Wireless environment quality prediction method and device and storage medium

Abstract

The invention provides a wireless environment quality prediction method and device and a storage medium, and the method comprises the steps: determining a remote radio unit combination according to the arrival time of a remote radio unit, carrying out the data classification of the remote radio unit combination with the uplink measurement number greater than a preset classification threshold, obtaining the classification data, constructing a grid based on the classification data, and carrying out the prediction of the quality of a wireless environment. The method comprises the following steps of: acquiring a plurality of grids, positioning historical uplink measurement data of user equipment to a specific target grid in the grids to obtain a historical movement track of the user equipment, associating historical wireless environment measurement data to the target grids, and generating a wireless environment state of each target grid, so that the wireless environment state of each target grid can be determined according to the target arrival time reported by the user equipment in real time. According to the method, the predicted motion trail of the user equipment is predicted from the grids, and the wireless environment quality on the predicted motion trail is predicted, so that the time when the user equipment enters and exits the weak field area and the wireless signal change of a future path can be determined, and data support is provided for the user equipment to make a response and process in advance.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a method, device and storage medium for predicting wireless environment quality. Background Art

[0002] With the continuous development of communication technology, 5G technology has been widely used in the toB field, and many factories have also accelerated their digital transformation. At present, there are many automatically running user equipment (UE) in factories, mines, docks and other scenes, such as unmanned cars, which are equipped with cameras and need to collect video and audio information in real time to monitor the surrounding environment for the automatic and normal operation of UE. However, in some weak field areas, due to poor signal quality, serious video packet loss and unclear video and audio, monitoring is affected, and the reliability and deterministic latency of UE cannot be guaranteed. Summary of the invention

[0003] The embodiments of the present application provide a method, device and storage medium for predicting wireless environment quality, so as to at least solve the problem in the related art that the reliability of user equipment operation is affected due to the inability to predict the wireless environment quality in advance.

[0004] According to an embodiment of the present application, a method for predicting wireless environment quality is provided, including:

[0005] Based on the uplink measurement of each remote radio unit, a remote radio unit combination is determined from the multiple remote radio units; wherein the remote radio unit combination includes at least two remote radio units; and the uplink measurement includes at least arrival time;

[0006] Classifying the radio remote unit combinations whose number of uplink measurements is greater than a preset classification threshold to obtain classified data, and constructing a grid based on the classified data; wherein the preset classification threshold is greater than or equal to 2;

[0007] Acquire historical measurement data of the user equipment, the historical measurement data including historical uplink measurement data and historical wireless environment measurement data, locate the historical uplink measurement data to target grids in the grid, and generate a historical movement trajectory of the user equipment according to the time sequence of the historical uplink measurement data;

[0008] Associating the historical wireless environment measurement data with the target grid to generate a wireless environment state of the target grid;

[0009] Determine a predicted motion trajectory of the user equipment according to the target arrival time reported in real time by the user equipment and the historical motion trajectory, and predict the wireless environment quality of the user equipment according to the predicted motion trajectory and the wireless environment state;

[0010] Optionally, based on uplink measurement of each remote radio unit, determining a remote radio unit combination among the multiple remote radio units includes:

[0011] Determining a set of remote radio units based on uplink measurements of each remote radio unit;

[0012] Determining a reference remote radio unit from the set of remote radio units;

[0013] determining at least one first target remote radio frequency unit from the remote radio frequency unit set according to the reference remote radio frequency unit, and taking the reference remote radio frequency unit and the first target remote radio frequency unit as the remote radio frequency unit combination;

[0014] Optionally, the uplink measurement further includes a reference signal received power, and determining a reference remote radio unit from the remote radio unit set includes:

[0015] Determine a second target remote radio unit having the largest number of occurrences of the remote radio unit identifier in the remote radio unit set;

[0016] If the number of the second target remote radio unit is one, using the second target remote radio unit as the reference remote radio unit;

[0017] If there are multiple second target remote radio units, determining a remote radio unit with the largest reference signal received power among the multiple second target remote radio units as the reference remote radio unit;

[0018] Optionally, determining at least one first target remote radio frequency unit from the remote radio frequency unit set according to the reference remote radio frequency unit includes:

[0019] respectively calculating the modulus of the arrival time difference between any remote radio unit in the remote radio unit set and the reference remote radio unit, and sorting them from small to large;

[0020] Determine the top N corresponding radio remote units as the first target radio remote units, where N is greater than or equal to 1;

[0021] Optionally, determining a set of remote radio units based on uplink measurement of each remote radio unit includes:

[0022] Extracting a user equipment identifier, a base station identifier, and a cell identifier carried in the uplink measurement; the base station identifier includes one of a 3G base station identifier, a 4G base station identifier, and a 5G base station identifier;

[0023] Determine the set of remote radio units under each combination of the user equipment identifier, the base station identifier and the cell identifier respectively;

[0024] Wherein, for any combination of the user equipment identifier, the base station identifier, and the cell identifier, determining the radio remote unit set includes:

[0025] sorting the collected uplink measurements by time;

[0026] According to the data processing time window, the uplink measurement is divided into M time windows;

[0027] For the uplink measurement in each of the time windows, counting the number of occurrences of each corresponding radio remote unit identifier;

[0028] Determining the remote radio unit set according to the remote radio units whose occurrence times are greater than a preset threshold;

[0029] Optionally, classifying the radio remote unit combinations whose number of uplink measurements is greater than a preset classification threshold to obtain classified data, and constructing a grid based on the classified data, including:

[0030] Determine a combination of remote radio units whose number of uplink measurements is greater than a preset classification threshold;

[0031] Get the grid index;

[0032] Grouping the radio remote unit combinations according to the grid index to obtain X data subsets;

[0033] Get the target cluster number;

[0034] Clustering the data subsets according to the target number of clusters, and constructing a grid for the clustered data subsets;

[0035] Optionally, get the target cluster number, including:

[0036] Obtain the grid granularity and the inter-station spacing of the radio remote units;

[0037] Determine the target cluster number according to the station spacing and the grid granularity;

[0038] or,

[0039] respectively obtaining the modulus of arrival time differences between a reference remote radio unit and other remote radio units in the remote radio unit combination;

[0040] Obtaining a preset difference distribution interval and a threshold value for each interval;

[0041] Taking the difference distribution interval in which the number of moduli of arrival time differences is greater than or equal to the threshold value as the target difference distribution interval;

[0042] Counting the number of target difference distribution intervals, and using the number of target difference distribution intervals as the target cluster number;

[0043] Optionally, locating the historical uplink measurement data to target grids in the grids respectively includes:

[0044] Positioning the historical uplink measurement data to positioning grids respectively according to grid indexes;

