Carrier selection method, device, computer equipment and computer readable storage medium

Abstract

The present application relates to the field of communication technology, and in particular to a carrier selection method, device, computer equipment and computer-readable storage medium. The method comprises: in the case of communication demand, according to the communication time corresponding to the communication demand, the current position of the terminal and the carrier information of the available carrier at the current position, determining the predicted transmission rate corresponding to each available carrier; according to the predicted transmission rate corresponding to each available carrier, selecting a target carrier from each available carrier; wherein the target carrier is used for the terminal to communicate with the base station corresponding to the communication demand.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a carrier selection method, apparatus, computer equipment, and computer-readable storage medium. Background Art

[0002] The development of mobile communication networks has evolved from the first generation of mobile communication technology (1G) to the fifth generation of mobile communication technology (5G). The integrated networking of the fourth generation of mobile communication technology (4G) and 5G has become the current status quo and will continue to exist for a long time.

[0003] In the early stage of 5G deployment, it is difficult to achieve full coverage due to the high 5G frequency band and large propagation loss. Therefore, operators tend to adopt 4G and 5G multi-carrier multi-standard integrated networking to build networks. This method can effectively utilize existing 4G network resources and introduce 5G technology to meet users' needs for higher speeds, shorter communication delays, and more communication connections.

[0004] In converged networking, carrier selection has become an important issue. Since 4G and 5G use different frequency bands and technical standards, how to make the best carrier selection between the two based on network conditions, device capabilities and user needs has become an issue that needs to be solved urgently. Summary of the invention

[0005] Based on this, it is necessary to provide a carrier selection method, apparatus, computer device and computer-readable storage medium that can improve the accuracy of carrier selection in response to the above technical problems.

[0006] In a first aspect, the present application provides a carrier selection method, comprising:

[0007] In the case of communication demand, determining a predicted transmission rate corresponding to each available carrier according to the communication time corresponding to the communication demand, the current position of the terminal and the carrier information of each available carrier at the current position;

[0008] A target carrier is selected from the available carriers according to the predicted transmission rate corresponding to each available carrier; wherein the target carrier is used for the terminal to communicate with the base station corresponding to the communication demand.

[0009] In one of the embodiments, determining a predicted transmission rate corresponding to each available carrier according to a communication time corresponding to a communication demand, a current location of a terminal, and carrier information of each available carrier at the current location includes:

[0010] Based on the prediction model, the predicted transmission rate corresponding to each available carrier is determined according to the communication time corresponding to the communication demand, the current position of the terminal and the carrier information of each available carrier at the current position.

[0011] In one embodiment, the method further comprises:

[0012] During the communication with the base station via the target carrier, monitoring whether the communication connection times out;

[0013] If so, the prediction model is updated;

[0014] Based on the updated prediction model, the operation of determining the predicted transmission rate corresponding to each available carrier is returned.

[0015] In one embodiment, selecting a target carrier from each available carrier according to a predicted transmission rate corresponding to each available carrier includes:

[0016] The available carrier with the highest predicted transmission rate among all available carriers is used as the target carrier.

[0017] In one embodiment, the communication demand includes an uplink data transmission demand or a downlink data transmission demand.

[0018] In one embodiment, the carrier information of each available carrier includes a signal to interference plus noise ratio SINR and a reference signal received power RSRP.

[0019] In a second aspect, the present application further provides a carrier selection device, which is configured in a terminal, and the device includes:

[0020] A communication detection module, used to determine the predicted transmission rate corresponding to each available carrier according to the communication time corresponding to the communication demand, the current position of the terminal and the carrier information of each available carrier at the current position when there is a communication demand;

[0021] The carrier selection module is used to select a target carrier from each available carrier according to the predicted transmission rate corresponding to each available carrier; wherein the target carrier is used for the terminal to communicate with the base station corresponding to the communication demand.

[0022] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0023] In the case of communication demand, determining a predicted transmission rate corresponding to each available carrier according to the communication time corresponding to the communication demand, the current position of the terminal and the carrier information of each available carrier at the current position;

[0024] A target carrier is selected from the available carriers according to the predicted transmission rate corresponding to each available carrier; wherein the target carrier is used for the terminal to communicate with the base station corresponding to the communication demand.

[0025] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the following steps are implemented:

[0026] In the case of communication demand, determining a predicted transmission rate corresponding to each available carrier according to the communication time corresponding to the communication demand, the current position of the terminal and the carrier information of each available carrier at the current position;

[0027] A target carrier is selected from the available carriers according to the predicted transmission rate corresponding to each available carrier; wherein the target carrier is used for the terminal to communicate with the base station corresponding to the communication demand.

