Device and computer-implemented method for operating a mobile terminal, and device and method for supporting the mobile terminal in said method
Patent Information
- Application Number
- EP2023814430
- Authority / Receiving Office
- EP · EP
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2022-12-07
- Filing Date
- 2023-11-29
- Publication Date
- 2025-10-15
AI Technical Summary
Conventional methods for predicting radio connection properties in mobile terminals are limited in accuracy and robustness, especially when a mobile terminal moves between cells in a cellular network, as they rely solely on local measurements without collaborative learning or updating of model parameters.
A computer-implemented method that determines radio connection characteristics using a model with trainable parameters, where the model is updated centrally and collaboratively with other mobile terminals, allowing for improved prediction accuracy by incorporating quality measures and estimates from different locations and ages, thereby enhancing prediction quality across cell transitions.
This approach provides a more robust and accurate prediction of radio connection properties, especially during cell transitions, by leveraging distributed learning and collaborative estimation, leading to improved Quality of Service (QoS) in cellular networks.
Smart Images
Figure 1.1
Abstract
Description
[0001] Description
[0002] title
[0003] Device and computer-implemented method for operating a mobile terminal, device and method for supporting the mobile terminal in this method
[0004] State of the art
[0005] The invention relates to a device and a computer-implemented method for operating a mobile terminal and to a device and a method for supporting the mobile terminal in this method.
[0006] Traditionally, a passive measurement of a property of a radio link is performed by the mobile device itself and used to predict a property of the radio link.
[0007] Disclosure of the invention
[0008] The computer-implemented method for operating a mobile terminal provides that a variable is determined in the mobile terminal that characterizes a radio connection between the mobile terminal and an access point of a telecommunications network, wherein in the mobile terminal, a prediction for the property is determined depending on the determined variable and the at least one model parameter using a model that is designed to predict a property of the radio connection and / or a radio connection between the mobile terminal and another access point of the telecommunications network depending on the determined variable and depending on at least one model parameter, wherein in the mobile terminal, a reference variable is determined that characterizes the radio connection(s) for which the prediction was determined, wherein in the mobile terminal, a measure for a quality of the prediction is determined depending on the prediction and the reference variable,The mobile terminal sends the measure to a receiver outside the mobile terminal. At least one model parameter for the model, which was determined outside the mobile terminal as a function of the quality measure, is received by the mobile terminal from a transmitter outside the mobile terminal. At least one of the model parameters of the model is replaced in the mobile terminal by the at least one model parameter for the model. The model is thus trained in a distributed manner, i.e., with a learning step taking place outside the mobile terminal. This means that in the learning step, the model parameters of the local model of the mobile terminal are determined on a central learning unit.
[0009] For inference, it is provided that a further variable is determined in the mobile terminal and wherein a further prediction is determined in the mobile terminal depending on the further variable and the model in which the at least one model parameter for the model replaces the at least one model parameter of the model, wherein the further variable and the further prediction characterize the radio connection between the mobile terminal and the access point and / or the radio connection between the mobile terminal and the other access point and / or a further radio connection between the mobile terminal and another access point of the telecommunications network.
[0010] The quantity is preferably determined at a first time and at a first location, the prediction being determined for a second time and for a second location, the reference quantity being determined at the second time and at the second location, or the further quantity being determined at a third time and at a third location, and the further prediction being determined for a fourth time and for a fourth location.
[0011] Preferably, it is provided that a first estimate of the property for a given location is determined in the mobile terminal using the model depending on the size or the further size, wherein a second estimate of the property for the given location is received in the mobile terminal from a transmitter outside the mobile terminal, wherein the second estimate was determined outside the mobile terminal depending on a size that characterizes a radio connection between another mobile terminal and its access point to the telecommunications network, and wherein the prediction is determined depending on the first estimate and the second estimate. The prediction is thus determined in collaboration with another mobile terminal.In particular, when the first mobile terminal moves from one cell of a cell-based telecommunications network in which the first mobile terminal is located to another cell of this telecommunications network in which the other mobile terminal is located, this enables a more robust prediction.
[0012] The first estimate is preferably determined with a first part of the model, wherein the prediction is determined with a second part of the model depending on the first estimate and the second estimate.
