Handover prediction method and apparatus, and device and storage medium
By receiving map information of the UE physical environment and extracting environmental error information using pre-trained models, the problem of low handover prediction accuracy in the prior art is solved, and more efficient base station handover prediction is achieved, ensuring the stability of communication quality.
Patent Information
- Application Number
- PCT/CN2023/094083
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-12
- Publication Date
- 2024-11-21
AI Technical Summary
In the prior art, the prediction accuracy of the switching prediction method is low, and the factors of the peripheral physical environment of the user equipment (UE) cannot be effectively considered, resulting in unstable communication quality.
By receiving map information of the physical environment in which the UE is located, the environment error information is extracted using the pre-trained model, and based on the information, the base station to which the UE is to be switched is predicted, thereby improving the accuracy and performance of the handover prediction.
The accuracy and performance of handover prediction are improved, and the communication quality of the UE is ensured, with wide applicability and low limitation. It does not need to rely on the position information and received signal strength of the UE, which reduces the calculation amount and improves efficiency.
Smart Images

Figure CN2023094083_21112024_PF_FP_ABST
Abstract
Description
A switching prediction method, device, equipment and storage medium Technical Field
[0001] The present disclosure relates to the field of communication technology, and in particular to a handover prediction method, apparatus, device, and storage medium. Background Art
[0002] In a communication system, the base station to which a user equipment (UE) is connected typically switches. For example, when the UE moves from the coverage area of the current serving base station to the coverage area of another base station due to a change in location, or when the UE's communication quality deteriorates, or in order to balance the load between cells, the UE typically switches from the current serving base station to another base station.
[0003] In related technologies, before switching base stations, switching predictions are usually performed. For example, it is predicted in advance whether the UE will switch base stations at the next moment, and when the base station is to be switched at the next moment, the target base station to which the UE will switch at the next moment is also predicted, so that the UE can directly switch to the target base station at the next moment to ensure the continuity and stability of the UE's communication.
[0004] However, the prediction accuracy of the switching prediction method in the related art is low.
[0005] Summary of the Invention
[0006] The present disclosure provides a handover prediction method, apparatus, device, and storage medium.
[0007] In a first aspect, an embodiment of the present disclosure provides a handover prediction method, comprising:
[0008] receiving map information of a physical environment of a user equipment UE sent by a second device;
[0009] The base station to which the UE is to switch is predicted according to the map information.
[0010] In a second aspect, an embodiment of the present disclosure provides a handover prediction method, including:
[0011] Obtaining location information and received signal strength of the UE at at least one moment collected by the UE;
[0012] Acquire error position information and error received signal strength based on the position information and received signal strength;
[0013] Combining the position information and the received signal strength with the error position information and the error received signal strength to obtain at least one set of combined information;
[0014] The at least one set of combined information is input into a pre-trained third model to obtain an output result of the third model, where the output result of the third model is: the base station to which the UE is to switch, as predicted by the third model.
[0015] In a third aspect, an embodiment of the present disclosure provides a handover prediction method, including:
[0016] Determine map information of the physical environment in which the UE is located;
[0017] The map information is sent to the first device.
[0018] In a fourth aspect, an embodiment of the present disclosure provides a handover prediction method, including:
[0019] Collecting location information and received signal strength of the UE at at least one moment;
[0020] Send the location information and received signal strength at at least one moment collected by the UE to the first device.
[0021] In a fifth aspect, an embodiment of the present disclosure provides a communication device, including:
[0022] a transceiver module, configured to receive map information of a physical environment of a user equipment UE sent by a second device;
[0023] A processing module is used to predict the base station to which the UE is to switch based on the map information.
[0024] In a sixth aspect, an embodiment of the present disclosure provides a communication device, including:
[0025] a transceiver module, configured to obtain location information and received signal strength of the UE at at least one moment collected by the UE;
[0026] A processing module, configured to obtain error position information and error received signal strength based on the position information and received signal strength;
[0027] The processing module is further configured to combine the position information and the received signal strength with the error position information and the error received signal strength to obtain at least one set of combined information;
[0028] The processing module is also used to input the at least one set of combined information into a pre-trained third model to obtain an output result of the third model, where the output result of the third model is: the base station to which the UE is to switch as predicted by the third model.
[0029] In a seventh aspect, an embodiment of the present disclosure provides a communication device, including:
[0030] A processing module, configured to determine map information of the physical environment in which the UE is located;
[0031] The transceiver module is used to send the map information to the first device.
[0032] In an eighth aspect, an embodiment of the present disclosure provides a communication device, including:
[0033] a processing module, configured to collect location information and received signal strength of the UE at at least one moment;
[0034] The transceiver module is used to send the location information and received signal strength at at least one moment collected by the UE to the first device.
[0035] In a ninth aspect, an embodiment of the present disclosure provides a communication device, which includes a processor. When the processor calls a computer program in a memory, the method described in any one of the first to fourth aspects above is executed.
[0036] In the tenth aspect, an embodiment of the present disclosure provides a communication device, which includes a processor and a memory, in which a computer program is stored; the processor executes the computer program stored in the memory so that the communication device executes the method described in any one of the first to fourth aspects above.
[0037] In the eleventh aspect, an embodiment of the present disclosure provides a communication device, which includes a processor and an interface circuit, wherein the interface circuit is used to receive code instructions and transmit them to the processor, and the processor is used to run the code instructions to enable the device to execute the method described in any one of the first to fourth aspects above.
[0038] In aspect 12, an embodiment of the present disclosure provides a communication system, which includes the communication device described in any one of aspects 5 to 8, or the system includes the communication device described in aspect 9, or the system includes the communication device described in aspect 10, or the system includes the communication device described in aspect 11.
[0039] In the thirteenth aspect, an embodiment of the present disclosure provides a computer-readable storage medium for storing instructions used for the above-mentioned network device. When the instructions are executed, the terminal executes the method described in any one of the above-mentioned aspects from the first to the fourth aspects.
[0040] In a fourteenth aspect, the present disclosure further provides a computer program product comprising a computer program, which, when executed on a computer, enables the computer to execute the method described in any one of the first to fourth aspects above.
[0041] In a fifteenth aspect, the present disclosure provides a chip system comprising at least one processor and an interface for supporting a network device in implementing the functions described in any one of aspects 1 to 4, such as determining or processing at least one of the data and information involved in the above method. In one possible design, the chip system further comprises a memory for storing computer programs and data necessary for the source slave node. The chip system may be composed of a chip or may include a chip and other discrete components.
[0042] In a sixteenth aspect, the present disclosure provides a computer program, which, when executed on a computer, enables the computer to execute the method described in any one of the first to fourth aspects above. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] The above and / or additional aspects and advantages of the present disclosure will become apparent and readily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:
[0044] FIG1 is a schematic diagram of the architecture of some communication systems provided by embodiments of the present disclosure;
[0045] FIG2a is a schematic flow chart of a handover prediction method provided by another embodiment of the present disclosure;
[0046] FIG2 b is a schematic flow chart of a handover prediction method provided by another embodiment of the present disclosure;
[0047] FIG3a is a schematic flow chart of a handover prediction method provided in yet another embodiment of the present disclosure;
[0048] FIG3 b presents a flowchart of a process for training a first model provided by an embodiment of the present disclosure;
[0049] FIG4a is a schematic flow chart of a handover prediction method provided in yet another embodiment of the present disclosure;
[0050] FIG4 b is a flowchart of a process for training a second model provided by an embodiment of the present disclosure;
[0051] FIG5 is a schematic flow chart of a handover prediction method provided in yet another embodiment of the present disclosure;
[0052] FIG6 a is a schematic flow chart of a handover prediction method provided in yet another embodiment of the present disclosure;
[0053] FIG6 b presents a flowchart of a process for training a third model provided by an embodiment of the present disclosure;
[0054] FIG6c is a structural block diagram of how to select a TTI according to an embodiment of the present disclosure;
[0055] FIG7 is a schematic flow chart of a handover prediction method provided in yet another embodiment of the present disclosure;
[0056] FIG8 is a schematic flow chart of a handover prediction method provided in yet another embodiment of the present disclosure;
[0057] FIG9 is a schematic structural diagram of a communication device provided by an embodiment of the present disclosure;
[0058] FIG10 is a schematic structural diagram of a communication device provided by an embodiment of the present disclosure;
[0059] FIG11 is a schematic structural diagram of a communication device provided by an embodiment of the present disclosure;
[0060] FIG12 is a schematic structural diagram of a communication device provided by an embodiment of the present disclosure;
[0061] FIG13 is a block diagram of a communication device provided by an embodiment of the present disclosure;
[0062] FIG14 is a schematic structural diagram of a chip provided in accordance with an embodiment of the present disclosure. DETAILED DESCRIPTION
[0063] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible implementations consistent with the present disclosure. Rather, they are merely examples of apparatuses and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
[0064] The terms used in the embodiments of the present disclosure are for the purpose of describing specific embodiments only and are not intended to limit the embodiments of the present disclosure. The singular forms "a," "an," and "the" used in the embodiments of the present disclosure and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and includes any or all possible combinations of one or more associated listed items.