[0028] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0029] In the case of communication demand, determining a predicted transmission rate corresponding to each available carrier according to the communication time corresponding to the communication demand, the current position of the terminal and the carrier information of each available carrier at the current position;

[0030] A target carrier is selected from the available carriers according to the predicted transmission rate corresponding to each available carrier; wherein the target carrier is used for the terminal to communicate with the base station corresponding to the communication demand.

[0031] The above-mentioned carrier selection method, device, computer equipment and computer-readable storage medium analyze the predicted transmission rate of each available carrier from multiple time and space dimensions according to the communication time corresponding to the communication demand, the current position of the terminal and the carrier information of each available carrier at the current position, with the purpose of selecting the best one from multiple available carriers according to the predicted transmission rate to ensure the efficiency and quality of communication. This process is dynamic and can be performed every time a communication demand is generated to ensure that the best communication path can be selected under various network conditions, thereby ensuring the accuracy of carrier selection. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0033] Figure 1 A schematic diagram of a flow chart of a carrier selection method in an embodiment;

[0034] Figure 2 A schematic diagram of a flow chart of the steps of updating a prediction model in one embodiment;

[0035] Figure 3 A schematic diagram of a flow chart of a step of determining a predicted transmission rate corresponding to each available carrier in an embodiment;

[0036] Figure 4 is a structural block diagram of a carrier selection device in one embodiment;

[0037] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0039] In an exemplary embodiment, Figure 1 As shown, a carrier selection method is provided. Taking the method applied to a terminal as an example, the terminal communicates with a base station. The method includes S101 and S102, wherein:

[0040] S101, when there is a communication demand, determining a predicted transmission rate corresponding to each available carrier according to the communication time corresponding to the communication demand, the current position of the terminal and the carrier information of each available carrier at the current position.

[0041] Among them, the communication demand can be triggered by the user or paged by the base station. When the user wants to communicate (such as making a call, sending text messages, browsing the web, etc.), the user will perform the corresponding operations on the terminal (such as a smartphone). The terminal will respond to these operations and initiate a communication request to the network. This process involves selecting a suitable carrier to establish a connection. In addition, in a mobile communication network, the base station may need to actively communicate with the terminal. For example, when there is an incoming call, the base station will page the corresponding terminal. In this case, the terminal needs to be prepared to receive signals from the base station and may need to adjust its communication parameters, including carrier selection, according to the instructions of the base station.

[0042] Among them, the communication moment refers to the communication moment corresponding to the communication demand, specifically refers to the specific time point or time period when information transmission is required during the communication process; the communication moment can be real-time, such as a telephone conference or video call, or delayed, such as an email or text message. In real-time communication, the communication moment needs to accurately match the available time of both parties; while in delayed communication, it is necessary to determine the arrival of communication data within a reasonable time. The "current moment" is the time when the communication demand is generated, that is, at this point in time, a communication demand is triggered or generated, which marks the beginning of the communication process and affects a series of operations such as subsequent resource allocation, signal processing and data transmission. Therefore, in this embodiment, the "communication moment, the current position of the terminal and the carrier information of each available carrier at the current position" corresponding to the "predicted transmission rate corresponding to each available carrier" is predicted at the "current moment".

[0043] It is understandable that network usage varies greatly at different time periods. For example, the network may be more congested during peak hours of the day, resulting in a decrease in transmission rate. Therefore, determining the "communication moment" can help predict network load conditions. In addition, weather, traffic in buildings, and other environmental factors can change over time, all of which can affect the propagation and reception quality of wireless signals. The quality of wireless signals fluctuates over time. Knowing the signal conditions at the "communication moment" can more accurately predict the transmission rate of an upcoming communication session. Accordingly, in mobile communication networks, resources (such as frequencies, time slots, etc.) are usually allocated dynamically. Knowing the "communication moment" can further determine which resources are available and how they can affect the transmission rate.

[0044] Among them, the geographical location of the terminal has a direct impact on signal quality and transmission rate. That is, buildings, terrain and other environmental factors can hinder or enhance the propagation of wireless signals. Therefore, knowing the exact location of the terminal can help more accurately predict the performance of a specific carrier at that location. The relationship between the geographical location of the terminal and the transmission rate of the carrier is indirect. The geographical location indirectly affects the data transmission rate by affecting factors such as the signal propagation environment, network infrastructure and topology, transmission distance and power limitations.

[0045] Specifically, the information of all carriers available at the current location may include frequency, bandwidth, signal strength (Received Signal Strength Indication, RSSI), signal to noise ratio (Signal to Interference plus Noise Ratio, SNR) and bit error rate, etc., which are key factors affecting the transmission rate.