[0013] The second part of the model is preferably configured to weight the first estimate based on a weight, wherein the weight is determined based on the age of the first estimate, and the prediction is determined based on the weight-weighted first estimate. The second part of the model is preferably configured to weight the second estimate based on a weight, wherein the weight is determined based on the age of the second estimate, and the prediction is determined based on the weight-weighted second estimate. This further increases the quality of the prediction.
[0014] Preferably, the mobile terminal receives a third estimate of the property for the given location from the transmitter or another transmitter external to the mobile terminal, wherein an age of the third estimate is determined, and wherein the prediction is determined based on the third estimate instead of the second estimate if the age of the third estimate is younger than the age of the second estimate. This further improves the prediction.
[0015] The variable preferably characterizes the radio connection in a first cell of a cell-based telecommunications network, and the further variable characterizes the radio connection in the first cell or a second cell of the cell-based telecommunications network. This determines the prediction for the same cell or a different cell, respectively.
[0016] A computer-implemented method for assisting a mobile terminal in a method for operating the mobile terminal provides that a measure for a quality of a prediction of a property of a radio connection between a mobile terminal and an access point of the telecommunications network is received, wherein the measure is determined as a function of a prediction and a reference value for the property, wherein the prediction was determined in the mobile terminal using a model having at least one model parameter, wherein at least one model parameter is determined for the model as a function of the measure and as a function of at least one further measure for a quality of a prediction of a property of a radio connection between another mobile terminal and its access point to the telecommunications network outside the mobile terminal,wherein the at least one model parameter for the model is sent to the mobile device from a transmitter external to the mobile device. During training, the mobile device is supported in distributed learning by centrally determining the model parameters.
[0017] Preferably, a quantity characterizing the radio connection between another mobile terminal and its access point to the telecommunications network is received and transmitted to the mobile terminal. During training, the mobile terminal is assisted by forwarding this quantity in determining the reference quantity for determining the quality measure when the prediction is determined for a location where the other mobile terminal determines the quantity.
[0018] Preferably, an estimate of the property characterizing the radio connection between another mobile terminal and its access point to the telecommunications network at a given location is received and sent to the mobile terminal.
[0019] The mobile terminal is configured to execute the method for operating the mobile terminal. The device for supporting the mobile terminal in the method for operating the mobile terminal is configured to execute the method for supporting the mobile terminal.
[0020] A computer program comprising computer-executable instructions, the execution of which by the computer results in the respective method, as well as a corresponding computer-readable medium on which the computer program is stored, has advantages corresponding to the advantages of these methods.
[0021] Further advantageous embodiments can be found in the following description and the drawing. The drawing shows:
[0022] Fig. 1 is a schematic representation of a telecommunications network, Fig. 2 is a schematic representation of a first embodiment of a system for operating a mobile terminal,
[0023] Fig. 3 steps in a method according to the first embodiment,
[0024] Fig. 4 is a schematic representation of a second embodiment of the system for operating the mobile terminal,
[0025] Fig. 5 is a schematic representation of a third embodiment of the system for operating the mobile terminal.
[0026] Figure 1 shows a schematic representation of a telecommunications network 100.
[0027] The telecommunications network 100 comprises a plurality of access points, of which a first access point 100-1, a second access point 100-2 and a third access point 100-3 are shown in Figure 3.
[0028] The telecommunications network 100 is a cell-based
[0029] Telecommunications network 100, where in the example, one cell is defined for each access point. The first access point 100-1 provides a first cell 101-1.
[0030] The second access point 100-2 provides a second cell 101-2. The third access point 100-3 provides a third cell 101-3.
[0031] The cells partially overlap each other in the example. The first cell provides a mobile terminal located in the first cell with a radio connection to a service offered in the telecommunications network 100 via the first access point 100-1. The second cell provides a mobile terminal located in the second cell with a radio connection to the service via the second access point 100-2. The third cell provides a mobile terminal located in the third cell with a radio connection to the service via the third access point 100-1. In the example, a mobile terminal is located in one or more of the cells, depending on its respective position. In the example, a mobile terminal is connected to one of the access points.
