Method, equipment and device for selecting target cell and storage medium

Abstract

The embodiment of the invention provides a method, equipment and device for selecting a target cell and a storage medium. The method comprises the steps that source network equipment acquires a parameter prediction result; the parameter prediction result comprises a performance parameter obtained after the terminal is switched to the neighbor cell and / or an optimal neighbor cell identifier corresponding to the terminal, wherein the performance parameter is predicted based on the parameter prediction model; selecting a target cell to which the terminal is switched based on the parameter prediction result; wherein the parameter prediction model is obtained by training based on sample parameter information, and the sample parameter information at least comprises parameters used for representing uplink capability and / or downlink capability of the sample terminal on the sample adjacent region. According to the method for selecting the target cell provided by the embodiment of the invention, the cell with the maximum uplink and downlink capability can be selected as the target cell, so that the user performance is improved.

Description

Technical Field

[0001] The present application relates to the field of wireless communication technology, and in particular to a method, device, apparatus and storage medium for selecting a target cell. Background Art

[0002] In the existing cell switching mechanism, the source cell cannot obtain the uplink and downlink capabilities of the neighboring cells (such as uplink and downlink spectrum efficiency and / or user experience parameters). Therefore, the uplink and downlink capabilities of the neighboring cells cannot be considered when selecting the target cell. As a result, the source cell may not be able to select the target cell with the largest uplink and downlink capabilities, and user performance cannot be optimized. Summary of the invention

[0003] In view of the problems existing in the prior art, embodiments of the present application provide a method, device, apparatus and storage medium for selecting a target cell.

[0004] In a first aspect, an embodiment of the present application provides a method for selecting a target cell, which is applied to a source network device, including:

[0005] Obtaining parameter prediction results; the parameter prediction results include performance parameters of the terminal after switching to a neighboring cell and / or an optimal neighboring cell identifier corresponding to the terminal, which are predicted based on a parameter prediction model;

[0006] Based on the parameter prediction result, selecting a target cell to which the terminal switches;

[0007] The parameter prediction model is obtained through training based on sample parameter information, and the sample parameter information at least includes parameters for characterizing the uplink capability and / or downlink capability of the sample terminal in the sample neighboring area.

[0008] In a second aspect, an embodiment of the present application further provides a method for selecting a target cell, which is applied to a second network device, including:

[0009] Receiving switching optimization request information sent by the source network device;

[0010] According to the handover optimization request information, one or more of the following is sent to the source network device:

[0011] Sample parameter information used to train parameter prediction models;

[0012] The parameter prediction model;

[0013] Feedback information after the terminal switches to the target cell;

[0014] Parameter prediction results; the parameter prediction results include performance parameters of the terminal after switching to a neighboring cell predicted based on a parameter prediction model and / or an optimal neighboring cell identifier corresponding to the terminal.

[0015] In a third aspect, an embodiment of the present application further provides a source network device, including a memory, a transceiver, and a processor;

[0016] A memory for storing a computer program; a transceiver for transmitting and receiving data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations:

[0017] Obtaining parameter prediction results; the parameter prediction results include performance parameters of the terminal after switching to a neighboring cell and / or an optimal neighboring cell identifier corresponding to the terminal, which are predicted based on a parameter prediction model;

[0018] Based on the parameter prediction result, selecting a target cell to which the terminal switches;

[0019] The parameter prediction model is obtained through training based on sample parameter information, and the sample parameter information at least includes parameters for characterizing the uplink capability and / or downlink capability of the sample terminal in the sample neighboring area.

[0020] In a fourth aspect, an embodiment of the present application further provides a second network device, including a memory, a transceiver, and a processor;

[0021] A memory for storing a computer program; a transceiver for transmitting and receiving data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations:

[0022] Receiving switching optimization request information sent by the source network device;

[0023] According to the handover optimization request information, one or more of the following is sent to the source network device:

[0024] Sample parameter information used to train parameter prediction models;

[0025] The parameter prediction model;

[0026] Feedback information after the terminal switches to the target cell;

[0027] Parameter prediction results; the parameter prediction results include performance parameters of the terminal after switching to a neighboring cell predicted based on a parameter prediction model and / or an optimal neighboring cell identifier corresponding to the terminal.

