Wireless cell intelligent switching method and device, equipment and storage medium
By acquiring multi-dimensional signal parameters and using predictive models for scoring, the problem of poor user experience caused by a single parameter in wireless cell handover was solved, achieving more accurate wireless cell handover and improving the user experience.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- FIBOCOM TECHNOLOGY CO LTD
- Filing Date
- 2026-01-09
- Publication Date
- 2026-04-10
AI Technical Summary
Existing wireless cell handover methods rely on a single signal quality parameter, resulting in a poor user experience.
By acquiring parameters such as reference signal received power, reference signal received quality, signal-to-noise ratio, and bandwidth of neighboring cells, a nonlinear mapping is performed using a preset signal quality prediction model to determine the signal quality score, and wireless cell handover is performed based on the score.
By comprehensively predicting the actual performance of neighboring communities using multi-dimensional parameters, the traditional single-decision mechanism can be replaced, thereby maximizing the improvement of user experience.
Smart Images
Figure CN121842776A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of data processing, in particular to a wireless cell intelligent switching method and device, equipment and storage medium. BACKGROUND
[0002] Cell switching is a key process in wireless communication, which refers to the technology of keeping communication continuity when a mobile terminal transfers from the service range of one cell (base station) to another cell (base station). The core is to ensure seamless switching of the terminal to realize uninterrupted user call or data transmission. In the current network environment, switching mainly occurs in the scenario of signal strength / quality change, that is, when the current base station signal is lower than the threshold and the adjacent cell signal is stronger. The key parameters for detection are Reference Signal Received Power (RSRP) and Reference Signal Received Quality (RSRQ), and the terminal sends a measurement report to the base station. The base station or core network decides whether to switch, and finally the terminal switches (Handover) to a new cell to complete resource allocation. SUMMARY
[0003] The main purpose of the present application is to provide a wireless cell intelligent switching method, device, equipment and storage medium, which aims to solve the technical problem that the existing wireless cell switching relies on a single signal quality parameter, resulting in poor user experience.
[0004] To achieve the above purpose, the present application provides a wireless cell intelligent switching method, which comprises: In the case where it is detected that the signal quality of the current serving cell meets the preset cell switching condition, the signal quality parameters of the adjacent cell are obtained, the signal quality parameters comprising at least two of the following: Reference Signal Received Power, Reference Signal Received Quality, Signal-to-Noise Ratio and Bandwidth; The signal quality parameters are input into a preset signal quality prediction model to obtain the signal quality score of the adjacent cell output by the preset signal quality prediction model, and the preset signal quality prediction model is used to determine the signal quality score based on the nonlinear mapping relationship between the signal quality parameters and the throughput; Based on the signal quality score, wireless cell switching is performed.
[0005] Optionally, the preset signal quality prediction model is deployed on the terminal. Before the signal quality parameters are input into the preset signal quality prediction model to obtain the signal quality score of the adjacent cell output by the preset signal quality prediction model, the method further comprises: Collecting sample signal quality parameters; determine the real throughput through a bag test; train an initial signal quality prediction model based on the sample signal quality parameters and the real throughput to obtain a preset signal quality prediction model.
[0006] Optionally, the training of the initial signal quality prediction model based on the sample signal quality parameters and the real throughput to obtain the preset signal quality prediction model comprises: performing data cleaning on the sample signal quality parameters and the real throughput to obtain target sample data; dividing the target sample data into a training set and a test set; performing supervised learning on the initial signal quality prediction model based on the training set to obtain a supervised learning initial signal quality prediction model; verifying the generalization ability of the supervised learning initial signal quality prediction model based on the test set to obtain a verification result; in a case where the verification result is verified, determining a preset signal quality prediction model according to the supervised learning initial signal quality prediction model.
[0007] Optionally, the wireless cell switching based on the signal quality score comprises: determining a target cell based on the signal quality score; reporting a signal quality parameter of the target cell to a target base station; receiving a wireless cell switching command issued by the target base station and performing wireless cell switching based on the wireless cell switching command.
[0008] Optionally, the determination of the target cell based on the signal quality score comprises: sorting the neighboring cells based on the signal quality score to obtain a sorting result; determining a preset number of target cells from the neighboring cells according to the sorting result.
[0009] Optionally, the obtaining of the bandwidth of the neighboring cell comprises: obtaining standard broadcast information of the neighboring cell; determining carrier bandwidth field information in the standard broadcast information; determining the bandwidth of the neighboring cell based on the carrier bandwidth field information.