[0032] The example shows a first vehicle 103-1, which includes the first mobile terminal 101-1. In the example, the first mobile terminal 101-1 is integrated into the first vehicle 103-1. The example shows a second vehicle 103-2, which includes the second mobile terminal 101-2. In the example, the second mobile terminal 101-2 is integrated into the second vehicle 103-2. The example shows a third vehicle 103-3, which includes the third mobile terminal 101-3. In the example, the third mobile terminal 101-3 is integrated into the third vehicle 103-3.
[0033] A quality with which the service is available at a position of a mobile terminal in a cell, ie a Quality of Service, QoS, is characterized, for example, by a quantity that characterizes a radio connection between the mobile terminal and an access point of a telecommunications network 100.
[0034] The quality is characterized, for example, by a bandwidth of the transmission over the radio connection at the position.
[0035] The quality is characterized, for example, by an indicator of the received field strength at the location. For example, the radio connection is provided with a reference signal of the received field strength at the mobile device, RSRP, which characterizes the quality.
[0036] The quality is characterized, for example, by an indicator of the received power in a frequency channel of the radio link. For example, the radio link is provided with a received broadband power in the frequency channel, including thermal noise (RSSI), which characterizes the quality.
[0037] The quality is characterized, for example, by a calculated ratio value resulting from the RSRP value and the RSSI. For example, the radio connection is provided with a ratio value RSRQ calculated from these two values, which characterizes the quality.
[0038] RSRP, RSSI, and RSRQ are defined, for example, according to the 3rd Generation Partnership Project, 3GPP, Release 15. RSRP and RSSI are measurable in the mobile device.
[0039] Other metrics that characterize QoS and are measurable in the mobile device can also be used. Other metrics that characterize QoS and are measured externally to the mobile device and provided to the mobile device via a service external to the mobile device and an application, such as Mobilelnsight, on the mobile device, can also be used.
[0040] Mobilelnsight is e.g. in Mobileinsight: extracting and analyzing cellular network information on smartphones, Yuanjie Li, Chunyi Peng, Zengwen Yuan, Jiayao Li, Haotian Deng, Tao Wang, MobiCom '16: Proceedings of the 22nd Annual International Conference on Mobile Computing and NetworkingOctober 2016 Pages 202-215, https: / / dl.acm.org / doi / 10.1145 / 2973750.2973751.
[0041] In the example, a first mobile terminal 102-1 is located in the first cell 101-1. In the example, a second mobile terminal 102-2 is located in the second cell 101-2. In the example, a third mobile terminal 102-3 is located in the third cell 101-3.
[0042] The first mobile terminal 102-1 is configured to execute a method for operating the first mobile terminal 102-1.
[0043] In the example, the telecommunications network 100 comprises a device 104 configured to support the first mobile terminal 102-1 in this method. The device 104 is connected, for example, via an optical or wired communication link 105 to the first access point 101-1, the second access point 101-2, and the third access point 101-3.
[0044] It can be provided that the second mobile terminal 102-2 is designed to carry out the method for operating the second mobile terminal 102-2. It can be provided that the second mobile terminal 102-2 is designed to support the first mobile terminal 102-1 in carrying out the method without the second mobile terminal 102-2 itself carrying out the method. It can be provided that the third mobile terminal 102-3 is designed to carry out the method for operating the third mobile terminal 102-3. It can be provided that the third mobile terminal 102-3 is designed to support the first mobile terminal 102-1 in carrying out the method without the third mobile terminal 102-3 itself carrying out the method.
[0045] In the method for operating the first mobile terminal 102-1, the first mobile terminal 102-1 detects at least one variable that characterizes the quality of the radio connection to an access point that is accessible to the first mobile terminal 102-1. In the method, the first mobile terminal 102-1 determines a prediction for the quality of the radio connection between the first mobile terminal 102-1 and at least one access point of the telecommunications network 100. The access point is, for example, the access point currently used by the first mobile terminal 102-1 for its radio connection to the telecommunications network 100 or another access point that could be used currently or in the future.
[0046] Figure 2 schematically illustrates a system 200 for operating a mobile terminal according to a first embodiment.
[0047] The first embodiment is described below using the example of the first mobile terminal 102-1 integrated in the first vehicle 103-1. The system 200 comprises the first mobile terminal 102-1 and the device 104.
