中，ESN负责MR采集、并基于采集的MR确定流量分布结果，并上传到中心云OSS上。
这里的流量分布结果可以包括在第一时间段内对应第一栅格的流量统计结果，或者，在第一时间段内多个栅格分别对应的流量统计结果，或者第一栅格在多个时间段分别对应的流量统计结果，或者多个栅格在多个时间段分别对应的流量统计结果等。流量分布结果的具体内容可以根据具体需求而定。
为了实现上述本申请实施例提供的方法中的各功能，本申请实施例还提供一种装置用于实现上述方法。该装置可以包括硬件结构和/或软件模块，以硬件结构、软件模块、或硬件结构加软件模块的形式来实现上述各功能。上述各功能中的某个功能以硬件结构、软件模块、还是硬件结构加软件模块的方式来执行，取决于技术方案的特定应用和设计约束条件。
本申请实施例提供的装置可以是能够执行上述方法对应的功能的芯片或电路，该芯片或电路可以设置在处理器等设备中。进一步的，本申请实施例提供的装置，还能够以硬件或硬件和计算机软件的结合形式来实现。某个功能究竟以硬件还是计算机软件驱动硬件的方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请实施例的范围。
本申请实施例提供的装置可以进行功能模块的划分，例如，可对应各个功能划分各个功能模块，也可将两个或两个以上的功能集成在一个处理模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。需要说明的是，本申请实施例中对模块的划分是示意性的，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式。
一种可能的实现方式中，如图9所示，为本申请实施例提供一种确定流量统计结果的装置的结构示意图。该装置可以是处理器，也可以是处理器中的装置。该装置900可以包括：处理模块91和通信模块92。当然，该装置900还可能包括其他模块，本申请实施例并不限定，仅示出主要的功能模块。通信模块92用于获取第一数据集合，第一数据集合包括在第一时间段被采集的多个数据，每个数据包括流量测量值和n个波束的电平测量值，处理模块91用于根据每个数据的n个波束的电平测量值和第一栅格的中心坐标确定第一数据集合中与第一栅格关联的第二数据集合，根据第二数据集合中每个数据包括的流量测量值确定在第一时间段内对应第一栅格的流量统计结果。其中，第二数据集合包括第一数据集合中与n维波束空间中的第一栅格关联的数据，第二数据集合中的任意一个数据包括 的n个波束的电平测量值与第一栅格的中心坐标的距离小于或等于第一栅格的半径，第一栅格的中心坐标用n个波束的电平值表示。
装置900中的处理模块91可以支持装置900执行上文中各方法示例中第一服务器的动作，例如可以支持装置900执行图4中的步骤402，步骤403，步骤404，图5中的步骤502，步骤503。
通信模块92可以支持装置900与设备(例如，基站或其他服务器)之间的通信，例如，通信模块92可以支持装置900执行图4中的步骤401，图5中的步骤501。
应理解，本申请实施例中的处理模块91可以由处理器或处理器相关电路组件实现，通信模块92可以由通信接口或通信接口相关电路组件或者通信接口实现。应理解，通信接口可以包括例如发射器和接收器，处理器、发射器和接收器相互耦合，其中，发射器和接收器例如通过天线、馈线和编解码器等实现，或者，如果所述装置为设置在设备中的芯片，那么发射器和接收器例如为芯片中的通信接口，该通信接口与设备中的射频收发组件连接，以通过射频收发组件实现信息的收发。
例如，如图10所示为本申请实施例提供的装置1000，图10所示的装置可以为图9所示的装置的一种硬件电路的实现方式。该装置可用于执行图5所示出的流程图中的第一服务器的功能。为了便于说明，图10仅示出了该装置的主要部件。
需要说明的是，图10所示的装置可以是能够执行上述方法对应的功能的芯片或电路，也可以是包括上述芯片或电路的设备，本申请实施例对此并不限定。
图10所示的装置1000包括至少一个处理器1020，用于实现本申请实施例提供的图5中第一服务器的功能。
装置1000还可以包括至少一个存储器1030，用于存储程序指令和/或数据。存储器1030和处理器1020耦合。本申请实施例中的耦合是装置、单元或模块之间的间接耦合或通信连接，可以是电性，机械或其它的形式，用于装置、单元或模块之间的信息交互。处理器1020可能和存储器1030协同操作。处理器1020可能执行存储器1030中存储的程序指令。所述至少一个存储器中的至少一个可以包括于处理器中。
可选地，若该装置1000为芯片或电路，该装置1000也可以不包括存储器1030，处理器1020可以读取该芯片或电路外部的存储器中的指令(程序或代码)以实现图5所示的实施例所提供的第一服务器的功能。
装置1000还可以包括通信接口1010，用于通过传输介质和其它设备进行通信，从而用于装置1000中的装置可以和其它设备进行通信。在本申请实施例中，通信接口可以是收发器、电路、总线、模块或其它类型的通信接口。在本申请实施例中，收发器可以为独立的接收器、独立的发射器、集成收发功能的收发器、或者是接口电路。处理器1020利用通信接口1010收发数据，并用于实现图5所示实施例中第一服务器的功能，具体可以参考前面的描述，在此不再赘述。