[0028] In a fifth aspect, an embodiment of the present application further provides a device for selecting a target cell, comprising:

[0029] An acquisition unit, configured to acquire a parameter prediction result; the parameter prediction result includes a performance parameter after the terminal switches to a neighboring cell and / or an optimal neighboring cell identifier corresponding to the terminal, which is predicted based on a parameter prediction model;

[0030] A selection unit, configured to select a target cell to which the terminal switches based on the parameter prediction result;

[0031] The parameter prediction model is obtained through training based on sample parameter information, and the sample parameter information at least includes parameters for characterizing the uplink capability and / or downlink capability of the sample terminal in the sample neighboring area.

[0032] In a sixth aspect, an embodiment of the present application further provides an apparatus for selecting a target cell, comprising a second receiving unit, configured to receive handover optimization request information sent by a source network device;

[0033] A second sending unit is configured to send one or more of the following to the source network device according to the handover optimization request information:

[0034] Sample parameter information used to train parameter prediction models;

[0035] The parameter prediction model;

[0036] Feedback information after the terminal switches to the target cell;

[0037] Parameter prediction results; the parameter prediction results include performance parameters of the terminal after switching to a neighboring cell predicted based on a parameter prediction model and / or an optimal neighboring cell identifier corresponding to the terminal.

[0038] In the seventh aspect, an embodiment of the present application also provides a computer-readable storage medium, which stores a computer program, and the computer program is used to enable a computer to execute the method for selecting a target cell as described in the first aspect, or execute the method for selecting a target cell as described in the second aspect.

[0039] In an eighth aspect, an embodiment of the present application further provides a communication device, in which a computer program is stored, and the computer program is used to enable the communication device to execute the method for selecting a target cell as described in the first aspect, or to execute the method for selecting a target cell as described in the second aspect.

[0040] In the ninth aspect, an embodiment of the present application also provides a processor-readable storage medium, wherein the processor-readable storage medium stores a computer program, and the computer program is used to enable the processor to execute the method for selecting a target cell as described in the first aspect, or to execute the method for selecting a target cell as described in the second aspect.

[0041] In the tenth aspect, an embodiment of the present application also provides a chip product, in which a computer program is stored, and the computer program is used to enable the chip product to execute the method for selecting a target cell as described in the first aspect, or to execute the method for selecting a target cell as described in the second aspect.

[0042] The method, device, apparatus and storage medium for selecting a target cell provided in the embodiment of the present application obtains parameter prediction results and selects the target cell to which the terminal switches according to the parameter prediction results; wherein the parameter prediction results are obtained by inference using a parameter prediction model, and the sample parameter information used to train the parameter prediction model includes parameters for characterizing the uplink capability and / or downlink capability of the sample terminal in the sample neighboring area, and the parameter prediction results include the performance parameters after the terminal switches to the neighboring area and / or the optimal neighboring area identifier corresponding to the terminal. Thus, the cell with the largest uplink and downlink capabilities can be selected as the target cell, thereby improving user performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the following is a brief introduction to the drawings required for use in the embodiments or the related technical descriptions. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0044] Figure 1 This is one of the flowcharts of the method for selecting a target cell provided in an embodiment of the present application;

[0045] Figure 2 It is a flowchart of a method for estimating uplink and downlink effective bandwidth of a neighboring cell provided in an embodiment of the present application;

[0046] Figure 3 This is a second flow chart of the method for selecting a target cell provided in an embodiment of the present application;

[0047] Figure 4 This is a third flowchart of a method for selecting a target cell provided in an embodiment of the present application;