[0048] The first mobile terminal 102-1 comprises an interface 202 for the radio connection, a model 204 for predicting a property of the radio connection, and a device 206 for parameterizing the model 204. The model 204 comprises at least one model parameter. The model 204 is configured to determine the prediction depending on at least one model parameter and depending on the size and the at least one model parameter. The device 206 for parameterizing the model 204 is configured to determine at least one of the model parameters in the model 204.
[0049] The device 104 comprises an interface 208 for communication with the first mobile terminal 102-1 via a communication connection 210 to the interface 202 in the first mobile terminal 102-1. The device 104 comprises a device 212 for assisting in parameterizing the model 204.
[0050] In the first embodiment, model 204 comprises an artificial neural network whose weights are defined by the model parameters. Means 206 for parameterizing model 204 is configured, for example, to determine at least one of the model parameters in the artificial neural network.
[0051] The means 212 for assisting in parameterizing the model 204 is configured to determine the at least one model parameter in an optimization method in which a loss function is minimized using a gradient descent method. In the example, the loss function is defined as a function of the measure.
[0052] The device 212 for supporting the parameterization of the model 204 is configured to receive from a plurality of mobile terminals that are configured to determine a respective measure for the quality of their radio connection to the telecommunications network 100. The device 212 for supporting the parameterization of the model 204 is configured to minimize the loss function depending on these measures. The loss function is, for example, an average of the measures. The device 212 for supporting the parameterization of the model 204 is configured to determine gradients for the gradient descent method depending on the loss function and to determine the at least one model parameter for which the gradient is smaller than a threshold.
[0053] It can be provided that the device 212 for assisting in parameterizing the model 204 is configured to send the at least one model parameter to the plurality of mobile terminals. The plurality of mobile terminals includes, for example, the second mobile terminal 102-2 and / or the third mobile terminal 102-3.
[0054] The device 104 includes an output 214 for prediction.
[0055] Figure 3 shows steps of a first embodiment of a computer-implemented method for operating the first mobile terminal 102-1.
[0056] In a step 302, the size that characterizes the radio connection between the first mobile terminal 102-1 and an access point of the telecommunications network 100 is determined in the first mobile terminal 102-1.
[0057] For example, RSRP or RSSI is measured as a variable, or RSRQ is calculated from these. It can also be provided that the variable is another variable that can be measured in the first mobile terminal 102-1 and that characterizes the QoS. It can also be provided that the variable is another variable that is measured outside of the first mobile terminal 102-1 and that characterizes the QoS and is provided to the first mobile terminal 102-1 via the service outside the mobile terminal and the application, such as Mobilel nsight, in the first mobile terminal 102-1.
[0058] In the example, the size characterizes the radio connection between the first mobile terminal 102-1 and the first access point 100-1.
[0059] In the example, the size is determined at a first time and at a first location. The first location is the position of the first mobile terminal 102-1 at the first time and corresponds to the position of the first vehicle 103-1 at the time at which the size is determined. In a step 304, the prediction is determined in the first mobile terminal 102-1 using the model 204. In the example, the prediction is determined for a second time and for a second location. The second location is the position of the first mobile terminal 102-1 at the second time and corresponds to the position of the first vehicle at the second time.
[0060] In one example, the prediction of the property of the radio link via which the first mobile terminal 102-1 is connected to the first access point 100-1 is determined.
[0061] Instead or in addition thereto, it may be provided that the prediction of the property of a radio connection between the first mobile terminal 102-1 and another access point of the telecommunications network 100, e.g. the second access point 100-2 or the third access point 100-3, is determined.
[0062] In a step 306, a reference variable is determined in the first mobile terminal 102-1, which characterizes the radio connection for which the prediction was determined. In the example, the reference variable is characterized by the same property as the variable, ie, both the variable and the reference variable are, for example, bandwidth, RSRP or RSSI or RSRQ, or one of the other variables that are measured or provided.
[0063] In the example, the reference variable is determined at the second time and at the second location. In the example, it is intended that the second time or the second location at which the reference variable is determined and the second time or the second location for which the prediction is determined exactly or at least substantially coincide. It can be intended that the second time or the second location at which the reference variable is determined and the second time or the second location for which the prediction is determined deviate from each other by a given tolerance.