[0045] Determine the positioning grid having the smallest Euclidean distance to the user equipment as the target grid;

[0046] Optionally, after determining that the positioning grid having the smallest Euclidean distance to the user equipment is the target grid, the method further includes:

[0047] Acquire the residence time of the user equipment in the target grid;

[0048] Obtaining a grid identifier of a previous hop of the user equipment;

[0049] Acquire a target probability of the user equipment in the target grid;

[0050] Recording the dwell time, the grid identifier of the previous jump and the target probability in the target grid;

[0051] Optionally, associating the historical wireless environment measurement data with the target grid to generate the wireless environment state of the target grid includes:

[0052] Get the timestamp corresponding to the measurement time;

[0053] Associating the historical wireless environment measurement data with the timestamp satisfying a preset time parameter to the target grid;

[0054] Get the signal status classification interval;

[0055] Taking the target signal state satisfied by the historical wireless environment measurement data as the wireless environment state of the target grid;

[0056] Optionally, predicting the radio environment quality of the user equipment according to the predicted motion trajectory and the radio environment state includes:

[0057] Determine the wireless environment state of the future Y hops according to the predicted motion trajectory;

[0058] The wireless environment quality of the user equipment is determined according to the wireless environment status of the Y hops.

[0059] According to another embodiment of the present application, a wireless environment quality prediction device is provided, including:

[0060] A combination determination module, configured to determine a remote radio unit combination among a plurality of remote radio units based on uplink measurements of each remote radio unit; wherein the remote radio unit combination includes at least two remote radio units; and the uplink measurements include at least arrival time;

[0061] A grid construction module, used to classify the radio remote unit combinations whose number of uplink measurements is greater than a preset classification threshold, obtain classification data, and construct a grid based on the classification data; wherein the preset classification threshold is greater than or equal to 2;

[0062] A trajectory positioning module, used to obtain historical measurement data of the user equipment, the historical measurement data including historical uplink measurement data and historical wireless environment measurement data, locate the historical uplink measurement data to target grids in the grid, and generate a historical movement trajectory of the user equipment according to the time sequence of the historical uplink measurement data;

[0063] A wireless environment association module, used to associate the historical wireless environment measurement data with the target grid to generate the wireless environment state of the target grid;

[0064] The prediction module is used to determine the predicted motion trajectory of the user equipment according to the target arrival time reported in real time by the user equipment and the historical motion trajectory, and predict the wireless environment quality of the user equipment according to the predicted motion trajectory and the wireless environment state.

[0065] According to another embodiment of the present application, a storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0066] According to another embodiment of the present application, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0067] Through the present application, a combination of radio frequency remote units is determined according to the arrival time of the radio frequency remote units, data classification is performed on the combination of radio frequency remote units whose number of uplink measurements is greater than a preset classification threshold to obtain classified data, and a grid is constructed based on the classified data, and the historical uplink measurement data of the user device is located to a specific target grid in the grid to obtain the historical motion trajectory of the user device, and then the historical wireless environment measurement data is associated with the target grid to generate the wireless environment state of each target grid, so that the predicted motion trajectory of the user device can be predicted from the grid according to the target arrival time reported by the user device in real time, and the wireless environment quality on the motion trajectory can be predicted. Therefore, the problem in the related technology that the wireless environment quality cannot be predicted in advance, thereby affecting the operating reliability of the user device, can be solved, and the periodic motion trajectory of the user device can be predicted, and then the time of entering and exiting the weak field area and the future path wireless signal changes can be determined, thereby providing data support for the user device to respond and process in advance. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0069] Figure 1 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application;

[0070] Figure 2 This is a system architecture diagram of a wireless environment quality prediction method provided by an embodiment of the present application;

[0071] Figure 3 is a system architecture diagram of a wireless environment quality prediction method provided by another embodiment of the present application;

[0072] Figure 4 It is a flowchart of a wireless environment quality prediction method provided by an embodiment of the present application;

[0073] Figure 5 is a flowchart of a wireless environment quality prediction method provided by another embodiment of the present application;

[0074] Figure 6 It is a structural diagram of a wireless environment quality prediction device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0075] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0076] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0077] Example 1

[0078] The method embodiment provided in the first embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 1 is a hardware structure block diagram of a mobile terminal of a wireless environment quality prediction method according to an embodiment of the present application. Figure 1 As shown, the mobile terminal 10 may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data. Optionally, the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is for illustration only and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0079] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the wireless environment quality prediction method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the mobile terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0080] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the mobile terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0081] The embodiment of the present application can be implemented in a network prediction module, which is a logic module that can be deployed on a base station, such as a 4G or 5G base station (e.g. Figure 2 ), or it can be deployed on computing base stations (or edge computing nodes) outside 4G / 5G base stations (such as Figure 3 ).

[0082] The present application embodiment can be run on Figure 2 In the network architecture shown in Figure 2 As shown, the network architecture includes: a base station and an application server, wherein the base station and the application server establish a communication connection, a network prediction module is configured in the base station, the network prediction module obtains measurements from the base station side, builds a logical grid of the physical environment based on the uplink measurements, learns the user's movement trajectory and wireless environment changes, and the network prediction module notifies the base station of the wireless environment status of the user's future path.

[0083] The present application embodiment can also be run on Figure 3 In the network architecture shown in Figure 3 As shown, the network architecture includes: a base station, a computing power base station and an application server, wherein the computing power base station establishes communication connections with the base station and the application server respectively. The network prediction module obtains service indicators from the application server or gateway, such as latency, packet loss rate, and if it is a video application, the video freeze situation can be obtained; the network prediction module associates the above indicators obtained with the user device and the logical grid; the network prediction module notifies the application server of the wireless environment status of the future path of the user device, as well as the service changes.

[0084] In this embodiment, a wireless environment quality prediction method running on the above mobile terminal or network architecture is provided. Figure 4 is a flow chart of a wireless environment quality prediction method according to an embodiment of the present application, such as Figure 4 As shown, the process includes the following steps:

[0085] Step S402: determining a remote radio unit combination from a plurality of remote radio units based on uplink measurement of each remote radio unit; wherein the remote radio unit combination includes at least two remote radio units; and the uplink measurement includes at least arrival time.

[0086] Each base station includes multiple radio remote units (pRRUs). The uplink (UL) measurement parameters of the pRRUs may include multiple parameters, such as the arrival time (TA), the channel sounding reference signal (SRS), and the SRS specifically includes the reference signal receiving power (RSRP).