[0010] Optionally, the obtaining of the signal quality parameter of the neighboring cell in a case where it is detected that the signal quality of the current serving cell meets a preset cell switching condition comprises: In a case where it is detected that the signal quality of the current serving cell meets a preset cell switching condition, current location information is acquired; A number of cells to be measured is determined according to the current location information; A signal quality parameter of a neighbor cell is acquired based on the number of cells to be measured.
[0011] In addition, to achieve the above object, the present application further provides a wireless cell intelligent switching device, which comprises: An acquisition module is configured to acquire a signal quality parameter of a neighbor cell in a case where it is detected that the signal quality of a current serving cell meets a preset cell switching condition, the signal quality parameter comprising at least two of the following: reference signal received power, reference signal received quality, signal-to-noise ratio and bandwidth; A signal quality score prediction module is configured to input the signal quality parameter into a preset signal quality prediction model to obtain a signal quality score of the neighbor cell output by the preset signal quality prediction model, the preset signal quality prediction model being configured to determine the signal quality score based on a nonlinear mapping relationship between the signal quality parameter and throughput; A wireless cell switching module is configured to perform wireless cell switching based on the signal quality score.
[0012] In addition, to achieve the above object, the present application further provides a wireless cell intelligent switching device, which comprises a memory, a processor and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the wireless cell intelligent switching method as described above.
[0013] In addition, to achieve the above object, the present application further provides a storage medium, which is a computer readable storage medium, and has a computer program stored thereon, the computer program being executable by a processor to implement the steps of the wireless cell intelligent switching method as described above.
[0014] The application obtains a signal quality parameter of a neighbor cell in the case that it is detected that the signal quality of a current serving cell meets a preset cell switching condition, the signal quality parameter including at least two of the following: reference signal received power, reference signal received quality, signal-to-noise ratio, and bandwidth; inputs the signal quality parameter into a preset signal quality prediction model to obtain a signal quality score of the neighbor cell output by the preset signal quality prediction model, the preset signal quality prediction model being used to determine the signal quality score based on a nonlinear mapping relationship between the signal quality parameter and throughput; and performs wireless cell switching based on the signal quality score. Since the application determines the signal quality score of the neighbor cell based on the signal quality parameter of the neighbor cell and performs wireless cell switching based on the signal quality score, compared with the prior art of performing wireless cell switching only based on reference signal received power, the above manner of the application can predict the actual performance of the neighbor cell by comprehensively using multi-dimensional parameters, replace the traditional single decision mechanism, and maximize the user experience. BRIEF DESCRIPTION OF DRAWINGS
[0015] The accompanying drawings, which are incorporated herein and form part of the specification, illustrate embodiments consistent with the present application and, together with the description, further serve to explain the principles of the application.
[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, those skilled in the art can obtain other drawings from these drawings without any creative effort.
[0017] Figure 1 A flowchart is provided for the wireless cell intelligent switching method embodiment one of the present application; Figure 2 A WWAN module structure diagram is provided for the wireless cell intelligent switching method embodiment one of the present application; Figure 3 A flowchart is provided for the wireless cell intelligent switching method embodiment two of the present application; Figure 4 A module structure diagram is provided for the wireless cell intelligent switching device of the present application embodiment; Figure 5 A device structure diagram of a hardware running environment involved in the wireless cell intelligent switching method of the present application embodiment is provided.
[0018] The object implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION
[0019] It should be understood that the specific embodiments described herein are merely intended to explain the technical solutions of the present application, and are not intended to limit the present application.
[0020] In order to better understand the technical solutions of the present application, the following will be described in detail in combination with the drawings of the specification and specific embodiments.
[0021] It should be noted that the execution subject of the present embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device, a terminal, etc. capable of realizing the above functions. The following will take the terminal as an example to describe the present embodiment and each of the following embodiments.
[0022] Based on this, the present embodiment provides a wireless cell intelligent switching method, which is described with reference to Figure 1 , Figure 1 The flowchart provided by the first embodiment of the wireless cell intelligent switching method of the present application.
[0023] In the present embodiment, the wireless cell intelligent switching method comprises the following steps: Step S10, in the case where it is detected that the signal quality of the current serving cell meets the preset cell switching condition, acquiring the signal quality parameters of the neighboring cell, the signal quality parameters comprising at least two of the following: reference signal received power, reference signal received quality, signal-to-noise ratio and bandwidth; It should be noted that the signal quality of the current serving cell meeting the preset cell switching condition can be that the A2 event is triggered. In the measurement mechanism of LTE / 5GNR, 3GPP protocol defines a series of measurement events (Measurement Events) to let the terminal report the measurement results to the base station under certain conditions, so that the base station decides whether to perform switching and other operations. A2 event (Event A2) is one of them, which means that the signal quality of the serving cell is lower than a certain threshold, for example: when the terminal detects that the reference signal received power (RSRP) or the reference signal received quality (RSRQ) of the current serving cell is lower than the set absolute threshold, the event is triggered, and the measurement of the neighboring cell is started.
