Machine learning based geolocation

Abstract

A computer-implemented method of geolocating a user equipment (UE) in a wireless network includes, for each cell of a plurality of cells in the wireless network, predicting a plurality of ranges of distances at which the UE is likely to be located from the cell, predicting a plurality of ranges of azimuth angles at which the UE is likely to be located relative to the cell, combining the prediction of the plurality of ranges of distances with the prediction of the plurality of ranges of azimuth angles to obtain a geographic region, associated with the cell, in which the UE is likely to be located, and determining an intersection of the geographic regions associated with respective ones of the cells to obtain an intersection geographic region in which the UE is likely to be located.

Description

MACHINE LEARNING BASED GEOLOCATIONTECHNICAL FIELD

[0001] The present disclosure relates to wireless communication networks, and in particular to techniques for performing geolocation in wireless communication networks.BACKGROUND

[0002] Geolocation is a generic term in the telecommunications industry for any technology that is used to obtain the geographic location of devices, such as user equipment (UE), that use a wireless communication network. Using geolocation, a network may obtain an estimate of the positional coordinates (e.g., latitude and longitude) of a device, or the relative position (e.g., distance and angle) of the device with respect to a serving cell whose geographic position is known.

[0003] The geolocation problem is wireless technology-specific. That is, geolocation techniques used in third generation (3G) systems are different from geolocation techniques used in fourth generation (4G) systems, which are different from those used in fifth generation (5G) systems. The reason is that each wireless standard provides a different set of features that can make the process of geolocation easier or more difficult.

[0004] In Long Term Evolution (LTE), which is a 4G standard, geolocation is typically performed using information obtained from a global navigational satellite system (GNSS). However, GNSS data is not always available for every UE. If GNSS data is not available, an LTE network can perform geolocation by estimating the location of a UE using other data available to the network. The known methods for geolocation in LTE systems without the use of GNSS data can be divided into two categories, namely Category 1 techniques, which use direct features / configurations available in the network, and Category 2 techniques, which use mathematical modeling based on observed network measurements.

[0005] Category 1 methods can use various information that is available in a network, such as Observed Time Difference of Arrival (OTDOA) to estimate the location of a UE. Another Category 1 method is to use Timing Advance (TA) information to estimate the distance from the serving cell and Angle of Arrival (AoA) information is used to estimate the angle (direction) at which the device is located relative to the serving cell.

[0006] Similar to GNSS, OTDOA and AoA are not available in all LTE networks. TA is available as basic information of LTE connection but it can only offer a partialestimation of the geolocation, as it can only provide information about the distance to the server. For that reason, various Category 2 techniques have been proposed to estimate the location of a device using indirect features.

[0007] One example of a Category 2 method uses a mathematical way to model the antenna gain of a UE. A searching area is broken down into smaller zones, and an algorithm finds the zone that has the smallest divergence from the mathematical model. This zone is assumed to be the location of the UE.

[0008] In another example of a Category 2 method illustrated in Figure 1, information such as the reference signal received power (RSRP) of a serving cell and neighboring cells, as well as the TA for a UE are provided as input features 12 to a geolocation model 10 that generates the latitude and longitude of the UE as outputs 14. The geolocation model 10 may be a regression model that is trained using supervised learning.SUMMARY

[0009] There currently exist certain challenge(s) with non-GNSS based geolocation techniques. For example, Category 1 methods that use network features may not be available, because not all networks may have either OTDOA, TA and / or AoA enabled. Category 2 methods which rely on mathematical modelling for regression, such models may be prone to overfitting, which means that the models can accurately represent training data but are not able to generalize to new data.

[0010] Some embodiments described herein provide ML-based techniques that can perform geolocation based on measurement reports that do not rely on data such as OTDOA and AoA.

[0011] In particular, a computer-implemented method of geolocating a user equipment (UE) in a wireless network includes, for each cell of a plurality of cells in the wireless network, predicting a plurality of ranges of distances at which the UE is likely to be located from the cell, predicting a plurality of ranges of azimuth angles at which the UE is likely to be located relative to the cell, combining the prediction of the plurality of ranges of distances with the prediction of the plurality of ranges of azimuth angles to obtain a geographic region, associated with the cell, in which the UE is likely to be located, and determining an intersection of the geographic regions associated with respective ones of the cells to obtain an intersection geographic region in which the UE is likely to be located.

[0012] In some embodiments, predicting the plurality of ranges of distances is performed using a first classification model.

[0013] The first classification model takes as input reference signal received power, RSRP, reported by the UE for each of the cells and relative geographic locations of each of the cells.

[0014] The first classification model may include a first neural network having one output for each possible range of distances that can be output by the first neural network.

[0015] In some embodiments, predicting the plurality of ranges of azimuth angles is performed using a second classification model.

[0016] The second classification model takes as input reference signal received power, RSRP, reported by the UE for each of the cells and relative geographic locations of each of the cells.

[0017] The second classification model may include a second neural network having one output for each possible range of azimuth angles that can be output by the second neural network.

[0018] The method may further include obtaining additional information relating to the geographic location of the UE, and narrowing a possible location of the UE within the intersection geographic region in which the UE is likely to be located.

[0019] The additional information may include timing advance information for the UE relative to a serving cell. Narrowing the possible location of the UE within the intersection geographic region in which the UE is likely to be located may include narrowing the possible location of the UE to an arc within the intersection geographic region based on the timing advance information.

[0020] In some embodiments, predicting the plurality of ranges of distances is performed using a regression model.

[0021] A system for geolocating a UE in a wireless network according to some embodiments includes a first classifier that predictions, for each cell of a plurality of cells in the wireless network reported by the UE, a plurality of ranges of distances at which the UE is likely to be located from the cell, a second classifier that predicts, for each cell of the plurality of cells reported by the UE, a plurality of ranges of azimuth angles at which the UE is likely to be located relative to the cell, a first stage combiner that, for each cell, combines the prediction of the plurality of ranges of distances with the prediction of the plurality of ranges of azimuth angles to obtain a geographic region, associated with the cell, in which the UE is likely to be located, and a second stage combiner that determines an intersection of the geographic regions associated with respective ones of the cells to obtain an intersection geographic region in which the UE is likely to be located.

[0022] A system for geolocating a UE in a wireless network according to further embodiments includes a first classifier that predictions, for each cell of a plurality of cells in the wireless network reported by the UE, a plurality of ranges of distances at which the UE is likely to be located from the cell, a second classifier that predicts, for each cell of the plurality of cells reported by the UE, a plurality of ranges of azimuth angles at which the UE is likely to be located relative to the cell, and a combiner that determines an intersection of the plurality of ranges of distances and the plurality of ranges of azimuth angles to obtain an intersection geographic region in which the UE is likely to be located.

[0023] A computer-implemented method of geolocating a UE in a wireless network according to further embodiments includes, for each cell of a plurality of cells reported by the UE in the wireless network, predicting a plurality of ranges of distances at which the UE is likely to be located from the cell, predicting a plurality of ranges of azimuth angles at which the UE is likely to be located relative to the cell, and determining an intersection of the plurality of ranges of distances and plurality of ranges of azimuth angles to obtain an intersection geographic region in which the UE is likely to be located.

[0024] In some embodiments, predicting the plurality of ranges of distances is performed using a first classification model.

[0025] The first classification model takes as input reference signal received power, RSRP, reported by the UE for each of the cells and relative geographic locations of each of the cells.

[0026] The first classification model may include a first neural network having one output for each possible range of distances that can be output by the first neural network.

[0027] In some embodiments, predicting the plurality of ranges of azimuth angles is performed using a second classification model.

[0028] The second classification model takes as input reference signal received power, RSRP, reported by the UE for each of the cells and relative geographic locations of each of the cells.