[0087] In one embodiment, based on the uplink measurement of each remote RF unit, a remote RF unit combination is determined among multiple remote RF units, including: determining a remote RF unit set based on the uplink measurement of each remote RF unit, determining a reference remote RF unit from the remote RF unit set, determining at least one first target remote RF unit from the remote RF unit set according to the reference remote RF unit, and using the reference remote RF unit and the first target remote RF unit as the remote RF unit combination.

[0088] In this embodiment, all the remote radio units that send uplink measurements may first be determined as a remote radio unit set, and then a reference remote radio unit may be determined from the remote radio units.

[0089] When determining the reference remote radio frequency unit, a second target remote radio frequency unit with the largest number of occurrences of the remote radio frequency unit identifier may be determined from the remote radio frequency unit set, and if the number of the second target remote radio frequency unit is one, the second target remote radio frequency unit may be used as the reference remote radio frequency unit. If the number of the second target remote radio frequency units is multiple, a remote radio frequency unit with the largest reference signal received power among the multiple second target remote radio frequency units is determined as the reference remote radio frequency unit.

[0090] In one embodiment, at least one first target remote RF unit is determined from a remote RF unit set according to a reference remote RF unit, comprising: respectively calculating the modulus of the arrival time difference between any remote RF unit in the remote RF unit set and the reference remote RF unit, and sorting them from small to large, and determining the first N corresponding remote RF units in the sorting as the first target remote RF unit, wherein N is greater than or equal to 1.

[0091] In this embodiment, after determining the reference remote radio unit, the modulus (ΔTA) of the difference between the TA of other remote radio units and the TA of the reference remote radio unit may be calculated respectively (ΔTA in subsequent embodiments may be regarded as the value after taking the modulus of the difference between the two TAs). The smaller the value, the better the signal quality. Therefore, the first N in ascending order are selected, where N is greater than or equal to 1. For example, N may be 3, i.e., three corresponding remote radio units are selected as the first target remote radio unit. The three remote radio units may be referred to as the first strongest remote radio unit, the second strongest remote radio unit and the third strongest remote radio unit of the reference remote radio unit.

[0092] It should be noted that the larger the value of N is, the better it is. The amount of data calculation and the deviation between multiple TA differences need to be considered comprehensively. The above N of 3 is only an example and does not represent a limitation thereto.

[0093] Of course, in the above process, each remote radio unit can be distinguished by the identification information of the remote radio unit, such as the ID of the remote radio unit. For example, the user equipment identifier (UE ID), base station identifier and cell identifier (cell ID) carried by the uplink measurement are extracted, and the base station identifier can be one of the 3G base station identifier (NB ID), 4G base station identifier (eNB ID) and 5G base station identifier (gNB ID), without limitation.

[0094] In one embodiment, determining a set of remote radio units based on uplink measurement of each remote radio unit includes: determining a set of remote radio units for each combination of user equipment identifier, base station identifier and cell identifier.

[0095] Wherein, for any combination of a user equipment identifier, a base station identifier, and a cell identifier, determining a set of radio remote units includes: sorting the collected uplink measurements by time, dividing the uplink measurements into M time windows according to a data processing time window (data Window), counting the number of occurrences of each corresponding radio remote unit identifier (pRRU ID) for the uplink measurements in each time window, and determining a set of radio remote units according to the number of occurrences of the radio remote units greater than a preset threshold. Wherein, the value of M is not limited and can be set as needed.

[0096] In this embodiment, the data can be screened. First, the uplink measurement is divided into M time windows through the data processing time window. In each time window, the pRRU whose pRRU ID appears more than a preset threshold is determined as a pRRU set. The preset threshold can be determined as needed without restriction. The screened pRRU set can be used for subsequent grid construction more accurately.

[0097] Step S404, classifying the radio remote unit combinations whose number of uplink measurements is greater than a preset classification threshold, obtaining classified data, and constructing a grid based on the classified data; wherein the preset classification threshold is greater than or equal to 2.

[0098] In one embodiment, data classification is performed on a radio remote unit combination whose number of uplink measurements is greater than a preset classification threshold to obtain classified data, and a grid is constructed based on the classified data, including: determining a radio remote unit combination whose number of uplink measurements is greater than a preset classification threshold, obtaining a grid index, grouping the radio remote unit combination according to the grid index to obtain X data subsets, obtaining a target number of clusters, clustering the data subsets according to the target number of clusters, and constructing a grid for the clustered data subsets.

[0099] Optionally, obtaining the target cluster number may include at least the following two methods:

[0100] The first method is to obtain the grid granularity and the inter-station distance of the radio remote unit, and determine the number of target clusters according to the inter-station distance and the grid granularity.

[0101] For example, the pRRU station spacing parameter is d meters, the grid granularity is p meters (the parameter can be set, the value is 1m, 2m, 5m, 10m...), the target cluster number is

[0102] The second method is to obtain the modulus of the arrival time difference between the reference remote radio frequency unit and other remote radio frequency units in the remote radio frequency unit combination, obtain a preset difference distribution interval and a threshold value for each interval, and use the difference distribution interval in which the number of moduli of the arrival time difference is greater than or equal to the threshold value as the target difference distribution interval, count the number of target difference distribution intervals, and use the number of target difference distribution intervals as the target cluster number.

[0103] The raster data obtained by clustering the data subsets by any of the above methods is more accurate.

[0104] Step S406, obtaining historical measurement data of the user equipment, the historical measurement data including historical uplink measurement data and historical wireless environment measurement data, locating the historical uplink measurement data to target grids in the grid, and generating a historical movement trajectory of the user equipment according to the time sequence of the historical uplink measurement data.

[0105] In one embodiment, locating the historical uplink measurement data to target grids in the grids includes: locating the historical uplink measurement data to positioning grids according to grid indexes, and determining the positioning grid with the smallest Euclidean distance to the user equipment as the target grid.

[0106] In this embodiment, by calculating the Euclidean distance, each piece of historical uplink measurement data of the UE can be more accurately located at the target grid. It should be understood that the target grid is the grid corresponding to the historical uplink measurement data.

[0107] In one embodiment, after determining that the positioning grid with the smallest Euclidean distance to the user device is the target grid, the method also includes: obtaining the residence time (staytime) of the user device in the target grid, obtaining the grid identifier (grid ID) of the previous hop of the user device, obtaining the target probability (probability) of the user device in the target grid, and recording the residence time, the grid identifier of the previous hop and the target probability in the target grid.

[0108] In this embodiment, the residence time of the UE in the target grid, the grid identifier of the previous hop and the target probability are recorded in the target grid, which can facilitate the subsequent prediction of the motion trajectory of the next hop through the grid.

[0109] Step S408: Associating the historical wireless environment measurement data with the target grid to generate the wireless environment status of the target grid.