[0046] Optionally, in combination with the above factors (communication time, terminal location and carrier information), a setting algorithm or prediction model can be used to predict the transmission rate of each available carrier. The transmission rate of the available carrier may include an uplink transmission rate, a downlink transmission rate and a comprehensive transmission rate. The comprehensive transmission rate is obtained by weighted calculation based on the uplink insertion transmission rate, the uplink weighted value corresponding to the uplink transmission rate, the downlink transmission rate and the downlink weighted value corresponding to the downlink transmission rate; wherein the ratio between the uplink weighted value and the downlink weighted value is determined based on the ratio between the uplink transmission data volume and the downlink transmission data volume. These setting algorithms can be calculated based on historical data, real-time measurement values, network planning information and other relevant parameters; the prediction model can be obtained through complex calculations or based on predictions of machine learning prediction models, which are trained to learn how to estimate the transmission rate based on input parameters.

[0047] S102: Select a target carrier from each available carrier according to the predicted transmission rate corresponding to each available carrier.

[0048] The target carrier is used for communication between the terminal and the base station corresponding to the communication demand.

[0049] Specifically, in a network environment where multiple carriers and multiple standards coexist, the terminal may have different transmission rates at each available carrier, standard, time, and location. This embodiment selects a target carrier from each available carrier by comparing the predicted transmission rates of all available carriers.

[0050] In one possible implementation, based on the comparison results, the carrier with the highest predicted transmission rate is selected as the "target carrier", so that the terminal can select the best target carrier for the user from the available carriers. If the predicted rates of multiple carriers are the same or very close, other additional factors such as carrier stability, historical performance, network load balancing requirements, etc. may be considered to make the final selection. The main criterion for selecting the target carrier is usually the transmission rate. Ideally, the carrier with the highest predicted transmission rate is preferred, as this usually means faster data transmission and better communication efficiency.

[0051] In another possible implementation, when selecting a target carrier, in addition to the predicted transmission rate, other factors may be considered, such as carrier stability, coverage, delay, packet loss rate, etc. These factors may have a significant impact on communication quality. For example, different weights are assigned to different factors (such as predicted transmission rate, stability, coverage, etc.), and then each available carrier is scored. Finally, the carrier with the highest score is selected as the target carrier.

[0052] In addition, the hardware and software capabilities of the terminal may limit the use of certain carriers. At the same time, users may prefer to use specific carriers or formats. These factors can be considered when selecting the target carrier. Furthermore, historical communication data can be used to predict the performance of different carriers at different times and locations through machine learning algorithms, and the target carrier can be selected based on these prediction results.

[0053] Once the target carrier is selected, the terminal will configure its radio interface to establish communication with the base station on that carrier. This means that the terminal will tune to the frequency of the target carrier and prepare to send and receive data on that carrier. That is, after the target carrier is selected, the terminal will use that carrier to communicate with the base station corresponding to the communication needs. This includes all interactions with the base station, such as sending signals, receiving signals, and performing data transmission.

[0054] The above carrier selection method analyzes the predicted transmission rate of each available carrier from multiple time and space dimensions according to the communication time corresponding to the communication demand, the current location of the terminal and the carrier information of the available carrier at the current location, with the purpose of selecting the best one from multiple available carriers according to the predicted transmission rate to ensure the efficiency and quality of communication. This process is dynamic and can be performed every time a communication demand is generated to ensure that the best communication path can be selected under various network conditions, thereby ensuring the accuracy of carrier selection.

[0055] In an exemplary embodiment, the predicted transmission rate corresponding to each available carrier is determined according to the communication time corresponding to the communication demand, the current position of the terminal and the carrier information of the available carriers at the current position, including: based on a prediction model, the predicted transmission rate corresponding to each available carrier is determined according to the communication time corresponding to the communication demand, the current position of the terminal and the carrier information of each available carrier at the current position.

[0056] Specifically, the prediction model takes as input the specific time point when the communication demand is generated (i.e., the communication moment), which can affect the network load and signal quality. The prediction model also receives as input the geographical location information of the terminal (i.e., the current location of the terminal), which helps to understand the signal coverage and possible interference sources. The carrier information of the available carrier as input can specifically include frequency, bandwidth, and signal strength, which are key factors in determining the transmission rate.

[0057] Optionally, the prediction model can be a machine learning prediction model trained based on historical data and real-time data, such as a self-organizing incremental neural network (SOINN), a decision tree, or a random forest. The prediction model performs complex calculations and reasoning based on the input data to find the potential relationship between the input parameters and the transmission rate. Through this relationship, the prediction model can predict the transmission rate that can be achieved by each available carrier at a given communication time, current location, and carrier information.