[0029] The second classification model may include a second neural network having one output for each possible range of azimuth angles that can be output by the second neural network.

[0030] The method may further include obtaining additional information relating to the geographic location of the UE, and narrowing a possible location of the UE within the intersection geographic region in which the UE is likely to be located.

[0031] The additional information may include timing advance information for the UE relative to a serving cell. Narrowing the possible location of the UE within the intersection geographic region in which the UE is likely to be located may include narrowing the possible location of the UE to an arc within the intersection geographic region based on the timing advance information.

[0032] In some embodiments, predicting the plurality of ranges of distances is performed using a regression model.BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 illustrates a conventional machine learning based approach to geolocation.

[0034] Figures 2A and 2B illustrate systems for performing geolocation according to some embodiments.

[0035] Figures 3A and3B illustrate a geographic area around a serving cell.

[0036] Figures 4, 5, 6, 7, 8, 9, and 10 illustrate operations performed by a system to perform geolocation according to some embodiments.

[0037] Figure 11 illustrates modeling of the distance of a UE from the serving cell may as an arc having a center at the location of the serving cell.

[0038] Figure 12 illustrates determining the expected location of a UE as being on the intersection of an arc with a geographic region.

[0039] Figures 13 and 14 illustrates systems for performing geolocation according to further embodiments.

[0040] Figure 15 is a flowchart that illustrates operations of systems / methods according to some embodiments.

[0041] Figure 16 shows an example of a communication system in accordance with some embodiments.

[0042] Figure 17 shows a UE in accordance with some embodiments.

[0043] Figure 18 shows a network node in accordance with some embodiments.DETAILED DESCRIPTION OF EMBODIMENTS

[0044] As indicated above, Category 2 methods may be prone to overfitting. Moreover, regression model such as the model 10 shown in Figure 1 may expect to have input data (features) from a fixed number of neighbors. If any neighbor is missing, it is notclear how missing data will be handled. Of course, a straight-forward approach would be to replace the missing features with some value, but this approach makes the prediction completely unexplainable and inaccurate.

[0045] The regression approach does not show a clear correlation between the number of existing neighbors and the accuracy of the prediction. Intuitively, there should be a direct relationship between the prediction accuracy and the number of neighbors, i.e., the more the neighbors, the higher the accuracy. However, this does not appear to be the case.

[0046] Additionally, formulating geolocation as a regression problem may not be accurate, because for the same input features (RSRP and location of serving and neighbor cells), the output (latitude and longitude) can be quite different, because RSRP and cell location are not conclusive to estimate the position of a UE, as some variables remain outside the model.

[0047] For example, with a specific set of RSRP values of serving and neighbor cells, a UE can be located 10, 15, -10, or 32 degrees aways from the azimuth of the serving cell. Therefore, when training a supervised regression model, it will either overfit or underfit because it is being fed by contradicting input-output pairs.

[0048] Certain aspects of the disclosure and their embodiments may provide solutions to these or other challenges. Some embodiments described herein provide ML- based techniques that can perform geolocation based on measurement reports that do not rely on data such as OTDOA and AoA.

[0049] Some embodiments described herein first use ML to predict a possible area in which a UE is expected to be located relative to its serving cell. For example, a UE could be anywhere around the serving cell, i.e. at an azimuth angle of 0 to 360 degrees and a distance of up to several kilometers.

[0050] After this step of prediction, the possible area of the UE relative to the serving cell may shrink to an azimuthal range of a number of degrees and a distance range of a few tens to hundreds of meters.

[0051] Next, ML is used to predict, in a similar way, a possible area of the UE in the proximity to each neighbor cell. This step is applied to each existing neighbor cell individually to generate a plurality of possible areas in which the UE may be located.

[0052] After applying this step, the possible area of the UE relative to each neighbor cell may shrink to an azimuthal range of a number of degrees defined by the predicted / selected ranges of azimuths and a distance range of a few hundreds of meters.

[0053] The systems / methods then determine an intersection of all of the identified areas. This intersection between all possible positions around each neighbor and the serving cell defines a small region in which the UE is expected to be. The intersection region may be defined as a polygon having a plurality of vertices defined as geographic points.

[0054] In some embodiments, the final geolocation of the UE may be determined as the centroid of the final polygon. The area of the polygon indicates the precision of the prediction. When data from more neighbor cells is available, the final area of intersection should be smaller.

[0055] After identifying the area of intersection, additional features can be used to narrow down the expected location of the UE even more. For example, if TA information is available, it can be used to shrink the searching area from a polygon to an arc. In that case, the center of the arc may be determined as the location of the UE, and the size of the arc may provide an indication of the accuracy of the location.

[0056] Certain embodiments may provide one or more of the following technical advantage(s). Some embodiments described herein are accurate and can work for both urban and rural areas without strong approximations, are generalizable (i.e. no overfitting), are highly explainable, and have a clear relationship between prediction accuracy and the number of available neighbor cells.

[0057] Some embodiments only require that a maximum number of neighboring cells be specified. However, the number of cells to be used for any given UE is not dictated.

[0058] The accuracy of some embodiments be high without overfitting nor underfitting.

[0059] The models used in some embodiments are able to leam a pattern. For example, whenever there are sets of input features that share different locations, the models leam all possible locations without forcing it to select only a single location.

[0060] Some embodiments can generate a predicted UE location can work even if TA information is not available.

[0061]

[0062] The area of the final polygon generated as an output of some embodiments provides an indication of the accuracy of the prediction. Moreover, some embodiments described herein can be combined with other techniques to obtain higher precision.

[0063] Some of the embodiments contemplated herein will now be described more fully with reference to the accompanying drawings. Embodiments are provided by way of example to convey the scope of the subject matter to those skilled in the art.

[0064] Instead of predicting latitude and longitude of the UE some embodiments described herein provide systems / methods that predict distance (R) and azimuth angle (q) relative to the serving cell.

[0065] A prediction of UE distance may have less variance than a prediction of azimuth angle. Thus, in some embodiments, distance may be predicted using a regression algorithm.

[0066] However, the angle prediction may be implemented as a classification problem. That is, instead of estimating an exact azimuth angle of the UE relative to the serving cell, some embodiments use a classifier to predict a range of possible azimuth angles.

[0067] In some embodiments discussed below, the range prediction may also be formulated as a classification problem.

[0068] Accordingly, a system 100 for performing geolocation is shown in Figure 2A. As shown therein, the system 100 includes a distance range estimator 110 and an azimuth range classifier 120. Each of the distance range estimator 110 and the azimuth range classifier 120 receive a set of features as inputs. The input features include a serving cell RSRP and one or more RSRP values of neighboring cells (N1 RSRP, N2 RSRP, etc.) As known in the art, RSRP is a measure the power level of a reference signal received at the UE. The input features also include locations of the neighboring cells (N1 Location, N2 Location, etc.) The input features may optionally include a TA value of the serving cell, if known.

[0069] The distance range estimator 110 generates an estimate 115 of a range of distances at which the UE is believed to be located based on a model, such as a regression model or a classification model. For example, the range estimator 110 may estimate that the UE is located within one or more predetermined distance ranges (i. e. , "rings") away from the serving cell.

[0070] Brief reference is made to Figure 3A, which illustrates a geographic area 200 around a serving cell 210. The geographic area 200 is divided into a number of concentric rings 124, each of which has a width of 1000 m to cover the entire geographic area200.

[0071] Referring again to Figure 2A, the azimuth range classifier 120 generates an estimate 125 of a range of azimuths at which the UE is believed to be located based on a classification model. For example, the azimuth range classifier 120 may generate an estimate 125 that the UE is located within one or more predetermined azimuthal angular ranges or angular sectors (i.e. , "wedges") relative to the serving cell.