[0110] In one embodiment, historical wireless environment measurement data is associated with a target grid to generate a wireless environment state of the target grid, including: obtaining a timestamp corresponding to the measurement time, associating historical wireless environment measurement data that satisfies a preset time parameter with the timestamp to the target grid, obtaining a signal state classification interval, and using the target signal state satisfied by the historical wireless environment measurement data as the wireless environment state of the target grid.

[0111] In this embodiment, the historical wireless environment measurement data (referred to as wireless environment measurement) can be divided into good, medium, and poor states according to the signal quality. For example, the uplink signal to interference plus noise ratio (SINR) can be good, medium, and poor respectively: 15dB, 5dB, and 0dB. That is, the uplink wireless environment state corresponds to a good signal quality of (15dB, ++), the state corresponds to a medium signal quality of (5dB, 15dB], and the state corresponds to a poor signal quality of (--, 5dB].

[0112] Downlink RSRP good, medium and poor can be: -75dBm, -85dBm, -96dBm. That is, the downlink wireless environment state is good and the corresponding signal quality is: (-75dBm, ++), the state is medium and the corresponding signal quality is: (-85dBm, -75dBm], and the state is poor and the corresponding signal quality is: (--, -85dBm].

[0113] There will be multiple UL (uplink) and DL (downlink) signal status records in a grid, and the one with the most occurrences is taken as the grid status. If the signal status is poor, it is considered to be a weak network environment or weak network area.

[0114] Step S410, determining a predicted motion trajectory of the user equipment according to the target arrival time and the historical motion trajectory reported in real time by the user equipment, and predicting the wireless environment quality of the user equipment according to the predicted motion trajectory and the wireless environment state.

[0115] Through the present application, a combination of radio frequency remote units is determined according to the arrival time of the radio frequency remote units, data classification is performed on the combination of radio frequency remote units whose number of uplink measurements is greater than a preset classification threshold to obtain classified data, and a grid is constructed based on the classified data, and the historical uplink measurement data of the user device is located to a specific target grid in the grid to obtain the historical motion trajectory of the user device, and then the historical wireless environment measurement data is associated with the target grid to generate the wireless environment state of each target grid, so that the predicted motion trajectory of the user device can be predicted from the grid according to the target arrival time reported by the user device in real time, and the wireless environment quality on the motion trajectory can be predicted. Therefore, the problem in the related technology that the wireless environment quality cannot be predicted in advance, thereby affecting the operating reliability of the user device, can be solved, and the periodic motion trajectory of the user device can be predicted, and then the time of entering and exiting the weak field area and the future path wireless signal changes can be determined, thereby providing data support for the user device to respond and process in advance.

[0116] In one embodiment, predicting the wireless environment quality of the user equipment according to the predicted motion trajectory and the wireless environment state includes: determining the wireless environment state of Y hops in the future according to the predicted motion trajectory, and determining the wireless environment quality of the user equipment according to the wireless environment state of Y hops.

[0117] This application can predict the periodic motion trajectory of user equipment, the time of entering and exiting a weak field, and future path wireless signal changes, so that the application end can react and process in advance, reduce end-to-end service delay and packet loss rate, and ensure network determinism. At the same time, it can enable the base station to perceive network coverage in advance, thereby optimizing measurement control, switching parameters, and scheduling parameters.

[0118] Next, the wireless environment quality prediction method is described in detail in conjunction with a specific embodiment. Figure 5 ,include:

[0119] Step 1: Data processing.

[0120] Data processing mainly includes pRRU combination selection. Obtain pRRU (also known as TRP transmission and reception point) uplink measurements from the base station: UL TA and UL SRS-RSRP. Select the benchmark pRRU ID according to the pRRU ID with the most occurrences or the smallest TA, and then select the first / second / third strongest pRRU ID from small to large according to the TA difference (ΔTA).

[0121] Step 2: Grid construction.

[0122] Data classification (e.g., clustering) is performed on pRRU combinations whose measurement number is greater than the classification number n. The pRRU combination format is (NBID+cellID+pRRU0+pRRU1+pRRU2+pRRU3). The mean / minimum / maximum TA difference is calculated for each pRRU combination. The classification number n can be determined based on the actual physical distance + user moving speed, or based on the number of TA difference distribution intervals.

[0123] Step 3: User correlation (user path learning).

[0124] The UE (user equipment, user terminal) is associated with the grid, and the UE is taken as the object, and the measurement of the UE is located in different grids, and the movement trajectory of the UE is generated in time sequence.

[0125] Step 4: Grid correlation (wireless environment learning).

[0126] The wireless environment measurement reported by the base station is associated with the grid according to the UE and the measurement time to generate the wireless environment state of the grid.

[0127] Step 5: Grid application.

[0128] The UE is located in the grid according to the TA (arrival time) measurement reported by the UE in real time, and the future movement trajectory of the UE and the wireless environment status are obtained according to the historical information stored in the grid.

[0129] The wireless environment quality prediction method of this embodiment takes advantage of TA difference construction to more accurately mark the user's position and reduce the error of user path learning.

[0130] This method can be used in the toB field, and can also be applied to user devices with periodic motion trajectories in the toC field. This method can predict the periodic motion trajectory of the user device, the time of entering and exiting the weak field, and future path wireless signal changes, so that the application end can react and process in advance, reduce the end-to-end delay and packet loss rate of the service, and ensure the determinism of the network. At the same time, it can enable the base station to perceive the network coverage in advance, thereby optimizing measurement control, switching parameters and scheduling parameters, etc.

[0131] Next, each of the above steps is explained in detail.

[0132] Step 1: Data processing, as follows:

[0133] The network prediction module obtains the uplink measurements of the pRRU from the base station: UL TA and UL SRS-RSRP. It should be noted that the measurements here refer to measurement parameters.

[0134] The received measurements are processed as follows:

[0135] The top four pRRUs are selected for each UE ID+NBID+cellID. It should be noted that NBID can be replaced with gNBID or eNBID. In addition, if pRRUID is unique under NBID, the top four pRRUs (benchmark pRRU and top three pRRUs other than benchmark pRRU) are selected for each UE ID+NBID.

[0136] The collected measurements are sorted separately by time.

[0137] Data processing is performed according to the data processing time window dataWindow.

[0138] Filter data:

[0139] For the data in each time window, the number of times each pRRUID appears is counted. The statistical results are as follows: [pRRUID1, N1], [pRRUID2, N2], ... [pRRUID m , N m ].

[0140] Calculate the probability of each pRRUID appearing:

[0141]

[0142] pRRUs with probability less than 20% are eliminated to form a pRRU set.

[0143] The method for determining the reference pRRU is as follows: sort all pRRU IDs in the set from large to small according to the number of occurrences, and the one with the largest number of occurrences is considered as the reference pRRU ID0. If there are multiple pRRUs, the one with the largest RSRP average is taken as the reference pRRU ID0.

