Service network device determination method, control device and storage medium

Abstract

The invention relates to a service network device determination method, a control device and a storage medium. The method comprises the following steps: predicting a key index of a target moment after a current moment through an index prediction AI model according to a key index of the current moment and a key index of a historical moment, the key indexes of the current moment and the historical moment are obtained by measuring downlink reference information of each alternative network device in an alternative network device set by the terminal; and determining a first service network equipment set of the terminal from the alternative network equipment set based on the key index of the target moment.

Description

[0001] This application incorporates Chinese Patent Application No. 2024106337192, filed on May 21, 2024, entitled “Method for determining a service network device, control device and storage medium”, which is incorporated herein by reference in its entirety. Technical Field

[0002] This application relates to the field of communication technology, and in particular to a method for determining a service network device, a control device, and a storage medium. Background Technology

[0003] In collaborative communication scenarios, multiple network devices cooperate to serve a single terminal. The selection of these cooperating network devices significantly impacts the communication performance of the served terminal: when the terminal is stationary or moving at low speed, the choice of serving network device affects the terminal's data rate; while when the terminal is moving at high speed, the choice of serving network device relates to whether the terminal will encounter more serious problems such as communication interruption. Therefore, the selection of serving network devices when the terminal is moving at high speed is an important problem to be solved. Summary of the Invention

[0004] Therefore, it is necessary to provide a method for determining service network devices, a control device, and a storage medium to address the aforementioned technical problems.

[0005] In a first aspect, this application provides a method for determining a service network device, the method comprising:

[0006] Based on the key indicators at the current moment and the key indicators at historical moments, the key indicators at the target moment after the current moment are predicted by the indicator prediction AI model. The key indicators at the current moment and the key indicators at historical moments are obtained by the terminal measuring the downlink reference information of each candidate network device in the candidate network device set.

[0007] From the set of candidate network devices, the first set of serving network devices for the terminal is determined based on key indicators at the target time.

[0008] In one embodiment, the step of predicting key indicators for a target time after the current time using an indicator prediction AI model based on key indicators at the current time and key indicators at historical times includes:

[0009] The key indicators at the current moment, the key indicators at the historical moment, and the first time interval are input into the indicator prediction AI model;

[0010] Obtain the key indicators for the target time output by the indicator prediction AI model;

[0011] Wherein, the first time interval is the time interval between the first moment and the target moment, the first moment is the moment when the earliest downlink reference signal for measuring the key indicator is sent in the candidate network device set, the target moment is the moment when the first control device determines the first service network device set based on the measurement result, and the measurement result is obtained by measuring based on the downlink reference signal sent at the first moment.

[0012] In one embodiment, the first time interval is determined based on the following time:

[0013] The propagation time of the downlink reference signal sent by the alternative network device for measuring the key indicator;

[0014] The time at which the terminal measures the key indicators;

[0015] The time at which the terminal feeds back the key indicators to the first control device;

[0016] The first control device predicts the timing of the key indicator.

[0017] The first control device determines the timing of the first service network device set of the terminal based on the predicted key indicators.

[0018] In one embodiment, the first time interval is determined based on the following time:

[0019] The propagation time of the downlink reference signal sent by the alternative network device for measuring the key indicator;

[0020] The time at which the terminal measures the key indicators;

[0021] The terminal predicts the timing of the key indicators.

[0022] The time when the terminal feeds back the predicted key indicator to the first control device.

[0023] The first control device determines the timing of the first service network device set of the terminal based on the predicted key indicators.

[0024] In one embodiment, the first time interval corresponds to the case where the candidate network device belongs to the second service network device set, wherein the second service network design set is the original service network device set that provides services to the terminal.

[0025] In one embodiment, the first time interval also includes the time spent by the terminal establishing a connection with the service network device in the first service network device.

[0026] In one embodiment, the first time interval corresponds to the case where the candidate network device does not belong to the second set of serving network devices, wherein the second set of serving network devices is the original set of serving network devices that provide services to the terminal.

[0027] In one embodiment, the indicator prediction AI model is obtained by training an initial AI model based on a first training sample;

[0028] The first training sample includes: a first training dataset and a first label dataset; the first training dataset includes: key indicators at a third time step, and key indicators at at least one historical time step prior to the third time step; the first label dataset includes: key indicators at a fourth time step, wherein the fourth time step is equal to the third time step plus the first time interval.

[0029] In one embodiment, determining the set of serving network devices for the terminal from the set of candidate network devices based on key indicators at the target time includes:

[0030] The top M candidate network devices with the highest key indicators from the candidate network device set are selected as the service network device set for the terminal, where M is greater than or equal to 1.

[0031] In one embodiment, when the key indicator is a first-type indicator, a larger value of the key indicator corresponds to better system performance. The step of determining the first set of serving network devices for the terminal from the set of candidate network devices based on the key indicator at the target time includes:

[0032] The candidate network devices in the candidate network device set whose ratio of all key indicators is greater than a set threshold are determined as the first service network device set of the terminal.

[0033] The key indicator ratio is the ratio of the key indicator of the candidate network device to the maximum key indicator, where the maximum key indicator is the maximum value of the key indicators of all candidate network devices in the candidate network device set.

[0034] In one embodiment, when the key indicator is a second type of indicator, the smaller the value of the key indicator, the better the system performance. The step of determining the first set of serving network devices for the terminal from the set of candidate network devices based on the key indicator at the target time includes:

[0035] The first set of serving network devices for the terminal is determined by selecting the candidate network devices whose ratio of all key indicators is less than a set threshold from the candidate network device set.

[0036] The key indicator ratio is the ratio of the key indicator of the candidate network device to the minimum key indicator, where the minimum key indicator is the minimum value of the key indicators of all candidate network devices in the candidate network device set.

[0037] In one embodiment, the key metrics include at least one of the following:

[0038] SS-RSRP, SS-RSRQ, SS-SINR, CSI-RSRP, CSI-RSRQ, CSI-SINR, SS-CQI, SS-RSSI, CSI-CQI, CSI-RSSI.

[0039] In one embodiment, before determining the first set of serving network devices for the terminal from the set of candidate network devices based on key indicators at the target time, the method further includes:

[0040] Based on the terminal's location information at the current time and its location information at historical times, the location information at the target time is predicted using a location prediction AI model;

[0041] From the initial set of network devices, the first control device determines the set of candidate network devices based on the location information at the target time.

[0042] In one embodiment, the method predicts the location information of the target time using a location prediction AI model based on the location information of the terminal at the current time and the location information at historical times, including:

[0043] The current location information, the historical location information, and the second time interval are input into the location prediction AI model;

[0044] Obtain the location information at the target time output by the location prediction AI model;

[0045] The second time interval is the interval between the transmission of a downlink reference signal for positioning from the second control device and the target time.