[0072] Brief reference is made to Figure 3B, which illustrates a geographic area 200 around a serving cell 210. The geographic area 200 is divided into a number of wedges 134, each of which spans an angle of 15 degrees to cover the entire geographic area 200.

[0073] For example, the geographic area 200 shown in Figures 3A and 3B is generally circular and has a diameter of 6 km, and is thus spanned by six rings 124 and 24 angular wedges 134. Thus, for example, a first ring 124 has an inner diameter of zero and an outer diameter of 1000 m. The second ring 124 has an inner diameter of 1000 m and an outer diameter of 2000 m, and so on. Likewise, a first angular wedge 134 spans a range of azimuthal angles from 0 degrees to 15 degrees. The second angular wedge 134 spans a range of azimuthal angles from 15 degrees to 30 degrees, and so on.

[0074] It will be appreciated that the numbers of rings and wedges shown in Figures 3A and 3B are arbitrary, and different numbers and sizes of rings 124 and / or wedges 134 may be defined or even redefined dynamically, depending on certain characteristics to the environment, to cover the geographic area 200.

[0075] Referring again to Figure 2 A, a combiner 130 determines a geographical intersection between the range of distances 115 output by the distance range estimator 110 and the range of azimuths output by the azimuth range classifier 120 to obtain a predicted area 135 ,i.e., an intersection region that corresponds to the geographic area in which the UE is predicted to be located.

[0076] The combiner 130 may perform a single combining operation that combines distance range estimates 115 and azimuth range estimates 125 relative to the serving cell and relative to each neighbor cell in a single combining step.

[0077] Alternatively, the combining operation may be split into two combining operations as illustrated in Figure 2B. As shown therein, in a first combining operation, for each cell, a first stage combiner I30A combines a distance range estimate 115A-N and an azimuth range estimate 125A-N by finding the intersection of the distance range estimate 115A and the azimuth range estimate 125A for the cell to obtain a predicted area 135A relative to the cell. This is repeated for each cell including the serving cell and neighboring cells N1 -Nn to obtain predicted areas 135A-N. In a second combining operation, a second stage combiner BOB combines the predicted areas 135A-N by finding the intersection of the predicted areas 135A-N to find a predicted area 135 based on predictions from each of the cells. Splitting the combining operation into multiple stages may allow the problem of determining the predicted area 135 to be performed in a distributed fashion by multiple different network nodes, thereby increasing the speed of the operation.

[0078] Figures 4 to 10 illustrate operations performed by a system 100 according to some embodiments. Referring to Figures 4 to 7, a geographic area 200 around a serving cell is divided into a plurality of concentric rings 124 (Figures 4 and 5) and angular wedges 134 (Figures 6 and 7). In the example shown in Figures 4 to 7, each ring 124 is 1000m in width, and each wedge spans 15 degrees.

[0079] In the example shown in Figures 4 to 7, a UE whose location is being estimated is located at geographic point 105 within the geographic area 200, which corresponds to ring 122 and wedge 132.

[0080] Referring to Figure 5, the distance range estimator 110 predicts which ring or rings 124 the UE is likely to be located in using a first ML model, such as a regression model, a classification model, or another model, the target of which is to predict the correct ring 122 where the UE is located.

[0081] The input to the first model may include the serving cell RSRP, the RSRP of the neighbor cells Nl, N2, N3, N4, and the relative positions of the neighbor cells Nl, N2, N3, N4.

[0082] In this example, because there are six possible rings 124, the output layer of the first model may have 6 outputs. A sigmoid activation function may be used for the first model, although other activation functions are possible.

[0083] During training of the first model, a target vector is one-hot-encoded such that only the correct ring 124 will be assigned a value of one, and the others will be assigned a value of zero.

[0084] However, during the inference stage (i.e., the stage of operation following training in which the model is applied), the first model may predict multiple rings 124. For example, the first model may identify as a likely location of the UE, any ring 124 with probability higher than a predefined threshold, such as 0.5. This may increase the probability that the correct ring 122 will be predicted.

[0085] In this example, the model may identify the three shaded rings 124 in the region 126 shown in Figure 5 as being rings in which the UE is likely to be located. This output is stored for later use.

[0086] Referring to Figures 6 and 7, the azimuth range classifier 120 predicts which wedge or wedges 134 the UE is likely to be located in using a second ML model, which is a classification model, the target of which is to predict the correct wedge 132 where the UE is located.

[0087] The input to the second model may include serving cell RSRP, the RSRP of the neighbor nodes Nl, N2, N3, N4, and the relative positions of the neighbor nodes Nl, N2, N3, N4.

[0088] In this example, because there are 24 (360 / 15) possible wedges 134, the output layer of the second model may have 24 outputs. A sigmoid activation function may be used for the second model, although other activation functions are possible.

[0089] During training of the second model, a target vector is one-hot-encoded such that only the correct wedge 132 will be assigned a value of one, and the others will be assigned a value of zero.

[0090] However, during the inference stage, the second model may predict multiple wedges 134. For example, the second model may identify as a likely location of the UE, any wedge 134 with probability higher than a predefined threshold, such as 0.5. This may increase the probability that the correct wedge 134 will be predicted.

[0091] In this example, the model may identify the nine shaded wedges 134 in the region 136 shown in Figure 7 as being rings in which the UE is likely to be located. This output is stored for later use.

[0092] The same two-step process described above of finding possible rings 124 and wedges / slices 134 in which the UE is likely located is then applied to the neighbors Nl, N2, etc, of the UE.

[0093] The output of this step is similar to that shown in Figures 5 and 7 - namely, an identification of regions 126, 136 containing one or more rings 124 and one or more wedges 134 in which the UE is likely to be located.

[0094] Figures 8 and 9 illustrate the process for neighbor Nl . As shown therein the distance range estimator 110 identifies an annular area 126-1 around neighbor Nl in which the UE is likely located, and the azimuth range classifier identifies a wedge-shaped area 136-1 around neighbor Nl in which the UE is likely to be located.

[0095] This operation is repeated for each neighboring cell of the UE.

[0096] Since each step in the previous three steps predicts a possible area where the UE might be located, and since each of the three steps has high confidence, the system 100 takes the intersection of all of these regions using a combiner 130. That is, the combiner 130 finds the intersection of all possible rings 124 and all possible slices of the geographic area 200 around the serving cell 210 and of all possible rings and all possible slices of the geographic area around each neighboring cell.

[0097] Referring to Figures 2 and 10, the output 135 of the combiner 130 is a small area 150 that represents the area where all of the rings and wedges 152-1, 152-2, 153-3 output by the distance range estimator 110 and the azimuth range classifier 120 overlap. This region 150 provides an estimated location of the UE with high probability.

[0098] The location of the UE within the region 150 can be further narrowed using additional information. For example, TA information may be available from the serving cell 210. In that case, the TA information can be used with a third model to predict the distance of the UE from the serving cell with greater accuracy. Referring to Figure 11, the distance of the UE from the serving cell may be modeled as an arc 160 (not a polygon) having a center at the location of the serving cell. Referring to Figure 12, the system 100 may then determine the expected location of the UE as being on the intersection 162 of the arc 160 with the region 150 output by the combiner 130.

[0099] Figure 13 illustrates an embodiment of a system 100' including a second combiner250. The system 100' includes a distance prediction unit 230 that receives TA information 225 from the serving cell and generates a distance prediction 235. A second combiner 250 finds the intersection 162 of the arc 160 (Figure 12) with the intersection region 135 output by the combiner!30 and generates an arc location prediction 255 of the arc 162 where the UE is expected to be located.

[0100] Figure 14 illustrates an embodiment of a system 100" according to further embodiments that processes the arc location prediction 255 using an additional algorithm 310 to produce a refined location prediction 315. The additional algorithm 310 may be any ML algorithm that predicts the location of the UE along the arc 162 output in the arc location prediction 255.