[0144] Method for determining the first, second, and third strongest pRRU:

[0145] ΔTA=|TAi-TA0| of other pRRU IDs in the set M and pRRU ID0 is calculated. It should be noted that ΔTA mentioned below refers to |ΔTA|.

[0146] The average ΔTAavg of the ΔTA of other pRRU IDs is calculated, and the ΔTAavg is sorted from small to large to select the first, second, and third strongest pRRU IDs. If the ΔTA is the same, the RSRP average is sorted from large to small to select the first, second, and third strongest pRRU IDs.

[0147] The data storage format is as follows:

[0148] Table 1

[0149]

[0150] It should be noted that: one record is recorded in one measurement reporting cycle; if ΔTA1, ΔTA2, and ΔTA3 are all empty, the record is deleted; if pRRUID is unique under NBID, cellID is ignored.

[0151] Optionally, during data processing, each measured reported data may also be processed as follows:

[0152] The collected measurements are sorted separately by time.

[0153] Each piece of data is processed and the combination of pRRU0+pRRU1+pRRU2+pRRU3 is selected according to the following principles:

[0154] Reference pRRU (i.e., pRRU0): The one with the smallest TA value is considered as reference pRRU ID0. If there are multiple pRRUs, the one with the largest RSRP is taken as reference pRRU ID0.

[0155] The first, second and third strongest pRRUs: calculate ΔTA=|TAi-TA0| between other pRRU IDs and pRRU ID0. Note: ΔTA mentioned below refers to |ΔTA|.

[0156] Sort ΔTAavg from small to large and select the first / second / third strongest pRRU ID. If ΔTA is the same, sort RSRP from large to small and select the first / second / third strongest pRRU ID.

[0157] Step 2: Grid construction, as follows:

[0158] According to "NBID+cellID+pRRU0+pRRU1+pRRU2+pRRU3" as the index, the data is divided into several subsets D i , each data subset D i Execute Build Raster separately.

[0159] If the information of the first, second and third strongest pRRUs is insufficient, it is necessary to fill in the information, and ΔTA is filled in with the corresponding average value ΔTAavg.

[0160] Determine the target number of K-means clustering clusters n_clusters and perform clustering.

[0161] Method 1: Based on the obtained pRRU station spacing parameters d meters, grid granularity p meters (the parameters can be set, such as 1m, 2m, 5m, 10m...),

[0162] If method 1 cannot be obtained, method 2 can be used.

[0163] Method 2: Based on the ΔTA distribution interval.

[0164] Segment ΔTA1, ΔTA2, and ΔTA3 in Table 1 according to the fixed intervals given in Table 2 below; count the number of ΔTAs ΔTANum in each interval; and take the number of intervals n that satisfy ΔTANum ≥ the threshold as the target number of clusters n_clusters.

[0165] Table 2

[0166] ΔTA distribution range ΔTA segment number [0,50) 1 [50,100) 2 [100,150) 3 [150,200) 4 [200,250) 5 [250,300) 6 [300,350) 7 [350,400) 8 [450,500) 9 [500,550) 10 [550,600) 11

[0167] If the data subset D i If the number of measurements in is greater than n_clusters, clustering is performed according to n_clusters, otherwise no clustering is performed.

[0168] The effective grid update is as follows ΔTA:

[0169] The first strongest pRRUID1: ΔTAavg1, ΔTAmin1, ΔTAmax1;

[0170] The second strongest pRRUID2: ΔTAavg2, ΔTAmin2, ΔTAmax2;

[0171] The third strongest pRRUID3: ΔTAavg3, ΔTAmin3, ΔTAmax3.

[0172] The grid index may be in the format shown in Table 3.

[0173] Table 3

[0174]

[0175] Note: ΔTAavg1, ΔTAmax1, and ΔTAmin1 represent the average, maximum, and minimum values ​​of ΔTA of pRRUID1 and pRRUID0, respectively. The same is true for the others.

[0176] Step 3 is user-related (user path learning), as follows:

[0177] UE ID:

[0178] According to Table 1 and Table 3, [NBID+cellID+pRRU0+pRRU1+pRRU2+pRRU3] locates the UE to a certain grid. If multiple grids meet the conditions, for each UE record in Table 1, according to the criterion: the Euclidean distance between UE [ΔTA1, ΔTA2, ΔTA3] and grid [ΔTAavg1, ΔTAavg2, ΔTAavg3] is the smallest, and the grid ID (gridIndex) to which each record belongs is selected.

[0179] like:

[0180] UE real-time (pRRUID1ΔTA1n, pRRUID2ΔTA2n, pRRUID3ΔTA3n) is considered to be (x n ,y n , z n );

[0181] The grid (pRRUID1ΔTA1, pRRUID2ΔTA2, pRRUID3ΔTA3) is considered to be (x, y, z);

[0182] but:

[0183] (x n ,y n , z n ) and (x, y, z)

[0184] The UE path is learned based on the time, where the time is [date+h:m:s.ms].

[0185] Each grid record records at least the UE's residence time, the UE's last hop grid ID, and the probability of the UE being in the grid, as shown in Table 4.

[0186] Table 4

[0187]

[0188] UE's dwell time:

[0189] According to the grid ID to which the UE belongs obtained by the above process, the time difference between the last record and the first record of multiple consecutive records of the UE in each grid ID is calculated. If there is only one grid ID record, the measurement reporting period is taken as the residence time.

[0190] Count the number of times each type of residence time (assuming m types) appears in the grid N i, calculate the probability of each time value occurring p represents the probability of the UE in this grid (probality).

[0191] Calculate the mean Staytime_avg for the residence time with an occurrence probability p≥90%; calculate the standard deviation Staytime_std for all times.

[0192] Probability of the UE in this grid: With the same UE previous-hop grid ID, the probability of the next-hop grid ID = the number of times entering the next-hop grid i / the number of times entering all next-hop grids.

[0193] Step 4, Grid-related (radio environment learning), specifically as follows:

[0194] The network prediction module obtains the following measurements from the base station as shown in Table 5 below:

[0195] Table 5

[0196]

[0197] Associate according to UEID + measurement time, and take the timestamp as [date + h:m:s.ms], and mark the UL / DL radio environment signal status of the grid, specifically as follows:

[0198] When the times in Table 5 and Table 1 are the same in terms of date, if the absolute value of the time difference [h:m:s..ms] satisfies <timeDiffThrd (preset parameter), make the following judgments on the data in Table 5:

[0199] Convert the radio signal quality into good, medium, and poor states.