[0024] Further, in order to avoid the need to add new signaling to acquire the bandwidth of the neighboring cell, the present embodiment acquires the bandwidth of the neighboring cell, comprising: Acquiring the standard broadcast information of the neighboring cell; Determining the carrier bandwidth field information in the standard broadcast information; Determining the bandwidth of the neighboring cell based on the carrier bandwidth field information.
[0025] It should be noted that the standard broadcast information can be broadcast information sent by neighboring cells (System Information Block Type 1, SIB1), and the carrier bandwidth field information can be a field called `carrierBandwidth` in the standard broadcast information, used to indicate the carrier bandwidth (bandwidth) configured for that cell. The bandwidth of neighboring cells can be obtained based on this field. This embodiment obtains the bandwidth by parsing the `carrierBandwidth` field in SIB1, without requiring additional signaling. Furthermore, there is no forged data transmission or protocol process disruption; standard procedures are used to achieve protocol compatibility.
[0026] Furthermore, to avoid the terminal measuring the signal quality parameters of all neighboring cells, step S10 may include: obtaining current location information when the signal quality of the current serving cell meets the preset cell handover conditions; The number of cells to be measured is determined based on the current location information; The signal quality parameters of neighboring cells are obtained based on the number of cells to be measured.
[0027] It should be noted that the current location information can be the current location of the terminal. Determining the number of cells to be measured based on the current location information can be done by judging the area grid corresponding to the current location. The area grid can include dense urban commercial areas, urban main roads, urban ring roads, urban peripheral roads, etc., and different area grids correspond to different numbers of measurement cells. For example, if the current location belongs to a dense urban commercial area, the number of cells to be measured can be 12; if the current location belongs to an urban peripheral road, the number of cells to be measured can be 4. The specific grid division and the corresponding number of cells to be measured can be customized. Obtaining the signal quality parameters of neighboring cells based on the number of cells to be measured can be done by obtaining the signal quality parameters of 12 neighboring cells if the number of cells to be measured is 12.
[0028] Step S20: Input the signal quality parameters into a preset signal quality prediction model to obtain the signal quality score of the neighboring cell output by the preset signal quality prediction model. The preset signal quality prediction model is used to determine the signal quality score based on the nonlinear mapping relationship between the signal quality parameters and the throughput. It should be noted that the preset signal quality prediction model can be a model trained in advance with sample data to predict the signal quality score of neighboring cells. The above-mentioned signal quality parameters of the sample data cell and the corresponding throughput at the same time. By training with sample data, the preset signal quality prediction model can predict the throughput of neighboring cells based on the nonlinear mapping relationship between signal quality parameters and throughput, and then determine the signal quality score of neighboring cells based on the predicted throughput. The signal quality score can be the predicted throughput. It can also be the signal quality score calculated based on the predicted throughput and Shannon's formula. Calculating the signal quality score based on the predicted throughput and Shannon's formula can be: calculate the maximum information transmission rate based on Shannon's formula, and then calculate the signal quality score based on the predicted throughput and the maximum information transmission rate. Specifically, it can be signal quality score = predicted throughput / maximum information transmission rate. Among them, Shannon's formula can refer to the following formula (1): C = B × log2(1 + SINR) (1) Where C represents the channel capacity (bps), i.e. the maximum information transmission rate, B represents the bandwidth, and SINR represents the signal-to-noise ratio.
[0029] Step S30: Perform wireless cell handover based on the signal quality score.
[0030] It should be noted that the wireless cell handover based on the signal quality score can be performed by the wireless cell intelligent handover device (terminal) determining multiple neighboring cells with higher signal quality scores based on the signal quality score, then reporting the signal quality parameters of the neighboring cells to the base station, and then the base station issuing a cell handover command based on the signal quality parameters, and the terminal performing wireless cell handover based on the received cell handover command.
[0031] Furthermore, in order to improve the user experience, step S30 may include: determining the target cell based on the signal quality score; The signal quality parameters of the target cell are reported to the target base station; Receive the wireless cell handover command issued by the target base station, and perform wireless cell handover based on the wireless cell handover command.