[0046] In one embodiment, the second time interval is determined based on the following time:

[0047] The positioning time of the second control device;

[0048] The second control device predicts the time of the terminal's location information;

[0049] The second control device sends the predicted location information of the terminal to the first control device at the time when;

[0050] The first control device determines the time of the candidate network device set based on the predicted location information of the terminal;

[0051] The first control device notifies the alternative network device of the time to send downlink reference signals for measuring key indicators;

[0052] First time interval.

[0053] In one embodiment, before determining the first set of serving network devices for the terminal from the set of candidate network devices based on key indicators at the target time, the method further includes:

[0054] Determine the distance between the location information of each network device in the initial set of network devices and the location information of the terminal at the target time;

[0055] In the initial set of network devices, the network devices whose distance is less than a preset distance are selected as the candidate set of network devices.

[0056] In one embodiment, the preset distance is less than or equal to the minimum coverage radius of the network devices in the initial set of network devices.

[0057] In one embodiment, the location prediction AI model is obtained by training an initial AI model based on a second training sample;

[0058] The second training sample includes: a second training dataset and a second label dataset; the second training dataset includes: location information at the fifth time point, and location information at least one historical time point prior to the fifth time point; the label dataset includes: location information at the sixth time point, where the sixth time point is equal to the fifth time point plus the second time interval.

[0059] Secondly, this application also provides a control device, including a memory, a transceiver, and a processor:

[0060] Memory is used to store computer programs; transceiver is used to send and receive data under the control of the processor; processor is used to read the computer programs from memory and perform the following operations:

[0061] Based on the key indicators at the current moment and the key indicators at historical moments, the key indicators at the target moment after the current moment are predicted. The key indicators at the current moment and the key indicators at historical moments are obtained by the terminal measuring the downlink reference information of each candidate network device in the candidate network device set.

[0062] From the set of candidate network devices, the first set of serving network devices for the terminal is determined based on key indicators at the target time.

[0063] Thirdly, this application also provides a control device, which includes:

[0064] The prediction module is used to predict the key indicators of a target time after the current time based on the key indicators of the current time and the key indicators of the historical time. The key indicators of the current time and the historical time are obtained by the terminal measuring the downlink reference information of each candidate network device in the candidate network device set.

[0065] The determination module is used to determine the first set of serving network devices for the terminal from the set of candidate network devices based on key indicators at the target time.

[0066] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in the first aspect or any embodiment thereof.

[0067] Fifthly, this application also provides a computer program product comprising a computer program that, when executed by a processor, implements the method described in the first aspect or any embodiment thereof.

[0068] The aforementioned method for determining service network devices, control equipment, storage media, and computer program products can predict key indicators for a target time after the current time based on key indicators at the current and historical times using an indicator prediction AI model. From a set of candidate network devices, the first set of service network devices for the terminal is determined based on the key indicators for the target time. The key indicators at the current and historical times are obtained by the terminal measuring downlink reference information of each candidate network device in the candidate set. This scheme considers the impact of terminal mobility on network device selection and avoids the influence of terminal mobility on network device selection by predicting key indicators, making the selection of network devices more accurate even when the terminal is mobile. Attached Figure Description

[0069] Figure 1 Flowchart of a method for determining a service network device Figure 1 ;

[0070] Figure 2 Flowchart of a method for determining a service network device Figure 2 ;

[0071] Figure 3 A schematic diagram of the structure of a control device provided in one embodiment;

[0072] Figure 4 This is a structural block diagram of a control device. Detailed Implementation

[0073] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0074] In this embodiment of the invention, the term "and / or" describes the relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. The character " / " generally indicates that the preceding and following associated objects have an "or" relationship.

[0075] One method for selecting serving network devices is for the User Equipment (UE) to measure the reference signal received power of downlink reference signals (e.g., Synchronization Block Reference Signal (PBCH-Reference Signal, SSB-RS) and Channel State Information Reference Signal (CSI-RS) sent to the UE by N network devices in the set (N is greater than or equal to 2, i.e., the number of network devices is greater than or equal to 2). The system transmits the received RSRP (Receiving RSRP) to the control center (or centralized processing unit). The control center and each network device are connected via fronthaul and backhaul. The control center selects M network devices from N network devices as the UE's serving network devices. The selection can be achieved by: arranging the RSRPs of the N network devices to the UE in descending order and selecting the top M devices as the UE's serving network devices; or by determining the M network devices with the largest RSRP ratios to the RSRPs of all N network devices; or by selecting network devices with RSRP ratios greater than a set threshold as serving network devices.

[0076] In addition to selecting serving network equipment based on RSRP, serving network equipment can also be selected based on parameters such as Reference Signal Received Quality (RSRQ), Signal to Interference and Noise Ratio (SINR), Channel Quality Indicator (CQI), and Received Signal Strength Indicator (RSSI).

[0077] The selection of serving network equipment for high-speed mobile terminals is mainly for high-speed rail scenarios. For example, the 3GPP standard uses Single Frequency Network (SFN) technology for high-speed rail scenarios. In this technology, multiple network devices are connected to the same baseband unit (BBU) via optical fiber and share the same cell identity document (ID) to avoid frequent selection of serving network equipment and cell handover.

[0078] The above methods for selecting service network devices based on RSRP, RSRQ, etc. are only applicable when the terminal is stationary or moving at low speed. When the terminal is moving at high speed, it is no longer accurate to select service network devices based solely on the above indicators, because the above indicators have changed significantly since the selected network device started providing communication services.

[0079] The SFN technology mentioned above for high-speed rail scenarios is deployed along the railway tracks, which is equivalent to knowing the possible movement trajectory of the terminal. It is not suitable for situations where the terminal moves at high speed in urban areas.

[0080] In collaborative communication scenarios, multiple network devices cooperate to serve a single terminal (e.g., UE). These network devices can be base stations, transmission and reception points (TRPs), remote radio units (RRUs), etc. The selection of these cooperating network devices significantly impacts the communication performance of the served terminal: when the terminal is stationary or moving at low speed, the choice of serving network device affects the terminal's data rate; while when the terminal is moving at high speed, the choice of serving network device relates to whether the terminal will encounter serious problems such as communication interruption. Therefore, how to solve user-centric distributed multiple input multiple output (MIMO) communication is crucial. In the MIMO (Multi-Interface, Multi-Mobile) architecture, the selection of serving network equipment when terminals move at high speeds is an important problem to be solved.

[0081] In this application, user movement is predicted based on artificial intelligence (AI), and the service network devices are initially screened based on the predicted location information after movement. Key indicators used for network device selection are predicted based on AI between the terminal and the initially selected network devices. A second screening of the service network devices is then conducted based on these key indicators (e.g., ...). Figure 2 In the embodiment, steps 201 and 202 are the initial screening, and steps 203 and 204 are the secondary screening, to obtain the final set of service network devices. This application considers the impact of terminal mobility on network device selection and avoids the impact of terminal mobility on network device selection by using AI to predict terminal mobility trajectories and key indicators, making the selection of network devices more accurate in the case of terminal mobility.