[0101] Accordingly, some embodiments described herein split the geolocation problem into separate angle and distance predictions. The angle prediction is re-formulated as two classification problems, namely, a ring prediction and a wedge prediction.

[0102] In the ring prediction problem, the area around the serving cell is divided into a set of concentric rings. A first ML model, such as a neural network, is trained to predict one or more rings around the serving cell where the UE is expected to be located. This process is repeated for each neighboring cell of the UE.

[0103] In the wedge prediction problem, the area around the serving cell is divided into a set of slices. A second ML model, such as a neural network, is trained to predict one or more wedges around the serving cell where the UE is expected to be located.

[0104] This process is repeated for each neighboring cell of the UE.

[0105] The system finds the intersection of the rings and wedges for the serving cell and each neighboring cell. This intersection of those regions defines a polygon where the UE is expected to be located.

[0106] Distance prediction, which is a relatively simpler problem, is optional and may be performed if TA information is available. Distance prediction can be used to narrow the location of the UE within the predicted polygon.

[0107] Another optional algorithm (ML-based or a simple searching algorithm) can be further applied to reduce the predicted polygon / arc location of the UE into a point.

[0108] Figure 15 is a flowchart that illustrates operations of systems / methods according to some embodiments. Referring to Figure 15, a system 100 first selects a cell from a group of cells including the serving cell of the UE and the neighboring cells reported by the UE (block 602). The system 100 then predicts a plurality of ranges of distances at which the UE is likely to be located from the selected cell (block 604). The ranges of distances are referred to rings as depicted in Figure 3A.

[0109] Predicting the plurality of ranges of distances may be performed using a first classification model. The first classification model may take as input a reference signal received power (RSRP) reported by the UE for each of the cells and relative geographic locations of each of the cells.

[0110] In some embodiments, the first classification model may be a first neural network having one output for each possible range of distances that can be output by the first neural network.[oni] The system 100 also predicts a plurality of ranges of azimuth angles at which the UE is likely to be located relative to the cell (block 606). The ranges of azimuths are referred to sectors (“wedges”) as depicted in Figure 3B. Predicting the plurality of ranges of azimuth angles may be performed using a second classification model that takes as input the RSRP reported by the UE for each of the cells and relative geographic locations of each of the cells. The second classification model may be a second neural network having one output for each possible range of azimuth angles that can be output by the second neural network.

[0112] At block 608, the system 100 combines the prediction of the plurality of ranges of distances with the prediction of the plurality of ranges of azimuth angles to obtain a geographic region, associated with the cell, in which the UE is likely to be located.

[0113] The system then determines whether there are any remaining cells in the group (block 610). If so, operations return to block 602 and the system selects the next cell.

[0114] Otherwise, if no cells remain, the system determines an intersection of the geographic regions associated with respective ones of the cells to obtain an intersection geographic region in which the UE is likely to be located (block 612).

[0115] The method may optionally include obtaining additional information relating to the geographic location of the UE, and using the information to narrow a possible location of the UE within the intersection geographic region in which the UE is likely to be located (block 614).

[0116] The additional information may include timing advance information for the UE relative to a serving cell, and narrowing the possible location of the UE within the intersection geographic region in which the UE is likely to be located may include narrowing the possible location of the UE to an arc within the intersection geographic region based on the timing advance information.

[0117] In some embodiments, predicting the plurality of ranges of distances is performed using a regression model.

[0118] Figure 16 shows an example of a communication system 1600 in which some embodiments described herein may be advantageously employed.

[0119] In the example, the communication system 1600 includes a telecommunication network 1602 that includes an access network 1604, such as a radio access network (RAN), and a core network 1606, which includes one or more core network nodes 1608. The access network 1604 includes one or more access network nodes, such as network nodes 1610a and 1610b (one or more of which may be generally referred to as network nodes 1610), or any other similar 3rdGeneration Partnership Project (3GPP) access nodes or non-3GPP access points. Moreover, as will be appreciated by those of skill in the art, a network node is not necessarily limited to an implementation in which a radio portion and a baseband portion are supplied and integrated by a single vendor. Thus, it will be understood that network nodes include disaggregated implementations or portions thereof. For example, in some embodiments, the telecommunication network 1602 includes one or more Open-RAN (ORAN) network nodes. An ORAN network node is a node in the telecommunication network 1602 that supports an ORAN specification (e.g., a specification published by the O-RAN Alliance, or any similar organization) and may operate alone or together with other nodes to implement one or more functionalities of any node in the telecommunication network 1602, including one or more network nodes 1610 and / or core network nodes 1608.

[0120] Examples of an ORAN network node include an open radio unit (O-RU), an open distributed unit (O-DU), an open central unit (O-CU), including an O-CU control plane (O-CU-CP) or an O-CU user plane (O-CU-UP), a RAN intelligent controller (near-real time or non-real time) hosting software or software plug-ins, such as a near-real time control application (e.g., xApp) or a non-real time control application (e.g., rApp), or any combination thereof (the adjective “open” designating support of an ORAN specification). The network node may support a specification by, for example, supporting an interface defined by the ORAN specification, such as an Al, Fl, Wl, El, E2, X2, Xn interface, an open fronthaul user plane interface, or an open fronthaul management plane interface. Moreover, an ORAN access node may be a logical node in a physical node. Furthermore, an ORAN network node may be implemented in a virtualization environment (described further below) in which one or more network functions are virtualized. For example, the virtualization environment may include an O-Cloud computing platform orchestrated by a Service Management and Orchestration Framework via an 0-2 interface defined by the O- RAN Alliance or comparable technologies. The network nodes 1610 facilitate direct or indirect connection of user equipment (UE), such as by connecting UEs 1612a, 1612b, 1612c, and 1612d (one or more of which may be generally referred to as UEs 1612) to the core network 1606 over one or more wireless connections.

[0121] Embodiments described herein may be performed in a network node, such as a core network node 1608 and / or an access network node 1610 of a wireless communication network. For example, some embodiments described herein may be performed in a core network node 1608 and / or an access network node 1610 to perform geolocation to determine a location of a user equipment 1612 that is connected to an access network node 1610 via a wireless interface. In some embodiments, a system for geolocating a UE in a wireless network may be performed in various core and / or access network nodes of a wireless communication network. For example, some embodiments described above include a first classifier 110, a second classifier 120, a first combiner 130, 130A, BOB, and a second combiner 250. Each of these and other system elements described herein may be embodied in one or more core and / or access network nodes of a wireless communication network. Moreover, other network nodes and / or network functions may participate in the operation of a system according to embodiments described herein. For example, a network node or network function may store a ML model and / or training data that is used to train an ML model as described herein.

[0122] Example wireless communications over a wireless connection include transmitting and / or receiving wireless signals using electromagnetic waves, radio waves, infrared waves, and / or other types of signals suitable for conveying information without the use of wires, cables, or other material conductors. Moreover, in different embodiments, the communication system 1600 may include any number of wired or wireless networks, network nodes, UEs, and / or any other components or systems that may facilitate or participate in the communication of data and / or signals whether via wired or wireless connections. The communication system 1600 may include and / or interface with any type of communication, telecommunication, data, cellular, radio network, and / or other similar type of system.

[0123] The UEs 1612 may be any of a wide variety of communication devices, including wireless devices arranged, configured, and / or operable to communicate wirelessly with the network nodes 1610 and other communication devices. Similarly, the network nodes 1610 are arranged, capable, configured, and / or operable to communicate directly or indirectly with the UEs 1612 and / or with other network nodes or equipment in the telecommunication network 1602 to enable and / or provide network access, such as wireless network access, and / or to perform other functions, such as administration in the telecommunication network 1602.