[0064] The time and location for determining the reference variable are determined, for example, depending on a planned route of the first vehicle in which the first mobile terminal 102-1 is located. The time is, for example, the exact absolute time or a comparable time, e.g., the same time on a different day or the same day in a different year. The reference variable can also be determined at a different time within a predetermined time period that includes the time.
[0065] It can be provided that a quantity characterizing the radio connection between another mobile terminal and its access point to the telecommunications network 100 is received, and the reference quantity is determined depending thereon.
[0066] It may be provided that the telecommunications network 100, in particular the device 104, receives this variable from the other mobile terminal and sends it to the mobile terminal 102-1.
[0067] In a step 308, a measure of a quality of the prediction is determined in the first mobile terminal 102-1 depending on the prediction and the reference variable.
[0068] For example, a deviation, in particular a difference between the prediction and the reference value, is determined.
[0069] In a step 310, the measure is sent from the first mobile terminal 102-1 to a receiver outside the first mobile terminal 102-1.
[0070] In the example, the receiver is device 104. In the example, the measurement is transmitted from interface 202 in the first mobile terminal 102-1 to interface 208 in device 104.
[0071] It can be provided that the measure is received by a plurality of mobile terminals which are designed to determine a respective measure for the quality of their radio connection to the telecommunications network 100.
[0072] In a step 312, at least one of the model parameters is determined outside of the first mobile terminal 102-1. In the example, the at least one model parameter is determined by the device 104.
[0073] The at least one model parameter is determined depending on the measure received from the first mobile terminal 102-.
[0074] In the example, the at least one model parameter is determined in the optimization process, in which the loss function is minimized using the gradient descent method. In the example, the loss function is defined as a function of the measure received from the first mobile terminal 102-1.
[0075] It can be provided that the loss function is defined as a function of the majority of the measures. The loss function is, for example, the mean of these measures. The gradients for the gradient descent method are determined, for example, as a function of the loss function. In the example, at least one model parameter is determined for which the gradient is smaller than the threshold.
[0076] In a step 314, the first mobile terminal 102-1 receives at least one model parameter for the model 204. This means that the first mobile terminal 102-1 receives the model parameter from a transmitter external to the first mobile terminal 102-1.
[0077] It can be provided that the device 212 for assisting in parameterizing the model 204 is designed to determine the at least one model parameter and to send it to the plurality of mobile terminals, including the first mobile terminal 102-1.
[0078] In the example, the transmitter is device 104. In the example, at least one model parameter is transmitted from interface 208 in device 104 to interface 202 in the first mobile terminal 102-1.
[0079] In a step 316, at least one of the model parameters of model 204 is replaced in the first mobile terminal 102-1 by the at least one model parameter for model 204. Model 204 is trained through steps 302 to 316. These steps can be performed repeatedly to further train model 204.
[0080] It may be provided that the procedure ends thereafter.
[0081] In the example, the model 204 is planned to be used.
[0082] In a step 318, a further variable is determined in the first mobile terminal 102-1. In one example, the further variable characterizes the radio connection between the first mobile terminal 102-1 and the first access point 100-1. It may be provided that the further variable instead characterizes the radio connection between the first mobile terminal 102-1 and the other access point, e.g., the second access point 100-2 or the third access point 100-3.
[0083] In a step 320, a further prediction is determined in the first mobile terminal 102-2 depending on the further size and the model 204.
[0084] In model 204, the at least one model parameter for model 204 replaces the at least one model parameter of model 204.
[0085] In the example, the further prediction characterizes the radio connection between the first mobile terminal 102-1 and the first access point 100-1. It can be provided that the further variable characterizes the radio connection between the first mobile terminal 102-1 and the other access point, e.g., the second access point 100-2 or the third access point 100-3.
[0086] In the example, the additional variable is determined at a third time and a third location. The additional prediction is determined for a fourth time and a fourth location.
[0087] In the example, the variable characterizes the radio connection in the first cell 101-1. The further variable characterizes the radio connection in the first cell 101-1. It can also be provided that the further variable characterizes the radio connection in the second cell 101-2 or the third cell 101-3.
[0088] The device 104 is, for example, a central server. It can be provided that the device 104 is designed to provide a part of the server for each cell.
[0089] Figure 4 schematically illustrates the system 200 for operating a mobile terminal according to a second embodiment. The elements included in both embodiments are designated in Figure 4 with the same reference numerals as in Figure 2.