[0200] UL SINR good, medium, poor: 15dB, 5dB, 0dB. That is, good point: (15dB, ++), medium point: (5dB, 15dB], poor point: (--, 5dB].

[0201] DL RSRP good, medium, poor: -75dBm, -85dBm, -96dBm. That is, good point: (-75dBm, ++), medium point: (-85dBm, -75dBm], poor point: (--, -85dBm].

[0202] There will be multiple UL / DL signal status records in a grid. Take the one with the most occurrences as the grid status, and the index of the grid status can be as shown in Table 6. Among them, if the signal status is poor, it is considered a weak network.

[0203] Table 6

[0204] gridIndex DL: [good, medium, poor] UL: [Good, Medium, Poor]

[0205] Step 5: Grid application, i.e. grid positioning, is as follows:

[0206] Method 1: If the UE ID in the processed scenario is fixed, query Table 4 according to the UE ID. If the UE ID exists, obtain the path information and wireless signal information according to the recorded content. Otherwise, you can try method 2.

[0207] Method 2: Find the corresponding grid based on UE real-time measurement. Specific method:

[0208] Step 51: The pRRU with the smallest TA value in the real-time measurement of the UE is taken as pRRU0, and ΔTA=|TAi-TA0| between other pRRU IDs and pRRU ID0 is calculated, and the first / second / third strongest pRRU IDs are selected according to the order of ΔTA from small to large.

[0209] Step 52, in Table 3, find a grid with the same order of "[NBID+cellID+pRRU0+pRRU1+pRRU2+pRRU3]". If there is one, go to step 53. If not, take the grid with the same combination of "[NBID+cellID+pRRU0+pRRU1+pRRU2+pRRU3]". If none is found, UE positioning fails; otherwise, go to step 53.

[0210] Step 53: According to Table 3, determine whether the UE's ΔTA is within the range of [ΔTAmin, ΔTAmax] of the grid, and retain the grid that meets the condition. If there is no such grid, the UE positioning fails; otherwise, go to step 54.

[0211] Step 54: among these grids, calculate the ΔTA Euclidean distance between it and each grid, select the grid with the smallest Euclidean distance as the positioning grid, and output the grid ID.

[0212] Step 55: Obtain path information and wireless signal information (Table 6) according to the recorded content for further application, such as predicting the wireless environment quality (i.e., network quality) of the user device. If the user device is about to enter a weak network environment, the receiving bit rate of the user device can be adjusted to reduce the network demand of the user device to meet normal data transmission, etc.

[0213] In a specific embodiment, the wireless environment quality prediction method can be used for weak network prediction, including:

[0214] Step 61: The network prediction module obtains TA and RSRP measurements from the base station, for example, according to the format and specific parameters of Table 3, the following Table 7 is obtained.

[0215] Table 7

[0216] gridIndex ΔTAavg1 ΔTAmax1 ΔTAmin1 ΔTAavg2 ΔTAmax2 ΔTAmin2 ΔTAavg3 ΔTAnax2 ΔTAmin3 4942652+pRRUID=48+pRRUID=53+pRRUID=34+pRRUID=32 54 54 54 59 59 59 112 112 112 4942652+pRRUID=48+pRRUID=36+pRRIUD=34+pRRUID=49 13 13 13 50 50 50 78 78 78

[0217] The gridIndex is: eNBID+pRRU0+pRRU1+pRRU2+pRRU3, which means that the cellID is ignored. If the pRRU is unique under the same NBID, the cellID does not need to be considered.

[0218] Step 62: According to the acquired UE measurement, Table 8 is obtained according to the format and specific parameters of Table 1. An example is as follows:

[0219] Table 8

[0220]

[0221] The UE is located in a grid according to [eNBID+pRRU0+pRRU1+pRRU2+pRRU3]. If multiple grids meet the conditions, for each UE record in the above table, according to the criterion: the Euclidean distance between UE [ΔTA1, ΔTA2, ΔTA3] and grid [ΔTAavg1, ΔTAavg2, ΔTAavg3] is the smallest, and the grid ID (gridIndex) to which each record belongs is selected.

[0222] Step 63: Create UE related grid information.

[0223] According to step 62, the UE is associated with a series of grids gridIndex in time sequence, and the following Table 9 is obtained according to the format of Table 4. The example is as follows:

[0224] Table 9

[0225]

[0226] The calculation methods of staytime and probability will not be elaborated here.

[0227] Step 64: Create grid wireless signal environment information

[0228] The network prediction module obtains the information in Table 5 from the base station, associates it according to UEID+measurement time, takes the timestamp as [date+h:m:s.ms], and then marks the UL and DL wireless environment signal states of the grid.

[0229] For example, UE 10.10.114.106 measures DL RSRP=-80dBm and UL SINR=4dB of the serving cell at 2023-03-27 18:18:13, and then locates to grid 4942652+pRRUID=48+pRRUID=36+pRRUID=34+pRRUID=49 according to UE+time.

[0230] If the uplink SINR is good, medium or poor: 15dB, 5dB, 0dB. That is, the good point: (15dB, ++), the medium point: (5dB, 15dB], the poor point: (--, 5dB]. Field information reference: the good point generally refers to 15-20, the medium point is 5-10, and the poor point is about 0.

[0231] Downlink RSRP good, medium and poor: -75dBm, -85dBm, -96dBm. That is, good point: (-75dBm, ++), medium point: (-85dBm, -75dBm], poor point: (--, -85dBm].

[0232] Then the grid DL: medium; UL: poor.

[0233] The following Table 10 is generated according to the format of Table 6. The example is as follows:

[0234] Table 10

[0235]

[0236] Step 65: Application: According to the real-time report from the UE, specifically including:

[0237] Step 651: Look up the UE ID in Table 4 or Table 9. If the UE ID exists, obtain the path information and the wireless signal information according to the recorded content. Otherwise, go to step 652.

[0238] Step 652: Take the smallest TA value in the real-time measurement of the UE as the reference pRRUID (pRRU0), calculate ΔTA=|TAi-TA0| between other pRRU IDs and pRRU ID0, sort them from small to large according to ΔTA, and select the first / second / third strongest pRRU IDs.

[0239] Step 653. In Table 3 or Table 7, find a grid that is completely consistent with the following order, in the format of [eNBID+cellID+pRRU0+pRRU1+pRRU2+pRRU3]. If so, go to step 654. If not, take the grid with the same combination of "[eNBID+cellID+pRRU0+pRRU1+pRRU2+pRRU3]". If it is not screened out, the UE positioning fails; otherwise, go to step 654.

[0240] Step 654: According to Table 3 or Table 7, determine whether the UE's ΔTA is within the range of [ΔTAmin, ΔTAmax] of the grid, and retain the grid that meets the condition. If there is no such grid, the UE positioning fails; otherwise, go to step 655.