[0124] In the depicted example, the core network 1606 connects the network nodes 1610 to one or more hosts, such as host 1616. These connections may be direct or indirect via one or more intermediary networks or devices. In other examples, network nodes may be directly coupled to hosts. The core network 1606 includes one more core network nodes (e.g., core network node 1608) that are structured with hardware and software components. Features of these components may be substantially similar to those described with respect to the UEs, network nodes, and / or hosts, such that the descriptions thereof are generally applicable to the corresponding components of the core network node 1608. Example core network nodes include functions of one or more of a Mobile Switching Center (MSC), Mobility Management Entity (MME), Home Subscriber Server (HSS), Access and Mobility Management Function (AMF), Session Management Function (SMF), Authentication Server Function (AUSF), Subscription Identifier De-concealing function (SIDF), Unified Data Management (UDM), Security Edge Protection Proxy (SEPP), Network Exposure Function (NEF), and / or a User Plane Function (UPF).

[0125] The host 1616 may be under the ownership or control of a service provider other than an operator or provider of the access network 1604 and / or the telecommunication network 1602, and may be operated by the service provider or on behalf of the serviceprovider. The host 1616 may host a variety of applications to provide one or more service. Examples of such applications include live and pre-recorded audio / video content, data collection services such as retrieving and compiling data on various ambient conditions detected by a plurality of UEs, analytics functionality, social media, functions for controlling or otherwise interacting with remote devices, functions for an alarm and surveillance center, or any other such function performed by a server.

[0126] As a whole, the communication system 1600 of Figure 16 enables connectivity between the UEs, network nodes, and hosts. In that sense, the communication system may be configured to operate according to predefined rules or procedures, such as specific standards that include, but are not limited to: Global System for Mobile Communications (GSM); Universal Mobile Telecommunications System (UMTS); Long Term Evolution (LTE), and / or other suitable 2G, 3G, 4G, 5G standards, or any applicable future generation standard (e.g., 6G); wireless local area network (WLAN) standards, such as the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standards (WiFi); and / or any other appropriate wireless communication standard, such as the Worldwide Interoperability for Microwave Access (WiMax), Bluetooth, Z-Wave, Near Field Communication (NFC) ZigBee, LiFi, and / or any low-power wide-area network (LPWAN) standards such as LoRa and Sigfox.

[0127] In some examples, the telecommunication network 1602 is a cellular network that implements 3GPP standardized features. Accordingly, the telecommunications network 1602 may support network slicing to provide different logical networks to different devices that are connected to the telecommunication network 1602. For example, the telecommunications network 1602 may provide Ultra Reliable Low Latency Communication (URLLC) services to some UEs, while providing Enhanced Mobile Broadband (eMBB) services to other UEs, and / or Massive Machine Type Communication (mMTC) / Massive loT services to yet further UEs.

[0128] In some examples, the UEs 1612 are configured to transmit and / or receive information without direct human interaction. For instance, a UE may be designed to transmit information to the access network 1604 on a predetermined schedule, when triggered by an internal or external event, or in response to requests from the access network 1604. Additionally, a UE may be configured for operating in single- or multi-RAT or multistandard mode. For example, a UE may operate with any one or combination of Wi-Fi, NR (New Radio) and LTE, i.e. being configured for multi -radio dual connectivity (MR-DC), suchas E-UTRAN (Evolved-UMTS Terrestrial Radio Access Network) New Radio - Dual Connectivity (EN-DC).

[0129] In the example, the hub 1614 communicates with the access network 1604 to facilitate indirect communication between one or more UEs (e.g., UE 1612c and / or 1612d) and network nodes (e.g., network node 1610b). In some examples, the hub 1614 may be a controller, router, content source and analytics, or any of the other communication devices described herein regarding UEs. For example, the hub 1614 may be a broadband router enabling access to the core network 1606 for the UEs. As another example, the hub 1614 may be a controller that sends commands or instructions to one or more actuators in the UEs. Commands or instructions may be received from the UEs, network nodes 1610, or by executable code, script, process, or other instructions in the hub 1614. As another example, the hub 1614 may be a data collector that acts as temporary storage for UE data and, in some embodiments, may perform analysis or other processing of the data. As another example, the hub 1614 may be a content source. For example, for a UE that is a VR headset, display, loudspeaker or other media delivery device, the hub 1614 may retrieve VR assets, video, audio, or other media or data related to sensory information via a network node, which the hub 1614 then provides to the UE either directly, after performing local processing, and / or after adding additional local content. In still another example, the hub 1614 acts as a proxy server or orchestrator for the UEs, in particular if one or more of the UEs are low energy loT devices.

[0130] The hub 1614 may have a constant / persistent or intermittent connection to the network node 1610b. The hub 1614 may also allow for a different communication scheme and / or schedule between the hub 1614 and UEs (e.g., UE 1612c and / or 1612d), and between the hub 1614 and the core network 1606. In other examples, the hub 1614 is connected to the core network 1606 and / or one or more UEs via a wired connection. Moreover, the hub 1614 may be configured to connect to an M2M service provider over the access network 1604 and / or to another UE over a direct connection. In some scenarios, UEs may establish a wireless connection with the network nodes 1610 while still connected via the hub 1614 via a wired or wireless connection. In some embodiments, the hub 1614 may be a dedicated hub - that is, a hub whose primary function is to route communications to / from the UEs from / to the network node 1610b. In other embodiments, the hub 1614 may be a non-dedicated hub - that is, a device which is capable of operating to route communications between the UEs and network node 1610b, but which is additionally capable of operating as a communication start and / or end point for certain data channels.

[0131] Figure 17 shows a UE 1700 in accordance with some embodiments. As used herein, a UE refers to a device capable, configured, arranged and / or operable to communicate wirelessly with network nodes and / or other UEs. Examples of a UE include, but are not limited to, a smart phone, mobile phone, cell phone, voice over IP (VoIP) phone, wireless local loop phone, desktop computer, personal digital assistant (PDA), wireless cameras, gaming console or device, music storage device, playback appliance, wearable terminal device, wireless endpoint, mobile station, tablet, laptop, laptop-embedded equipment (LEE), laptop-mounted equipment (LME), smart device, wireless customer-premise equipment (CPE), vehicle, vehicle-mounted or vehicle embedded / integrated wireless device, etc. Other examples include any UE identified by the 3rd Generation Partnership Project (3 GPP), including a narrow band internet of things (NB-IoT) UE, a machine type communication (MTC) UE, and / or an enhanced MTC (eMTC) UE.

[0132] The UE 1700 includes processing circuitry 1702 that is operatively coupled via a bus 1704 to an input / output interface 1706, a power source 1708, a memory 1710, a communication interface 1712, and / or any other component, or any combination thereof. Certain UEs may utilize all or a subset of the components shown in Figure 17. The level of integration between the components may vary from one UE to another UE. Further, certain UEs may contain multiple instances of a component, such as multiple processors, memories, transceivers, transmitters, receivers, etc.

[0133] The processing circuitry 1702 is configured to process instructions and data and may be configured to implement any sequential state machine operative to execute instructions stored as machine-readable computer programs in the memory 1710. The processing circuitry 1702 may be implemented as one or more hardware-implemented state machines (e.g., in discrete logic, field-programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), etc.); programmable logic together with appropriate firmware; one or more stored computer programs, general-purpose processors, such as a microprocessor or digital signal processor (DSP), together with appropriate software; or any combination of the above. For example, the processing circuitry 1702 may include multiple central processing units (CPUs).