[0032] It should be noted that determining the target cell based on the signal quality score can refer to selecting the top-ranked neighboring cells based on the signal quality score. The signal quality parameters of the target cell may include reference signal received power, reference signal received quality, signal-to-noise ratio, and bandwidth. The target base station may be the base station currently connected to the terminal. The wireless cell handover command may be a command issued by the target base station to cause the terminal to switch the connected cell.
[0033] Furthermore, determining the target cell based on the signal quality score includes: The neighboring cells are ranked based on the signal quality score to obtain the ranking result; Based on the sorting results, a preset number of target cells are determined from the neighboring cells.
[0034] It should be noted that the ranking of neighboring cells based on the signal quality score can be achieved by ranking the neighboring cells according to their signal quality scores. The preset number can be a pre-set threshold used to determine the number of neighboring cells reported to the base station. In this embodiment, the first two cells are preferred. Selecting the first two cells is for redundancy backup. Since handover may involve the base station actively adjusting its load, if the load of a single cell is too high, the base station will refuse to handover to the top-ranked cell. In this embodiment, in addition to reporting the signal quality parameters of the target cell to the base station, the signal quality parameters of the currently serving cell are also reported, enabling the base station to perform cell handover based on the reported cell's signal quality parameters.
[0035] In specific implementation, the terminal in this embodiment has a built-in Wireless Wide Area Network (WWAN) module. The structure of the WWAN module can be referred to... Figure 2 , Figure 2This is a schematic diagram of the WWAN module structure provided in Embodiment 1 of the wireless cell intelligent handover method of this application. The WWAN module includes a CPU AI computing module, a radio frequency unit, a memory unit, and other modules. The radio frequency unit is mainly responsible for transmitting and receiving wireless signals. It handles operations such as modulation, demodulation, and power amplification of radio frequency signals, enabling the WWAN module to communicate with external wireless networks (such as cellular mobile networks, Wi-Fi, etc.). The memory unit is used for temporary storage of data and program instructions, ensuring that components such as the CPU can quickly access and process this information. Sufficient memory is crucial for the module's operating speed and multitasking capabilities. Other modules represent other necessary components besides the main components mentioned above, which may include a power management module, interface circuits, debugging interfaces, sensor interfaces, etc. These components work together to ensure that the entire WWAN module can operate stably and efficiently, and connect and interact with other devices or systems. The CPU AI computing module (Central Processing Unit) is the core of the WWAN module's computation and control, responsible for executing various instructions and processing data. AI computing indicates that the module may possess artificial intelligence processing capabilities, enabling it to perform tasks such as machine learning and deep learning, thereby improving the module's intelligence level and processing efficiency. In this embodiment, the CPU AI computing module supports the deployment and lightweight computation of the AI model (a preset signal quality prediction model). The specific process is as follows: i. The signal of the current server cell deteriorates, triggering an A2 event to initiate measurement; ii. The terminal collects neighboring cell parameters; iii. The AI model (preset signal quality prediction model) is input to predict performance; iv. Performance score is calculated; v. The measurement values of the top two performing cells plus the server cell are selected and reported; vi. The base station issues a target handover.
[0036] In this embodiment, when the signal quality of the current serving cell meets preset cell handover conditions, signal quality parameters of neighboring cells are obtained. These parameters include at least two items: reference signal received power, reference signal received quality, signal-to-noise ratio, and bandwidth. The signal quality parameters are input into a preset signal quality prediction model to obtain a signal quality score for the neighboring cell. The preset signal quality prediction model is used to determine the signal quality score based on the nonlinear mapping relationship between the signal quality parameters and throughput. Wireless cell handover is then performed based on the signal quality score. Since this embodiment determines the signal quality score of the neighboring cell based on its signal quality parameters and performs wireless cell handover based on the score, compared to existing methods that only rely on reference signal received power, this embodiment comprehensively predicts the actual performance of neighboring cells using multiple parameters, replacing the traditional single-decision mechanism and maximizing the improvement of user experience.
[0037] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 3 , Figure 3 This is a flowchart illustrating an embodiment of the intelligent handover method for wireless cells in this application. Before step S20, the method further includes the following steps: Step S001: Acquire sample signal quality parameters; It should be noted that the sample signal quality parameters acquired may include reference signal received power (RSRP), reference signal received quality (RSRQ), signal-to-noise ratio (SINR), and bandwidth.