[0048] Figure 5 It is a schematic diagram of a process for estimating the uplink and downlink capabilities of a neighboring cell and selecting a target cell according to a parameter prediction result provided by an embodiment of the present application;

[0049] Figure 6 It is a flow chart of a node 1 sending a switching optimization request message to a node 2 to obtain information provided by an embodiment of the present application;

[0050] Figure 7This is a flow chart of gNB1 requiring gNB2 to provide sample information provided in an embodiment of the present application;

[0051] Figure 8 It is a schematic diagram of a process of gNB3 selecting a target cell for a UE using a parameter prediction model provided in an embodiment of the present application;

[0052] Fig. 9 It is a flowchart of an algorithm for selecting a target cell using parameter prediction results provided in an embodiment of the present application;

[0053] Fig.10 It is a flow chart of node three sending input parameters of a parameter prediction model to node four and node four sending parameter prediction results to node three provided in an embodiment of the present application;

[0054] Fig.11 It is a schematic diagram of a process of obtaining a parameter prediction model from node 6 by node 5 provided in an embodiment of the present application;

[0055] Fig.12 is a schematic diagram of the structure of a source network device provided in an embodiment of the present application;

[0056] Fig.13 is a schematic diagram of the structure of a second network device provided in an embodiment of the present application;

[0057] Fig.14 It is one of the structural schematic diagrams of the device for selecting a target cell provided in an embodiment of the present application;

[0058] Fig.15 This is the second structural diagram of the device for selecting a target cell provided in an embodiment of the present application. DETAILED DESCRIPTION

[0059] In the embodiments of the present application, the term "and / or" describes the association relationship of the associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0060] In the embodiments of the present application, the term "plurality" refers to two or more than two, and other quantifiers are similar.

[0061] In the embodiments of the present application, the terms "first", "second", etc. are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first" and "second" are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more.

[0062] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0063] Figure 1 One of the flowcharts of the method for selecting a target cell provided in an embodiment of the present application is as follows: Figure 1 As shown, the method is applied to a source network device and comprises the following steps:

[0064] Step 100, obtaining parameter prediction results; the parameter prediction results include performance parameters of the terminal after switching to a neighboring cell and / or an optimal neighboring cell identifier corresponding to the terminal, which are predicted based on a parameter prediction model.

[0065] Step 101: Based on the parameter prediction result, select a target cell to which the terminal switches.

[0066] The parameter prediction model is obtained through training based on sample parameter information, and the sample parameter information at least includes parameters for characterizing the uplink capability and / or downlink capability of the sample terminal in the sample neighboring area.

[0067] Specifically, when the source network device needs to switch the service cell for the terminal (for example, the signal strength of the source cell measured by the terminal is less than a preset threshold, the terminal's business volume is large, or it is determined through an existing mechanism that the terminal needs to switch the service cell), the parameter prediction result obtained by the parameter prediction model can be obtained first, and then the target cell to which the terminal switches can be selected based on the parameter prediction result.

[0068] The source network device can be a 5G base station (gNB) in the 5G network architecture (next generation system), an evolutionary network device (eNB), an evolutionary network device (next generation system-evolutional Node B, ng-eNB) in the 5G network architecture, a 5G base station in the evolved universal mobile communication system terrestrial radio access network (E-UTRAN New Radio-gNB, en-gNB), a gNB centralized unit (CU), a gNB centralized unit control plane (CU-CP), a gNB centralized unit user plane (CU-UP), a gNB distributed unit (DU) or a radio network intelligent resource control (RAN Intelligent Controller, RIC) in any one.

[0069] The parameter prediction result may include the performance parameters after the terminal switches to the neighboring cell and / or the optimal neighboring cell identifier corresponding to the terminal. The performance parameters after the terminal switches to the neighboring cell may be parameters used to characterize the user performance after the terminal switches to the neighboring cell, such as parameters used to characterize channel quality, service performance, etc.