[0134] In the example, the input / output interface 1706 may be configured to provide an interface or interfaces to an input device, output device, or one or more input and / or output devices. Examples of an output device include a speaker, a sound card, a video card, a display, a monitor, a printer, an actuator, an emitter, a smartcard, another output device, or any combination thereof. An input device may allow a user to capture informationinto the UE 1700. Examples of an input device include a touch-sensitive or presence-sensitive display, a camera (e.g., a digital camera, a digital video camera, a web camera, etc.), a microphone, a sensor, a mouse, a trackball, a directional pad, a trackpad, a scroll wheel, a smartcard, and the like. The presence-sensitive display may include a capacitive or resistive touch sensor to sense input from a user. A sensor may be, for instance, an accelerometer, a gyroscope, a tilt sensor, a force sensor, a magnetometer, an optical sensor, a proximity sensor, a biometric sensor, etc., or any combination thereof. An output device may use the same type of interface port as an input device. For example, a Universal Serial Bus (USB) port may be used to provide an input device and an output device.

[0135] In some embodiments, the power source 1708 is structured as a battery or battery pack. Other types of power sources, such as an external power source (e.g., an electricity outlet), photovoltaic device, or power cell, may be used. The power source 1708 may further include power circuitry for delivering power from the power source 1708 itself, and / or an external power source, to the various parts of the UE 1700 via input circuitry or an interface such as an electrical power cable. Delivering power may be, for example, for charging of the power source 1708. Power circuitry may perform any formatting, converting, or other modification to the power from the power source 1708 to make the power suitable for the respective components of the UE 1700 to which power is supplied.

[0136] The memory 1710 may be or be configured to include memory such as random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic disks, optical disks, hard disks, removable cartridges, flash drives, and so forth. In one example, the memory 1710 includes one or more application programs 1714, such as an operating system, web browser application, a widget, gadget engine, or other application, and corresponding data 1716. The memory 1710 may store, for use by the UE 1700, any of a variety of various operating systems or combinations of operating systems.

[0137] The memory 1710 may be configured to include a number of physical drive units, such as redundant array of independent disks (RAID), flash memory, USB flash drive, external hard disk drive, thumb drive, pen drive, key drive, high-density digital versatile disc (HD-DVD) optical disc drive, internal hard disk drive, Blu-Ray optical disc drive, holographic digital data storage (HDDS) optical disc drive, external mini-dual in-line memory module (DIMM), synchronous dynamic random access memory (SDRAM), external micro-DIMM SDRAM, smartcard memory such as tamper resistant module in the form of auniversal integrated circuit card (UICC) including one or more subscriber identity modules (SIMs), such as a USIM and / or ISIM, other memory, or any combination thereof. The UICC may for example be an embedded UICC (eUICC), integrated UICC (iUICC) or a removable UICC commonly known as ‘SIM card.’ The memory 1710 may allow the UE 1700 to access instructions, application programs and the like, stored on transitory or non-transitory memory media, to off-load data, or to upload data. An article of manufacture, such as one utilizing a communication system may be tangibly embodied as or in the memory 1710, which may be or comprise a device-readable storage medium.

[0138] The processing circuitry 1702 may be configured to communicate with an access network or other network using the communication interface 1712. The communication interface 1712 may comprise one or more communication subsystems and may include or be communicatively coupled to an antenna 1722. The communication interface 1712 may include one or more transceivers used to communicate, such as by communicating with one or more remote transceivers of another device capable of wireless communication (e.g., another UE or a network node in an access network). Each transceiver may include a transmitter 1718 and / or a receiver 1720 appropriate to provide network communications (e.g., optical, electrical, frequency allocations, and so forth). Moreover, the transmitter 1718 and receiver 1720 may be coupled to one or more antennas (e.g., antenna 1722) and may share circuit components, software or firmware, or alternatively be implemented separately.

[0139] In the illustrated embodiment, communication functions of the communication interface 1712 may include cellular communication, Wi-Fi communication, LPWAN communication, data communication, voice communication, multimedia communication, short-range communications such as Bluetooth, near-field communication, location-based communication such as the use of the global positioning system (GPS) to determine a location, another like communication function, or any combination thereof. Communications may be implemented in according to one or more communication protocols and / or standards, such as IEEE 802.11, Code Division Multiplexing Access (CDMA), Wideband Code Division Multiple Access (WCDMA), GSM, LTE, New Radio (NR), UMTS, WiMax, Ethernet, transmission control protocol / intemet protocol (TCP / IP), synchronous optical networking (SONET), Asynchronous Transfer Mode (ATM), QUIC, Hypertext Transfer Protocol (HTTP), and so forth.

[0140] Regardless of the type of sensor, a UE may provide an output of data captured by its sensors, through its communication interface 1712, via a wireless connectionto a network node. Data captured by sensors of a UE can be communicated through a wireless connection to a network node via another UE. The output may be periodic (e.g., once every 15 minutes if it reports the sensed temperature), random (e.g., to even out the load from reporting from several sensors), in response to a triggering event (e.g., when moisture is detected an alert is sent), in response to a request (e.g., a user initiated request), or a continuous stream (e.g., a live video feed of a patient).

[0141] As another example, a UE comprises an actuator, a motor, or a switch, related to a communication interface configured to receive wireless input from a network node via a wireless connection. In response to the received wireless input the states of the actuator, the motor, or the switch may change. For example, the UE may comprise a motor that adjusts the control surfaces or rotors of a drone in flight according to the received input or to a robotic arm performing a medical procedure according to the received input.

[0142] A UE, when in the form of an Internet of Things (loT) device, may be a device for use in one or more application domains, these domains comprising, but not limited to, city wearable technology, extended industrial application and healthcare. Non-limiting examples of such an loT device are a device which is or which is embedded in: a connected refrigerator or freezer, a TV, a connected lighting device, an electricity meter, a robot vacuum cleaner, a voice controlled smart speaker, a home security camera, a motion detector, a thermostat, a smoke detector, a door / window sensor, a flood / moisture sensor, an electrical door lock, a connected doorbell, an air conditioning system like a heat pump, an autonomous vehicle, a surveillance system, a weather monitoring device, a vehicle parking monitoring device, an electric vehicle charging station, a smart watch, a fitness tracker, a head-mounted display for Augmented Reality (AR) or Virtual Reality (VR), a wearable for tactile augmentation or sensory enhancement, a water sprinkler, an animal- or item-tracking device, a sensor for monitoring a plant or animal, an industrial robot, an Unmanned Aerial Vehicle (UAV), and any kind of medical device, like a heart rate monitor or a remote controlled surgical robot. A UE in the form of an loT device comprises circuitry and / or software in dependence of the intended application of the loT device in addition to other components as described in relation to the UE 1700 shown in Figure 17.

[0143] As yet another specific example, in an loT scenario, a UE may represent a machine or other device that performs monitoring and / or measurements, and transmits the results of such monitoring and / or measurements to another UE and / or a network node. The UE may in this case be an M2M device, which may in a 3GPP context be referred to as an MTC device. As one particular example, the UE may implement the 3GPP NB-IoT standard.In other scenarios, a UE may represent a vehicle, such as a car, a bus, a truck, a ship and an airplane, or other equipment that is capable of monitoring and / or reporting on its operational status or other functions associated with its operation.

[0144] In practice, any number of UEs may be used together with respect to a single use case. For example, a first UE might be or be integrated in a drone and provide the drone’s speed information (obtained through a speed sensor) to a second UE that is a remote controller operating the drone. When the user makes changes from the remote controller, the first UE may adjust the throttle on the drone (e.g. by controlling an actuator) to increase or decrease the drone’s speed. The first and / or the second UE can also include more than one of the functionalities described above. For example, a UE might comprise the sensor and the actuator, and handle communication of data for both the speed sensor and the actuators.