[0082] In some embodiments, such as Figure 1 The diagram illustrates a method for determining a service network device. Figure 1 This method can be applied to a first control device and may include, but is not limited to, the following steps:

[0083] 101. Based on the key indicators at the current moment and the key indicators at historical moments, use the indicator prediction AI model to predict the key indicators for the target moment after the current moment.

[0084] The key metrics for the current moment are obtained by the terminal measuring the downlink reference information of each candidate network device in the candidate network device set at the current moment. The key metrics for historical moments are obtained by the terminal measuring the downlink reference information of each candidate network device in the candidate network device set at historical moments. Historical moments can refer to moments within a certain time interval preceding the current moment.

[0085] The key indicators mentioned above include at least one of the following:

[0086] SS-RSRP, SS-RSRQ, SS-SINR, CSI-RSRP, CSI-RSRQ, CSI-SINR, SS-CQI, SS-RSSI, CSI-CQI, CSI-RSSI.

[0087] Wherein, SS-RSRP represents the RSRP measured on the SSB-RS signal resource unit; SS-RSRQ represents the RSRQ measured on the SSB-RS signal resource unit; SS-SINR represents the SINR measured on the SSB-RS signal resource unit; CSI-RSRP represents the RSRP measured on the CSI-RS signal resource unit; CSI-RSRQ represents the RSRQ measured on the CSI-RS signal resource unit; CSI-SINR represents the SINR measured on the CSI-RS signal resource unit; SS-CQI represents the CQI measured on the SSB-RS signal resource unit; SS-RSSI represents the RSSI measured on the SSB-RS signal resource unit; CSI-CQI represents the CQI measured on the CSI-RS signal resource unit; and CSI-RSSI represents the RSSI measured on the CSI-RS signal resource unit.

[0088] The first control device mentioned above can be the control center mentioned above.

[0089] In the process of acquiring the above key indicators, the alternative network device can send downlink reference information (i.e. downlink reference signal) to the terminal. The corresponding terminal receives the downlink reference information and measures the above key indicators. Then, the measured key indicators are transmitted to the first control device through the alternative network device, or the measured key indicators are transmitted directly to the first control device.

[0090] In some embodiments, the above-mentioned prediction of key indicators for a target time after the current time based on key indicators at the current time and key indicators at historical times may include, but is not limited to: inputting the key indicators at the current time, the key indicators at historical times, and a first time interval into the indicator prediction AI model; and obtaining the key indicators for the target time output by the indicator prediction AI model. Here, the aforementioned historical time can refer to a time prior to the current time.

[0091] Wherein, the first time interval is the time interval between the first moment and the target moment, the first moment is the moment when the earliest downlink reference signal for key indicator measurement is sent in the candidate network device set, the target moment is the moment when the first control device determines the first service network device set based on the measurement result, and the measurement result is obtained by measuring based on the downlink reference signal sent in the first moment.

[0092] In some embodiments, if the candidate network devices in the candidate network device set have already undergone synchronization processing, then the first moment mentioned above is the same moment for each candidate network device in the candidate network device set; if the candidate network devices in the candidate network device set have not undergone synchronization processing, and the downlink reference signals sent by each candidate network device for measuring key indicators are slightly different, then the first moment is the moment when the earliest downlink reference signal for measuring key indicators is sent in the candidate network device set.

[0093] In some embodiments, the first set of serving network devices may include identification information of at least one serving network device determined based on key indicators at a target time. This identification information may be an index of at least one serving network device, used to distinguish and indicate each serving network device.

[0094] The aforementioned first moment can be the moment when each candidate network device in the set of candidate network devices begins to transmit downlink reference signals for measuring key indicators. In this application, the control center can control each candidate network device to simultaneously begin transmitting downlink reference signals for measuring key indicators.

[0095] In some embodiments, the aforementioned set of candidate network devices can be an initial set of network devices, which may include identification information of multiple network devices. These multiple network devices may be multiple network devices within an initially selected target area, and the target area may be an area within a preset distance range from the terminal. In this embodiment, the preset distance range can be set according to actual needs, and this embodiment does not impose any limitations.

[0096] In some embodiments, the above-mentioned candidate network device set may also be a set of network devices selected from the initial network device set based on the predicted location information of the terminal at the target time, and the selected network devices are within a certain range of the distance from the location information of the terminal at the target time. The set includes: identification information of some network devices within a certain range of the distance from the location information of the terminal at the target time.

[0097] In some embodiments, the determination method of the first time interval differs depending on whether the first control device predicts key indicators or the terminal predicts key indicators. In this embodiment, the predicted key indicators refer to key indicators that predict the target time after the current time.

[0098] In some embodiments, the method for determining the first time interval differs depending on whether the candidate network device belongs to the second serving network device set. The second serving network device set is the original serving network device set that provides services to the terminal.

[0099] In some embodiments, corresponding to the case where the candidate network device belongs to the second set of serving network devices and the first control device predicts key indicators, the aforementioned first time interval is determined based on the following time:

[0100] The propagation time of the downlink reference signal sent by the alternative network device for measuring key indicators can be expressed as t1;

[0101] The time taken for the terminal to measure key indicators can be represented as t2;

[0102] The time it takes for the terminal to feed back key indicators to the first control device can be represented as t3;

[0103] The time it takes for the first control device to predict key indicators can be represented as t4.

[0104] The time for the first control device to determine the first set of service network devices for the terminal based on the predicted key indicators can be represented as t5.

[0105] In some embodiments, the first time interval can be expressed as ∆T1, where ∆T1 = t1 + t2 + t3 + t4 + t5.

[0106] Among them, the multiple times t1, t2, t3, t4, and t5 that determine the first time interval are time lengths.

[0107] In some embodiments, corresponding to the case where the candidate network device belongs to the second serving network device set and the terminal predicts key indicators, the aforementioned first time interval is determined based on the following time:

[0108] The propagation time t1 of the downlink reference signal sent by the alternative network device for measuring key indicators;

[0109] The time t2 for terminal measurement of key indicators;

[0110] The time frame for predicting key indicators at the terminal can be represented as t6;

[0111] The time it takes for the terminal to feed back the predicted key indicators to the first control device can be represented as t7;

[0112] The first control device determines the time t5 of the first service network device set of the terminal based on the predicted key indicators.

[0113] In some embodiments, the first time interval described above can be represented as ∆T1, where ∆T1 = t1 + t2 + t6 + t7 + t5.

[0114] Among them, the multiple times t1, t2, t6, t7, and t5 that determine the first time interval are time lengths.

[0115] If a candidate network device belongs to the second set of serving network devices, and the candidate network device is ultimately determined to be a serving network device in the first set of serving network devices of the terminal, then the candidate network device belongs to the intersection of the second set of serving network devices and the first set of serving network devices.

[0116] In some embodiments, corresponding to the case where the candidate network device does not belong to the second serving network device set and the first control device predicts key indicators, the aforementioned first time interval is determined based on the following time:

[0117] The propagation time t1 of the downlink reference signal sent by the alternative network device for measuring key indicators;

[0118] The time t2 for terminal measurement of key indicators;

[0119] The time t3 for the terminal to feed back key indicators to the first control device;

[0120] The first control device predicts the key indicators at time t3;

[0121] The first control device determines the time t5 of the first service network device set of the terminal based on the predicted key indicators.