装置1000还可以包括通信总线1040。其中，通信接口1010、处理器1020以及存储器1030可以通过通信总线1040相互连接；通信总线1040可以是外设部件互连标准(peripheral component interconnect，简称PCI)总线或扩展工业标准结构(extended industry standard architecture，简称EISA)总线等。所述通信总线1040可以分为地址总线、数据总线、控制总线等。为便于表示，图10中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。
再一种可选的方式，本申请实施例提供的装置使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行所述计算机程序指令时，全部或部分地实现本申请实施例所述的流程或功能。所述计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。所述计算机指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，所述计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(digital subscriber line，DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质，(例如软盘、硬盘、磁带)、光介质(例如DVD)、或者半导体介质(例如固态硬盘(solid state disk，SSD))等。
需要说明的是，用于执行本申请实施例提供的方法的上述装置中所包含的处理器可以是中央处理器(central processing unit，CPU)，通用处理器、数字信号处理器(digital signal processor，DSP)、专用集成电路(application-specific integrated circuit，ASIC)，现场可编程门阵列(field programmable gate array，FPGA)或者其他可编程逻辑器件、晶体管逻辑器件，硬件部件或者其任意组合。其可以实现或执行结合本申请公开内容所描述的各种示例性的逻辑方框，模块和电路。所述处理器也可以是实现计算功能的组合，例如包含一个或多个微处理器组合，DSP和微处理器的组合等等。
结合本申请实施例所描述的方法或者算法的步骤可以硬件的方式来实现，也可以是由处理器执行软件指令的方式来实现。软件指令可以由相应的软件模块组成，软件模块可以被存放于随机存取存储器(random access memory，RAM)、闪存、只读存储器(read-only memory，ROM)存储器、可擦除可编程只读存储器(erasable programmable read-only memory，EPROM)、电可擦除可编程只读存储器(electrically erasable programmable read-only memory，EEPROM)、寄存器、硬盘、移动硬盘、只读光盘(compact disc read-only memory，CD-ROM)或者本领域熟知的任何其它形式的存储介质中。一种示例性的存储介质耦合至处理器，从而使处理器能够从该存储介质读取信息，且可向该存储介质写入信息。当然，存储介质也可以是处理器的组成部分。处理器和存储介质可以位于ASIC中。另外，该ASIC可以位于雷达装置或者安装雷达装置的探测设备中。当然，处理器和存储介质也可以作为分立组件存在于雷达装置或者安装雷达装置的探测设备中。
可以理解的是，图9～图10仅仅示出了该装置的简化设计。在实际应用中，本申请实施例提供的装置可以包含任意数量的发射器，接收器，处理器，控制器，存储器以及其他可能存在的元件。
通过以上的实施方式的描述，所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，仅以上述各功能模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能模块完成，即将装置的内部结构划分成不同的功能模块，以完成以上描述的全部或者部分功能。
本申请实施例还提供一种芯片，所述芯片与存储器相连，用于读取并执行所述存储器中存储的软件程序，当在所述芯片上运行所述软件程序时，使得所述芯片实现图5中第一服务器的功能。
本申请实施例还提供一种计算机可读存储介质，包括指令，当在计算机上运行所述指令时，使得计算机实现图5中第一服务器的功能。
本领域内的技术人员应明白，本申请的实施例可提供为方法、系统、或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本申请是参照根据本申请的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
显然，本领域的技术人员可以对本申请进行各种改动和变型而不脱离本申请的精神和范围。这样，倘若本申请的这些修改和变型属于本申请权利要求及其等同技术的范围之内，则本申请也意图包含这些改动和变型在内。