[0038] Step S002: Determine the actual throughput through a packet filling test; It should be noted that the packet flooding test can be a throughput measurement method in communication testing. The packet flooding test continuously sends data at high speed to saturate the link, thereby measuring the maximum stable throughput achievable under the given wireless conditions, i.e., the actual throughput. Types of packet flooding tests can include FTP packet flooding and UDP packet flooding. FTP packet flooding simulates file transfer (such as uploading / downloading large files) using the TCP protocol, reflecting the actual throughput at the application layer (including the impact of retransmissions and congestion control). The actual throughput is measured by the sample signal quality parameters. UDP packet flooding measures the amount of effective data received by the receiver by sending UDP packets at a constant rate, unaffected by congestion control.
[0039] In practice, the sample data, consisting of sample signal quality parameters and actual throughput, can be collected through existing network testing. Specifically, each area can be divided into grids for testing and collection, with the collection priority in the following order: dense urban commercial districts > main urban roads > urban ring roads > outer urban routes. In other words, in the final sample data, the number of sample data from dense urban commercial districts > the number of sample data from main urban roads > the number of sample data from urban ring roads > the number of sample data from outer urban routes.
[0040] Step S003: Train the initial signal quality prediction model based on the sample signal quality parameters and the actual throughput to obtain the preset signal quality prediction model.
[0041] It should be noted that training the initial signal quality prediction model based on the sample signal quality parameters and the actual throughput can be achieved by converting multiple parameter values in the sample signal quality parameters into feature vector representations, such as [RSRP, RSRQ, SINR, Bandwidth]. Each sample is represented as (X, Y), where X = [RSRP, RSRQ, SINR, Bandwidth] is the feature vector, and Y = actual throughput (Throughput) is the label value. The initial signal quality prediction model is trained using (X, Y), with mean squared error as the loss function. Iterative optimization is performed to make the predicted throughput Y_pred infinitely close to the actual throughput Y until the loss function meets a preset convergence condition or reaches a preset number of training rounds. The specific stopping condition can be customized according to the actual training scenario.
[0042] Furthermore, in order to make the predicted throughput Y_pred predicted by the preset signal quality prediction model closer to the actual throughput Y, step S003 may include: performing data cleaning on the sample signal quality parameters and the actual throughput to obtain target sample data; The target sample data is divided into a training set and a test set; The initial signal quality prediction model is subjected to supervised learning using the training set to obtain a supervised learning initial signal quality prediction model. The generalization ability of the supervised learning-based initial signal quality prediction model is verified based on the test set, and the verification results are obtained. If the verification result is successful, a preset signal quality prediction model is determined based on the initial signal quality prediction model after supervised learning.
[0043] It should be noted that the data cleaning of the sample signal quality parameters and the actual throughput can include removing outliers (such as RSRP exceeding the normal range), handling missing values, normalizing, and performing time alignment to ensure that the feature vectors strictly correspond to the labels. Similarly, the signal quality parameters also need to be cleaned before being input into the preset signal quality prediction model for prediction. Dividing the target sample data into training and testing sets can be done by randomly dividing the target sample data into training and testing sets according to a preset ratio, such as 8:2. The initial signal quality prediction model can be a lightweight random forest model. The supervised learning of the initial signal quality prediction model using the training set to obtain the supervised initial signal quality prediction model can be achieved by using the training set to supervise the learning of the lightweight random forest model, using mean squared error as the loss function, and iteratively optimizing to make the predicted throughput Y_pred infinitely close to the actual throughput Y, thus obtaining the trained initial signal quality prediction model. The generalization capability verification of the supervised learning initial signal quality prediction model based on the test set can be performed by inputting the test set into the supervised learning initial signal quality prediction model to obtain the predicted throughput Y_pred output by the supervised learning initial signal quality prediction model, and then calculating the mean absolute error (MAE), coefficient of determination (R²), and other indicators of the test set based on the predicted throughput Y_pred and the actual throughput corresponding to the test set. The prediction accuracy of the supervised learning initial signal quality prediction model is evaluated based on these indicators. If the prediction accuracy meets the preset training conditions, the generalization capability verification is deemed successful, and the supervised learning initial signal quality prediction model is used as the preset signal quality prediction model.