[0058] Taking the self-organizing incremental learning neural network SOINN as an example, SOINN is a two-layer competitive neural network. In the prediction of carrier transmission rate, the network parameters and structure of SOINN can be adjusted according to the specific data characteristics and prediction targets. The incremental learning characteristics of SOINN enable the model to continuously learn new knowledge from new data samples and save previously learned experience. This helps the model adapt to the changing network environment and improve the accuracy and robustness of the prediction.

[0059] Specifically, the construction process of the self-organizing incremental learning neural network SOINN model is as follows:

[0060] 1. Model initialization:

[0061] 1) Determine the network structure: SOINN is a two-layer competitive neural network (excluding the input layer). The first layer is responsible for receiving raw data input and generating prototype neurons, while the second layer performs further processing based on the results of the first layer to stabilize the learning results.

[0062] 2) Initialization parameters: Set the basic parameters of the network, such as the number of nodes (which may be empty or contain a small number of randomly generated nodes at the beginning), the similarity threshold (used to determine whether a new data point belongs to a new category), and the learning rate.

[0063] 2. Online Learning:

[0064] 1) Data input: The communication time, current location and available carrier information of the terminal at the current location are taken as input data and input into the SOINN model after preprocessing.

[0065] 2) First layer processing: The first layer network receives input data in an online manner and adaptively generates prototype neurons to represent the input data. These prototype neurons can be regarded as clustering centers of the input data.

[0066] 3) Second layer processing: The second layer of the network estimates the inter-class distance and intra-class distance of the original data based on the results of the first layer, and uses this as a parameter to further process the neurons generated by the first layer to stabilize the learning results.

[0067] 3. Node insertion:

[0068] 1) Intra-class node insertion: When the similarity between the input data and the existing nodes is high, SOINN will consider inserting new nodes between the existing nodes to reduce the quantization error and more accurately approximate the distribution of the original data. The specific insertion timing and location depends on the degree of reduction of the quantization error and the setting of the similarity threshold.

[0069] 2) Inter-class node insertion: When the similarity between the input data and the existing nodes is low, that is, the difference is large, SOINN will generate a new node at the position of the input data to represent the possible new category. This is achieved by setting a similarity threshold for each neuron. When the similarity between the input data and a neuron is lower than the threshold, it is considered that the input data may belong to a new category.

[0070] 4. Model Optimization

[0071] 1) Parameter adjustment: During the learning process, SOINN automatically adjusts parameters such as node similarity threshold and learning rate according to changes in input data to adapt to the changing input pattern.

[0072] 2) Topology update: As new nodes are inserted and old nodes are adjusted, the topology of SOINN is continuously updated to reflect the distribution of the original data.

[0073] 5. Model training: Use historical data to train SOINN so that it can learn the mapping relationship between input data and transmission rate.

[0074] Then, using the trained prediction model, for new input data (i.e., new communication time, current location, and available carrier information), the trained SOINN model will output the predicted transmission rate of the corresponding available carrier at the communication time. That is, the prediction model will eventually output a predicted transmission rate value for each available carrier. These predicted values ​​are based on the current network conditions, environmental factors, and historical data, and can serve as an important basis for carrier selection.

[0075] In order to maintain the accuracy of the prediction model, it is necessary to regularly use new data for training and optimization. This ensures that the prediction model can adapt to the changing network environment and provide more accurate prediction results. Figure 2 As shown, the method also includes:

[0076] S201, during the communication with the base station via the target carrier, monitoring whether the communication connection times out.

[0077] Specifically, in the process of communicating with the base station through the target carrier, the actual data transmission rate and the actual data transmission volume are recorded, and an inactivity timer can also be used to continuously monitor the status of the communication connection between the terminal and the base station. If the communication connection is not successfully established within the specified time or there is a long period of stagnation during the data transmission process, it will be determined that the communication connection has timed out.

[0078] In this embodiment, the actual transmission records (including the above-mentioned actual data transmission rate and actual data transmission volume) within the set historical period before the "current moment" are used as training data for the above-mentioned prediction model, and the prediction model is continuously trained; wherein, the difference between the actual data transmission rate in the actual transmission record and the predicted transmission rate is less than the set error value (that is, correct data within the set error range).

[0079] S202: If yes, update the prediction model.

[0080] It is understandable that if a communication connection timeout is detected, this may mean that the current communication conditions deviate from the previous prediction results of the prediction model. In order to improve the accuracy of future predictions, the prediction model is updated. The specific circumstances that caused the connection timeout are collected, including data such as the communication time, terminal location, carrier information, and network environment at that time. The newly collected data will be added to the training set of the prediction model for retraining or fine-tuning the prediction model. This allows the prediction model to better adapt to the current network environment and improve the accuracy of predictions for future communication conditions. If the connection has not timed out, communication with the base station continues through the target carrier.