[0065] It should be understood that although the terms first, second, third, etc. may be used to describe various information in the embodiments of the present disclosure, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of the embodiments of the present disclosure, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".
[0066] The embodiments of the present disclosure are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present disclosure, and should not be understood as limiting the present disclosure.
[0067] In related technologies, the switching prediction methods may include the following two:
[0068] Method 1: Handover prediction based on UE location information.
[0069] Optionally, the UE's location information can be obtained in real time, the UE's movement trajectory can be determined based on the UE's location information, and a handover prediction can be made based on the UE's movement trajectory. For example, if the UE's current serving base station is base station A, and the UE's movement trajectory is determined to be moving toward the coverage area of base station B based on the UE's location information, then if it is determined based on the UE's location information that the UE is currently close to the boundary of the coverage area of base station A, then it is determined that the UE needs to perform a base station handover at the next moment, and the target base station to be switched to at the next moment is: base station B.
[0070] Method 2: Handover prediction based on the UE's received signal strength.
[0071] Optionally, the received signal strength of the current serving base station and adjacent base stations can be monitored in real time, and the decision on whether to trigger a handover to the next location can be made based on their changes. For example, if it is determined that the received signal strength of the UE's current serving base station A changes from strong to weak, and the received signal strength of the UE's adjacent base station B changes from weak to strong, then it is determined that the UE needs to perform a base station handover at the next moment, and the target base station to be handed over at the next moment is: base station B.
[0072] However, in the first method, the location information cannot include real-time channel fading information, and is less robust to sudden changes and interference in the propagation environment, lacking timeliness. Furthermore, the accuracy of the location information itself is also greatly affected by the surrounding environment and fluctuates greatly. When handover prediction is performed based on location information containing large errors, both prediction accuracy and performance are reduced. Furthermore, in the second method, due to the complexity of wireless propagation and the numerous interference factors, the variation pattern of received signal strength is unstable. The actual predicted handover results are often suboptimal due to environmental factors such as multipath and non-line-of-sight. Furthermore, in order to accurately simulate the variation pattern of signal strength, the amount of data required for prediction is relatively large, resulting in reduced prediction efficiency.
[0073] Based on this, the present disclosure provides a handover prediction method.
[0074] In order to better understand a handover prediction method disclosed in an embodiment of the present disclosure, the communication system to which the embodiment of the present disclosure is applicable is first described below.
[0075] Please refer to Figure 1, which is a schematic diagram of the architecture of a communication system provided by an embodiment of the present disclosure. The communication system may include but is not limited to at least one first device, at least one second device and at least one UE, wherein the first device may be a network device or a data analysis server, and the second device may be a Global Navigation Satellite System (GNSS) or a sensor. In addition, the number and form of devices shown in Figure 1 are only for example and do not constitute a limitation on the embodiments of the present disclosure. The application may include one or more first devices, or one or more second devices, or one or more UEs. The communication system shown in Figure 1 takes a first device, which is a network device, a second device, which is a GNSS, and a UE as an example.
[0076] It should be noted that the technical solutions of the embodiments of the present disclosure can be applied to various communication systems, such as long-term evolution (LTE) systems, fifth-generation (5G) mobile communication systems, 5G new radio (NR) systems, or other future new mobile communication systems.
[0077] The UE in the embodiments of the present disclosure can be an entity on the user side for receiving or transmitting signals, such as a mobile phone. UE can also be called a terminal, terminal equipment, mobile station (MS), mobile terminal (MT), etc. GNSS can be a car with communication functions, a smart car, a mobile phone, a wearable device, a tablet computer (Pad), a computer with wireless transceiver functions, a virtual reality (VR) terminal, an augmented reality (AR) terminal, a wireless terminal in industrial control (industrial control), a wireless terminal in self-driving, a wireless terminal in remote medical surgery, a wireless terminal in a smart grid, a wireless terminal in transportation safety (transportation safety), a wireless terminal in a smart city (smart city), a wireless terminal in a smart home (smart home), etc. The embodiments of the present disclosure do not limit the specific technology and specific device form adopted by the terminal device.
[0078] The network device in the embodiment of the present disclosure may be an entity on the network side for transmitting or receiving signals. For example, the network device may be an evolved NodeB (eNB), a transmission reception point (TRP), a radio remote head (RRH), a next generation NodeB (gNB) in an NR system, a base station in other future mobile communication systems, or an access node in a wireless fidelity (WiFi) system. The embodiment of the present disclosure does not limit the specific technology and specific device form adopted by the base station. The base station provided in the embodiment of the present disclosure may be composed of a central unit (CU) and a distributed unit (DU), wherein the CU may also be referred to as a control unit. The CU-DU structure may be used to split the base station, such as the protocol layer of the base station, and the functions of some protocol layers are placed in the CU for centralized control, while the functions of the remaining part or all of the protocol layers are distributed in the DU, and the DU is centrally controlled by the CU.
[0079] It can be understood that the communication system described in the embodiment of the present disclosure is for the purpose of more clearly illustrating the technical solution of the embodiment of the present disclosure, and does not constitute a limitation on the technical solution provided by the embodiment of the present disclosure. Ordinary technicians in this field can know that with the evolution of the system architecture and the emergence of new business scenarios, the technical solution provided by the embodiment of the present disclosure is also applicable to similar technical problems.
[0080] In addition, in order to facilitate understanding of the embodiments of the present disclosure, the following points are explained.
[0081] First, in the present disclosure, unless there is any contradiction, each step in any embodiment or example can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a certain embodiment or example can also be implemented as an independent embodiment, and the order of the steps in a certain embodiment or example can be arbitrarily exchanged. In addition, the optional methods or optional examples in a certain embodiment or example can be arbitrarily combined; in addition, the various embodiments or examples can be arbitrarily combined. For example, some or all steps of different embodiments or examples can be arbitrarily combined, and a certain embodiment or example can be arbitrarily combined with the optional methods or optional examples of other embodiments or examples.
[0082] Second, regarding the description methods of the present disclosure such as "A or B", "A and / or B", "at least one of A and B", "A in one case, B in another case", "in response to one case A, in response to another case B", etc., at least one of the following schemes may be included according to the situation: executing A independently of B, that is, A in some embodiments; executing B independently of A, that is, B in some embodiments; selectively executing A and B, that is, selecting to execute from A and B in some embodiments; executing both A and B, that is, A and B in some embodiments.
[0083] Third, each element, each row, or each column in the table involved in the present disclosure can be implemented as an independent embodiment, and the combination of any elements, any rows, and any columns can also be implemented as an independent embodiment.
[0084] Fourth, in some implementation modes or examples, “including A”, “comprising A”, “used to indicate A” and “carrying A” in this disclosure can be interpreted as directly carrying A or indirectly indicating A.
[0085] Fifth, in some implementation modes or examples, "in response to...", "in the case of...", "at the time of...", "when...", "if...", "if...", etc. in the present disclosure can be replaced with each other.
[0086] FIG2a is a flow chart of a handover prediction method provided by an embodiment of the present disclosure. The method is executed by a first device. As shown in FIG2a , the handover prediction method may include the following steps:
[0087] Step 201a: Receive map information of the physical environment of the UE sent by the second device.
[0088] Optionally, in some embodiments, the first device may include at least one of the following:
[0089] Network equipment (such as base stations);
[0090] Data analysis server;
[0091] High-precision mobile communication signal measuring instrument;
[0092] High-precision mobile communication signal test terminal;
[0093] Devices with positioning capabilities, such as those that can collect environmental information based on cameras or lidar to locate and reconstruct maps.
[0094] Optionally, in some embodiments, the second device may include at least one of the following:
[0095] GNSS;
[0096] sensor.
[0097] Optionally, in some embodiments, the aforementioned map information may be acquired by the second device and then sent to the first device. Optionally, the method for the second device to acquire the map information may include: the second device acquiring the map information by locating the UE and collecting information about the physical environment surrounding the UE. For example, the second device may use a lidar combined with GNSS to acquire map information of the physical environment in which the UE is located. Optionally, the map information may be, for example, a 3D map.
[0098] Step 202a: predict the base station to which the UE will switch based on the map information.
[0099] Optionally, in some embodiments, the above-mentioned “predicting a base station to be switched by the UE according to map information” may include the following steps:
[0100] The first step is to input the map information into a pre-trained first model so that the first model outputs the environmental error information corresponding to the UE.
[0101] Optionally, the first model may be deployed in a first device; the specific training process of the first model will be described in subsequent embodiments. Furthermore, the first model may be, for example, a Map Neural Network (MAPNN) model, and optionally, the first model may include, for example, a Convolutional Neural Network (CNN).
[0102] Optionally, in some embodiments, the environmental error information may reflect an acquisition error caused by the physical environment surrounding the UE during the UE's information acquisition process. For example, the environmental error information may reflect an error between the location information acquired by the UE and the UE's actual location information, or an error between the received signal strength (e.g., Reference Signal Received Power (RSRP)) acquired by the UE and the UE's actual received signal strength.