[0070] In some embodiments, the performance parameters after the terminal switches to the neighboring cell included in the parameter prediction result may include one or more of the following:

[0071] (1) The measurement results of the neighboring cell on the terminal.

[0072] Among them, the measurement results of the neighboring cell on the terminal may include at least one of the measurement results of the neighboring cell measuring the sounding reference signal (SRS) of the terminal, the measurement results of the neighboring cell measuring other uplink reference signals of the terminal, and the measurement results of the neighboring cell measuring the new radio in unlicensed spectrum (NR-U) channel of the unlicensed spectrum used by the terminal.

[0073] The above measurement results include at least one of the following: Reference Signal Receiving Power (RSRP), Reference Signal Received Quality (RSRQ), Signal to Interference plus Noise Ratio (SINR), Received Signal Strength Indicator (RSSI) and Channel occupancy time ratio (CO) measured in the cell.

[0074] In the case that the above measurement result includes the CO measured in the cell, the measurement result may also include an Energy Detection Threshold (EDT).

[0075] (2) Channel Quality Indication (CQI) and / or downlink modulation and coding scheme index (MCS Index) of the terminal.

[0076] (3) The uplink MCS Index of the terminal.

[0077] (4) Downlink spectrum efficiency parameters of the terminal in the neighboring cell.

[0078] Among them, the spectrum efficiency parameter can be a spectrum efficiency parameter corresponding to all or part of the resources of the cell, for example, it can be at least one of the spectrum efficiency parameters of all bandwidths of the cell, the spectrum efficiency parameters of the physical downlink shared channel (Physical Downlink Shared Channel, PDSCH) resources, and the spectrum efficiency parameters of the physical uplink shared channel (Physical Uplink Shared Channel, PUSCH) resources.

[0079] In one implementation, the spectrum efficiency parameter may be spectrum efficiency, that is, the amount of data that can be transmitted per unit spectrum.

[0080] In one implementation, the minimum and maximum values ​​of the spectrum efficiency supported by the cell may be divided into multiple intervals, each of which corresponds to a characterization value. The spectrum efficiency parameter is the characterization value of the interval to which the spectrum efficiency of the sample terminal belongs. The characterization value may be a numerical value, for example, assuming that the maximum value is 100 points and the minimum value is 0 points, the score corresponding to the interval to which the spectrum efficiency of the sample terminal belongs. The characterization value may also be the number of the interval, which may be the maximum value, minimum value, median or average value of the spectrum efficiency within the interval, or may be an indication information, for example, indicating that the spectrum efficiency is high, medium or low.

[0081] In one implementation, terminals (also referred to as user equipment (UE)) with similar uplink and / or downlink signal receiving and transmitting states in a cell may be divided into different groups. For example, if UE1 and UE2 have multiple identical neighboring cells, and the mean square error of the uplink and / or downlink signal measurements of the two UEs in all identical neighboring cells is less than a preset threshold, UE1 and UE2 are divided into the same group. The spectrum efficiency parameter may be the maximum, minimum, median or average value of the spectrum efficiency of all UEs in the group to which the sample terminal belongs.

[0082] The concepts of the above spectrum efficiency parameters remain consistent throughout the text and will not be repeated below.

[0083] (5) Uplink spectrum efficiency parameters of the terminal in the neighboring cell.

[0084] (6) User experience parameters of the terminal in the neighboring cell. The user experience parameters may include at least one of the following information:

[0085] A. Uplink Quality of Service (QoS) parameters.

[0086] B. Downlink QoS parameters.

[0087] C. Quality of Experience (QoE) parameters.

[0088] The QoS parameters may include at least one of the following information:

[0089] a. Data granularity identifier. The data granularity identifier may indicate that the QoS parameter is measured based on the data corresponding to the data granularity identifier. The data granularity identifier may be at least one of a slice identifier, a 5G QoS identifier (5G QoS Identifier, 5QI) identifier, a Quality of Service (Quality of Service, QoS) flow identifier, a Protocol Data Unit (Protocol Data Unit, PDU) session identifier, and a UE identifier.