[0081] S203: Based on the updated prediction model, return to the operation of determining the predicted transmission rate corresponding to each available carrier.

[0082] Specifically, after updating the prediction model, the operation of determining the predicted transmission rate corresponding to each available carrier is returned, that is, based on the updated prediction model, the predicted transmission rate corresponding to each available carrier is determined according to the communication time corresponding to the communication demand, the current position of the terminal, and the carrier information of each available carrier at the current position. This operation will be performed based on the updated prediction model to more accurately reflect the current communication environment and conditions. Using the new prediction model, combined with the current communication demand, time, terminal position and carrier information, the predicted transmission rate of each available carrier is recalculated. Based on the new prediction results, the carrier that best suits the current communication demand is selected as the new target carrier.

[0083] In this way, it is possible to dynamically adapt to changes in the network environment and continuously optimize communication performance. This feedback mechanism enables the prediction model to continuously learn and evolve, thereby better serving the carrier selection and transmission rate prediction of communication.

[0084] Furthermore, corresponding to the output result of the prediction model, the communication demand includes an uplink data transmission demand or a downlink data transmission demand, or a comprehensive data transmission demand; specifically, the uplink data transmission demand may refer to the uplink data transmission rate reaching the set uplink rate threshold or taking the uplink data transmission demand as the highest priority; the downlink data transmission demand may refer to the downlink data transmission rate reaching the set downlink rate threshold or taking the downlink data transmission demand as the highest priority; the comprehensive data transmission demand may refer to the comprehensive data transmission rate reaching the set comprehensive rate threshold or taking the comprehensive data transmission demand as the highest priority. According to the different communication needs of the users, the corresponding target carrier is matched. The carrier information of each available carrier includes the signal to interference plus noise ratio SINR and the reference signal received power (RSRP).

[0085] Among them, SINR is a key indicator to measure signal quality, which represents the ratio between useful signal and interference signal and background noise. A high SINR means better signal quality and less interference and noise, which usually leads to higher data transmission rate and lower bit error rate. The calculation of SINR usually involves the measurement of received signal power, interference power and noise power.

[0086] Among them, the reference signal received power (RSRP) is the power measurement of the reference signal received by the terminal from the base station. It provides information about signal strength or coverage, which helps to evaluate the quality of the communication link between the terminal and the base station. A higher RSRP value generally means better signal coverage and higher potential transmission rate.

[0087] When evaluating the predicted transmission rate of each available carrier, carrier information such as SINR and RSRP is taken into account. This information can be used as input parameters and incorporated into the prediction model to more accurately estimate the best carrier selection under given communication requirements. In this way, the carrier that best suits the current communication conditions can be dynamically selected to optimize the performance of uplink or downlink data transmission.

[0088] In this embodiment, by using this prediction model-based method, the transmission rate of each available carrier can be predicted more accurately, thereby providing strong support for subsequent carrier selection and communication optimization. This method is particularly suitable for dynamically changing wireless communication environments and helps to improve communication efficiency and user experience.

[0089] In an exemplary embodiment, Figure 3 As shown, according to the communication time corresponding to the communication demand, the current position of the terminal and the carrier information of the available carrier at the current position, the predicted transmission rate corresponding to each available carrier is determined, including:

[0090] S301, determining environmental features at the current location according to the current location of the terminal.

[0091] Specifically, it is achieved through the GPS module or other positioning technology configured in the terminal. The current location of the terminal is matched with a pre-established environmental database. This database contains environmental feature information of different geographical locations. By querying the database, the environmental features corresponding to the current location of the terminal can be found. According to the database query results, the environmental features at the current location of the terminal are determined. For example, if the terminal is located in a high-rise building dense area in the city center, then the environmental feature is "high-rise building dense area".

[0092] S302: Determine the congestion level corresponding to the communication time according to the communication time corresponding to the communication demand.

[0093] Specifically, query the historical congestion data of the communication network, which usually records the network congestion status in different time periods. Match the communication time with the historical congestion data to determine the network congestion status at that time. According to the degree of congestion, the congestion level is divided into low, medium, and high levels.

[0094] For example, network congestion may be affected by a variety of factors, such as large-scale events, holidays, etc. Therefore, when judging the congestion level, it is necessary to consider the potential impact of these factors on network congestion. If there are major changes in the communication network (such as adding new base stations, expanding capacity, etc.), it may be necessary to re-evaluate and update the historical congestion data to ensure the accuracy of the congestion level judgment.

[0095] S303: Determine a potential transmission rate of each available carrier according to carrier information of the available carriers at the current location.