[0103] Optionally, in some embodiments, the first model is configured to output environmental error information of the UE so that the first device can subsequently predict the base station to which the UE is to switch based on the environmental error information. Optionally, because the first model in the embodiments of the present disclosure may include a CNN, which can efficiently process map or environmental image data and accurately extract error features, the environmental error information output by the first model can be highly accurate. Thus, when a subsequent handover prediction is performed based on the environmental error information output by the first model, the accuracy of the prediction can be ensured.
[0104] Optionally, in some embodiments, at least one first model may be deployed on the first device, where different first models correspond to different physical environments, for outputting environmental error information in different physical environments. Optionally, the physical environments may include, for example, a home environment, a shopping mall environment, a field environment, a street environment, etc.
[0105] Optionally, in some embodiments, the above-mentioned “inputting the map information into the pre-trained first model” may include: inputting the map information into the pre-trained first model corresponding to the physical environment of the map information.
[0106] For example, it is assumed that three first models are deployed on the first device, namely the first model #1, the first model #2, and the first model #3, wherein the physical environment corresponding to the first model #1 is: home environment, the physical environment corresponding to the first model #2 is: shopping mall environment, and the physical environment corresponding to the first model #3 is: street environment. At this time, if the user is currently holding the UE in a shopping mall, the first device obtains the map information of the physical environment of the UE collected by the second device, and determines that the UE is currently in the shopping mall environment based on the map information. The map information can then be input into the pre-trained first model #2 to output the environmental error information of the UE.
[0107] As can be seen, in the disclosed embodiments, corresponding first models are specifically configured for different physical environments. This allows for accurate extraction of environmental error information for each physical environment, further ensuring the accuracy of subsequent handover predictions based on this environmental error information. Furthermore, because the first models in the disclosed embodiments correspond one-to-one to the physical environments, the first models do not need to account for all physical environments, resulting in a simpler structure and higher prediction efficiency.
[0108] The second step is to input the environmental error information into the pre-trained second model to obtain the output result of the second model. The output result of the second model is: the base station to which the UE is to switch, as predicted by the second model.
[0109] Optionally, the second model can be deployed in the first device, and the second model can be used to predict the base station to which the UE will switch at the next moment. Optionally, in some embodiments, when the base station to which the UE is to switch predicted by the second model is the same as the UE's current serving base station, it means that the UE does not need to switch base stations at the next moment; when the base station to which the UE is to switch predicted by the second model is different from the UE's current serving base station, it means that the UE needs to switch base stations at the next moment. In addition, the first device can send the output result of the second model to the UE so that the UE performs base station switching based on the base station predicted by the second model.
[0110] The specific training process of the second model will be described in the subsequent embodiments. Optionally, the second model can be, for example, a Long Short-Term Memory (LSTM) model.
[0111] As can be seen from the above, in the handover prediction method provided by the embodiment of the present disclosure, a first model and a second model are pre-trained and arranged in the first device, wherein the first model is used to output the environmental error information of the UE, and the second model is used to predict the base station to which the UE is to switch. In addition, the first device receives the map information of the physical environment in which the UE is currently located, which is sent by the second device. After that, the first device uses the first model to determine the current environmental error information of the UE based on the map information, and the first device also determines the base station to which the UE is to switch based on the second model and the current environmental error information of the UE. It can be seen that in the method of the present disclosure, the first device predicts the base station to which the UE is to switch based on the map information of the physical environment in which the UE is located. That is, when the first device predicts the base station to which the UE is to switch, it can fully consider the environmental factors of the physical environment surrounding the UE, so that the predicted base station is the base station that is most suitable for the UE to switch in the physical environment in which the UE is currently located, thereby improving the accuracy and performance of the handover prediction and further ensuring the communication quality of the UE.
[0112] In addition, it should be noted that, in some embodiments, the application scenario of the method of the embodiment of FIG. 2 may be: when the UE is unable to collect the UE's location information and / or the UE's received signal strength. Optionally, as can be seen from the above introduction to the related art, the UE's location information and / or the UE's received signal strength can be used for handover prediction. However, in a communication system, there is often a situation where "the UE is unable to collect the UE's location information and / or the UE's received signal strength", which results in the inability to perform handover prediction. The handover prediction method provided in the embodiment of FIG. 2 of the present disclosure performs handover prediction based on the UE's map information, without the need for the UE's location information and / or the UE's received signal strength. Therefore, even if the UE is unable to collect the UE's location information and / or the UE's received signal strength, the method of the embodiment of FIG. 2 can still implement handover prediction for the UE, which has wider applicability and lower restrictions. At the same time, the handover prediction method of the present disclosure does not need to simulate the change pattern of the received signal strength as in the method of the related art, so the amount of calculation required for the prediction is low and the prediction efficiency is high.
[0113] In summary, in the handover prediction method provided by the embodiment of the present disclosure, the first device will receive the map information of the physical environment in which the UE is located, which is sent by the second device; and will predict the base station to which the UE is to switch based on the map information. It can be seen that the handover prediction method of the present disclosure predicts the base station to which the UE is to switch based on the map information of the physical environment in which the UE is located, which can fully take into account the environmental factors of the physical environment around the UE, thereby making the handover prediction accuracy and performance higher. At the same time, in the handover prediction method provided by the present disclosure, there is no need to use the UE's location information and / or the UE's received signal strength. Therefore, even if the UE cannot collect the UE's location information and / or the UE's received signal strength, handover prediction can be implemented for the UE, which has a wide applicability and low restrictions. At the same time, in the handover prediction method of the present disclosure, there is no need to simulate the changing pattern of the received signal strength, so the amount of calculation required for the prediction is low, and the prediction efficiency is high.
[0114] FIG2 b is a flow chart of a handover prediction method provided by an embodiment of the present disclosure. The method is executed by a first device. As shown in FIG2 b , the handover prediction method may include the following steps:
[0115] Step 201b: Receive map information of the physical environment of the UE sent by the second device.
[0116] Step 202b: input the map information into the pre-trained first model, so that the first model outputs the environmental error information corresponding to the UE.
[0117] Step 203b: Input the environmental error information into the pre-trained second model to obtain the output result of the second model. The output result of the second model is: the base station to which the UE is to switch, as predicted by the second model.
[0118] For a detailed description of steps 201b - 203b , please refer to the above embodiment description.
[0119] In summary, in the handover prediction method provided by the embodiment of the present disclosure, the first device will receive the map information of the physical environment in which the UE is located, which is sent by the second device; and the map information will be input into the pre-trained first model so that the first model outputs the environmental error information corresponding to the UE; the first model is pre-trained; thereafter, the first device will input the environmental error information into the pre-trained second model to obtain the output result of the second model, and the output result of the second model is: the base station to which the UE is to switch, which is predicted by the second model, and the second model is pre-trained. It can be seen that the handover prediction method of the present disclosure predicts the base station to which the UE is to switch based on the map information of the physical environment in which the UE is located, which can fully take into account the environmental factors of the physical environment around the UE, thereby making the handover prediction more accurate and having higher performance. At the same time, in the handover prediction method provided by the present disclosure, there is no need to use the UE's location information and / or the UE's received signal strength. Therefore, even if the UE cannot collect the UE's location information and / or the UE's received signal strength, handover prediction can be implemented for the UE, which has a wide applicability and low restrictions. At the same time, the switching prediction method disclosed in the present invention does not need to simulate the variation pattern of the received signal strength, so the amount of calculation required for the prediction is low and the prediction efficiency is high.
[0120] FIG3a is a flow chart of a handover prediction method provided by an embodiment of the present disclosure. The method is executed by a first device. As shown in FIG3a , the handover prediction method may include the following steps:
[0121] Step 301: Train the first model.
[0122] Optionally, in some embodiments, the method for training the first model may include the following steps:
[0123] Step a: Obtain location information and received signal strength of the UE at at least one moment collected by the first device.
[0124] It should be understood that due to its high hardware configuration, the first device can overcome environmental errors well when collecting location information and received signal strength, and collect high-precision location information and received signal strength, so that the location information and received signal strength of the UE collected at at least one moment should be the closest to the actual location information and actual received signal strength of the UE. Therefore, the location information and received signal strength collected by the first device can be used as ground truth data, so as to adjust the model parameters of the first model based on the ground truth data when training the first model.
[0125] Step b: Acquire the location information and received signal strength of the UE at at least one moment collected by the UE.
[0126] Optionally, the UE can collect its location information and received signal strength at at least one moment, and can send the collected location information and received signal strength to the first device. It should be noted that in some embodiments, due to its low hardware configuration, the UE cannot overcome the environmental error well when collecting location information and received signal strength, which will result in low collection accuracy of the UE, so that the location information and received signal strength collected by the UE will have errors relative to the actual location information and actual received signal strength of the UE. Based on this, in the embodiment of the present disclosure, by obtaining the location information and received signal strength of the UE at at least one moment collected by the above-mentioned first device and obtaining the location information and received signal strength of the UE at at least one moment collected by the UE, the actual environmental error is calculated based on the location information and received signal strength collected by the first device and the location information and received signal strength collected by the UE, which is used for subsequent training of the first model.
[0127] Optionally, in some embodiments, the method for the UE to collect received signal strength may include: the UE periodically collects its received signal strength at multiple moments, and selects stable values of the received signal strength that do not change drastically over time and sends them to the first device.