[0044] In practice, each sample is represented as (X, Y), where X = [RSRP, RSRQ, SINR, Bandwidth] is the feature vector, and Y = Throughput is the label value. The training data sample structure can be: training_sample={ "features":[RSRP, RSRQ, SINR, Bandwidth] # Input feature vector X "label":throughput#actual throughput Y (label) } Model learning objective: Establish a nonlinear mapping of X and Y: `model.fit(X_train, Y_train)` # Fit the relationship through supervised learning. Data labeling basis: The label (Y) is obtained as follows: At the same time as collecting the feature parameters (RSRP, RSRQ, SINR, Bandwidth) on the terminal, a standardized FTP / UDP packet injection test is performed on the terminal, and the actual throughput at that moment is directly measured as the true label. Simultaneously, to ensure data accuracy, the collected raw data needs to be cleaned, including removing outliers (such as RSRP exceeding the normal range), handling missing values, and performing time alignment to ensure a strict correspondence between features and labels.
[0045] Training with massive amounts of sample data, the model learns the complex nonlinear relationship between multiple parameter combinations and actual throughput (e.g., high bandwidth + low signal strength may outperform low bandwidth + strong signal strength). This nonlinear relationship is typically manifested in wireless networks as follows: the model recognizes the positive gain of the 'high bandwidth' parameter on throughput, and in some scenarios, it can compensate for the negative impact of 'low signal strength'. For example, the throughput predicted by feature vector X1=[RSRP=-95dBm, RSRQ=-12dB, SINR=15dB, Bandwidth=100MHz] will be significantly higher than that predicted by feature vector X2=[RSRP=-85dBm, RSRQ=-8dB, SINR=20dB, Bandwidth=20MHz].
[0046] The specific model configuration is as follows: Model type: Lightweight Random Forest; Reason: Low computational overhead, suitable for real-time inference on the edge; Compression technology: Parameter quantization: FP32-INT8; Layer pruning: Remove decision tree branches with less than 5% contribution; Input layer: 4-dimensional vector [RSRP, RSRQ, SINR, Bandwidth]; Output layer: 1-dimensional scalar Y_pred (unit: Mbps); Deployment location: Built-in CPU AI computing unit of WWAN module.
[0047] In practical implementation, it is necessary to normalize the signal quality parameters of neighboring cells and the collected sample data. For example, the original parameters are: RSRP=-95dBm (-140dBm, -44dBm); RSRQ=-12dB (-34dB, 3dB); SINR=15dB (-10dB, 40dB); Bandwidth=100MHz (logarithmic scaling log2(Bandwidth)); after normalization: X=[0.32, 0.65, 0.62, log2(100) / 10≈0.66], the input vector of the model is [0.32, 0.65, 0.62, 0.66], and the output result can be: Y_pred Mbps (predicted throughput without conversion, intuitive rate).
[0048] In practical implementation, scenario 1: In the overlapping coverage area of N1 20MHz and N78 100MHz, the terminal stays on the N1 cell due to its stronger RSRP. Step 1, Parameter Acquisition: After the terminal detects the A2 event, it measures N1 and N78 as follows: RSRP: N1 = -90dBm, N78 = -95dBm RSRQ: N1 = -10dB, N78 = -12dB SINR: N1=15dB, N78=18dB Bandwidth: N1 = 20MHz (SIB1 resolution), N78 = 100MHz Step 2, AI scoring: Model input X = [RSRP, RSRQ, SINR, Bandwidth] N1 score = 65 (predicted throughput 160Mbps) N78 rating = 88 (predicted throughput 450Mbps) The third step is to report the decision: only report the measurement results of N78 and N1, that is, the acquired signal quality parameters; The fourth step is the handover execution: the base station issues a handover order to N78, and the user's measured throughput increases from 160Mbps to 450Mbps.
[0049] Scenario 2: The current serving cell (N78) experiences sudden interference (SINR drops sharply from 20dB to 5dB), and the traditional solution still switches based on RSRP; Step 1, Parameter Acquisition: The terminal measured the following for N78: RSRP=-92dBm, RSRQ=-14dB, SINR=5dB, Bandwidth=100MHz; The second step, AI scoring: the model automatically lowered its score to 30 (originally 85) due to the sudden drop in SINR, while the neighboring cell N1 score was 70; The third step is to report the decision: remove N78 and report to other communities; The fourth step is to switch to another cell to avoid interference and maintain service stability.
[0050] Scenario 3: In a densely populated urban commercial district, the terminal needs to measure 12 neighboring areas. Step 1, Parameter Acquisition: The terminal measures the RSRP / RSRQ / SINR / bandwidth of 12 neighboring cells; The second step is AI scoring: the model quickly calculates the score for each community. The third step is to report the decision: only the top-ranked service communities are reported. The fourth step is the handover execution: quickly switch to the optimal cell to reduce signaling overhead.