[0145] Figure 18 shows a network node 1800 in accordance with some embodiments. As used herein, network node refers to equipment capable, configured, arranged and / or operable to communicate directly or indirectly with a UE and / or with other network nodes or equipment, in a telecommunication network. Examples of network nodes include, but are not limited to, access points (APs) (e.g., radio access points), base stations (BSs) (e.g., radio base stations, Node Bs, evolved Node Bs (eNBs) and NR NodeBs (gNBs)), O-RAN nodes or components of an O-RAN node (e.g., O-RU, O-DU, O-CU).

[0146] Base stations may be categorized based on the amount of coverage they provide (or, stated differently, their transmit power level) and so, depending on the provided amount of coverage, may be referred to as femto base stations, pico base stations, micro base stations, or macro base stations. A base station may be a relay node or a relay donor node controlling a relay. A network node may also include one or more (or all) parts of a distributed radio base station such as centralized digital units, distributed units (e.g., in an O- RAN access node) and / or remote radio units (RRUs), sometimes referred to as Remote Radio Heads (RRHs).

[0147] Other examples of network nodes include multiple transmission point (multi-TRP) 5G access nodes, multi-standard radio (MSR) equipment such as MSR BSs, network controllers such as radio network controllers (RNCs) or base station controllers (BSCs), base transceiver stations (BTSs), transmission points, transmission nodes, multi- cell / multicast coordination entities (MCEs), Operation and Maintenance (O&M) nodes, Operations Support System (OSS) nodes, Self-Organizing Network (SON) nodes, positioning nodes (e.g., Evolved Serving Mobile Location Centers (E-SMLCs)), and / or Minimization of Drive Tests (MDTs).

[0148] The network node 1800 includes a processing circuitry 1802, a memory 1804, a communication interface 1806, and a power source 1808. The network node 1800 may be composed of multiple physically separate components (e.g., aNodeB component and a RNC component, or a BTS component and a BSC component, etc.), which may each have their own respective components. In certain scenarios in which the network node 1800 comprises multiple separate components (e.g., BTS and BSC components), one or more of the separate components may be shared among several network nodes. For example, a single RNC may control multiple NodeBs. In such a scenario, each unique NodeB and RNC pair, may in some instances be considered a single separate network node. In some embodiments, the network node 1800 may be configured to support multiple radio access technologies (RATs). In such embodiments, some components may be duplicated (e.g., separate memory 1804 for different RATs) and some components may be reused (e.g., a same antenna 1810 may be shared by different RATs). The network node 1800 may also include multiple sets of the various illustrated components for different wireless technologies integrated into network node 1800, for example GSM, WCDMA, LTE, NR, WiFi, Zigbee, Z-wave, LoRaWAN, Radio Frequency Identification (RFID) or Bluetooth wireless technologies. These wireless technologies may be integrated into the same or different chip or set of chips and other components within network node 1800.

[0149] The processing circuitry 1802 may comprise a combination of one or more of a microprocessor, controller, microcontroller, central processing unit, digital signal processor, application-specific integrated circuit, field programmable gate array, or any other suitable computing device, resource, or combination of hardware, software and / or encoded logic operable to provide, either alone or in conjunction with other network node 1800 components, such as the memory 1804, to provide network node 1800 functionality.

[0150] In some embodiments, the processing circuitry 1802 includes a system on a chip (SOC). In some embodiments, the processing circuitry 1802 includes one or more of radio frequency (RF) transceiver circuitry 1812 and baseband processing circuitry 1814. In some embodiments, the radio frequency (RF) transceiver circuitry 1812 and the baseband processing circuitry 1814 may be on separate chips (or sets of chips), boards, or units, such as radio units and digital units. In alternative embodiments, part or all of RF transceiver circuitry 1812 and baseband processing circuitry 1814 may be on the same chip or set of chips, boards, or units.

[0151] The memory 1804 may comprise any form of volatile or non-volatile computer-readable memory including, without limitation, persistent storage, solid-statememory, remotely mounted memory, magnetic media, optical media, random access memory (RAM), read-only memory (ROM), mass storage media (for example, a hard disk), removable storage media (for example, a flash drive, a Compact Disk (CD) or a Digital Video Disk (DVD)), and / or any other volatile or non-volatile, non-transitory device-readable and / or computer-executable memory devices that store information, data, and / or instructions that may be used by the processing circuitry 1802. The memory 1804 may store any suitable instructions, data, or information, including a computer program, software, an application including one or more of logic, rules, code, tables, and / or other instructions capable of being executed by the processing circuitry 1802 and utilized by the network node 1800. The memory 1804 may be used to store any calculations made by the processing circuitry 1802 and / or any data received via the communication interface 1806. In some embodiments, the processing circuitry 1802 and memory 1804 is integrated.

[0152] The communication interface 1806 is used in wired or wireless communication of signaling and / or data between a network node, access network, and / or UE. As illustrated, the communication interface 1806 comprises port(s) / terminal(s) 1816 to send and receive data, for example to and from a network over a wired connection. The communication interface 1806 also includes radio front-end circuitry 1818 that may be coupled to, or in certain embodiments a part of, the antenna 1810. Radio front-end circuitry 1818 comprises filters 1820 and amplifiers 1822. The radio front-end circuitry 1818 may be connected to an antenna 1810 and processing circuitry 1802. The radio front-end circuitry may be configured to condition signals communicated between antenna 1810 and processing circuitry 1802. The radio front-end circuitry 1818 may receive digital data that is to be sent out to other network nodes or UEs via a wireless connection. The radio front-end circuitry 1818 may convert the digital data into a radio signal having the appropriate channel and bandwidth parameters using a combination of filters 1820 and / or amplifiers 1822. The radio signal may then be transmitted via the antenna 1810. Similarly, when receiving data, the antenna 1810 may collect radio signals which are then converted into digital data by the radio front-end circuitry 1818. The digital data may be passed to the processing circuitry 1802. In other embodiments, the communication interface may comprise different components and / or different combinations of components.

[0153] In certain alternative embodiments, the network node 1800 does not include separate radio front-end circuitry 1818, instead, the processing circuitry 1802 includes radio front-end circuitry and is connected to the antenna 1810. Similarly, in some embodiments, all or some of the RF transceiver circuitry 1812 is part of the communication interface 1806. Instill other embodiments, the communication interface 1806 includes one or more ports or terminals 1816, the radio front-end circuitry 1818, and the RF transceiver circuitry 1812, as part of a radio unit (not shown), and the communication interface 1806 communicates with the baseband processing circuitry 1814, which is part of a digital unit (not shown).

[0154] The antenna 1810 may include one or more antennas, or antenna arrays, configured to send and / or receive wireless signals. The antenna 1810 may be coupled to the radio front-end circuitry 1818 and may be any type of antenna capable of transmitting and receiving data and / or signals wirelessly. In certain embodiments, the antenna 1810 is separate from the network node 1800 and connectable to the network node 1800 through an interface or port.

[0155] The antenna 1810, communication interface 1806, and / or the processing circuitry 1802 may be configured to perform any receiving operations and / or certain obtaining operations described herein as being performed by the network node. Any information, data and / or signals may be received from a UE, another network node and / or any other network equipment. Similarly, the antenna 1810, the communication interface 1806, and / or the processing circuitry 1802 may be configured to perform any transmitting operations described herein as being performed by the network node. Any information, data and / or signals may be transmitted to a UE, another network node and / or any other network equipment.

[0156] The power source 1808 provides power to the various components of network node 1800 in a form suitable for the respective components (e.g., at a voltage and current level needed for each respective component). The power source 1808 may further comprise, or be coupled to, power management circuitry to supply the components of the network node 1800 with power for performing the functionality described herein. For example, the network node 1800 may be connectable to an external power source (e.g., the power grid, an electricity outlet) via an input circuitry or interface such as an electrical cable, whereby the external power source supplies power to power circuitry of the power source 1808. As a further example, the power source 1808 may comprise a source of power in the form of a battery or battery pack which is connected to, or integrated in, power circuitry. The battery may provide backup power should the external power source fail.