[0128] Optionally, in some embodiments, the method for the UE to collect location information may include at least one of the following:
[0129] Use the time difference of arrival (TDoA) positioning method to obtain the UE's location information;
[0130] Use angle of arrival (AoA) positioning to obtain UE location information;
[0131] Use the GNSS database to obtain the UE's location information;
[0132] The location information of the UE is obtained based on a location fingerprint method based on wireless fidelity (WiFi).
[0133] Optionally, the above-mentioned TDoA positioning method, AoA positioning method, and method of obtaining UE location information from the GNSS database can be used to collect UE location information in outdoor scenarios; the above-mentioned WiFi-based location fingerprint method can be used to collect UE location information in indoor scenarios.
[0134] Optionally, when the UE collects the location information and the received signal strength through the above method, the collection accuracy of the UE can be ensured as much as possible.
[0135] Optionally, in some embodiments, the method for the UE to send location information and received signal strength to the first device may include: the UE determining the location information and received signal strength of the UE at each moment in real time; wherein, after the UE determines the location information and received signal strength of the UE at the current moment, the UE starts sending the location information and received signal strength of the UE at the current moment to the first device at the current moment; and when the UE determines the location information and received signal strength of the UE at the next moment, the UE starts sending the location information and received signal strength of the UE at the next moment to the first device at the next moment. Each moment corresponds to a transmission time interval (TTI), and the TTI is used to transmit the location and received signal strength of the UE at the corresponding moment.
[0136] Step c: adding the location information collected by the UE at each moment to the first error deviation value to obtain error location information.
[0137] Optionally, the first error deviation value can be pre-calculated, for example, the first error deviation value can be used to reflect the error caused by environmental interference, multipath, and positioning deviation; and, in some embodiments, the first error deviation value corresponding to the position information at different times may be the same or different.
[0138] Optionally, in some embodiments, a first error deviation value may be added to the position information transmitted in the TTI corresponding to the current moment and the position information transmitted in the TTIs corresponding to N moments before the current moment to obtain the error position information at the current moment and the error position information at N moments before the current moment, where N is a positive integer.
[0139] Step d, adding the received signal strength at each moment collected by the UE to the second error deviation value to obtain an error received signal strength;
[0140] Optionally, the second error deviation value can be pre-calculated, for example, the second error deviation value can be used to reflect the error caused by environmental interference, multipath, and positioning deviation; and, in some embodiments, the second error deviation value added to the position information at different times may be the same or different.
[0141] Optionally, in some embodiments, a second error deviation value may be added to the received signal strength transmitted in the TTI corresponding to the current moment and the received signal strength transmitted in the TTIs corresponding to N moments before the current moment to obtain the error received signal strength at the current moment and the error received signal strength at N moments before the current moment, where N is a positive integer.
[0142] Step e: determining actual environment error information corresponding to the UE based on the location information collected by the first device, the received signal strength collected by the first device, the location information collected by the UE, the received signal strength collected by the UE, the error location information, and the error received signal strength;
[0143] Optionally, the actual environment error information may be a combination of at least one of: the difference between the location information collected by the first device and the location information collected by the UE, the difference between the location information collected by the first device and the error location information, the difference between the location information collected by the first device and the received signal strength collected by the UE, and the difference between the location information collected by the first device and the error received signal strength.
[0144] Step f: inputting the map information corresponding to the UE into the pre-built first model to obtain the output result of the first model;
[0145] Step g, calculating a first loss value between the output result of the first model and the actual environment error information;
[0146] Optionally, the first loss value can be used to reflect the gap between the output result of the first model and the actual environmental error information. Optionally, the smaller the first loss value is, the smaller the gap between the output result of the first model and the actual environmental error information is.
[0147] Step h: Adjust the model parameters of the first model (such as the number of network layers, network node scale, learning rate, etc.) based on the first loss value until the output result of the first model meets the first preset condition, and determine that the training is completed.
[0148] Optionally, the first preset condition may include: a first loss value between the output result of the first model and the actual environment error information is less than a first threshold, and the first threshold may be 1 dB, for example.
[0149] Optionally, when the first loss value between the output result of the first model and the actual environmental error information is less than the first threshold, it means that the output result of the first model is infinitely close to the actual environmental error information. At this time, it is considered that the first model can accurately extract the environmental error information corresponding to the map information of the physical environment where the UE is located, and the training of the first model is confirmed to be completed.
[0150] It should be noted that, in some embodiments, since different first models correspond to different physical environments, when training the first model in step 301 , the first models corresponding to different physical environments may be trained separately.
[0151] Based on the above steps f to h, Figure 3b proposes a flow chart for training a first model provided in an embodiment of the present disclosure. Referring to Figure 3b, map information can be input into a pre-trained first model (i.e., a MAPNN model) to output environmental error information. Afterwards, the environmental error information output by the MAPNN model is compared with the actual environmental error information determined by the first device, and the model parameters are adjusted based on the comparison results until the output result of the first model meets the first preset condition.
[0152] In summary, the present disclosure provides a training method for a first model, which is used for a first device to train a first model that can extract the environmental error information of the UE. The first device can use the trained first model to output the environmental error information of the UE based on the map information of the physical environment in which the UE is located, so that the first device can subsequently accurately predict the base station to which the UE is to switch based on the environmental error information of the UE, thereby improving the accuracy and performance of the switching prediction.
[0153] FIG4a is a flow chart of a handover prediction method provided by an embodiment of the present disclosure. The method is executed by a first device. As shown in FIG4 , the handover prediction method may include the following steps:
[0154] Step 401: Train the second model.
[0155] Optionally, in some embodiments, the method for training the second model may include the following steps:
[0156] Step 1: Use the first model to determine the environmental error information corresponding to the UE.
[0157] Optionally, the map information of the environment in which the UE is located, obtained by the first device from the second device, may be input into the trained first model to obtain environmental error information corresponding to the UE.
[0158] Step 2: The first device determines the base station to which the UE is to be switched based on the location information and / or received signal strength of the UE at at least one moment collected by the first device;
[0159] Optionally, the method for the first device to determine the base station to which the UE is to switch based on the location information and / or the received signal strength may refer to the detailed description of the above method 1 and method 2. This disclosure will not elaborate on this.
[0160] Optionally, since the first device has a high accuracy in collecting the location information and / or received signal strength of the UE at at least one moment, the base station to which the UE is to switch determined by the first device in this step 2 can be understood as: the base station most suitable for UE switching, and the first device can subsequently adjust the model parameters of the second model based on the base station determined by the first device to realize training of the second model.
[0161] Step 3: Input the environmental error information into the pre-built second model to obtain the output result of the second model;
[0162] Optionally, in some embodiments, the output result of the second model may be: a base station to which the UE is to switch, predicted by the second model based on the environmental error information.
[0163] Step 4: Calculate a first accuracy between an output result of the second model and the base station determined by the first device;
[0164] Optionally, in some embodiments, the first accuracy may reflect: the degree of closeness between the output result of the second model and the base station determined by the first device, wherein the higher the first accuracy, the closer the output result of the second model is to the base station determined by the first device.
[0165] Step 5: Adjust the model parameters of the second model based on the first accuracy until the output result of the second model meets the second preset condition, and determine that the training is completed.
[0166] Optionally, in some embodiments, the second preset condition may include: a first accuracy between an output result of the second model and the base station determined by the first device is greater than a second threshold, and the second threshold may be, for example, 90%.
[0167] Optionally, when the first accuracy between the output result of the second model and the base station determined by the first device is greater than a second threshold, it means that the output result of the second model is infinitely close to the base station determined by the first device. At this time, it is considered that the second model can accurately predict the base station most suitable for UE switching, and the training of the second model is confirmed to be completed.
[0168] Based on the above steps 3 to 5, Figure 4b proposes a flow chart for training a second model provided in an embodiment of the present disclosure. Referring to Figure 4b, the environmental error information can be input into the pre-trained second model (i.e., the LSTM model) so that the LSTM model outputs the base station to which the UE is predicted to switch. Afterwards, the base station predicted by the LSTM model is compared with the base station to which the UE is determined to switch by the first device, and the model parameters are adjusted based on the comparison results until the output result of the second model meets the second preset condition.
[0169] In summary, the present disclosure provides a second model training method for a first device to train a second model that can accurately predict the base station to which the UE is to switch. The first device can then use the trained second model to perform accurate switching predictions, thereby improving the accuracy and performance of switching predictions.
[0170] FIG5 is a flow chart of a handover prediction method provided by an embodiment of the present disclosure. The method is executed by a first device. As shown in FIG5 , the handover prediction method may include the following steps:
[0171] Step 501: Acquire location information and received signal strength of a UE at at least one time point collected by the UE;
[0172] Optionally, the UE may collect its location information and received signal strength at at least one moment, and may send the collected location information and received signal strength to the first device.