[0241] Step 655: among these grids, calculate the ΔTA Euclidean distance between it and each grid, select the grid with the smallest Euclidean distance as the positioning grid, and output the grid ID.

[0242] Step 656: Obtain path information and wireless signal information (Table 6 or Table 10) according to the recorded content.

[0243] Step 657, enter and exit weak field time.

[0244] The position to be queried outputted according to the positioning is recorded as x.

[0245] Sequentially retrieve the UL SINR (signal to interference plus noise ratio) values ​​corresponding to the future hops. i If there are three consecutive points of UL difference at the beginning, it is considered that from x i Start entering the weak network and calculate the sum of the staytimes of all grids starting from the current position x to get t in , with precision reserved to ms. If there is no such point x i , then t in Set to an invalid value.

[0246] Continue to retrieve the UL SINR value corresponding to the future hop, starting from x j At the beginning (j≥i+3), if there are three consecutive points with good UL, it is considered that from x j Start to exit the weak network and calculate the sum of the staytime of all grids passed from the previous position x to get t out , with precision reserved to ms. If there is no such point x j , then t out Set to an invalid value. The format of the record timestamp can be as shown in Table 11.

[0247] Table 11

[0248]

[0249] Note: Timestamp refers to the timestamp when the UE reports the current measurement, and the accuracy can be retained to ms.

[0250] Step 658: When the time of entering and exiting a weak network is predicted, the network prediction module can notify the application server, such as a video application server, and adjust parameters such as bit rate and resolution in advance according to the predicted time of entering and exiting a weak network, thereby ensuring image quality and avoiding freezes.

[0251] The wireless environment quality prediction method provided in the above embodiments uses signals to construct a network grid to learn the user's mobile path and wireless environment, and provides users with end-to-end accurate guarantees of business following the network, or network following the business. For example, it can predict the periodic motion trajectory of user equipment and the time of entering and exiting the weak field, so that the application end can react and process in advance, reduce latency and packet loss rate, and ensure network certainty. At the same time, it can enable the base station to perceive the network coverage in advance, thereby optimizing measurement control, switching parameters and scheduling parameters, etc.

[0252] In a specific embodiment, the wireless environment quality prediction method can be used for base station wireless environment prediction.

[0253] Predict the wireless environment information of the UE's future path. The predicted content can open an interface to the base station side for optimization of the base station strategy. For example, Table 4 (or Table 9) notifies the wireless environment information of the current location gridIndex in the next three hops, such as ULSINR, DL RSRP, and the upcoming staytime. Then the base station's layer 3 can make the following optimizations based on the predicted wireless environment quality and the user's mobility rate:

[0254] Optimize measurement: Based on the predicted target frequency probability and target cell, the measurement control can be optimized to reduce the number of measurement frequency points, filter out high-interference cells, shorten the measurement time and avoid dropped calls.

[0255] Optimized handover: Directly trigger user handover without sending measurement control, waiting for measurement reports to be collected, and then making handover decisions, so as to avoid dropped calls on the wireless link.

[0256] Layer 2 of the base station can associate the predicted wireless environment information with the scheduling parameters, reduce the scheduling of large data blocks in weak network conditions, or increase the scheduling cycle in weak network conditions.

[0257] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0258] Example 2

[0259] In this embodiment, a wireless environment quality prediction device is also provided, which is used to implement the above embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0260] Figure 6 is a schematic diagram of the structure of a wireless environment quality prediction device provided according to an embodiment of the present application, such as Figure 6 As shown, the device comprises:

[0261] A combination determination module 602 is configured to determine a remote radio unit combination among multiple remote radio units based on uplink measurements of each remote radio unit; wherein the remote radio unit combination includes at least two remote radio units; and the uplink measurement includes at least an arrival time;

[0262] A grid construction module 604 is used to classify the radio remote unit combinations whose number of uplink measurements is greater than a preset classification threshold, obtain classification data, and construct a grid based on the classification data; wherein the preset classification threshold is greater than or equal to 2;

[0263] The trajectory positioning module 606 is used to obtain historical measurement data of the user equipment, the historical measurement data including historical uplink measurement data and historical wireless environment measurement data, locate the historical uplink measurement data to the target grid in the grid, and generate the historical movement trajectory of the user equipment according to the time sequence of the historical uplink measurement data;

[0264] A wireless environment association module 608 is used to associate the historical wireless environment measurement data with the target grid to generate the wireless environment state of the target grid;

[0265] The prediction module 610 is used to determine the predicted motion trajectory of the user equipment according to the target arrival time reported in real time by the user equipment and the historical motion trajectory, and predict the wireless environment quality of the user equipment according to the predicted motion trajectory and the wireless environment state.

[0266] The device determines a combination of radio frequency remote units according to the arrival time of the radio frequency remote units, classifies the radio frequency remote unit combinations whose number of uplink measurements is greater than a preset classification threshold, obtains classified data, constructs a grid based on the classified data, locates the historical uplink measurement data of the user equipment to a specific target grid in the grid, obtains the historical movement trajectory of the user equipment, and then associates the historical wireless environment measurement data with the target grid to generate the wireless environment state of each target grid, so that the predicted movement trajectory of the user equipment can be predicted from the grid according to the target arrival time reported by the user equipment in real time, and the wireless environment quality on the movement trajectory can be predicted. Therefore, the problem in the related technology that the wireless environment quality cannot be predicted in advance, thereby affecting the operation reliability of the user equipment, can be solved, and the periodic movement trajectory of the user equipment can be predicted, and then the time of entering and exiting the weak field area and the future path wireless signal changes can be determined, so as to provide data support for the user equipment to react and process in advance.

[0267] It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0268] Example 3

[0269] The embodiment of the present application also provides a storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments at runtime. Optionally, in this embodiment, the above storage medium can be configured to store a computer program for executing the method steps in the method embodiment. Optionally, in this embodiment, the above storage medium can include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store computer programs.

[0270] Example 4

[0271] The embodiment of the present application further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any of the above method embodiments. Figure 1 The memory 104 in is taken as an example of a memory in the electronic device.

[0272] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor. Optionally, in this embodiment, the processor may be configured to execute the method steps in the method embodiment through a computer program. Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiment and the optional implementation manner, and this embodiment will not be repeated here.