[0157] Embodiments of the network node 1800 may include additional components beyond those shown in Figure 18 for providing certain aspects of the network node’s functionality, including any of the functionality described herein and / or any functionality necessary to support the subject matter described herein. For example, thenetwork node 1800 may include user interface equipment to allow input of information into the network node 1800 and to allow output of information from the network node 1800. This may allow a user to perform diagnostic, maintenance, repair, and other administrative functions for the network node 1800.

[0158] Although the computing devices described herein (e.g., UEs, network nodes, hosts) may include the illustrated combination of hardware components, other embodiments may comprise computing devices with different combinations of components. It is to be understood that these computing devices may comprise any suitable combination of hardware and / or software needed to perform the tasks, features, functions and methods disclosed herein. Determining, calculating, obtaining or similar operations described herein may be performed by processing circuitry, which may process information by, for example, converting the obtained information into other information, comparing the obtained information or converted information to information stored in the network node, and / or performing one or more operations based on the obtained information or converted information, and as a result of said processing making a determination. Moreover, while components are depicted as single boxes located within a larger box, or nested within multiple boxes, in practice, computing devices may comprise multiple different physical components that make up a single illustrated component, and functionality may be partitioned between separate components. For example, a communication interface may be configured to include any of the components described herein, and / or the functionality of the components may be partitioned between the processing circuitry and the communication interface. In another example, non-computationally intensive functions of any of such components may be implemented in software or firmware and computationally intensive functions may be implemented in hardware.

[0159] In certain embodiments, some or all of the functionality described herein may be provided by processing circuitry executing instructions stored on in memory, which in certain embodiments may be a computer program product in the form of a non-transitory computer-readable storage medium. In alternative embodiments, some or all of the functionality may be provided by the processing circuitry without executing instructions stored on a separate or discrete device-readable storage medium, such as in a hard-wired manner. In any of those particular embodiments, whether executing instructions stored on a non-transitory computer-readable storage medium or not, the processing circuitry can be configured to perform the described functionality. The benefits provided by such functionality are not limited to the processing circuitry alone or to other components of thecomputing device, but are enjoyed by the computing device as a whole, and / or by end users and a wireless network generally.

Claims

Claims:

1. A computer-implemented method of geolocating a user equipment, UE, in a wireless network, comprising: for each cell of a plurality of cells in the wireless network: predicting (604) a plurality of ranges of distances at which the UE is likely to be located from the cell; predicting (606) a plurality of ranges of azimuth angles at which the UE is likely to be located relative to the cell; and combining (608) the prediction of the plurality of ranges of distances with the prediction of the plurality of ranges of azimuth angles to obtain a geographic region, associated with the cell, in which the UE is likely to be located; and determining (612) an intersection of the geographic regions associated with respective ones of the cells to obtain an intersection geographic region in which the UE is likely to be located.

2. The computer-implemented method of Claim 1, wherein predicting the plurality of ranges of distances is performed using a first classification model.

3. The computer-implemented method of Claim 2, wherein the first classification model takes as input reference signal received power, RSRP, reported by the UE for each of the cells and relative geographic locations of each of the cells.

4. The computer-implemented method of Claim 2, wherein the first classification model comprises a first neural network having one output for each possible range of distances that can be output by the first neural network.

5. The computer-implemented method of any of Claims 1 to 4, wherein predicting the plurality of ranges of azimuth angles is performed using a second classification model.

6. The computer-implemented method of Claim 5, wherein the second classification model takes as input reference signal received power, RSRP, reported by the UE for each of the cells and relative geographic locations of each of the cells.

7. The computer-implemented method of Claim 5, wherein the second classification model comprises a second neural network having one output for each possible range of azimuth angles that can be output by the second neural network.

8. The computer-implemented method of any previous Claim, further comprising: obtaining additional information relating to the geographic location of the UE; and narrowing a possible location of the UE within the intersection geographic region in which the UE is likely to be located.

9. The computer-implemented method of Claim 8, wherein the additional information comprises timing advance information for the UE relative to a serving cell; wherein narrowing the possible location of the UE within the intersection geographic region in which the UE is likely to be located comprises narrowing the possible location of the UE to an arc within the intersection geographic region based on the timing advance information.

10. The computer-implemented method of any of Claims 1 to 4, wherein predicting the plurality of ranges of distances is performed using a regression model.

11. A system for geolocating a user equipment, UE, in a wireless network, comprising: a first classifier (110) that predicts (604), for each cell of a plurality of cells in the wireless network reported by the UE, a plurality of ranges of distances at which the UE is likely to be located from the cell; a second classifier (120) that predicts (606), for each cell of the plurality of cells reported by the UE, a plurality of ranges of azimuth angles at which the UE is likely to be located relative to the cell; a first stage combiner (130A) that, for each cell, combines (608) the prediction of the plurality of ranges of distances with the prediction of the plurality of ranges of azimuth angles to obtain a geographic region, associated with the cell, in which the UE is likely to be located; and a second stage combiner (130B) that determines (612) an intersection of the geographic regions associated with respective ones of the cells to obtain an intersection geographic region in which the UE is likely to be located.

12. A system for geolocating a user equipment, UE, in a wireless network, comprising: a first classifier (110) that predicts (604), for each cell of a plurality of cells in the wireless network reported by the UE, a plurality of ranges of distances at which the UE is likely to be located from the cell; a second classifier (120) that predicts (606) , for each cell of the plurality of cells reported by the UE, a plurality of ranges of azimuth angles at which the UE is likely to be located relative to the cell; and a combiner (130, 130A, 130B) that determines (612) an intersection of the plurality of ranges of distances and the plurality of ranges of azimuth angles to obtain an intersection geographic region in which the UE is likely to be located.

13. A computer-implemented method of geolocating a user equipment, UE, in a wireless network, comprising: for each cell of a plurality of cells reported by the UE in the wireless network: predicting (604) a plurality of ranges of distances at which the UE is likely to be located from the cell; predicting (606) a plurality of ranges of azimuth angles at which the UE is likely to be located relative to the cell; and determining (612) an intersection of the plurality of ranges of distances and plurality of ranges of azimuth angles to obtain an intersection geographic region in which the UE is likely to be located.

14. The computer-implemented method of Claim 13, wherein predicting the plurality of ranges of distances is performed using a first classification model.

15. The computer-implemented method of Claim 14, wherein the first classification model takes as input reference signal received power, RSRP, reported by the UE for each of the cells and relative geographic locations of each of the cells.

16. The computer-implemented method of Claim 14, wherein the first classification model comprises a first neural network having one output for each possible range of distances that can be output by the first neural network.

17. The computer-implemented method of any of Claims 13 to 16, wherein predicting the plurality of ranges of azimuth angles is performed using a second classification model.

18. The computer-implemented method of Claim 17, wherein the second classification model takes as input reference signal received power, RSRP, reported by the UE for each of the cells and relative geographic locations of each of the cells.

19. The computer-implemented method of Claim 18, wherein the second classification model comprises a second neural network having one output for each possible range of azimuth angles that can be output by the second neural network.

20. The computer-implemented method of any of Claims 13 to 19, further comprising: obtaining additional information relating to the geographic location of the UE; and narrowing a possible location of the UE within the intersection geographic region in which the UE is likely to be located.

21. The computer-implemented method of Claim 20, wherein the additional information comprises timing advance information for the UE relative to a serving cell; wherein narrowing the possible location of the UE within the intersection geographic region in which the UE is likely to be located comprises narrowing the possible location of the UE to an arc within the intersection geographic region based on the timing advance information.

22. The computer-implemented method of any of Claims 13 to 16, wherein predicting the plurality of ranges of distances is performed using a regression model.

Images