[0090] The second embodiment is particularly suitable for using information about a radio connection to an access point of the telecommunications network 100 that is not directly accessible from the first mobile terminal 102-1 at the time or location of the prediction determination. The corresponding method is designed accordingly.
[0091] For example, the first mobile terminal 102-1 is located in the first cell 101-1 outside the second cell 101-2. For example, the second mobile terminal 102-2 is located in the second cell 101-2 and is capable of evaluating the radio connection at its current location to the second access point 100-2.
[0092] In contrast to the first embodiment, the model 204 according to the second embodiment comprises a first part 216 for determining a first estimate 218 of the property for a given location depending on a variable that characterizes the radio connection between the first mobile terminal 102-1 and an access point of the telecommunications network 100.
[0093] In contrast to the first embodiment, the model 204 according to the second embodiment comprises a second part 220 for determining the prediction depending on the first estimate 218 and depending on a second estimate 222 of the property for the predetermined location, which is received from a transmitter outside the first mobile terminal 102-1, e.g., via the interface 202. The second mobile terminal 102-2 is designed, for example, to determine the second estimate 222. The second mobile terminal 102-2 is designed, for example, to make the second estimate 222 available to other mobile terminals in the telecommunications network 100. The telecommunications network 100 is designed, for example, to receive the second estimate 222 from the second mobile terminal 102-2 and forward it to the first mobile terminal 102-1.
[0094] For example, device 104 is configured to receive and forward the second estimate 222 for the specified location. The telecommunications network 100 is configured, for example, to transmit the second estimate 222 required for the prediction for this location. For example, interface 202 is configured to send a request for the second estimate for the specified location to the telecommunications network 100.
[0095] The second part 220 of the model 204 is configured, for example, to weight the first estimate 218 depending on a weight. In one embodiment, the model 204 is configured to determine the weight depending on the age of the first estimate. The second part 220 is configured, for example, to determine the prediction depending on the weight-weighted first estimate 218.
[0096] The second part 220 of the model 204 is configured, for example, to weight the second estimate 222 depending on a weight. In one embodiment, the model 204 is configured to determine the weight depending on the age of the second estimate 222. The second part 220 is configured, for example, to determine the prediction depending on the weight-weighted second estimate 222.
[0097] The first part 216 comprises, for example, an artificial neural network that is designed to determine the first estimate 218.
[0098] The second part 220 comprises, for example, an artificial neural network configured to map the first estimate 218 and the second estimate 220 to the prediction. The means 206 for parameterizing the model 204 is configured, for example, to determine at least one of the model parameters in the first and / or second artificial neural network.
[0099] The method for operating the first mobile terminal 102-1 according to the second embodiment differs in the example from the method according to the first embodiment in that in step 304 the first estimate 218 is determined in the first mobile terminal 102-1 for a predetermined location, the second estimate 222 for the predetermined location is received from outside the first mobile terminal 102-1, and the prediction is determined in the first mobile terminal 102-1 depending on the two estimates for the predetermined location.
[0100] Step 306 according to the second embodiment differs from step 306 according to the first embodiment in that the reference variable is determined at the predetermined location or substantially there.
[0101] The step 320 according to the second embodiment differs from the step 320 according to the first embodiment in that the first estimate 218 is determined in the first mobile terminal 102-1 for a given location, the second estimate 222 for the given location is received from outside the first mobile terminal 102-1, and the prediction is determined in the first mobile terminal 102-1 depending on the two estimates for the given location.
[0102] For example, the second part 220 of the model 204 weights the first estimate 218 depending on the weight for the second estimate 218. For example, the second part 220 determines this weight depending on the age of the first estimate 218. This means that the prediction is determined depending on the first estimate 218 weighted with this weight.
[0103] For example, the second part 220 of the model 204 weights the second estimate 222 depending on the weight for the second estimate 218.
[0104] For example, the second part 220 determines this weight depending on the age of the second estimate 222. This means that the prediction is determined depending on the second estimate 222 weighted with this weight. It can be provided that the second part 220 of the model 204, in particular the artificial neural network representing this part, is designed to map a plurality of estimates received from outside the first mobile terminal 102-1, e.g., via the interface 202, as described for the second estimate 222, weighted or unweighted, together with the first estimate 218 and the second estimate 222, onto the prediction.