[0273] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0274] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for predicting wireless environment quality, characterized in that: The method comprises: Based on the uplink measurement of each remote radio unit, a remote radio unit combination is determined from the multiple remote radio units; wherein the remote radio unit combination includes at least two remote radio units; and the uplink measurement includes at least arrival time; Classifying the radio remote unit combinations whose number of uplink measurements is greater than a preset classification threshold to obtain classified data, and constructing a grid based on the classified data; wherein the preset classification threshold is greater than or equal to 2; Acquire historical measurement data of the user equipment, the historical measurement data including historical uplink measurement data and historical wireless environment measurement data, locate the historical uplink measurement data to target grids in the grid, and generate a historical movement trajectory of the user equipment according to the time sequence of the historical uplink measurement data; Associating the historical wireless environment measurement data with the target grid to generate a wireless environment state of the target grid; The predicted movement trajectory of the user equipment is determined according to the target arrival time reported in real time by the user equipment and the historical movement trajectory, and the wireless environment quality of the user equipment is predicted according to the predicted movement trajectory and the wireless environment state.

2. The method according to claim 1, characterized in that Based on the uplink measurement of each remote radio unit, a remote radio unit combination is determined among the multiple remote radio units, including: Determining a remote radio unit set based on uplink measurements of each remote radio unit; Determining a reference remote radio unit from the set of remote radio units; At least one first target remote radio frequency unit is determined from the remote radio frequency unit set according to the reference remote radio frequency unit, and the reference remote radio frequency unit and the first target remote radio frequency unit are used as the remote radio frequency unit combination.

3. The method according to claim 2, characterized in that The uplink measurement further includes a reference signal received power, and determining a reference remote radio unit from the remote radio unit set includes: Determine a second target remote radio unit having the largest number of occurrences of the remote radio unit identifier in the remote radio unit set; If the number of the second target remote radio unit is one, taking the second target remote radio unit as the reference remote radio unit; If there are multiple second target remote radio units, a remote radio unit having the largest reference signal received power among the multiple second target remote radio units is determined as the reference remote radio unit.

4. The method according to claim 2, characterized in that Determining at least one first target remote radio frequency unit from the remote radio frequency unit set according to the reference remote radio frequency unit includes: respectively calculating the modulus of the arrival time difference between any remote radio unit in the remote radio unit set and the reference remote radio unit, and sorting them from small to large; Determine the top N corresponding radio remote units as the first target radio remote units, where N is greater than or equal to 1.

5. The method according to claim 2, characterized in that: Based on the uplink measurement of each remote radio unit, a remote radio unit set is determined, including: Extracting a user equipment identifier, a base station identifier, and a cell identifier carried in the uplink measurement; the base station identifier includes one of a 3G base station identifier, a 4G base station identifier, and a 5G base station identifier; Determine the set of remote radio units under each combination of the user equipment identifier, the base station identifier and the cell identifier respectively; Wherein, for any combination of the user equipment identifier, the base station identifier, and the cell identifier, determining the radio remote unit set includes: sorting the collected uplink measurements by time; According to the data processing time window, the uplink measurement is divided into M time windows; For the uplink measurement in each of the time windows, counting the number of occurrences of each corresponding radio remote unit identifier; The radio remote unit set is determined according to the radio remote units whose occurrence times are greater than a preset threshold.

6. The method according to claim 1, characterized in that Classifying the radio remote unit combinations whose number of uplink measurements is greater than a preset classification threshold to obtain classified data, and constructing a grid based on the classified data, including: Determine a combination of remote radio units whose number of uplink measurements is greater than a preset classification threshold; Get the grid index; Grouping the radio remote unit combinations according to the grid index to obtain X data subsets; Get the target cluster number; The data subsets are clustered according to the target number of clusters, and a grid is constructed for the clustered data subsets.

7. The method according to claim 6, characterized in that Get the number of target clusters, including: Obtain the grid granularity and the inter-station spacing of the radio remote units; Determine the target cluster number according to the station spacing and the grid granularity; or, respectively obtaining the modulus of arrival time differences between a reference remote radio unit and other remote radio units in the remote radio unit combination; Obtaining a preset difference distribution interval and a threshold value for each interval; Taking the difference distribution interval in which the number of moduli of arrival time differences is greater than or equal to the threshold value as the target difference distribution interval; The number of target difference distribution intervals is counted, and the number of target difference distribution intervals is used as the target cluster number.

8. The method according to claim 1, characterized in that: Positioning the historical uplink measurement data to target grids in the grids respectively, comprising: Positioning the historical uplink measurement data to positioning grids respectively according to grid indexes; The positioning grid having the smallest Euclidean distance to the user equipment is determined as the target grid.

9. The method according to claim 8, characterized in that After determining that the positioning grid having the smallest Euclidean distance to the user equipment is the target grid, the method further includes: Acquire the residence time of the user equipment in the target grid; Obtaining a grid identifier of a previous hop of the user equipment; Acquire a target probability of the user equipment in the target grid; The residence time, the grid identifier of the previous jump and the target probability are recorded in the target grid.

10. The method according to claim 1, characterized in that Associating the historical wireless environment measurement data with the target grid to generate the wireless environment state of the target grid includes: Get the timestamp corresponding to the measurement time; Associating the historical wireless environment measurement data with the timestamp satisfying a preset time parameter to the target grid; Get the signal status classification interval; The target signal state satisfied by the historical wireless environment measurement data is used as the wireless environment state of the target grid.

11. The method according to claim 1, characterized in that: Predicting the wireless environment quality of the user equipment according to the predicted motion trajectory and the wireless environment state includes: Determine the wireless environment state of the future Y hops according to the predicted motion trajectory; The wireless environment quality of the user equipment is determined according to the wireless environment status of the Y hops.

12. A wireless environment quality prediction device, characterized in that: The device comprises: A combination determination module, configured to determine a remote radio unit combination among a plurality of remote radio units based on uplink measurements of each remote radio unit; wherein the remote radio unit combination includes at least two remote radio units; and the uplink measurements include at least arrival time; A grid construction module, used to classify the radio remote unit combinations whose number of uplink measurements is greater than a preset classification threshold, obtain classification data, and construct a grid based on the classification data; wherein the preset classification threshold is greater than or equal to 2; A trajectory positioning module, used to obtain historical measurement data of the user equipment, the historical measurement data including historical uplink measurement data and historical wireless environment measurement data, locate the historical uplink measurement data to target grids in the grid, and generate a historical movement trajectory of the user equipment according to the time sequence of the historical uplink measurement data; A wireless environment association module, used to associate the historical wireless environment measurement data with the target grid to generate the wireless environment state of the target grid; The prediction module is used to determine the predicted motion trajectory of the user equipment according to the target arrival time reported in real time by the user equipment and the historical motion trajectory, and predict the wireless environment quality of the user equipment according to the predicted motion trajectory and the wireless environment state.

13. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program is configured to execute the method according to any one of claims 1 to 11 when executed.

14. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to perform the method according to any one of claims 1 to 11.

Images