[0122] The time taken for the terminal to establish a connection with the service network device in the first service network device can be represented as t8.

[0123] The second set of service network devices is the original set of service network devices that provide services to the terminal.

[0124] In some embodiments, the first time interval can be expressed as ∆T1, where ∆T1 = t1 + t2 + t3 + t4 + t5 + t8.

[0125] Among them, the multiple times t1, t2, t3, t4, t5, and t8 that determine the first time interval are time lengths.

[0126] In some embodiments, corresponding to the case where the candidate network device does not belong to the second serving network device set and the terminal predicts key indicators, the aforementioned first time interval is determined based on the following time:

[0127] The propagation time of the downlink reference signal sent by the alternative network equipment for measuring key indicators;

[0128] The timeframe for measuring key indicators at the terminal;

[0129] Timing of key indicators for terminal forecasting;

[0130] The time it takes for the terminal to feed back the predicted key indicators to the first control device;

[0131] The first control device determines the timing of the first service network device set of the terminal based on the predicted key indicators.

[0132] The time spent by the terminal establishing a connection with the service network device in the first service network device.

[0133] In some embodiments, the first time interval described above can be expressed as ∆T1, where ∆T1 = t1 + t2 + t6 + t7 + t5 + t8.

[0134] Among them, the multiple times t1, t2, t6, t7, t5, and t8 that determine the first time interval are time lengths.

[0135] In some embodiments, before using the indicator prediction AI model, it is necessary to train the indicator prediction AI model first. The indicator prediction AI model is obtained by training an initial AI model based on a first training sample.

[0136] This training process may include, but is not limited to:

[0137] The initial AI model is trained based on the first training sample until the model converges, thus obtaining the indicator prediction AI model.

[0138] The input data in the above training process includes: key indicators at the third time step and key indicators at least one historical time step prior to the third time step; the output data includes: key indicators for the predicted fourth time step.

[0139] The first training sample includes: a first training dataset and a first label dataset; the first training dataset includes: key indicators at the third time step and key indicators at least one historical time step before the third time step; the first label dataset includes: key indicators at the fourth time step, the time interval between the third time step and the fourth time step is equal to the first time interval, and the fourth time step is equal to the third time step plus the first time interval.

[0140] In this embodiment of the application, the key indicators at the third time point and the key indicators at the fourth time point must both be included in the first training sample.

[0141] For example, the initial AI model described above can be a neural network such as a Long Short-Term Memory (LSTM) network or a Gate Recurrent Unit (GRU).

[0142] 102. From the set of candidate network devices, determine the first set of network devices serving the terminal based on key indicators at the target time.

[0143] In some embodiments, the top M candidate network devices with the highest key indicators from the candidate network device set can be used as the first set of serving network devices for the terminal, where M is greater than or equal to 1. The higher the value of the key indicator, the better the system performance.

[0144] In some embodiments, when the key indicator is a first type of indicator, the larger the value of the key indicator, the better the system performance. In this case, the candidate network devices in the candidate network device set whose key indicator ratio is greater than a set threshold can be determined as the first service network device set of the terminal.

[0145] The key indicator ratio is the ratio of the key indicator of the candidate network device to the maximum key indicator, and the maximum key indicator is the maximum value of the key indicators of all candidate network devices in the candidate network device set.

[0146] For example, the first type of indicator mentioned above may include, but is not limited to, at least one of SS-RSRP, SS-RSRQ, SS-SINR, SS-CQI, CSI-RSRP, CSI-RSRQ, CSI-SINR, and CSI-CQI.

[0147] In some embodiments, when the key indicator is a second type of indicator, the smaller the value of the key indicator, the better the system performance. The first service network device set of the terminal can be determined by selecting candidate network devices whose key indicator ratios are less than a set threshold.

[0148] The key indicator ratio is the ratio of the key indicators of the candidate network devices to the minimum key indicator, where the minimum key indicator is the minimum value of the key indicators of all candidate network devices in the candidate network device set.

[0149] For example, the first type of indicator mentioned above may include, but is not limited to, at least one of SS-RSSI and CSI-RSSI. RSSI can be used to characterize the interference level when the network device is not transmitting a signal.

[0150] In some embodiments, candidate network devices whose ratios of all key metrics are less than a set threshold can be identified as the first set of serving network devices for the terminal. Lower values ​​for the key metrics correspond to better system performance.

[0151] The aforementioned method for determining service network devices can predict key indicators for a target time after the current time based on key indicators at the current moment and key indicators at historical moments. From the set of candidate network devices, the first set of service network devices for the terminal is determined based on the key indicators for the target time. Here, the key indicators are obtained by the terminal measuring the downlink reference information of each candidate network device in the candidate set. This scheme considers the impact of terminal mobility on network device selection and avoids the influence of terminal mobility on network device selection by predicting key indicators, making the selection of network devices more accurate even when the terminal is mobile.

[0152] In this embodiment of the application, the terminal can communicate by establishing a connection with a service network device in the first set of service network devices.

[0153] In some embodiments, such as Figure 2 The diagram illustrates a method for determining a service network device. Figure 2 This method can be applied to a first control device and may include, but is not limited to, the following steps:

[0154] 201. Based on the terminal's current location information and historical location information, predict the target location information using a location prediction AI model.

[0155] In some embodiments, when the location information of the terminal at the current time and the location information at the historical time are used to predict the location information at the target time by the location prediction AI model, the location information at the current time, the location information at the historical time, and the second time interval can be input into the location prediction AI model; the location information at the target time output by the location prediction AI model can be obtained; wherein, the second time interval is the interval between the downlink reference signal for positioning sent from the second control device and the target time.

[0156] In some embodiments, the second time interval is determined based on the following time:

[0157] The positioning time of the second control device can be expressed as t9;

[0158] The time it takes for the second control device to predict the terminal's location information can be represented as t10;

[0159] The time when the second control device sends the predicted terminal location information to the first control device can be represented as t11;

[0160] The time it takes for the first control device to determine the set of candidate network devices based on the predicted location information of the terminals can be represented as t12.

[0161] The time when the first control device notifies the alternative network device to send a downlink reference signal for measuring key indicators can be represented as t13.

[0162] The first time interval can be represented as ∆T1.

[0163] It should be noted that, in this embodiment, the second control device and the first control device can be the same control device or different control devices. The second control device is used to transmit downlink reference signals for positioning.

[0164] When the second control device and the first control device are the same control device, t11 can be 0. When the second control device and the first control device are not the same control device, t11 is the transmission time of the predicted terminal location information between the second control device and the first control device.

[0165] In some embodiments, the second time interval described above can be expressed as ∆T2, ∆T2 = t9 + t10 + t11 + t12 + t13 + ∆T1.

[0166] In some embodiments, before using the location prediction AI model, it is necessary to train the location prediction AI model first, which is obtained by training the initial AI model based on a second training sample.