[0105] In one embodiment, the telecommunications network 100, in particular the device 104, is configured to capture the prediction of a mobile terminal together with the location at which this prediction was determined and to provide it to another mobile terminal as a second estimate 222. In one embodiment, these predictions are stored in a central database, in particular, with an identification of the cell for which the prediction was determined, and the prediction, which contains the identification, is provided as a second estimate 222 upon request from a mobile terminal.
[0106] A prediction, ie, the second estimate 222, is associated with a respective predetermined location or cell. The prediction, ie, the second estimate 222, may be time-independent in the second embodiment.
[0107] Figure 5 schematically shows the system 200 according to a third embodiment.
[0108] In the third embodiment, it is provided that the prediction, ie, the second estimate 222, is associated with a point in time at which the prediction was determined. The elements included in the second and third embodiments are designated in Figure 5 with the same reference numerals as in Figure 4.
[0109] The third embodiment is particularly suitable for using the most up-to-date information possible via a radio connection to an access point of the telecommunications network 100. The corresponding method is designed accordingly. According to the third embodiment, the apparatus 104 comprises a device 224 for selecting an estimate for determining the prediction. The device 224 for selecting the estimate is designed to determine a time associated with the second estimate 222. In the example, the interface 202 is designed to receive the second estimate 222 and the time. The telecommunications network 100 is designed, for example, to send the second estimate 222 and its time. For example, the interface 202 is designed to send a request for the second estimate together with its time to the telecommunications network 100.
[0110] The means 224 for selecting the estimate is designed to compare a current time or a time at which the first estimate 216 applies with the received time, and to select the second estimate 222 for determining the prediction if the second estimate 222 is the same age as or younger than the first estimate 216. The means 224 for selecting the estimate is designed not to select the second estimate 222 for determining the prediction otherwise.
[0111] In an example in which multiple estimates are received from outside the first mobile terminal 102-1, it may be provided that the device 224 is configured to select the estimate or multiple estimates used to determine the prediction. For example, the most recent of the estimates is selected, or the estimates that are more recent than the first estimate 216 are selected.
[0112] For example, if the second mobile terminal 102-2 determines a bandwidth of 10 Mbit at a location X as an estimate at a time t0, and the third mobile terminal 102-3 determines a bandwidth of 17 Mbit at a time t0 + x ms at the location X, and the first mobile terminal 102-1 then reaches the location X, the first mobile terminal 102-1 uses the estimate from the third mobile terminal 102-3 as the most recent estimate. It may also be provided to use both of these estimates if the time interval between the two estimates is less than a threshold.
Claims
Claims 1. A computer-implemented method for operating a mobile terminal (102-1), characterized in that a variable is determined (302) in the mobile terminal (102-1) that characterizes a radio connection between the mobile terminal (102-1) and an access point (100-1) of a telecommunications network (100), wherein in the mobile terminal (102-1), a model (204) that is designed to predict a property of the radio connection and / or a radio connection between the mobile terminal (102-1) and another access point (100-2, 100-3) of the telecommunications network depending on the determined variable and depending on at least one model parameter is used to determine a prediction for the property (304) depending on the determined variable and the at least one model parameter, wherein in the mobile terminal (102-1) a reference variable is determined (306) that characterizes the radio connection(s) for which the prediction was determined,wherein in the mobile terminal (102-1) a measure of the quality of the prediction is determined (308) depending on the prediction and the reference variable, wherein the measure is sent (310) from the mobile terminal (102-1) to a receiver outside the mobile terminal (102-1), wherein at least one model parameter for the model (204), which was determined outside the mobile terminal (102-1) depending on the measure of the quality, is received (314) from the mobile terminal (102-1) by a transmitter outside the mobile terminal (102-1), wherein in the mobile terminal (102-1) at least one of the model parameters of the model (204) is replaced (316) by the at least one model parameter for the model (204).