[0173] Optionally, in some embodiments, the method for the UE to send location information and received signal strength to the first device may include: the UE determining the location information and received signal strength of the UE at each moment in real time; wherein, after the UE determines the location information and received signal strength of the UE at the current moment, the UE starts sending the location information and received signal strength of the UE at the current moment to the first device at the current moment; and when the UE determines the location information and received signal strength of the UE at the next moment, the UE starts sending the location information and received signal strength of the UE at the next moment to the first device at the next moment. Each moment corresponds to a TTI, and the TTI is used to transmit the location and received signal strength of the UE at the corresponding moment.
[0174] Step 502: Obtain error position information and error received signal strength based on the position information and received signal strength;
[0175] Optionally, in some embodiments, the aforementioned "obtaining error location information and error received signal strength based on location information and received signal strength" may include: adding the location information collected by the UE at each moment to a first error deviation value to obtain the error location information; and adding the received signal strength collected by the UE at each moment to a second error deviation value to obtain the error received signal strength. For a detailed description of the first error deviation value and the second error deviation value, refer to the description of the above embodiment.
[0176] Optionally, in some embodiments, a first error deviation value may be added to the position information transmitted in the TTI corresponding to the current moment and the position information transmitted in the TTIs corresponding to N moments before the current moment to obtain the error position information at the current moment and the error position information at N moments before the current moment, where N is a positive integer.
[0177] Optionally, in some embodiments, a second error deviation value may be added to the received signal strength transmitted in the TTI corresponding to the current moment and the received signal strength transmitted in the TTIs corresponding to N moments before the current moment to obtain the error received signal strength at the current moment and the error received signal strength at N moments before the current moment, where N is a positive integer.
[0178] Optionally, in some embodiments, location information, received signal strength, error location information, and error received signal strength at the current moment and N moments are obtained so that handover prediction can be performed based on this information. Since the information included at each moment in the disclosed embodiments is relatively comprehensive, resulting in higher prediction accuracy, the value of N can be appropriately reduced to appropriately reduce the computational complexity of handover prediction while ensuring prediction accuracy, thereby improving prediction efficiency.
[0179] Step 503: Combine the position information, the received signal strength, the error position information, and the error received signal strength to obtain at least one set of combined information.
[0180] Optionally, the method of “combining the position information and received signal strength at each moment with the error position information and error received signal strength to obtain at least one set of combined information at each moment” may include at least one of the following:
[0181] Combining the location information and the received signal strength at the same time to obtain a first set of combined information;
[0182] Combining the position information and the error received signal strength at the same time to obtain a second set of combined information;
[0183] Combining the error position information and the received signal strength at the same time to obtain a third set of combined information;
[0184] The error position information and the error received signal strength at the same time are combined to obtain a fourth set of combined information.
[0185] Step 504: Input at least one set of combination information into a pre-trained third model to obtain an output result of the third model.
[0186] Optionally, the third model can be deployed in the first device. The third model can be used to predict the base station to which the UE will switch at the next moment. The output result of the third model can be: the output result corresponding to each combination of information, wherein the output result corresponding to each combination of information can be understood as: the base station to which the UE will switch, predicted by the third model based on each combination of information. Optionally, the output results corresponding to different combinations of information output by the third model are close to each other. The output result corresponding to any combination of information can be used as the base station to which the UE will switch at the next moment, as predicted by the third model.
[0187] For example, assuming that the first group of combination information, the second group of combination information, the third group of combination information, and the fourth group of combination information are input into the third model in the above step 503, the third model can output the output results corresponding to the first group of combination information, the output results corresponding to the second group of combination information, the output results corresponding to the third group of combination information, and the output results corresponding to the fourth group of combination information, wherein the output results corresponding to the first group of combination information, the output results corresponding to the second group of combination information, the output results corresponding to the third group of combination information, and the output results corresponding to the fourth group of combination information are close to each other, and any one of the output results corresponding to the first group of combination information, the output results corresponding to the second group of combination information, the output results corresponding to the third group of combination information, and the output results corresponding to the fourth group of combination information can be used as the base station predicted by the third model to be switched to by the UE at the next moment.
[0188] Optionally, in some embodiments, after the third model predicts the base station to which the UE is to switch, if the base station predicted by the third model is the same as the UE's current serving base station, then the UE does not need to switch base stations at the next moment; if the base station predicted by the third model is different from the UE's current serving base station, then the UE needs to switch base stations at the next moment. Furthermore, the first device may send the output result of the third model to the UE, so that the UE performs base station switching based on the base station predicted by the third model.
[0189] Optionally, in some embodiments, the third model may be a pre-trained model; wherein the specific training process of the third model will be described in subsequent embodiments. Optionally, the third model may be, for example, an LSTM model.
[0190] Optionally, in some embodiments, inputting at least one set of combined information into the pre-trained third model may include inputting at least one set of combined information at the current moment and N moments prior to the current moment into the pre-trained first model. Optionally, N may be a positive integer. It should be noted that because the combined information at each moment is composed of multiple pieces of information and includes a relatively large amount of information, N can be a smaller value. This reduces the computational complexity of the third model while ensuring prediction accuracy. For example, N may be equal to 9.
[0191] As can be seen from the above content, in the handover prediction method provided by the embodiment of the present disclosure, the first device uses the combined information as the input of the third model so that the third model performs handover prediction. The combined information includes the location information of the UE and the received signal strength of the UE, and the combined information also includes "the error location information obtained after introducing an error into the location information" and "the error received signal strength obtained after introducing an error into the received signal strength". Therefore, compared with the handover prediction method based only on location information or received signal strength in the related art, the information used in the embodiment of the present disclosure when performing handover prediction is more comprehensive, thereby improving the accuracy and performance of the prediction. At the same time, the handover prediction method of the present disclosure does not need to simulate the changing pattern of the received signal strength as in the method of the related art, so the amount of calculation required for the prediction is low and the prediction efficiency is high.
[0192] In summary, in the handover prediction method provided by the embodiment of the present disclosure, the first device will obtain the location information and received signal strength of the UE collected by the UE at at least one moment; thereafter, the first device will obtain the error location information and the error received signal strength based on the location information and the received signal strength; and the location information, the received signal strength and the error location information and the error received signal strength will be combined to obtain at least one set of combined information; finally, the first device will input at least one set of combined information into a pre-trained third model to obtain the output result of the third model, and the output result of the third model is: the base station to which the UE is to switch, as predicted by the third model, and the third model is pre-trained. Among them, the information used in the embodiment of the present disclosure when performing handover prediction is more comprehensive, thereby improving the accuracy and performance of the prediction. At the same time, the handover prediction method of the present disclosure does not need to simulate the changing pattern of the received signal strength, so the amount of calculation required for the prediction is low and the prediction efficiency is high.
[0193] FIG6a is a flow chart of a handover prediction method provided by an embodiment of the present disclosure. The method is executed by a first device. As shown in FIG6a , the handover prediction method may include the following steps:
[0194] Step 601: Train the third model.
[0195] Optionally, in some embodiments, the method for training the third model may include the following steps:
[0196] Step A: The first device collects the location information of the UE at at least one moment and the received signal strength of the UE at at least one moment;
[0197] Step B: The first device determines the base station to which the UE is to switch based on the location information of the UE at at least one moment collected by the first device and the received signal strength of the UE at at least one moment;
[0198] Step C: inputting at least one set of combination information at at least one moment into a pre-built third model to obtain output results corresponding to each set of combination information output by the third model;
[0199] For a detailed description of steps A to C, please refer to the above embodiment description.
[0200] Step D: Calculate the second accuracy between the output results corresponding to each set of combined information and the base station determined by the first device;
[0201] Optionally, in some embodiments, the third model determines a second accuracy for each output result of each set of combined information. Optionally, the second accuracy may reflect the degree of proximity between the output result corresponding to the combined information output by the third model and the base station determined by the first device, wherein a higher second accuracy corresponding to the output result of a certain combined information indicates that the output result corresponding to the combined information is closer to the base station determined by the first device.
[0202] Step E: Adjust the model parameters of the third model based on the second accuracy corresponding to each set of combination information until the output result of the third model meets the third preset condition, and determine that the training is completed.
[0203] Optionally, in some embodiments, the third preset condition includes at least one of the following:
[0204] The average of the second accuracy corresponding to the output results of all the combined information is greater than a third threshold (such as 90%);
[0205] The standard deviation of the second accuracy corresponding to the output results of all the combined information is less than a fourth threshold (eg, 0.05).
[0206] Optionally, when the mean of the second accuracy corresponding to the output results of all combined information is greater than a third threshold, and / or the standard deviation of the second accuracy corresponding to the output results of all combined information is less than a fourth threshold, it means that the output results of each group of combined information output by the third model are infinitely close to the base station determined by the first device. At this time, it is considered that the third model can accurately predict the base station that is most suitable for UE switching, and the training of the third model is confirmed to be completed.
[0207] Based on the above steps C to E, Figure 6b proposes a flow chart for training a third model provided in an embodiment of the present disclosure. Referring to Figure 6b, at least one set of combination information at at least one moment can be input into a pre-trained third model (i.e., an LSTM model) to output the base station to which the UE is to switch, as predicted by the LSTM model for each set of combination information. Afterwards, the base station predicted by the LSTM model is compared with the base station to which the UE is to switch, as determined by the first device, and the model parameters are adjusted based on the comparison results until the output result of the third model meets the second preset condition.