[0051] This embodiment collects sample signal quality parameters; determines the actual throughput through packet injection testing; and trains an initial signal quality prediction model based on the sample signal quality parameters and the actual throughput to obtain a preset signal quality prediction model. This embodiment trains the initial signal quality prediction model using the collected sample signal quality parameters and the actual throughput to obtain a preset signal quality prediction model. Furthermore, the preset signal quality prediction model can be used to determine the signal quality score of neighboring cells, avoiding decisions based solely on RSRP / RSRQ, which could lead to terminals prioritizing cells with strong signals but low bandwidth or other signal quality parameter values (such as N1 20MHz), thus missing out on the high-speed capabilities of high-bandwidth cells (such as N78 100MHz).
[0052] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the wireless cell intelligent handover method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.
[0053] This application also provides a wireless cell intelligent handover device, please refer to... Figure 4 The wireless cell intelligent handover device includes: The acquisition module 10 is used to acquire signal quality parameters of neighboring cells when the signal quality of the current serving cell meets the preset cell handover conditions. The signal quality parameters include at least two of the following: reference signal received power, reference signal received quality, signal-to-noise ratio, and bandwidth. The signal quality score prediction module 20 is used to input the signal quality parameters into a preset signal quality prediction model to obtain the signal quality score of the neighboring cell output by the preset signal quality prediction model. The preset signal quality prediction model is used to determine the signal quality score based on the nonlinear mapping relationship between the signal quality parameters and the throughput. The wireless cell handover module 30 is used to perform wireless cell handover based on the signal quality score.
[0054] In this embodiment, when the signal quality of the current serving cell meets preset cell handover conditions, signal quality parameters of neighboring cells are obtained. These parameters include at least two items: reference signal received power, reference signal received quality, signal-to-noise ratio, and bandwidth. The signal quality parameters are input into a preset signal quality prediction model to obtain a signal quality score for the neighboring cell. The preset signal quality prediction model is used to determine the signal quality score based on the nonlinear mapping relationship between the signal quality parameters and throughput. Wireless cell handover is then performed based on the signal quality score. Since this embodiment determines the signal quality score of the neighboring cell based on its signal quality parameters and performs wireless cell handover based on the score, compared to existing methods that only rely on reference signal received power, this embodiment comprehensively predicts the actual performance of neighboring cells using multiple parameters, replacing the traditional single-decision mechanism and maximizing the improvement of user experience.
[0055] The intelligent handover device for wireless cells provided in this application, employing the intelligent handover method for wireless cells in the above embodiments, can solve the technical problem of poor user experience caused by existing wireless cell handover relying on a single signal quality parameter. Compared with the prior art, the beneficial effects of the intelligent handover device for wireless cells provided in this application are the same as those of the intelligent handover method for wireless cells provided in the above embodiments, and other technical features in the intelligent handover device for wireless cells are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.
[0056] This application provides a wireless cell intelligent handover device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the wireless cell intelligent handover method in the above embodiment 1.
[0057] The following is for reference. Figure 5The diagram illustrates a structural schematic of a wireless smart handover device suitable for implementing embodiments of this application. The wireless smart handover device in these embodiments may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 5 The wireless cell intelligent handover device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.
[0058] like Figure 5 As shown, the smart cell handover device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the smart cell handover device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the wireless smart handover device to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows wireless smart handover devices with various systems, it should be understood that it is not required to implement or possess all of the systems shown. More or fewer systems may be implemented alternatively.
[0059] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.
[0060] The intelligent handover device for wireless cells provided in this application, employing the intelligent handover method for wireless cells in the above embodiments, can solve the technical problem of poor user experience caused by existing wireless cell handover relying on a single signal quality parameter. Compared with the prior art, the beneficial effects of the intelligent handover device for wireless cells provided in this application are the same as those of the intelligent handover method for wireless cells provided in the above embodiments, and other technical features in this intelligent handover device are the same as those disclosed in the method of the previous embodiment, and will not be repeated here.
[0061] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.
[0062] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
[0063] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the wireless cell intelligent handover method in the above embodiments.
[0064] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.
[0065] The aforementioned computer-readable storage medium may be included in the wireless cell intelligent handover device; or it may exist independently and not be assembled into the wireless cell intelligent handover device.
[0066] Computer program code for performing the operations of this application can be written in one or more programming languages or a combination thereof. These programming languages include object-oriented programming languages—such as Python, Java, Smalltalk, and C++—and conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0067] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.
[0068] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.