2. Method according to claim 1, characterized in that in the mobile terminal (102-1) a further variable is determined (318) and wherein in the mobile terminal (102-1) a further prediction is made depending on the further variable and the model (204) in which the at least one Model parameter for the model (204) replaces the at least one model parameter of the model (204), wherein the further variable and the further prediction characterize the radio connection between the mobile terminal (102-1) and the access point (100-1) and / or the radio connection between the mobile terminal (102-1) and the other access point (100-2) and / or a further radio connection between the mobile terminal (102-1) and another access point (100-3) of the telecommunications network (100).
3. Method according to claim 1 or 2, characterized in that the variable is determined at a first time and at a first location (302), wherein the prediction is determined for a second time and for a second location (304), wherein the reference variable is determined at the second time and at the second location (306), or wherein the further variable is determined at a third time and at a third location (318) and wherein the further prediction is determined for a fourth time and for a fourth location (320).
4. Method according to one of claims 1 to 3, characterized in that in the mobile terminal (102-1) with the model (204) a first estimate (218) of the property for a given location is determined depending on the size or the further size, wherein in the mobile terminal (102-1) a second estimate (222) of the property for the given location is received from a transmitter outside the mobile terminal (102-1), wherein the second estimate (222) was determined outside the mobile terminal (102-1) depending on a size that characterizes a radio connection between another mobile terminal (102-2) and its access point (100-1) to the telecommunications network (100), and wherein the prediction is determined depending on the first estimate (216) and the second estimate (222).
5. The method according to claim 4, characterized in that the first estimate (218) is determined with a first part (216) of the model (204), and the prediction is determined with a second part (220) of the model (204) depending on the first estimate and the second estimate. Method according to claim 5, characterized in that the second part (220) of the model (204) is designed to weight the first estimate (218) depending on a weight, wherein the weight is determined depending on an age of the first estimate (218) and the prediction is determined depending on the first estimate (218) weighted with the weight, and / or that the second part (220) of the model (204) is designed to weight the second estimate (222) depending on a weight, wherein the weight is determined depending on an age of the second estimate (222) and the prediction is determined depending on the second estimate (222) weighted with the weight.Method according to claim 6, characterized in that the mobile terminal (102-1) receives a third estimate of the property for the predetermined location from the transmitter or another transmitter outside the mobile terminal (102-1), wherein an age of the third estimate is determined, and wherein the prediction is determined as a function of the third estimate instead of the second estimate (222) if the age of the third estimate is younger than the age of the second estimate (222). Method according to one of the preceding claims, characterized in that the variable characterizes the radio connection in a first cell of a cell-based telecommunications network (100), and the further variable characterizes the radio connection in the first cell (101-1) or a second cell (101-2) of the cell-based telecommunications network (100).Computer-implemented method for supporting a mobile terminal (102-1) in a method for operating the mobile terminal (102-1), characterized in that a measure of a quality of a prediction of a property of a radio connection between a mobile terminal (102-1) and an access point of the telecommunications network (100) is received, wherein the measure is determined as a function of a prediction and a reference value for the property, wherein the prediction in the mobile terminal (102-1) is provided with a. A model (204) has been determined which has at least one model parameter, wherein, depending on the measure and depending on at least one further measure for a quality of a prediction of a property of a radio connection between another mobile terminal (102-2) and its access point to the telecommunications network outside the mobile terminal (102-1), at least one model parameter for the model (204) is determined, wherein the at least one model parameter for the model (204) is sent from a transmitter outside the mobile terminal (102-1) to the mobile terminal (102-1). Method according to claim 9, characterized in that a variable which characterizes the radio connection between another mobile terminal (102-2) and its access point to the telecommunications network (100) is received and sent to the mobile terminal (102-1).Method according to claim 8 or 9, characterized in that an estimate of the property that characterizes the radio connection between another mobile terminal and its access point to the telecommunications network (100) at a predetermined location is received and sent to the mobile terminal (102-1). Mobile terminal (102-1), characterized in that the mobile terminal (102-1) is designed to carry out the method according to one of claims 1 to 8. Device (104) for assisting a mobile terminal (102-1) in a method for operating the mobile terminal (102-1), characterized in that the device is designed to carry out the method according to one of claims 9 to 11. Computer program, characterized in that the computer program comprises computer-executable instructions, the execution of which by the computer causes the method according to one of claims 1 to 8 or 9 to 11 to run.
15. A computer-readable medium on which the computer program according to claim 14 is stored.