[0208] In summary, the present disclosure provides a third model training method, which is used for a first device to train a third model that can accurately predict the base station to which the UE is to switch. The first device can then use the trained third model to perform accurate switching predictions, thereby improving the accuracy and performance of switching predictions.
[0209] In addition, it can be seen from the aforementioned embodiments that the first device mainly predicts the base station to which the UE is to switch in the next TTI (i.e., the next moment) based on the information transmitted by the UE in at least one TTI. Among them, the relevant introduction about TTI and the information transmitted therein can refer to the aforementioned embodiments. Optionally, Figure 6c is a structural block diagram of how to select TTI provided by an embodiment of the present disclosure. Assuming that the TTI corresponding to the current moment is TTI10, the terminal can select TTI10 at the current moment, and TTI1-TTI9 corresponding to the 9 moments before the current moment, and use the information transmitted in TTI1-TTI10 to predict the base station to which the UE is to switch at the next moment (i.e., TTI11).
[0210] FIG7 is a flow chart of a handover prediction method provided by an embodiment of the present disclosure. The method is executed by a second device. As shown in FIG7 , the handover prediction method may include the following steps:
[0211] Step 701: Determine map information of the physical environment where the UE is located;
[0212] Step 702: Send the map information to the first device.
[0213] For a detailed description of steps 701 - 702 , please refer to the above embodiment description.
[0214] In summary, in the handover prediction method provided by the embodiment of the present disclosure, the second device will determine the map information of the physical environment in which the UE is located, and will send the map information to the first device, so that the first device can perform handover prediction based on the map information. It can be seen that the handover prediction method of the present disclosure predicts the base station to which the UE is to switch based on the map information of the physical environment in which the UE is located, which can fully take into account the environmental factors of the physical environment around the UE, thereby making the handover prediction more accurate and having higher performance. At the same time, in the handover prediction method provided by the present disclosure, there is no need to use the location information of the UE and / or the received signal strength of the UE. Therefore, even if the UE cannot collect the location information of the UE and / or the received signal strength of the UE, handover prediction can be implemented for the UE. Therefore, the handover prediction method provided by the embodiment of the present disclosure has wider applicability and lower restrictions.
[0215] FIG8 is a flow chart of a handover prediction method provided by an embodiment of the present disclosure. The method is executed by a UE. As shown in FIG8 , the handover prediction method may include the following steps:
[0216] Step 801: Collect the location information and received signal strength of the UE at at least one time;
[0217] Step 802: Send the location information and received signal strength at at least one moment collected by the UE to the first device.
[0218] For a detailed description of steps 801 - 802 , please refer to the above embodiment description.
[0219] In summary, in the handover prediction method provided by the embodiment of the present disclosure, the UE will collect the location information and received signal strength of the UE at at least one moment, and will send the location information and received signal strength collected by the UE at at least one moment to the first device. Among them, after the first device receives the location information and received signal strength sent by the UE, it can make a handover prediction based on the location information and received signal strength. Then, the information used in the embodiment of the present disclosure when making a handover prediction is more comprehensive, thereby improving the accuracy and performance of the prediction. In addition, after the first device receives the location information and received signal strength sent by the UE, it can predict and train a first model based on the location information and received signal strength to train a first model that can extract the environmental error information of the UE. Then, the first device can use the trained first model to output the environmental error information of the UE based on the map information of the physical environment in which the UE is located, so that the first device can subsequently accurately predict the base station to which the UE is to switch based on the environmental error information of the UE, thereby improving the accuracy and performance of the handover prediction.
[0220] FIG9 is a schematic structural diagram of a communication device provided by an embodiment of the present disclosure. As shown in FIG9 , the device may include:
[0221] a transceiver module, configured to receive map information of a physical environment of a user equipment UE sent by a second device;
[0222] A processing module is used to predict the base station to which the UE is to switch based on the map information.
[0223] In summary, in the communication device provided in the embodiment of the present disclosure, the first device will receive the map information of the physical environment where the UE is located, which is sent by the second device; and will predict the base station to which the UE is to switch based on the map information. It can be seen that the switching prediction method of the present disclosure predicts the base station to which the UE is to switch based on the map information of the physical environment where the UE is located, which can fully take into account the environmental factors of the physical environment around the UE, thereby making the accuracy and performance of the switching prediction higher. At the same time, in the switching prediction method provided in the present disclosure, there is no need to use the location information of the UE and / or the received signal strength of the UE. Therefore, even if the UE cannot collect the location information of the UE and / or the received signal strength of the UE, the switching prediction can be implemented for the UE. Therefore, the switching prediction method provided in the embodiment of the present disclosure has a wider applicability and lower restrictions.
[0224] Optionally, in one embodiment of the present disclosure, the processing module is further configured to:
[0225] Inputting the map information into a pre-trained first model so that the first model outputs environmental error information corresponding to the UE;
[0226] The environmental error information is input into a pre-trained second model to obtain an output result of the second model, wherein the output result of the second model indicates the base station to which the UE is to switch.
[0227] Optionally, in one embodiment of the present disclosure, the apparatus is further configured to:
[0228] Training the first model; wherein the device is specifically used to:
[0229] Obtaining location information and received signal strength of the UE at at least one moment collected by the first device;
[0230] Obtaining location information and received signal strength of the UE at at least one moment collected by the UE;
[0231] Adding the position information collected by the UE at each moment to the first error deviation value to obtain error position information;
[0232] Adding the received signal strength at each moment collected by the UE to the second error deviation value to obtain an error received signal strength;
[0233] Determine actual environment error information corresponding to the UE based on the location information and received signal strength collected by the first device, the location information and received signal strength collected by the UE, and the error location information and the error received signal strength;
[0234] Inputting the map information corresponding to the UE into a pre-built first model to obtain an output result of the first model;
[0235] Calculating a first loss value between an output result of the first model and the actual environment error information;
[0236] The model parameters of the first model are adjusted based on the first loss value until the output result of the first model meets the first preset condition, and the training is determined to be completed.
[0237] Optionally, in an embodiment of the present disclosure, the first preset condition includes: a first loss value between an output result of the first model and the actual environment error information is less than a first threshold.
[0238] Optionally, in an embodiment of the present disclosure, different first models correspond to different physical environments and are used to output environmental error information under different physical environments;
[0239] The training of the first model comprises:
[0240] The corresponding first models are trained for different physical environments.
[0241] Optionally, in one embodiment of the present disclosure, the apparatus is further configured to:
[0242] Training the second model; wherein the Zhuangzi is specifically used to:
[0243] Determining environmental error information corresponding to the UE using the first model;
[0244] Determining a base station to be switched by the UE based on the location information and received signal strength of the UE at at least one moment collected by the first device;
[0245] Inputting the environmental error information into a pre-built second model to obtain an output result of the second model;
[0246] Calculating a first accuracy between an output result of the second model and the base station determined by the first device;
[0247] The model parameters of the second model are adjusted based on the first accuracy until the output result of the second model meets a second preset condition, and the training is determined to be completed.
[0248] Optionally, in one embodiment of the present disclosure, the second preset condition includes: a first accuracy between an output result of the second model and a base station determined by the first device is greater than a second threshold.
[0249] Optionally, in an embodiment of the present disclosure, the first device includes at least one of the following:
[0250] Network equipment;
[0251] Data analysis server.
[0252] Optionally, in one embodiment of the present disclosure, the second device includes at least one of the following:
[0253] Global Navigation Satellite System (GNSS);
[0254] sensor.
[0255] FIG10 is a schematic structural diagram of a communication device provided by an embodiment of the present disclosure. As shown in FIG10 , the device may include:
[0256] a transceiver module, configured to obtain location information and received signal strength of the UE at at least one moment collected by the UE;
[0257] A processing module, configured to obtain error position information and error received signal strength based on the position information and received signal strength;
[0258] The processing module is further configured to combine the position information and the received signal strength with the error position information and the error received signal strength to obtain at least one set of combined information;
[0259] The processing module is also used to input the at least one set of combined information into a pre-trained third model to obtain an output result of the third model, where the output result of the third model is: the base station to which the UE is to switch as predicted by the third model.
[0260] In summary, in the communication device provided by the embodiment of the present disclosure, the first device will obtain the location information of the UE at at least one moment and the received signal strength at at least one moment sent by the UE; wherein, the location information and received signal strength collected by the UE are collected by the UE; thereafter, the first device will introduce errors into the location information and received signal strength at each moment to obtain the error location information and error received signal strength at each moment; and combine the location information and received signal strength at each moment with the error location information and error received signal strength to obtain at least one set of combined information at each moment; finally, the first device will input at least one set of combined information at at least one moment into a pre-trained third model to obtain the output result of the third model, and the output result of the third model is: the base station to which the UE is to switch, as predicted by the third model, and the third model is pre-trained. Among them, the information used in the embodiment of the present disclosure when performing switching prediction is more comprehensive, thereby improving the accuracy and performance of the prediction.