Claims (30)

  1. 一种确定流量统计结果的方法，其特征在于，该方法包括：
    获取第一数据集合，所述第一数据集合包括在第一时间段被采集的多个数据，每个数据包括流量测量值和n个波束的电平测量值，所述流量测量值包括上行流量测量值和/或下行流量测量值；
    根据每个数据的n个波束的电平测量值和第一栅格的中心坐标，确定所述第一数据集合中与所述第一栅格关联的第二数据集合，所述第一栅格的中心坐标用n个波束的电平值表示；
    根据所述第二数据集合中每个数据包括的流量测量值确定在所述第一时间段内对应所述第一栅格的上行流量或下行流量。
  2. 如权利要求1所述的方法，其特征在于，还包括：
    获取所述n维波束空间中的多个栅格的各栅格分别对应的中心坐标和半径，所述多个栅格包括所述第一栅格。
  3. 如权利要求2所述的方法，其特征在于，所述确定第一数据集合中与所述第一栅格关联的第二数据集合，包括：
    确定所述第一数据集合中任意一个数据包括的n个波束的电平测量值与所述第一栅格的中心坐标的距离小于或等于所述第一栅格的半径，则该数据为所述第二数据集合中的数据；或
    确定所述第一数据集合中任意一个数据包括的n个波束的电平测量值与所述第一栅格的中心坐标的距离小于该n个波束的电平测量值与所述多个栅格中除所述第一栅格之外的其它栅格的中心坐标的距离，则该数据为所述第二数据集合中的数据。
  4. 如权利要求3所述的方法，其特征在于，确定所述第一数据集合中任意一个数据包括的n个波束的电平测量值与所述第一栅格的中心坐标的距离小于或等于所述第一栅格的半径，则该数据为所述第二数据集合中的数据，包括：
    确定所述第一数据集合中任意一个数据包括的n个波束的电平测量值与所述第一栅格的中心坐标的距离小于等于所述第一栅格的半径，且该数据包括的n个波束的电平测量值与第二栅格的中心坐标的距离小于等于所述第二栅格的半径，其中，所述第二栅格为所述多个栅格中除所述第一栅格之外的一个栅格；
    在该数据包括的n个波束的电平测量值与所述第一栅格的中心坐标的距离小于该数据包括的n个波束的电平测量值与所述第二栅格的中心坐标的距离时，确定该数据为所述第二数据集合中数据。
  5. 如权利要求2-4任一项所述的方法，其特征在于，获取所述n维波束空间中的多个栅格的各栅格分别对应的中心坐标，包括：
    获取训练数据集合，所述训练数据集合包括多个样本，每个样本包括n个波束的电平测量值；
    根据所述多个样本中每个样本对应的n个波束的电平测量值获得所述训练数据集合对应的距离集合，所述训练数据集合对应的距离集合包括所述多个样本中每个样本对应的n个波束的电平测量值中的任意两组n个波束的电平测量值的距离；
    根据所述训练数据集合对应的距离集合确定所述多个栅格中的各栅格分别对应的样 本，其中，每个栅格对应的样本中的任意两个样本中的各样本包括的n个波束的电平测量值的距离满足预设距离条件；
    根据每个栅格对应的样本确定各栅格分别对应的中心坐标，其中，所述第一栅格的中心坐标是根据所述第一栅格对应的样本确定的。
  6. 如权利要求2-4任一项所述的方法，其特征在于，获取所述n维波束空间中的多个栅格的各栅格分别对应的中心坐标，包括：
    获取训练数据集合，所述训练数据集合包括多个样本，每个样本包括流量测量值和n个波束的电平测量值；
    根据所述多个样本中每个样本对应的n个波束的电平测量值获得训练数据集合对应的距离集合，所述训练数据集合对应的距离集合包括所述多个样本中每个样本对应的n个波束的电平测量值中的任意两组n个波束的电平测量值的距离；
    根据所述训练数据集合对应的距离集合确定多个候选栅格中各候选栅格分别对应的样本，其中，每个候选栅格对应的样本中的任意两个样本中的各样本包括的n个波束的电平测量值的距离满足预设距离条件；