[0167] The input data in the above training process includes: the position information at the fifth time point, and the position information at least one historical time point before the fifth time point; the output data in the above training process includes: the position information at the sixth time point.

[0168] The second training sample includes: a second training dataset and a second label dataset; the second training dataset includes: location information at the fifth time point and location information at least one historical time point before the fifth time point; the label dataset includes: location information at the sixth time point, the time interval between the fifth time point and the sixth time point is equal to the second time interval, and the sixth time point is equal to the fifth time point plus the second time interval.

[0169] In this embodiment of the application, the location information at the fifth time point and the location information at the sixth time point both need to be in the aforementioned second training sample.

[0170] For example, the initial AI model described above can be a neural network such as LSTM or GRU.

[0171] 202. From the initial set of network devices, the first control device determines the set of candidate network devices based on the location information at the target time.

[0172] In some embodiments, the distance between the location information of each network device in the initial network device set and the location information of the terminal at the target time can be determined first; then, network devices in the initial network device set whose distance is less than a preset distance can be determined as candidate network device sets.

[0173] In some embodiments, the preset distance is less than or equal to the minimum coverage radius of the network devices in the initial set of network devices.

[0174] For example, assuming the minimum coverage radius of the network devices in the initial set of network devices is R, network devices whose distance between the location information of the network devices in the initial set of network devices and the location information of the terminal at the target time is less than or equal to R are placed into the above candidate set of network devices, where R is greater than 0.

[0175] For example, the initial set of network devices can be a set of network devices within the target area. The target area can be divided into multiple sub-areas. The target sub-area where the location information of the terminal at the target time is located can be selected from these multiple sub-areas. Within the target sub-area, network devices whose distance between the location information of the network device and the location information of the terminal at the target time is less than or equal to R can be selected and placed into the above-mentioned set of candidate network devices.

[0176] The aforementioned target area can be an area within a preset radius of the terminal's location information at the target time. This preset radius can be set based on actual needs, and is not limited in this embodiment.

[0177] In the aforementioned sub-regions, the extent of each sub-region is greater than the minimum coverage of a single network device in the initial set of network devices.

[0178] 203. Based on the key indicators at the current moment and the key indicators at historical moments, use the indicator prediction AI model to predict the key indicators for the target moment after the current moment.

[0179] 204. From the set of candidate network devices, determine the first set of network devices serving the terminal based on the key indicators at the target time.

[0180] The descriptions of steps 203 and 204 above can be found in the descriptions of steps 101 and 102 above, and will not be repeated here.

[0181] The aforementioned method for determining service network devices can predict the target time's location information based on the terminal's current location information and historical location information using an indicator prediction AI model. Based on the predicted target time's location information, an initial set of network devices is selected to obtain a candidate set of network devices. Then, network devices are selected again from the candidate set based on predicted key indicators to finally determine the first set of service network devices. This avoids the impact of terminal movement on network device selection and makes the selection of network devices more accurate when the terminal is moving.

[0182] In this embodiment of the application, the network devices in the first set of service network devices can continue to provide communication services to the terminal or conduct random access procedures with the terminal.

[0183] In some embodiments, if a service network device in the first set of service network devices is directly connected and synchronized with the terminal, that is, it belongs to the intersection of the first set of service network devices and the second set of service network devices, then the selected service network device continues to provide communication services to the terminal.

[0184] In some embodiments, if the service network devices in the first set of service network devices are not in a connected and synchronized state, a random access procedure can be initiated with the terminal to enable the terminal to access the service network device.

[0185] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0186] Based on the same technical concept, this application also provides a control device. This control device can achieve the functions of the first control device in the foregoing embodiments.

[0187] For example, Figure 3 This is a schematic diagram of a control device provided in one embodiment. The control device includes: a memory 301, a transceiver 302, and a processor 303, wherein the memory 301, transceiver 302, and processor 303 are connected via a bus interface.

[0188] The memory 301 is used to store computer programs; the transceiver 302 is used to send and receive data under the control of the processor 303.

[0189] The processor 303 described above is used to read the computer program in the memory 301 and perform the following operations:

[0190] Based on the key indicators at the current moment and the key indicators at historical moments, the key indicators at the target moment after the current moment are predicted by the indicator prediction AI model. The key indicators at the current moment and the key indicators at historical moments are obtained by the terminal measuring the downlink reference information of each candidate network device in the candidate network device set.

[0191] From the set of candidate network devices, the first set of serving network devices for the terminal is determined based on key indicators at the target time.

[0192] In some embodiments, the processor 303 is specifically configured to read the computer program in the memory 301 and perform the following operations:

[0193] The step of predicting key indicators for a target time after the current time using an indicator prediction AI model based on key indicators at the current time and key indicators at historical times includes:

[0194] The key indicators at the current moment, the key indicators at the historical moment, and the first time interval are input into the indicator prediction AI model;

[0195] Obtain the key indicators for the target time output by the indicator prediction AI model;

[0196] Wherein, the first time interval is the time interval between the first moment and the target moment, the first moment is the moment when the earliest downlink reference signal for measuring the key indicator is sent in the candidate network device set, the target moment is the moment when the first control device determines the first service network device set based on the measurement result, and the measurement result is obtained by measuring based on the downlink reference signal sent at the first moment.

[0197] In some embodiments, the first time interval is determined based on the following time:

[0198] The propagation time of the downlink reference signal sent by the alternative network device for measuring the key indicator;

[0199] The time at which the terminal measures the key indicators;

[0200] The time at which the terminal feeds back the key indicators to the first control device;

[0201] The first control device predicts the timing of the key indicator.

[0202] The first control device determines the timing of the first service network device set of the terminal based on the predicted key indicators.

[0203] In some embodiments, the first time interval is determined based on the following time:

[0204] The propagation time of the downlink reference signal sent by the alternative network device for measuring the key indicator;

[0205] The time at which the terminal measures the key indicators;

[0206] The terminal predicts the timing of the key indicators.

[0207] The time when the terminal feeds back the predicted key indicator to the first control device.

[0208] The first control device determines the timing of the first service network device set of the terminal based on the predicted key indicators.

[0209] In some embodiments, the first time interval corresponds to the case where the candidate network device belongs to the second service network device set, wherein the second service network device set is the original service network device set that provides services to the terminal.

[0210] In some embodiments, the first time interval also includes the time spent by the terminal establishing a connection with a service network device in the first service network device.

[0211] In some embodiments, the first time interval corresponds to the case where the candidate network device does not belong to the second set of serving network devices, wherein the second set of serving network devices is the original set of serving network devices that provide services to the terminal.

[0212] In some embodiments, the indicator prediction AI model is obtained by training an initial AI model based on a first training sample;

[0213] The first training sample includes: a first training dataset and a first label dataset; the first training dataset includes: key indicators at a third time step, and key indicators at at least one historical time step prior to the third time step; the first label dataset includes: key indicators at a fourth time step, wherein the fourth time step is equal to the third time step plus the first time interval.