[0261] Optionally, in one embodiment of the present disclosure, the processing module is used for at least one of the following:
[0262] Combining the location information and the received signal strength at the same time to obtain a first set of combined information;
[0263] Combining the position information and the error received signal strength at the same time to obtain a second set of combined information;
[0264] Combining the error position information and the received signal strength at the same time to obtain a third set of combined information;
[0265] The error position information and the error received signal strength at the same time are combined to obtain a fourth set of combined information.
[0266] Optionally, in one embodiment of the present disclosure, the apparatus is further configured to:
[0267] Training the third model; wherein the training the third model comprises:
[0268] The first device collects location information and received signal strength of the UE at at least one moment;
[0269] The first device determines, based on the location information of the UE at at least one moment collected by the first device and the received signal strength of the UE at at least one moment, a base station to be switched by the UE;
[0270] Inputting at least one set of combination information at at least one moment into a pre-built third model to obtain output results corresponding to each set of combination information output by the third model;
[0271] Calculating a second accuracy between the output results corresponding to each set of combined information and the base station determined by the first device;
[0272] The model parameters of the third model are adjusted based on the second accuracy corresponding to each set of combination information until the output result of the third model meets the third preset condition, and the training is determined to be completed.
[0273] Optionally, in an embodiment of the present disclosure, the third preset condition includes at least one of the following:
[0274] The average of the second accuracy corresponding to all the combined information is greater than a third threshold;
[0275] The standard deviation of the second accuracy corresponding to all the combined information is less than a fourth threshold.
[0276] FIG11 is a schematic structural diagram of a communication device provided by an embodiment of the present disclosure. As shown in FIG11 , the device may include:
[0277] A processing module, configured to determine map information of the physical environment in which the UE is located;
[0278] The transceiver module is used to send the map information to the first device.
[0279] In summary, in the communication device provided in the embodiment of the present disclosure, the second device will determine the map information of the physical environment in which the UE is located, and will send the map information to the first device, so that the first device can perform switching prediction based on the map information. It can be seen that the switching prediction method of the present disclosure predicts the base station to which the UE is to switch based on the map information of the physical environment in which the UE is located, which can fully take into account the environmental factors of the physical environment around the UE, thereby making the accuracy and performance of the switching prediction higher. At the same time, in the switching prediction method provided in the present disclosure, there is no need to use the location information of the UE and / or the received signal strength of the UE. Therefore, even if the UE cannot collect the location information of the UE and / or the received signal strength of the UE, switching prediction can be implemented for the UE. Therefore, the switching prediction method provided in the embodiment of the present disclosure has a wider applicability and lower restrictions.
[0280] FIG12 is a schematic diagram of the structure of a communication device provided by an embodiment of the present disclosure. As shown in FIG12 , the device may include:
[0281] a processing module, configured to collect location information and received signal strength of the UE at at least one moment;
[0282] The transceiver module is used to send the location information and received signal strength at at least one moment collected by the UE to the first device.
[0283] In summary, in the communication device provided in the embodiment of the present disclosure, the UE will collect the location information and received signal strength of the UE at at least one moment, and will send the location information and received signal strength collected by the UE at at least one moment to the first device. Among them, after the first device receives the location information and received signal strength sent by the UE, it can make a switching prediction based on the location information and received signal strength. Then, when making a switching prediction, the information used in the embodiment of the present disclosure is more comprehensive, thereby improving the accuracy and performance of the prediction. In addition, after the first device receives the location information and received signal strength sent by the UE, it can train a first model based on the location information and received signal strength prediction to train a first model that can extract the environmental error information of the UE. Then, the first device can use the trained first model to output the environmental error information of the UE based on the map information of the physical environment in which the UE is located, so that the first device can subsequently accurately predict the base station to which the UE is to switch based on the environmental error information of the UE, thereby improving the accuracy and performance of the switching prediction.
[0284] Please refer to Figure 13, which is a schematic diagram of the structure of a communication device 1300 provided in an embodiment of the present disclosure. Communication device 1300 can be a base station or a terminal, or a chip, chip system, or processor that supports a base station in implementing the above-mentioned method. It can also be a chip, chip system, or processor that supports a terminal in implementing the above-mentioned method. This device can be used to implement the method described in the above-mentioned method embodiment. For details, please refer to the description of the above-mentioned method embodiment.
[0285] The communication device 1300 may include one or more processors 1301. The processor 1301 may be a general-purpose processor or a dedicated processor. For example, it may be a baseband processor or a central processing unit (CPU). The baseband processor may be used to process communication protocols and communication data, while the CPU may be used to control the communication device (e.g., a base station, a baseband chip, a terminal, a terminal chip, a DU or a CU), execute computer programs, and process computer program data.
[0286] Optionally, the communication device 1300 may further include one or more memories 1302, on which a computer program 1304 may be stored. The processor 1301 executes the computer program 1304 to cause the communication device 1300 to perform the method described in the above method embodiment. Optionally, the memory 1302 may also store data. The communication device 1300 and the memory 1302 may be provided separately or integrated together.
[0287] Optionally, the communication device 1300 may further include a transceiver 1305 and an antenna 1306. The transceiver 1305 may be referred to as a transceiver unit, a transceiver, or a transceiver circuit, and is configured to implement transceiver functions. The transceiver 1305 may include a receiver and a transmitter. The receiver may be referred to as a receiver or a receiving circuit, and is configured to implement a receiving function; the transmitter may be referred to as a transmitter or a transmitting circuit, and is configured to implement a transmitting function.
[0288] Optionally, the communication device 1300 may further include one or more interface circuits 1307. The interface circuit 1307 is configured to receive code instructions and transmit the instructions to the processor 1301. The processor 1301 executes the code instructions to enable the communication device 1300 to perform the method described in the above method embodiment.
[0289] In one implementation, processor 1301 may include a transceiver for implementing receiving and transmitting functions. For example, the transceiver may be a transceiver circuit, an interface, or an interface circuit. The transceiver circuit, interface, or interface circuit for implementing the receiving and transmitting functions may be separate or integrated. The transceiver circuit, interface, or interface circuit may be used for reading and writing code / data, or may be used for transmitting or delivering signals.
[0290] In one implementation, processor 1301 may store a computer program 1303. Computer program 1303, when executed on processor 1301, enables communication device 1300 to perform the method described in the above method embodiment. Computer program 1303 may be embedded in processor 1301, in which case processor 1301 may be implemented by hardware.
[0291] In one implementation, the communication device 1300 may include a circuit that can implement the functions of sending, receiving, or communicating in the aforementioned method embodiments. The processor and transceiver described in the present disclosure can be implemented on an integrated circuit (IC), an analog IC, a radio frequency integrated circuit RFIC, a mixed signal IC, an application specific integrated circuit (ASIC), a printed circuit board (PCB), an electronic device, etc. The processor and transceiver can also be manufactured using various IC process technologies, such as complementary metal oxide semiconductor (CMOS), N-type metal oxide semiconductor (nMetal-oxide-semiconductor, NMOS), P-type metal oxide semiconductor (positive channel metal oxide semiconductor, PMOS), bipolar junction transistor (bipolar junction transistor, BJT), bipolar CMOS (BiCMOS), silicon germanium (SiGe), gallium arsenide (GaAs), etc.
[0292] The communication device described in the above embodiments may be a base station or a terminal, but the scope of the communication device described in this disclosure is not limited thereto, and the structure of the communication device may not be limited to FIG13. The communication device may be an independent device or may be part of a larger device. For example, the communication device may be:
[0293] (1) An independent integrated circuit (IC), or chip, or chip system or subsystem;
[0294] (2) a collection of one or more ICs, optionally including a storage component for storing data and computer programs;
[0295] (3) ASIC, such as modem;
[0296] (4) Modules that can be embedded in other devices;
[0297] (5) Receivers, terminals, smart terminals, cellular phones, wireless devices, handheld devices, mobile units, vehicle-mounted devices, base stations, cloud devices, artificial intelligence devices, etc.;
[0298] (6)Others, etc.
[0299] If the communication device can be a chip or a chip system, please refer to the schematic diagram of the chip structure shown in Figure 14. The chip shown in Figure 14 includes a processor 1401 and an interface 1402. The number of processors 1401 can be one or more, and the number of interfaces 1402 can be multiple.
[0300] Optionally, the chip further includes a memory 1403, which is used to store necessary computer programs and data.
[0301] Those skilled in the art will also appreciate that the various illustrative logical blocks and steps listed in the embodiments of the present disclosure may be implemented by electronic hardware, computer software, or a combination of both. Whether such functionality is implemented by hardware or software depends on the specific application and the design requirements of the entire system. Those skilled in the art may use various methods to implement the described functionality for each specific application, but such implementation should not be construed as exceeding the scope of protection of the embodiments of the present disclosure.
[0302] The present disclosure also provides a readable storage medium having instructions stored thereon, which implement the functions of any of the above method embodiments when executed by a computer.
[0303] The present disclosure also provides a computer program product, which implements the functions of any of the above method embodiments when executed by a computer.
[0304] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer programs. When the computer program is loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present disclosure are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer program can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer program can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated therein. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a high-density digital video disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).
[0305] Those skilled in the art will understand that the various numerical numbers such as first and second involved in the present disclosure are only for the convenience of description and are not used to limit the scope of the embodiments of the present disclosure, and also indicate the order of precedence.