[0096] Specifically, carrier information may include signal strength (RSSI), signal-to-noise ratio (SNR), and bandwidth information. Normalize signal quality indicators (such as RSSI or SNR) to between 0 and 1. Based on historical data or experience, establish a model (such as a bandwidth utilization model) to estimate bandwidth utilization under different signal qualities. This model can be linear, nonlinear, or based on a lookup table. Input the normalized signal quality value into the bandwidth utilization model to obtain the corresponding bandwidth utilization.

[0097] Specifically, the calculation process of the linear bandwidth utilization model is: potential transmission rate = bandwidth * bandwidth utilization.

[0098] For example, the use of the bandwidth utilization model means that the relationship between the normalized signal quality and the bandwidth utilization is linear, that is, bandwidth utilization = normalized signal quality.

[0099] The input to the model is:

[0100] Carrier 1: Signal strength RSSI = -70dBm, bandwidth = 10Mbps;

[0101] Carrier 2: Signal strength RSSI = -80dBm, bandwidth = 10Mbps;

[0102] The processing process of this model is as follows: Assume that the minimum value of RSSI is -90dBm and the maximum value is -50dBm.

[0103] Normalized signal quality:

[0104] Carrier 1: (-70-(-90)) / (-50-(-90))=0.5;

[0105] Carrier 2: (-80-(-90)) / (-50-(-90))=0.25;

[0106] The potential transmission rate calculated by the model is:

[0107] Carrier 1: 10Mbps*0.5=5Mbps;

[0108] Carrier 2: 10Mbps*0.25=2.5Mbps.

[0109] S304, determining a predicted transmission rate corresponding to each available carrier according to the environmental characteristics, the congestion level corresponding to the communication time, and the potential transmission rate of each available carrier.

[0110] Optionally, environmental characteristics (such as city center, suburbs, etc.) are represented by env; the congestion level corresponding to the communication moment is represented by congestion_level (for example, the congestion_level values ​​corresponding to low, medium, and high are 1, 2, and 3, respectively); the potential transmission rate of each available carrier is represented by the array potential_rates.

[0111] Specifically, create an array predicted_rates of the same length as potential_rates to store the predicted transmission rate. According to the environmental feature env, determine an environmental factor env_factor.

[0112] For example, if env is a city center, env_factor may be 0.8; if it is a suburb, it may be 1.0; if it is a high-rise area, it may be 0.6. According to the congestion level congestion_level, a congestion factor congestion_factor is determined.

[0113] For example, if congestion_level is 1 (low), congestion_factor might be 0.1; if it is 2 (medium), it might be 0.3; if it is 3 (high), it might be 0.5. For each potential transmission rate in potential_rates, calculate the corresponding predicted transmission rate and store it in predicted_rates.

[0114] The calculation formula for the predicted transmission rate is:

[0115] predicted_rate = rate * env_factor * (1 - congestion_factor).

[0116] Returns the array predicted_rates, which contains the predicted transmission rates corresponding to each available carrier.

[0117] Exemplary:

[0118] Set the input as follows:

[0119] Environmental features: city center (env = "city_center");

[0120] Congestion level: medium (congestion_level = 2);

[0121] Potential transmission rates of each available carrier: [10, 20, 30] Mbps (potential_rates = [10, 20, 30]);

[0122] The algorithm execution process is: initialize predicted_rates = []; determine env_factor = 0.8 based on environmental characteristics; determine congestion_factor = 0.3 based on congestion level.

[0123] Calculate the predicted transfer rate:

[0124] For the first carrier: predicted_rate = 10*0.8*(1-0.3) = 5.6Mbps;

[0125] For the second carrier: predicted_rate = 20*0.8*(1-0.3) = 11.2Mbps;

[0126] For the third carrier: predicted_rate = 30*0.8*(1-0.3) = 16.8Mbps.

[0127] The calculation result is stored in predicted_rates and returned: [5.6, 11.2, 16.8] Mbps.

[0128] In an exemplary embodiment, the above-mentioned carrier selection method includes: in the case of communication demand, based on the prediction model, according to the communication time corresponding to the communication demand, the current position of the terminal and the carrier information of each available carrier at the current position, determining the predicted transmission rate corresponding to each available carrier; according to the predicted transmission rate corresponding to each available carrier, selecting a target carrier from each available carrier; in the process of communicating with the base station through the target carrier, monitoring whether the communication connection times out; if so, updating the prediction model; based on the updated prediction model, according to the communication time corresponding to the communication demand, the current position of the terminal and the carrier information of each available carrier at the current position, determining the predicted transmission rate corresponding to each available carrier.