[0069] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described intelligent handover method for wireless cells. This addresses the technical problem of poor user experience caused by existing wireless cell handover methods relying on a single signal quality parameter. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the intelligent handover method for wireless cells provided in the above embodiments, and will not be elaborated upon here.
[0070] The above description is only a part of the embodiments of this application and does not limit the scope of protection of this application. All equivalent structural transformations made under the technical concept of this application and using the content of this application specification and drawings, or direct / indirect applications in other related technical fields, are included in the scope of protection of this application.
Claims
1. A method for intelligent handover of wireless cells, characterized in that, The intelligent handover method for wireless cells includes the following steps: When the signal quality of the current serving cell meets the preset cell handover conditions, the signal quality parameters of the neighboring cell are obtained. The signal quality parameters include at least two of the following: reference signal received power, reference signal received quality, signal-to-noise ratio, and bandwidth. The signal quality parameters are input into a preset signal quality prediction model to obtain the signal quality score of the neighboring cell output by the preset signal quality prediction model. The preset signal quality prediction model is used to determine the signal quality score based on the nonlinear mapping relationship between the signal quality parameters and the throughput. Wireless cell handover is performed based on the signal quality score.
2. The intelligent handover method for wireless cells as described in claim 1, characterized in that, The preset signal quality prediction model is deployed on the terminal; Before inputting the signal quality parameters into a preset signal quality prediction model to obtain the signal quality score of the neighboring cell output by the preset signal quality prediction model, the method further includes: Acquire sample signal quality parameters; Determine the actual throughput through packet injection testing; The initial signal quality prediction model is trained based on the sample signal quality parameters and the actual throughput to obtain the preset signal quality prediction model.
3. The intelligent handover method for wireless cells as described in claim 2, characterized in that, The step of training an initial signal quality prediction model based on the sample signal quality parameters and the actual throughput to obtain a preset signal quality prediction model includes: Data cleaning is performed on the sample signal quality parameters and the actual throughput to obtain the target sample data; The target sample data is divided into a training set and a test set; The initial signal quality prediction model is subjected to supervised learning using the training set to obtain a supervised learning initial signal quality prediction model. The generalization ability of the supervised learning-based initial signal quality prediction model is verified based on the test set, and the verification results are obtained. If the verification result is successful, a preset signal quality prediction model is determined based on the initial signal quality prediction model after supervised learning.
4. The intelligent handover method for wireless cells as described in any one of claims 1-3, characterized in that, The wireless cell handover based on the signal quality score includes: The target cell is determined based on the signal quality score; The signal quality parameters of the target cell are reported to the target base station; Receive the wireless cell handover command issued by the target base station, and perform wireless cell handover based on the wireless cell handover command.
5. The intelligent handover method for wireless cells as described in claim 4, characterized in that, The determination of the target cell based on the signal quality score includes: The neighboring cells are ranked based on the signal quality score to obtain the ranking result; Based on the sorting results, a preset number of target cells are determined from the neighboring cells.
6. The intelligent handover method for wireless cells as described in any one of claims 1-3, characterized in that, Obtain the bandwidth of neighboring cells, including: Obtain standard broadcast information from neighboring communities; Determine the carrier bandwidth field information in the standard broadcast information; The bandwidth of neighboring cells is determined based on the carrier bandwidth field information.
7. The intelligent handover method for wireless cells as described in any one of claims 1-3, characterized in that, The step of obtaining signal quality parameters of neighboring cells when the signal quality of the current serving cell meets the preset cell handover conditions includes: If the signal quality of the current serving cell meets the preset cell handover conditions, obtain the current location information; The number of cells to be measured is determined based on the current location information; The signal quality parameters of neighboring cells are obtained based on the number of cells to be measured.
8. A wireless cell intelligent handover device, characterized in that, The wireless cell intelligent handover device includes: The acquisition module is used to acquire signal quality parameters of neighboring cells when the signal quality of the current serving cell meets the preset cell handover conditions. The signal quality parameters include at least two of the following: reference signal received power, reference signal received quality, signal-to-noise ratio, and bandwidth. The signal quality score prediction module is used to input the signal quality parameters into a preset signal quality prediction model to obtain the signal quality score of the neighboring cell output by the preset signal quality prediction model. The preset signal quality prediction model is used to determine the signal quality score based on the nonlinear mapping relationship between the signal quality parameters and the throughput. A wireless cell handover module is used to perform wireless cell handover based on the signal quality score.
9. A wireless cell intelligent handover device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the wireless cell intelligent handover method as described in any one of claims 1 to 7.
10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the wireless cell intelligent handover method as described in any one of claims 1 to 7.