[0090] b. Rate: The rate may be the rate of different protocol layers, such as at least one of the Medium Access Control (MAC) layer rate, the Radio Link Control (RLC) layer rate, and the Packet Data Convergence Protocol (PDCP) layer rate.

[0091] c. Packet loss rate: The packet loss rate may be the number of transmission packet losses or transmission failures per unit time, such as at least one of the RLC layer packet loss rate, the PDCP layer packet loss rate, and the Hybrid Automatic Repeat reQuest (HARQ) transmission failure rate.

[0092] d. Retransmission rate: The retransmission rate may be the number of retransmissions per unit time, such as at least one of an RLC layer retransmission rate, a PDCP layer retransmission rate, and a HARQ retransmission rate.

[0093] e. Delay: The delay may be one delay, multiple delays, or the sum of multiple delays in the components of the Radio Access Network (RAN) side delay (RAN part of delay) in 3GPP technical specification 38.314.

[0094] f. Transmission queue length: The transmission queue length may be a transmission queue length of different protocol layers, such as an RLC layer transmission queue length and / or a PDCP layer transmission queue length.

[0095] g. Packet jitter: Packet jitter may be packet jitter at different protocol layers, such as RLC layer packet jitter and / or PDCP layer packet jitter.

[0096] The QoE parameters may include at least one of the following information:

[0097] a. Service type: The service type may be at least one of voice, video, and a service type for application layer measurement defined in 3GPP Technical Specification 38.331 (transferred using serviceType in the AppLayerMeasConfig field).

[0098] b. At least one information in an application layer measurement report. The application layer measurement report is consistent with the application layer measurement report used in 3GPP technical specification 38.331 (delivered using measReportAppLayerContainer).

[0099] c. At least one information in the RAN visible measurement report. The RAN visible measurement report is consistent with the RAN visible measurement report used in 3GPP technical specification 38.331 (delivered using RAN-VisibleMeasurements).

[0100] The concepts of the above user experience parameters remain consistent throughout the article and will not be repeated below.

[0101] The parameter prediction result may also directly include the optimal neighboring cell identifier corresponding to the terminal predicted by the parameter prediction model, and the optimal neighboring cell may be selected as the target cell. The optimal neighboring cell identifier corresponding to the terminal may be at least one of a Cell Global Identifier (CGI), a Physical Cell Identifier (PCI), an Absolute Radio Frequency Channel Number (ARFCN), a Tracking Area Code (TAC), a RAN-based Notification Area Code (RANAC), and a Public Land Mobile Network (PLMN).

[0102] The parameter prediction model can be trained based on the sample information using a machine learning method (e.g., reinforcement learning, supervised learning, etc.). The sample information used for training includes at least parameters for characterizing the uplink capability and / or downlink capability of the sample terminal in the sample neighborhood. The uplink capability and / or downlink capability of the sample terminal in the sample neighborhood can reflect the ability of the sample terminal to perform uplink and / or downlink data transmission in the sample neighborhood.

[0103] In some embodiments, the parameters in the sample parameter information used to characterize the uplink capability and / or downlink capability of the sample terminal in the sample neighboring area may include one or more of the following:

[0104] (1) Uplink spectrum efficiency parameters and / or downlink spectrum efficiency parameters of the sample terminal in the sample neighboring area.

[0105] (2) The uplink bandwidth and / or downlink bandwidth of the sample terminal in the sample neighboring cell, that is, the uplink bandwidth and / or downlink bandwidth used by the sample terminal in the sample neighboring cell.

[0106] (3) User experience parameters of sample terminals in sample neighborhood areas.