[0306] The at least one in the present disclosure can also be described as one or more, and the multiple can be two, three, four or more, which is not limited in the present disclosure. In the embodiments of the present disclosure, for a technical feature, the technical features in the technical feature are distinguished by "first", "second", "third", "A", "B", "C" and "D", and there is no order of precedence or size between the technical features described by "first", "second", "third", "A", "B", "C" and "D".
[0307] The correspondences shown in the tables of the present disclosure can be configured or predefined. The values of the information in each table are merely examples and can be configured to other values, which are not limited by the present disclosure. When configuring the correspondences between information and parameters, it is not necessarily required to configure all the correspondences shown in each table. For example, in the tables of the present disclosure, the correspondences shown in certain rows may not be configured. For another example, appropriate deformation adjustments can be made based on the above tables, such as splitting, merging, etc. The names of the parameters shown in the titles of the above tables may also adopt other names that can be understood by the communication device, and the values or representations of the parameters may also adopt other values or representations that can be understood by the communication device. When implementing the above tables, other data structures may also be used, such as arrays, queues, containers, stacks, linear lists, pointers, linked lists, trees, graphs, structures, classes, heaps, hash tables or hash tables, etc.
[0308] The predefined in the present disclosure may be understood as defined, predefined, stored, pre-stored, pre-negotiated, pre-configured, solidified, or pre-burned.
[0309] Those skilled in the art will appreciate that the units and algorithmic steps described in the various examples in conjunction with the embodiments disclosed herein can be implemented using electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this disclosure.
[0310] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0311] The above description is merely a specific embodiment of the present disclosure, but the scope of protection of the present disclosure is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this disclosure should be included in the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure should be based on the scope of protection of the claims.
Claims
1. A switching prediction method, characterized in that: The method is performed by a first device, and includes: Receiving map information of a physical environment in which a user equipment UE is located, sent by a second device; The base station to which the UE is to switch is predicted according to the map information.
2. The method according to claim 1, characterized in that The predicting, according to the map information, the base station to which the UE is to switch includes: Inputting the map information into a pre-trained first model so that the first model outputs environmental error information corresponding to the UE; The environmental error information is input into a pre-trained second model to obtain an output result of the second model, wherein the output result of the second model indicates the base station to which the UE is to switch.
3. The method according to claim 1, characterized in that The method further comprises: Training the first model, wherein the training the first model comprises: Acquire location information and received signal strength of the UE at at least one time point collected by the first device; Acquire location information and received signal strength of the UE at at least one time point collected by the UE; Adding the location information collected by the UE at each time to the first error deviation value to obtain error location information; Adding the received signal strength at each time point collected by the UE to the second error deviation value to obtain an error received signal strength; Determine actual environment error information corresponding to the UE based on the location information and received signal strength collected by the first device, the location information and received signal strength collected by the UE, and the error location information and the error received signal strength; Inputting the map information corresponding to the UE into a pre-built first model to obtain an output result of the first model; Calculate a first loss value between an output result of the first model and the actual environment error information; The model parameters of the first model are adjusted based on the first loss value until the output result of the first model meets a first preset condition, and it is determined that the training is completed.
4. The method according to claim 3, characterized in that The first preset condition includes: a first loss value between an output result of the first model and the actual environment error information is less than a first threshold.
5. The method according to claim 2, characterized in that Different first models correspond to different physical environments and are used to output environmental error information under different physical environments; The training of the first model comprises: The corresponding first models are trained for different physical environments.
6. The method according to any one of claims 2 to 5, characterized in that: The method further comprises: Training the second model; wherein the training the second model comprises: Determine the environmental error information corresponding to the UE by using the first model; Determine the base station to be switched by the UE based on the location information and / or received signal strength of the UE at at least one time collected by the first device; Inputting the environmental error information into a pre-built second model to obtain an output result of the second model; Calculating a first accuracy between an output result of the second model and a base station determined by the first device; The model parameters of the second model are adjusted based on the first accuracy until the output result of the second model meets a second preset condition, and it is determined that the training is completed.
7. The method according to claim 6, characterized in that The second preset condition includes: a first accuracy between an output result of the second model and a base station determined by the first device is greater than a second threshold.
8. The method according to any one of claims 1 to 7, characterized in that: The first device includes at least one of the following: Network equipment; Data analysis server.
9. The method according to any one of claims 1 to 8, characterized in that: The second device includes at least one of the following: Global Navigation Satellite System (GNSS); sensor.
10. A switching prediction method, characterized in that: The method is performed by a first device, and includes: Acquire location information and received signal strength of the UE at at least one time point collected by the UE; Acquire error position information and error received signal strength based on the position information and received signal strength; Combining the position information and the received signal strength with the error position information and the error received signal strength to obtain at least one set of combined information; The at least one set of combined information is input into a pre-trained third model to obtain an output result of the third model, where the output result of the third model is: the base station to which the UE is to switch as predicted by the third model.
11. The method according to claim 10, characterized in that The combining the position information, the received signal strength with the error position information, the error received signal strength to obtain at least one set of combined information includes at least one of the following: Combining the location information and the received signal strength at the same time to obtain a first set of combined information; Combining the position information and the error received signal strength at the same time to obtain a second set of combined information; Combining the error position information and the received signal strength at the same time to obtain a third set of combined information; The error position information and the error received signal strength at the same time are combined to obtain a fourth set of combined information.
12. The method according to claim 10 or 11, characterized in that The method further comprises: Training the third model; wherein the training the third model comprises: The first device collects location information and received signal strength of the UE at at least one time; The first device determines, based on the location information of the UE at at least one time point collected by the first device and the received signal strength of the UE at at least one time point, a base station to be switched by the UE; Inputting at least one set of combination information at at least one moment into a pre-built third model to obtain output results corresponding to each set of combination information output by the third model; Calculating a second accuracy between the output results corresponding to each group of combined information and the base station determined by the first device; The model parameters of the third model are adjusted based on the second accuracy corresponding to each group of combined information until the output result of the third model meets the third preset condition, and it is determined that the training is completed.
13. The method according to claim 12, characterized in that The third preset condition includes at least one of the following: The average of the second accuracy corresponding to all the combined information is greater than a third threshold; The standard deviation of the second accuracy corresponding to all the combined information is less than the fourth threshold.
14. A switching prediction method, characterized in that: The method is performed by a second device, and the method includes: Determine map information of the physical environment in which the UE is located; The map information is sent to the first device.
15. A switching prediction method, characterized in that: The method is performed by a UE, and the method includes: Collecting location information and received signal strength of the UE at at least one time; Send the location information and received signal strength at at least one moment collected by the UE to the first device.
16. A communication device, comprising: A transceiver module, configured to receive map information of a physical environment in which a user equipment UE is located, sent by a second device; A processing module is used to predict the base station to which the UE is to switch based on the map information.
17. A communication device, comprising: a transceiver module, configured to obtain location information and received signal strength of the UE at at least one time point collected by the UE; A processing module, configured to obtain error position information and error received signal strength based on the position information and received signal strength; The processing module is further used to compare the position information and the received signal strength with the error position information and the error received signal strength. Combine with each other to obtain at least one set of combined information; The processing module is also used to input the at least one set of combined information into a pre-trained third model to obtain an output result of the third model, and the output result of the third model is: the base station to which the UE is to switch as predicted by the third model.
18. A communication device, comprising: A processing module, used to determine map information of the physical environment where the UE is located; The transceiver module is used to send the map information to the first device.
19. A communication device, comprising: A processing module, used to collect location information and received signal strength of the UE at at least one time; The transceiver module is used to send the location information and received signal strength at at least one moment collected by the UE to the first device.
20. A communication device, characterized in that: The device includes a processor and a memory, wherein a computer program is stored in the memory, and the processor executes the computer program stored in the memory so that the device performs the method as claimed in any one of claims 1 to 9, or the processor executes the computer program stored in the memory so that the device performs the method as claimed in any one of claims 10 to 13, or the processor executes the computer program stored in the memory so that the device performs the method as claimed in claim 14, or the processor executes the computer program stored in the memory so that the device performs the method as claimed in claim 15.
21. A communication device, characterized in that: include: processor and interface circuitry, wherein The interface circuit is used to receive code instructions and transmit them to the processor; The processor is used to run the code instructions to execute the method as described in any one of claims 1 to 9, or to run the code instructions to execute the method as described in any one of claims 10 to 13, or to run the code instructions to execute the method as described in claim 14, or to run the code instructions to execute the method as described in claim 15.
22. A computer-readable storage medium storing instructions, which, when executed, implement the method according to any one of claims 1 to 9, or implement the method according to any one of claims 10 to 13, or implement the method according to any one of claims 14, or implement the method according to any one of claims 15.
Citation Information
Patent Citations
Switching method utilizing fuzzy prediction model
CN107249200A
A switching algorithm based on machine learning in a UDN
CN109447275A
Cross-domain seamless switching method based on space-ground integrated network
CN111314983A
Machine learning handover prediction based on sensor data from wireless devices
CN115804147A
Machine learning for handover
US20220322195A1
Cited By
Low-altitude intelligent flight management system and method
CN119723954A