    根据每个候选栅格对应的样本中每个样本包括的流量测量值，确定所述多个候选栅格中每个候选栅格对应的流量统计值；
    根据所述多个候选栅格中每个候选栅格对应的流量统计值确定满足预设流量条件的候选栅格，将满足预设流量条件的候选栅格作为所述n维波束空间中的多个栅格；
    根据所述多个栅格中每个栅格对应的样本确定各栅格分别对应的中心坐标，其中，所述第一栅格的中心坐标是根据所述第一栅格对应的样本确定的。
  7. 如权利要求6所述的方法，其特征在于，每个样本中的流量测量值包括上行流量测量值和/或下行流量测量值；
    所述第一栅格对应的流量统计值包括所述第一栅格对应的上行流量统计值和/或所述第一栅格对应的下行流量统计值；
    所述第一栅格对应的上行流量统计值是根据所述第一栅格对应的样本中包括上行流量测量值的样本确定的；和/或所述第一栅格对应的下行流量统计值是根据所述第一栅格对应的样本中包括下行流量测量值的样本确定的；
    所述第一栅格为所述多个候选栅格中满足预设流量条件的候选栅格中的任一栅格，所述第一栅格对应的流量统计值满足预设流量条件是指所述第一栅格对应的上行流量统计值大于等于预设上行流量阈值，和/或所述第一栅格对应的下行流量统计值大于等于预设下行流量阈值。
  8. 如权利要求6所述的方法，其特征在于，所述多个栅格为k1个上行流量统计值分别对应的候选栅格和k2个下行流量统计值分别对应的候选栅格的交集；
    其中，所述k1个上行流量统计值之和与上行总流量统计值的比值大于等于第一阈值，所述k2个下行流量统计值之和与下行总流量统计值的比值大于等于第二阈值，k1和k2为正整数；
    所述k1个上行流量统计值根据从大到小的顺序从所述多个候选栅格中每个候选栅格对应的上行流量统计值中确定，所述k2个下行流量统计值根据从大到小的顺序从所述多个候选栅格中每个候选栅格对应的下行流量统计值中确定，所述上行总流量是指所述多个样本中包括的上行流量测量值之和，所述下行总流量是指所述多个样本中包括的下行流量 测量值之和；
    所述第一栅格为所述多个候选栅格中满足预设流量条件的候选栅格中的任一栅格，所述第一栅格对应的流量统计值满足预设流量条件是指所述第一栅格对应的上行流量统计值为所述k1个上行流量统计值中的一个，且所述第一栅格对应的下行流量统计值为所述k2个下行流量统计值中的一个；
    其中，所述第一栅格对应的上行流量统计值是指所述第一栅格对应的样本中包括的上行流量测量值之和；所述第一栅格对应的下行流量统计值是指所述第一栅格对应的样本中包括的下行流量值之和。
  9. 如权利要求6所述的方法，其特征在于，所述多个栅格为k1个上行流量统计值分别对应的候选栅格和k2个下行流量统计值分别对应的候选栅格的并集；
    其中，所述k1个上行流量统计值之和与上行总流量统计值的比值大于等于第一阈值，所述k2个下行流量统计值之和与下行总流量统计值的比值大于等于第二阈值，k1和k2为正整数；
    所述k1个上行流量统计值根据从大到小的顺序从所述多个候选栅格中每个候选栅格对应的上行流量统计值中确定，所述k2个下行流量统计值根据从大到小的顺序从所述多个候选栅格中每个候选栅格对应的下行流量统计值中确定，所述上行总流量是指所述多个样本中包括的上行流量测量值之和，所述下行总流量是指所述多个样本中包括的下行流量测量值之和；
    所述第一栅格为所述多个候选栅格中满足预设流量条件的候选栅格中的任一栅格，所述第一栅格对应的流量统计值满足预设流量条件是指所述第一栅格对应的上行流量统计值为所述k1个上行流量统计值中的一个，或所述第一栅格对应的下行流量统计值为所述k2个下行流量统计值中的一个；