[0129] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0130] Based on the same inventive concept, the embodiment of the present application also provides a carrier selection device for implementing the carrier selection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more carrier selection device embodiments provided below can refer to the limitations on the carrier selection method above, and will not be repeated here.

[0131] In an exemplary embodiment, Figure 4 As shown, a carrier selection device is provided, which is configured in a terminal and includes: a communication detection module 11 and a carrier selection module 12, wherein:

[0132] The communication detection module 11 is used to determine the predicted transmission rate corresponding to each available carrier according to the communication time corresponding to the communication demand, the current position of the terminal and the carrier information of each available carrier at the current position when there is a communication demand;

[0133] The carrier selection module 12 is used to select a target carrier from each available carrier according to the predicted transmission rate corresponding to each available carrier; wherein the target carrier is used for the terminal to communicate with the base station corresponding to the communication demand.

[0134] In one embodiment, the communication detection module 11 is further used for:

[0135] Based on the prediction model, the predicted transmission rate corresponding to each available carrier is determined according to the communication time corresponding to the communication demand, the current position of the terminal and the carrier information of each available carrier at the current position.

[0136] In one of the embodiments, the apparatus further comprises an updating module, which is used to: monitor whether the communication connection has timed out during the communication with the base station via the target carrier;

[0137] If so, the prediction model is updated;

[0138] Based on the updated prediction model, the operation of determining the predicted transmission rate corresponding to each available carrier is returned.

[0139] In one embodiment, the carrier selection module 12 is used to: select an available carrier with the highest predicted transmission rate among all available carriers as a target carrier.

[0140] In one embodiment, the communication demand includes an uplink data transmission demand or a downlink data transmission demand.

[0141] In one embodiment, the carrier information of each available carrier includes a signal to interference plus noise ratio SINR and a reference signal received power RSRP.

[0142] Each module in the above-mentioned carrier selection device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.

[0143] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 5 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a carrier selection method is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0144] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0145] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0146] In the case of communication demand, determining a predicted transmission rate corresponding to each available carrier according to the communication time corresponding to the communication demand, the current position of the terminal and the carrier information of each available carrier at the current position;

[0147] A target carrier is selected from the available carriers according to the predicted transmission rate corresponding to each available carrier; wherein the target carrier is used for the terminal to communicate with the base station corresponding to the communication demand.

[0148] In one embodiment, when the processor executes the computer program, the following steps are also implemented: based on the prediction model, the predicted transmission rate corresponding to each available carrier is determined according to the communication time corresponding to the communication demand, the current position of the terminal and the carrier information of each available carrier at the current position.

[0149] In one embodiment, when the processor executes the computer program, the following steps are also implemented: in the process of communicating with the base station through the target carrier, monitoring whether the communication connection times out; if so, updating the prediction model; based on the updated prediction model, returning to execute the operation of determining the predicted transmission rate corresponding to each available carrier.

[0150] In one embodiment, when the processor executes the computer program, the following steps are further implemented: using the available carrier with the highest predicted transmission rate among the available carriers as the target carrier.

[0151] In one embodiment, the communication demand includes an uplink data transmission demand or a downlink data transmission demand.

[0152] In one embodiment, the carrier information of each available carrier includes a signal to interference plus noise ratio SINR and a reference signal received power RSRP.

[0153] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0154] In the case of communication demand, determining a predicted transmission rate corresponding to each available carrier according to the communication time corresponding to the communication demand, the current position of the terminal and the carrier information of each available carrier at the current position;

[0155] A target carrier is selected from the available carriers according to the predicted transmission rate corresponding to each available carrier; wherein the target carrier is used for the terminal to communicate with the base station corresponding to the communication demand.

[0156] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: based on the prediction model, the predicted transmission rate corresponding to each available carrier is determined according to the communication time corresponding to the communication demand, the current position of the terminal and the carrier information of each available carrier at the current position.

[0157] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: during the communication with the base station through the target carrier, monitoring whether the communication connection times out; if so, updating the prediction model; based on the updated prediction model, returning to execute the operation of determining the predicted transmission rate corresponding to each available carrier.

[0158] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: using the available carrier with the highest predicted transmission rate among the available carriers as the target carrier.

[0159] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: the communication demand includes an uplink data transmission demand or a downlink data transmission demand.

[0160] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: the carrier information of each available carrier includes a signal to interference plus noise ratio SINR and a reference signal received power RSRP.

[0161] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0162] In the case of communication demand, determining a predicted transmission rate corresponding to each available carrier according to the communication time corresponding to the communication demand, the current position of the terminal and the carrier information of each available carrier at the current position;

[0163] A target carrier is selected from the available carriers according to the predicted transmission rate corresponding to each available carrier; wherein the target carrier is used for the terminal to communicate with the base station corresponding to the communication demand.