[0214] In some embodiments, the processor 303 is specifically configured to read the computer program in the memory 301 and perform the following operations:

[0215] The step of determining the first set of serving network devices for the terminal from the set of candidate network devices based on key indicators at the target time includes:

[0216] The top M candidate network devices with the highest key indicators from the candidate network device set are selected as the first service network device set for the terminal, where M is greater than or equal to 1.

[0217] In some embodiments, the processor 303 is specifically configured to read the computer program in the memory 301 and perform the following operations:

[0218] When the key indicator is a first-type indicator, the larger the value of the key indicator, the better the system performance. The step of determining the first set of serving network devices for the terminal from the set of candidate network devices based on the key indicator at the target time includes:

[0219] The candidate network devices in the candidate network device set whose ratio of all key indicators is greater than a set threshold are determined as the first service network device set of the terminal.

[0220] The key indicator ratio is the ratio of the key indicator of the candidate network device to the maximum key indicator, where the maximum key indicator is the maximum value of the key indicators of all candidate network devices in the candidate network device set.

[0221] For example, the first type of indicator mentioned above may include, but is not limited to, at least one of SS-RSRP, SS-RSRQ, SS-SINR, SS-CQI, CSI-RSRP, CSI-RSRQ, CSI-SINR, and CSI-CQI.

[0222] In some embodiments, the processor 303 is specifically configured to read the computer program in the memory 301 and perform the following operations:

[0223] When the key indicator is a second type of indicator, the smaller the value of the key indicator, the better the system performance. The step of determining the first set of serving network devices for the terminal from the set of candidate network devices based on the key indicator at the target time includes:

[0224] The first set of serving network devices for the terminal is determined by selecting the candidate network devices whose ratio of all key indicators is less than a set threshold from the candidate network device set.

[0225] The key indicator ratio is the ratio of the key indicator of the candidate network device to the minimum key indicator, where the minimum key indicator is the minimum value of the key indicators of all candidate network devices in the candidate network device set.

[0226] For example, the first type of indicator mentioned above may include, but is not limited to, at least one of SS-RSSI and CSI-RSSI. RSSI can be used to characterize the interference level when the network device is not transmitting a signal.

[0227] In some embodiments, the key metrics include at least one of the following:

[0228] SS-RSRP, SS-RSRQ, SS-SINR, CSI-RSRP, CSI-RSRQ, CSI-SINR, SS-CQI, SS-RSSI, CSI-CQI, CSI-RSSI.

[0229] In some embodiments, the processor 303 is further configured to read the computer program in the memory 301 and perform the following operations:

[0230] Before determining the first set of serving network devices for the terminal from the set of candidate network devices based on the key indicators of the target time, the location information of the terminal at the target time is predicted by a location prediction AI model based on the location information of the terminal at the current time and the location information at the historical time.

[0231] The first control device determines the set of candidate network devices from the initial set of network devices based on the location information at the target time.

[0232] In some embodiments, the processor 303 is specifically configured to read the computer program in the memory 301 and perform the following operations:

[0233] The step of predicting the location information of the target time using a location prediction AI model based on the terminal's location information at the current time and its location information at historical times includes:

[0234] The current location information, the historical location information, and the second time interval are input into the location prediction AI model;

[0235] Obtain the location information at the target time output by the location prediction AI model;

[0236] The second time interval is the interval between the transmission of a downlink reference signal for positioning from the second control device and the target time.

[0237] In some embodiments, the second time interval is determined based on the following time:

[0238] The positioning time of the second control device;

[0239] The second control device predicts the time of the terminal's location information;

[0240] The second control device sends the predicted location information of the terminal to the first control device at the time when;

[0241] The first control device determines the time of the candidate network device set based on the predicted location information of the terminal;

[0242] The first control device notifies the alternative network device of the time to send downlink reference signals for measuring key indicators;

[0243] First time interval.

[0244] In some embodiments, the processor 303 is specifically configured to read the computer program in the memory 301 and perform the following operations:

[0245] The step of determining the candidate network device set from the initial network device set based on the location information at the target time includes:

[0246] Determine the distance between the location information of each network device in the initial set of network devices and the location information of the terminal at the target time;

[0247] In the initial set of network devices, the network devices whose distance is less than a preset distance are selected as the candidate set of network devices.

[0248] In some embodiments, the preset distance is less than or equal to the minimum coverage radius of the network devices in the initial set of network devices.

[0249] In some embodiments, the location prediction AI model is obtained by training an initial AI model based on a second training sample;

[0250] The second training sample includes: a second training dataset and a second label dataset; the second training dataset includes: location information at the fifth time point, and location information at least one historical time point prior to the fifth time point; the label dataset includes: location information at the sixth time point, where the sixth time point is equal to the fifth time point plus the second time interval.

[0251] In one exemplary embodiment, such as Figure 4 As shown, a structural block diagram of a control device is provided. This control device can be the first control device described above, comprising:

[0252] Prediction module 401 is used to predict key indicators of a target time after the current time based on key indicators at the current time and key indicators at historical time through an indicator prediction AI model. The key indicators at the current time and historical time are obtained by the terminal measuring downlink reference information of each candidate network device in the candidate network device set.

[0253] The determination module 402 is used to determine the first set of serving network devices for the terminal from the set of candidate network devices based on key indicators at the target time.

[0254] In one embodiment, the prediction module 401 is specifically used for:

[0255] The key indicators at the current moment, the key indicators at the historical moment, and the first time interval are input into the indicator prediction AI model;

[0256] Obtain the key indicators for the target time output by the indicator prediction AI model;

[0257] Wherein, the first time interval is the time interval between the first moment and the target moment, the first moment is the moment when the earliest downlink reference signal for measuring the key indicator is sent in the candidate network device set, the target moment is the moment when the first control device determines the first service network device set based on the measurement result, and the measurement result is obtained by measuring based on the downlink reference signal sent at the first moment.

[0258] In one embodiment, the first time interval is determined based on the following time:

[0259] The propagation time of the downlink reference signal sent by the alternative network device for measuring the key indicator;

[0260] The time at which the terminal measures the key indicators;

[0261] The time at which the terminal feeds back the key indicators to the first control device;

[0262] The first control device predicts the timing of the key indicator.

[0263] The first control device determines the timing of the first service network device set of the terminal based on the predicted key indicators.

[0264] In one embodiment, the first time interval is determined based on the following time:

[0265] The propagation time of the downlink reference signal sent by the alternative network device for measuring the key indicator;

[0266] The time at which the terminal measures the key indicators;

[0267] The terminal predicts the timing of the key indicators.

[0268] The time when the terminal feeds back the predicted key indicator to the first control device.

[0269] The first control device determines the timing of the first service network device set of the terminal based on the predicted key indicators.

[0270] In one embodiment, the first time interval corresponds to the candidate network device belonging to the second service network device set, wherein the second service network design set is the original service network device set that provides services to the terminal.

[0271] In one embodiment, the first time interval also includes the time spent by the terminal establishing a connection with the service network device in the first service network device.