    其中，所述第一栅格对应的上行流量统计值是指所述第一栅格对应的样本中包括的上行流量值之和；所述第一栅格对应的下行流量统计值是指所述第一栅格对应的样本中包括的下行流量值之和。
  10. 如权利要求5-9任一项所述的方法，其特征在于，所述第一栅格的中心坐标为根据所述第一栅格对应的样本中的每个样本包括的n个波束的电平测量值计算的所述n个波束的电平测量值的平均值。
  11. 如权利要求5-10任一项所述的方法，其特征在于，所述第一栅格的半径是根据所述第一栅格对应的样本中的每个样本包括的所述n个波束的电平测量值与所述第一栅格的中心坐标确定的。
  12. 如权利要求11所述的方法，其特征在于，所述第一栅格的半径为半径集合中的最大距离，所述半径集合包括所述第一栅格对应的样本中的任意一个样本包括的n个波束的电平测量值与所述第一栅格的中心坐标的距离。
  13. 如权利要求1-12任一项所述的方法，其特征在于，在所述第一时间段内对应所述第一栅格的上行流量是根据所述第二数据集合中包括上行流量测量值的数据确定的；
    在所述第一时间段内对应所述第一栅格的下行流量是根据所述第二数据集合中包括下行流量测量值的数据确定的。
  14. 如权利要求1-13任一项所述的方法，其特征在于，还包括：
    向服务器发送在所述第一时间段内对应所述第一栅格的上行流量或下行流量。
  15. 一种确定流量统计结果的装置，其特征在于，该装置包括：
    收发单元，用于获取第一数据集合，所述第一数据集合包括在第一时间段被采集的多个数据，每个数据包括流量测量值和n个波束的电平测量值，所述流量测量值包括上行流量测量值和/或下行流量测量值；
    处理单元，用于根据每个数据的n个波束的电平测量值和第一栅格的中心坐标确定所述第一数据集合中与所述第一栅格关联的第二数据集合，所述第一栅格的中心坐标用n个波束的电平值表示；根据所述第二数据集合中每个数据包括的流量测量值确定在所述第一时间段内对应所述第一栅格的上行流量或下行流量。
  16. 如权利要求15所述的装置，其特征在于，所述收发单元还用于获取所述n维波束空间中的多个栅格的各栅格分别对应的中心坐标和半径，所述多个栅格包括所述第一栅格。
  17. 如权利要求16所述的装置，其特征在于，所述处理单元，用于：在确定第一数据集合中与所述第一栅格关联的第二数据集合时，确定所述第一数据集合中任意一个数据包括的n个波束的电平测量值与所述第一栅格的中心坐标的距离小于或等于所述第一栅格的半径，则该数据为所述第二数据集合中的数据；或确定所述第一数据集合中任意一个数据包括的n个波束的电平测量值与所述第一栅格的中心坐标的距离小于该n个波束的电平测量值与所述多个栅格中除所述第一栅格之外的其它栅格的中心坐标的距离，则该数据为所述第二数据集合中的数据。
  18. 如权利要求17所述的装置，其特征在于，所述处理单元，用于：确定所述第一数据集合中任意一个数据包括的n个波束的电平测量值与所述第一栅格的中心坐标的距离小于等于所述第一栅格的半径，且该数据包括的n个波束的电平测量值与第二栅格的中心坐标的距离小于等于所述第二栅格的半径，其中，所述第二栅格为所述多个栅格中除所述第一栅格之外的一个栅格；在该数据包括的n个波束的电平测量值与所述第一栅格的中心坐标的距离小于该数据包括的n个波束的电平测量值与所述第二栅格的中心坐标的距离时，确定该数据为所述第二数据集合中数据。
  19. 如权利要求15-18任一项所述的装置，其特征在于，所述收发单元，用于在获取所述n维波束空间中的多个栅格的各栅格分别对应的中心坐标时，获取训练数据集合，所述训练数据集合包括多个样本，每个样本包括n个波束的电平测量值；