[0164] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: based on the prediction model, the predicted transmission rate corresponding to each available carrier is determined according to the communication time corresponding to the communication demand, the current position of the terminal and the carrier information of the available carrier at the current position.

[0165] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: during the communication with the base station through the target carrier, monitoring whether the communication connection times out; if so, updating the prediction model; based on the updated prediction model, returning to execute the operation of determining the predicted transmission rate corresponding to each available carrier.

[0166] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: using the available carrier with the highest predicted transmission rate among the available carriers as the target carrier.

[0167] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: the communication demand includes an uplink data transmission demand or a downlink data transmission demand.

[0168] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: the carrier information of each available carrier includes a signal to interference plus noise ratio SINR and a reference signal received power RSRP.

[0169] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0170] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0171] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0172] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A carrier selection method, characterized in that: Executed by a terminal, the method includes: In the case of communication demand, determining the predicted transmission rate corresponding to each available carrier according to the communication time corresponding to the communication demand, the current position of the terminal and the carrier information of each available carrier at the current position; wherein the communication time refers to the specific time point or time period when information transmission is required during the communication process, and the communication time is real-time or delayed; Selecting a target carrier from each available carrier according to the predicted transmission rate, stability and coverage corresponding to each available carrier; wherein the target carrier is used for the terminal to communicate with the base station corresponding to the communication demand; The step of determining the predicted transmission rate corresponding to each available carrier according to the communication time corresponding to the communication demand, the current position of the terminal, and the carrier information of each available carrier at the current position comprises: determining the predicted transmission rate corresponding to each available carrier according to the communication time corresponding to the communication demand, the current position of the terminal, and the carrier information of each available carrier at the current position based on a prediction model; Or, determining the predicted transmission rate corresponding to each available carrier according to the communication time corresponding to the communication demand, the current position of the terminal and the carrier information of each available carrier at the current position includes: determining the environmental characteristics at the current position according to the current position of the terminal; determining the congestion level corresponding to the communication time according to the communication time corresponding to the communication demand; determining the potential transmission rate of each available carrier according to the carrier information of the available carriers at the current position; determining the predicted transmission rate corresponding to each available carrier according to the environmental characteristics, the congestion level corresponding to the communication time and the potential transmission rate of each available carrier.

2. The method according to claim 1, characterized in that The method further comprises: During the communication with the base station via the target carrier, monitoring whether the communication connection times out; If yes, updating the prediction model; Based on the updated prediction model, the operation of determining the predicted transmission rate corresponding to each available carrier is returned.

3. The method according to claim 1, characterized in that The selecting a target carrier from each available carrier according to the predicted transmission rate corresponding to each available carrier includes: The available carrier with the highest predicted transmission rate among all available carriers is used as the target carrier.

4. The method according to claim 1, characterized in that: The communication requirement includes an uplink data transmission requirement or a downlink data transmission requirement.

5. The method according to any one of claims 1 to 4, characterized in that The carrier information of each available carrier includes a signal to interference plus noise ratio SINR and a reference signal received power RSRP.

6. A carrier selection device, characterized in that: Configured in a terminal, the device includes: A communication detection module, configured to determine, when there is a communication demand, a predicted transmission rate corresponding to each available carrier according to the communication time corresponding to the communication demand, the current position of the terminal and the carrier information of each available carrier at the current position; wherein the communication time refers to a specific time point or time period during which information transmission is required during the communication process, and the communication time is real-time or delayed; A carrier selection module, configured to select a target carrier from each available carrier according to the predicted transmission rate, stability and coverage corresponding to each available carrier; wherein the target carrier is used for the terminal to communicate with the base station corresponding to the communication demand; Wherein, determining the predicted transmission rate corresponding to each available carrier according to the communication time corresponding to the communication demand, the current position of the terminal, and the carrier information of each available carrier at the current position includes: determining the predicted transmission rate corresponding to each available carrier according to the communication time corresponding to the communication demand, the current position of the terminal, and the carrier information of each available carrier at the current position based on a prediction model; wherein the prediction model is a self-organizing incremental learning neural network model; Or, determining the predicted transmission rate corresponding to each available carrier according to the communication time corresponding to the communication demand, the current position of the terminal and the carrier information of each available carrier at the current position includes: determining the environmental characteristics at the current position according to the current position of the terminal; determining the congestion level corresponding to the communication time according to the communication time corresponding to the communication demand; determining the potential transmission rate of each available carrier according to the carrier information of the available carriers at the current position; determining the predicted transmission rate corresponding to each available carrier according to the environmental characteristics, the congestion level corresponding to the communication time and the potential transmission rate of each available carrier.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images