[0272] In one embodiment, the first time interval corresponds to the case where the candidate network device does not belong to the second set of serving network devices, wherein the second set of serving network devices is the original set of serving network devices that provide services to the terminal.

[0273] In one embodiment, the indicator prediction AI model is obtained by training an initial AI model based on a first training sample;

[0274] The first training sample includes: a first training dataset and a first label dataset; the first training dataset includes: key indicators at a third time step, and key indicators at at least one historical time step prior to the third time step; the first label dataset includes: key indicators at a fourth time step, wherein the fourth time step is equal to the third time step plus the first time interval.

[0275] In one embodiment, the determining module 402 is specifically used for:

[0276] The top M candidate network devices with the highest key indicators from the candidate network device set are selected as the service network device set for the terminal, where M is greater than or equal to 1.

[0277] In one embodiment, when the key indicator is a first type of indicator, the larger the value of the key indicator, the better the system performance. The determining module 402 is specifically used to: determine the candidate network devices in the candidate network device set whose key indicator ratio is greater than a set threshold as the first service network device set of the terminal.

[0278] The key indicator ratio is the ratio of the key indicator of the candidate network device to the maximum key indicator, where the maximum key indicator is the maximum value of the key indicators of all candidate network devices in the candidate network device set.

[0279] In one embodiment, when the key indicator is a second type of indicator, the smaller the value of the key indicator, the better the system performance. The determining module 402 is specifically used for:

[0280] The first set of serving network devices for the terminal is determined by selecting the candidate network devices whose ratio of all key indicators is less than a set threshold from the candidate network device set.

[0281] The key indicator ratio is the ratio of the key indicator of the candidate network device to the minimum key indicator, where the minimum key indicator is the minimum value of the key indicators of all candidate network devices in the candidate network device set.

[0282] In one embodiment, the key metrics include at least one of the following:

[0283] SS-RSRP, SS-RSRQ, SS-SINR, CSI-RSRP, CSI-RSRQ, CSI-SINR, SS-CQI, SS-RSSI, CSI-CQI, CSI-RSSI.

[0284] In one embodiment, the prediction module 401 is further configured to determine the location information at the target time by a location prediction AI model before the determination module 402 determines the first service network device set of the terminal from the candidate network device set based on the key indicators of the target time;

[0285] The determining module 402 is further configured to determine the candidate network device set from the initial network device set based on the location information at the target time.

[0286] In one embodiment, the prediction module 401 is specifically used for:

[0287] The current location information, the historical location information, and the second time interval are input into the location prediction AI model;

[0288] Obtain the location information at the target time output by the location prediction AI model;

[0289] The second time interval is the interval between the transmission of a downlink reference signal for positioning from the second control device and the target time.

[0290] In one embodiment, the second time interval is determined based on the following time:

[0291] The positioning time of the second control device;

[0292] The second control device predicts the time of the terminal's location information;

[0293] The second control device sends the predicted location information of the terminal to the first control device at the time when;

[0294] The first control device determines the time of the candidate network device set based on the predicted location information of the terminal;

[0295] The first control device notifies the alternative network device of the time to send downlink reference signals for measuring key indicators;

[0296] First time interval.

[0297] In one embodiment, the determining module 402 is further configured to: before determining the first serving network device set of the terminal from the initial network device set based on the key indicators of the target time, determine the distance between the location information of each network device in the initial network device set and the location information of the terminal at the target time;

[0298] In the initial set of network devices, the network devices whose distance is less than a preset distance are selected as the candidate set of network devices.

[0299] In one embodiment, the preset distance is less than or equal to the minimum coverage radius of the network devices in the initial set of network devices.

[0300] In one embodiment, the location prediction AI model is obtained by training an initial AI model based on a second training sample;

[0301] The second training sample includes: a second training dataset and a second label dataset; the second training dataset includes: location information at the fifth time point, and location information at least one historical time point prior to the fifth time point; the label dataset includes: location information at the sixth time point, where the sixth time point is equal to the fifth time point plus the second time interval.

[0302] It should be noted that the module division in the embodiments of this application is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods. Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0303] If the integrated modules described above are implemented as software functional modules and sold or used as independent products, they can be stored in a processor-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application.

[0304] It should be noted that the apparatus provided in this embodiment of the invention can implement all the method steps implemented in the above method embodiment and can achieve the same technical effect. Therefore, the parts and beneficial effects that are the same as those in the method embodiment will not be described in detail here.

[0305] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements all the method steps implemented in the above method embodiments.

[0306] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements all the method steps implemented in the above method embodiments.

[0307] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile 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. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0308] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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 specification.

[0309] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for determining a service network device, characterized in that, The method includes: Based on the key indicators at the current moment and the key indicators at historical moments, the key indicators at the target moment after the current moment are predicted by the indicator prediction AI model. The key indicators at the current moment and the key indicators at historical moments are obtained by the terminal measuring the downlink reference information of each candidate network device in the candidate network device set. From the set of candidate network devices, the first set of serving network devices for the terminal is determined based on key indicators at the target time.

2. The method according to claim 1, characterized in that, The step of predicting key indicators for a target time after the current time using an indicator prediction AI model based on key indicators at the current time and key indicators at historical times includes: The key indicators at the current moment, the key indicators at the historical moment, and the first time interval are input into the indicator prediction AI model; Obtain the key indicators for the target time output by the indicator prediction AI model; Wherein, the first time interval is the time interval between the first moment and the target moment, the first moment is the moment when the earliest downlink reference signal for measuring the key indicator is sent in the candidate network device set, the target moment is the moment when the first control device determines the first service network device set based on the measurement result, and the measurement result is obtained by measuring based on the downlink reference signal sent at the first moment.

3. The method according to claim 2, characterized in that, The first time interval is determined based on the following time: The propagation time of the downlink reference signal sent by the alternative network device for measuring the key indicator; The time at which the terminal measures the key indicators; The time at which the terminal feeds back the key indicators to the first control device; The first control device predicts the timing of the key indicator. The first control device determines the time of the first service network device set of the terminal based on the predicted key indicators. or, The first time interval is determined based on the following time: The propagation time of the downlink reference signal sent by the alternative network device for measuring the key indicator; The time at which the terminal measures the key indicators; The terminal predicts the timing of the key indicators. The time when the terminal feeds back the predicted key indicator to the first control device. The first control device determines the timing of the first service network device set of the terminal based on the predicted key indicators.

4. The method according to claim 3, characterized in that, The first time interval corresponds to the case where the candidate network device belongs to the second service network device set, wherein the second service network device set is the original service network device set that provides services to the terminal.

5. The method according to claim 4, characterized in that, The first time interval also includes the time spent by the terminal establishing a connection with the service network device in the first service network device.

6. The method according to claim 5, characterized in that, The first time interval corresponds to the case where the candidate network device does not belong to the second service network device set, wherein the second service network device set is the original service network device set that provides services to the terminal.