    所述处理单元，用于根据所述多个样本中每个样本对应的n个波束的电平测量值获得训练数据集合对应的距离集合，所述训练数据集合对应的距离集合包括所述多个样本中每个样本对应的n个波束的电平测量值中的任意两组n个波束的电平测量值的距离；根据所述训练数据集合对应的距离集合确定所述多个栅格中的各栅格分别对应的样本，其中，每个栅格对应的样本中的任意两个样本中的各样本包括的n个波束的电平测量值的距离满足预设距离条件；根据每个栅格对应的样本确定各栅格分别对应的中心坐标，其中，所述第一栅格的中心坐标是根据所述第一栅格对应的样本确定的。
  20. 如权利要求15-18任一项所述的装置，其特征在于，所述收发单元，用于在获取所述n维波束空间中的多个栅格的各栅格分别对应的中心坐标时，获取训练数据集合，所述训练数据集合包括多个样本，每个样本包括流量测量值和n个波束的电平测量值；
    所述处理单元，用于根据所述多个样本中每个样本对应的n个波束的电平测量值获得训练数据集合对应的距离集合，所述训练数据集合对应的距离集合包括所述多个样本中每个样本对应的n个波束的电平测量值中的任意两组n个波束的电平测量值的距离；根据所 述训练数据集合对应的距离集合确定多个候选栅格中各候选栅格分别对应的样本，其中，每个候选栅格对应的样本中的任意两个样本中的各样本包括的n个波束的电平测量值的距离满足预设距离条件；根据每个候选栅格对应的样本中每个样本包括的流量测量值，确定所述多个候选栅格中每个候选栅格对应的流量统计值；根据所述多个候选栅格中每个候选栅格对应的流量统计值确定满足预设流量条件的候选栅格，将满足预设流量条件的候选栅格作为所述n维波束空间中的多个栅格；根据所述多个栅格中每个栅格对应的样本确定各栅格分别对应的中心坐标，其中，所述第一栅格的中心坐标是根据所述第一栅格对应的样本确定的。
  21. 如权利要求20所述的装置，其特征在于，每个样本中的流量测量值包括上行流量测量值和/或下行流量测量值；
    所述第一栅格对应的流量统计值包括所述第一栅格对应的上行流量统计值和/或所述第一栅格对应的下行流量统计值；
    所述第一栅格对应的上行流量统计值是根据所述第一栅格对应的样本中包括上行流量测量值的样本确定的；和/或所述第一栅格对应的下行流量统计值是根据所述第一栅格对应的样本中包括下行流量测量值的样本确定的；
    所述第一栅格为所述多个候选栅格中满足预设流量条件的候选栅格中的任一栅格，所述第一栅格对应的流量统计值满足预设流量条件是指所述第一栅格对应的上行流量统计值大于等于预设上行流量阈值，和/或所述第一栅格对应的下行流量统计值大于等于预设下行流量阈值。
  22. 如权利要求20所述的装置，其特征在于，所述多个栅格为k1个上行流量统计值分别对应的候选栅格和k2个下行流量统计值分别对应的候选栅格的交集；
    其中，所述k1个上行流量统计值之和与上行总流量统计值的比值大于等于第一阈值，所述k2个下行流量统计值之和与下行总流量统计值的比值大于等于第二阈值，k1和k2为正整数；
    所述k1个上行流量统计值根据从大到小的顺序从所述多个候选栅格中每个候选栅格对应的上行流量统计值中确定，所述k2个下行流量统计值根据从大到小的顺序从所述多个候选栅格中每个候选栅格对应的下行流量统计值中确定，所述上行总流量是指所述多个样本中包括的上行流量测量值之和，所述下行总流量是指所述多个样本中包括的下行流量测量值之和；
    所述第一栅格为所述多个候选栅格中满足预设流量条件的候选栅格中的任一栅格，所述第一栅格对应的流量统计值满足预设流量条件是指所述第一栅格对应的上行流量统计值为所述k1个上行流量统计值中的一个，且所述第一栅格对应的下行流量统计值为所述k2个下行流量统计值中的一个；
    其中，所述第一栅格对应的上行流量统计值是指所述第一栅格对应的样本中包括的上行流量测量值之和；所述第一栅格对应的下行流量统计值是指所述第一栅格对应的样本中包括的下行流量值之和。
  23. 如权利要求20所述的装置，其特征在于，所述多个栅格为k1个上行流量统计值分别对应的候选栅格和k2个下行流量统计值分别对应的候选栅格的并集；
    其中，所述k1个上行流量统计值之和与上行总流量统计值的比值大于等于第一阈值，所述k2个下行流量统计值之和与下行总流量统计值的比值大于等于第二阈值，k1和k2为 正整数；
    所述k1个上行流量统计值根据从大到小的顺序从所述多个候选栅格中每个候选栅格对应的上行流量统计值中确定，所述k2个下行流量统计值根据从大到小的顺序从所述多个候选栅格中每个候选栅格对应的下行流量统计值中确定，所述上行总流量是指所述多个样本中包括的上行流量测量值之和，所述下行总流量是指所述多个样本中包括的下行流量测量值之和；
    所述第一栅格为所述多个候选栅格中满足预设流量条件的候选栅格中的任一栅格，所述第一栅格对应的流量统计值满足预设流量条件是指所述第一栅格对应的上行流量统计值为所述k1个上行流量统计值中的一个，或所述第一栅格对应的下行流量统计值为所述k2个下行流量统计值中的一个；
    其中，所述第一栅格对应的上行流量统计值是指所述第一栅格对应的样本中包括的上行流量值之和；所述第一栅格对应的下行流量统计值是指所述第一栅格对应的样本中包括的下行流量值之和。
  24. 如权利要求19-23任一项所述的装置，其特征在于，所述第一栅格的中心坐标为根据所述第一栅格对应的样本中的每个样本包括的n个波束的电平测量值计算的所述n个波束的电平测量值的平均值。
  25. 如权利要求19-24任一项所述的装置，其特征在于，所述第一栅格的半径是根据所述第一栅格对应的样本中的每个样本包括的所述n个波束的电平测量值与所述第一栅格的中心坐标确定的。
  26. 如权利要求25所述的装置，其特征在于，所述第一栅格的半径为半径集合中的最大距离，所述半径集合包括所述第一栅格对应的样本中的任意一个样本包括的n个波束的电平测量值与所述第一栅格的中心坐标的距离。
  27. 如权利要求15-26任一项所述的装置，其特征在于，在所述第一时间段内对应所述第一栅格的上行流量是根据所述第二数据集合中包括上行流量测量值的数据确定的；
    在所述第一时间段内对应所述第一栅格的下行流量是根据所述第二数据集合中包括下行流量测量值的数据确定的。
  28. 如权利要求15-27任一项所述的装置，其特征在于，所述收发单元，用于向服务器发送在所述第一时间段内对应所述第一栅格的上行流量或下行流量。
  29. 一种装置，其特征在于，包括处理器和接口电路，所述接口电路用于接收来自所述通信装置之外的其它通信装置的信号并传输至所述处理器或将来自所述处理器的信号发送给所述通信装置之外的其它通信装置，所述处理器通过逻辑电路或执行代码指令用于实现如权利要求1至14中任一项所述的方法。
  30. 一种计算机可读存储介质，其特征在于，所述存储介质中存储有计算机程序或指令，当所述计算机程序或指令被通信装置执行时，实现如权利要求1至14中任一项所述的方法。
PCT/CN2022/092285 2021-05-18 2022-05-11 一种确定流量统计结果的方法及装置 WO2022242530A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP22803852.7A EP4319245A1 (en) 2021-05-18 2022-05-11 Method and apparatus for determining traffic counting result
US18/513,811 US20240098009A1 (en) 2021-05-18 2023-11-20 Method and apparatus for determining traffic statistics result