7. The method according to claim 2, characterized in that, The indicator prediction AI model is obtained by training an initial AI model based on the first training sample; The first training sample includes: a first training dataset and a first label dataset; the first training dataset includes: key indicators at a third time step, and key indicators at at least one historical time step prior to the third time step; the first label dataset includes: key indicators at a fourth time step, wherein the fourth time step is equal to the third time step plus the first time interval.

8. The method according to claim 1, characterized in that, The step of determining the first set of serving network devices for the terminal from the set of candidate network devices based on key indicators at the target time includes: The top M candidate network devices with the highest key indicators from the candidate network device set are selected as the first service network device set for the terminal, where M is greater than or equal to 1.

9. The method according to claim 1, characterized in that, When the key indicator is a first-type indicator, the larger the value of the key indicator, the better the system performance. The step of determining the first set of serving network devices for the terminal from the set of candidate network devices based on the key indicator at the target time includes: The candidate network devices in the candidate network device set whose ratio of all key indicators is greater than a set threshold are determined as the first service network device set of the terminal. The key indicator ratio is the ratio of the key indicator of the candidate network device to the maximum key indicator. The maximum key indicator is the maximum value of the key indicators of all candidate network devices in the candidate network device set. The larger the value of the key indicator, the better the system performance.

10. The method according to claim 1, characterized in that, When the key indicator is a second type of indicator, the smaller the value of the key indicator, the better the system performance. The step of determining the first set of serving network devices for the terminal from the set of candidate network devices based on the key indicator at the target time includes: The first set of serving network devices for the terminal is determined by selecting the candidate network devices whose ratio of all key indicators is less than a set threshold from the candidate network device set. The key indicator ratio is the ratio of the key indicator of the candidate network device to the minimum key indicator. The minimum key indicator is the minimum value of the key indicators of all candidate network devices in the candidate network device set. The smaller the value of the key indicator, the better the system performance.

11. The method according to claim 1, characterized in that, The key indicators include at least one of the following: SS-RSRP, SS-RSRQ, SS-SINR, CSI-RSRP, CSI-RSRQ, CSI-SINR, SS-CQI, SS-RSSI, CSI-CQI, CSI-RSSI.

12. The method according to any one of claims 1 to 3, characterized in that, Before determining the first set of serving network devices for the terminal from the set of candidate network devices based on key indicators at the target time, the method further includes: Based on the terminal's location information at the current time and its location information at historical times, the location information at the target time is predicted using a location prediction AI model; The first control device determines the set of candidate network devices from the initial set of network devices based on the location information at the target time.

13. The method according to claim 12, characterized in that, The step of predicting the location information of the target time using a location prediction AI model based on the terminal's location information at the current time and its location information at historical times includes: The current location information, the historical location information, and the second time interval are input into the location prediction AI model; Obtain the location information at the target time output by the location prediction AI model; The second time interval is the interval between the transmission of a downlink reference signal for positioning from the second control device and the target time.

14. The method according to claim 13, characterized in that, The second time interval is determined based on the following time: The positioning time of the second control device; The second control device predicts the time of the terminal's location information; The second control device sends the predicted location information of the terminal to the first control device at the time when; The first control device determines the time of the candidate network device set based on the predicted location information of the terminal; The first control device notifies the alternative network device of the time to send downlink reference signals for measuring key indicators; First time interval.

15. The method according to claim 12, characterized in that, The step of determining the candidate network device set from the initial network device set based on the location information at the target time includes: Determine the distance between the location information of each network device in the initial set of network devices and the location information of the terminal at the target time; In the initial set of network devices, the network devices whose distance is less than a preset distance are selected as the candidate set of network devices.

16. The method according to claim 15, characterized in that, The preset distance is less than or equal to the minimum coverage radius of the network devices in the initial set of network devices.

17. The method according to claim 13, characterized in that, The location prediction AI model is obtained by training the initial AI model based on the second training samples; The second training sample includes: a second training dataset and a second label dataset; the second training dataset includes: location information at the fifth time point, and location information at least one historical time point prior to the fifth time point; the label dataset includes: location information at the sixth time point, where the sixth time point is equal to the fifth time point plus the second time interval.

18. A control device, characterized in that, include: Memory, transceiver, processor: The memory is used to store computer programs; the transceiver is used to send and receive data under the control of the processor; the processor is used to read the computer programs in the memory and perform the following operations: Based on the key indicators at the current moment and the key indicators at historical moments, the key indicators at the target moment after the current moment are predicted by the indicator prediction AI model. The key indicators at the current moment and the key indicators at historical moments are obtained by the terminal measuring the downlink reference information of each candidate network device in the candidate network device set. From the set of candidate network devices, the first set of serving network devices for the terminal is determined based on key indicators at the target time.

19. The control device according to claim 18, characterized in that, The processor is specifically configured to read the computer program in the memory and perform the following operations: The key indicators at the current moment, the key indicators at the historical moment, and the first time interval are input into the indicator prediction AI model; Obtain the key indicators for the target time output by the indicator prediction AI model; Wherein, the first time interval is the time interval between the first moment and the target moment, the first moment is the moment when the earliest downlink reference signal for measuring the key indicator is sent in the candidate network device set, the target moment is the moment when the first control device determines the first service network device set based on the measurement result, and the measurement result is obtained by measuring based on the downlink reference signal sent at the first moment.

20. The control device according to claim 18, characterized in that, The processor is specifically configured to read the computer program in the memory and perform the following operations: The top M candidate network devices with the highest key indicators from the candidate network device set are selected as the first service network device set for the terminal, where M is greater than or equal to 1.

21. The control device according to claim 19, characterized in that, When the key indicator is a first-type indicator, the larger the value of the key indicator, the better the system performance. The processor is specifically used to read the computer program in the memory and perform the following operations: The candidate network devices in the candidate network device set whose key indicator ratio is greater than a set threshold are determined as the first service network device set of the terminal. The key indicator ratio is the ratio of the key indicator of the candidate network device to the maximum key indicator, where the maximum key indicator is the maximum value of the key indicator of the candidate network devices in the set of candidate network devices.

22. The control device according to claim 18, characterized in that, When the key indicator is a second type of indicator, the smaller the value of the key indicator, the better the system performance. The processor is specifically used to read the computer program in the memory and perform the following operations: The first set of serving network devices for the terminal is determined by selecting the candidate network devices whose ratio of all key indicators is less than a set threshold from the candidate network device set. The key indicator ratio is the ratio of the key indicator of the candidate network device to the minimum key indicator, where the minimum key indicator is the minimum value of the key indicators of all candidate network devices in the candidate network device set.

23. A control device, characterized in that, include: The prediction module is used to predict the key indicators of the target time after the current time based on the key indicators of the current time and the key indicators of the historical time. The key indicators of the current time and the historical time are obtained by the terminal measuring the downlink reference information of each candidate network device in the candidate network device set. The determination module is used to determine the first set of serving network devices for the terminal from the set of candidate network devices based on key indicators at the target time.

24. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 17.

25. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 17.

Images