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110541055.3A CN115379471A (zh) 2021-05-18 2021-05-18 一种确定流量统计结果的方法及装置
CN202110541055.3 2021-05-18

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/513,811 Continuation US20240098009A1 (en) 2021-05-18 2023-11-20 Method and apparatus for determining traffic statistics result

Publications (1)

Publication Number Publication Date
WO2022242530A1 true WO2022242530A1 (zh) 2022-11-24

Family

ID=84058349

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/092285 WO2022242530A1 (zh) 2021-05-18 2022-05-11 一种确定流量统计结果的方法及装置

Country Status (4)

Country Link
US (1) US20240098009A1 (zh)
EP (1) EP4319245A1 (zh)
CN (1) CN115379471A (zh)
WO (1) WO2022242530A1 (zh)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102932848A (zh) * 2012-10-11 2013-02-13 北京拓明科技有限公司 一种基于栅格辅助的网络分流方法
CN104244446A (zh) * 2013-06-17 2014-12-24 华为技术有限公司 获得无线局域网部署信息的方法及装置
CN106998556A (zh) * 2017-03-17 2017-08-01 北京邮电大学 一种构建无线网络业务分布地图的系统及实现方法
CN107580337A (zh) * 2016-07-05 2018-01-12 中兴通讯股份有限公司 一种热点区域识别方法和装置
CN109150647A (zh) * 2017-06-28 2019-01-04 大唐移动通信设备有限公司 一种网络流量监控方法及装置
US10652115B1 (en) * 2016-08-12 2020-05-12 Amazon Technologies, Inc. Multi-source network traffic analysis tool

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102932848A (zh) * 2012-10-11 2013-02-13 北京拓明科技有限公司 一种基于栅格辅助的网络分流方法
CN104244446A (zh) * 2013-06-17 2014-12-24 华为技术有限公司 获得无线局域网部署信息的方法及装置
CN107580337A (zh) * 2016-07-05 2018-01-12 中兴通讯股份有限公司 一种热点区域识别方法和装置
US10652115B1 (en) * 2016-08-12 2020-05-12 Amazon Technologies, Inc. Multi-source network traffic analysis tool
CN106998556A (zh) * 2017-03-17 2017-08-01 北京邮电大学 一种构建无线网络业务分布地图的系统及实现方法
CN109150647A (zh) * 2017-06-28 2019-01-04 大唐移动通信设备有限公司 一种网络流量监控方法及装置

Also Published As

Publication number Publication date
CN115379471A (zh) 2022-11-22
US20240098009A1 (en) 2024-03-21
EP4319245A1 (en) 2024-02-07

Similar Documents

Publication Publication Date Title
WO2020042081A1 (en) Method and apparatus for location services
WO2020220847A1 (zh) 测量上报的方法与装置
US11451971B2 (en) Networking method, networking apparatus, network access method, and user equipment for coordinated multiple points transmission/reception
US10880854B2 (en) Intelligent base station with capability to identify three-dimensional environment, method for determining location thereof and storage medium
WO2020113845A1 (zh) 小区经纬度预测方法、装置、服务器、基站及存储介质
CN111586742A (zh) 一种定位信息上报的方法及装置
CN109803273B (zh) 天馈系统调整方法、装置、电子设备及存储介质
WO2022017012A1 (zh) 一种网络配置方法及装置
CN111867049A (zh) 定位方法、装置及存储介质
CN108632849B (zh) 一种天馈参数的调整方法、装置及设备
CN109963288B (zh) 基站的评估方法及装置
WO2021022479A1 (zh) 波束赋形方法、装置、无线接入网设备及可读存储介质
CN114762402A (zh) 一种定位方法及装置
WO2021057397A1 (zh) 一种信号测量方法、终端及网络侧设备
WO2021249109A1 (zh) 通信方法及装置
WO2022242530A1 (zh) 一种确定流量统计结果的方法及装置
WO2018121439A1 (zh) 一种直射径判断方法及装置
CN113438733A (zh) 基于5g和wifi实现室内定位的系统、方法及电子设备
CN116112959B (zh) 协同感知簇确定方法、装置、电子设备及可读存储介质
WO2020134522A1 (zh) 小区簇划分方法及电子设备
CN113228760B (zh) 利用多个接入点进行定位
EP3679732B1 (en) Network access node and methods thereof
CN115053585A (zh) 定位方法及装置
CN114339913B (zh) 无线网络的邻小区更新方法、装置、介质及电子设备
CN104469834A (zh) 一种业务仿真感知评价方法及系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22803852

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2022803852

Country of ref document: EP

ENP Entry into the national phase

Ref document number: 2022803852

Country of ref document: EP

Effective date: 20231027

NENP Non-entry into the national phase

Ref country code: DE