[0107] The method for selecting a target cell provided in an embodiment of the present application obtains parameter prediction results and selects a target cell to which the terminal switches according to the parameter prediction results; wherein the parameter prediction results are obtained by inference using a parameter prediction model, and the sample parameter information used to train the parameter prediction model includes parameters for characterizing the uplink capability and / or downlink capability of the sample terminal in the sample neighboring area, and the parameter prediction results include performance parameters after the terminal switches to the neighboring area and / or the optimal neighboring area identifier corresponding to the terminal. Thus, the cell with the largest uplink and downlink capabilities can be selected as the target cell, thereby improving user performance.

[0108] In some embodiments, obtaining parameter prediction results includes:

[0109] Acquire parameter prediction results from the first network device; or,

[0110] The parameter prediction results are obtained based on the parameter prediction model.

[0111] Specifically, the source network device can obtain the parameter prediction result from the first network device. Among them, the first network device can be any one of gNB, eNB, ng-eNB, en-gNB, gNB's CU, gNB's CUCP, gNB's CUUP, gNB's DU, RIC or a newly defined network node. The parameter prediction model is stored in the first network device. The first network device can be the same as the base station where the source network device is located or the component of the base station where the source network device is located (for example, CU, CUCP, CUUP or DU), can be the same as the base station where the neighboring cell is located or the component of the base station where the neighboring cell is located (for example, CU, CUCP, CUUP or DU), or can be different from the above base stations or devices.

[0112] Alternatively, the source network device may also directly use the parameter prediction model to predict and obtain the parameter prediction result. The parameter prediction model may be stored on the source network device before obtaining the parameter prediction result, or may be obtained by requesting other network devices during the process of obtaining the parameter prediction result.

[0113] In some embodiments, the method further comprises:

[0114] Sending a handover optimization request message to the second network device, where the handover optimization request message is used to obtain one or more of the following:

[0115] Sample parameter information;

[0116] Parameter prediction model;

[0117] Feedback information after the terminal switches to the target cell;

[0118] Parameter prediction results.

[0119] Specifically, the second network device can be any one of a gNB, an eNB, an ng-eNB, an en-gNB, a CU of a gNB, a CUCP of a gNB, a CUUP of a gNB, a DU of a gNB, a RIC, or a newly defined network node. The second network device can be the same as the first network device or different, and is not specifically limited here.

[0120] In one implementation, when the parameter prediction model needs to be trained, the source network device may send a handover optimization request message to the second network device to obtain sample parameter information. In this case, the second network device may be a network device in a neighboring cell of the source cell.

[0121] In one implementation, when the parameter prediction model is stored in the second network device, the source network device may send a handover optimization request message to the second network device to obtain the parameter prediction model.

[0122] The second network device may store a trained parameter prediction model.

[0123] In one implementation, when the target cell is within the jurisdiction of the second network device, the source network device may send a handover optimization request message to the second network device to obtain feedback information after the terminal switches to the target cell.

[0124] In one implementation, when the parameter prediction model is stored on the second network device, the source network device may not obtain the parameter prediction model, but may use the parameter prediction model on the second network device to perform prediction to obtain the parameter prediction result. The source network device may send a handover optimization request message to the second network device to obtain the parameter prediction result. The second network device may obtain the input parameters of the parameter prediction model from the source network device, or directly obtain the input parameters of the parameter prediction model from the neighboring cell of the source cell, and then obtain the parameter prediction result based on the input parameters of the parameter prediction model, and then send the parameter prediction result to the source network device.

[0125] In some embodiments, the sample parameter information may also include one or more of the following:

[0126] (1) A cell identifier of a sample source cell, where the cell identifier may be at least one of CGI, PCI, ARFCN, TAC, RANAC and PLMN.

[0127] (2) Cell identifier of the sample neighboring cell, where the cell identifier may be at least one of CGI, PCI, ARFCN, TAC, RANAC and PLMN.

[0128] (3) Identification of the serving beam in the sample neighborhood.

[0129] (4) Identification of the serving beam on the sample source cell.

[0130] (5) Identification of the sample terminal. The identification of the terminal may be at least one of the Source NG-RAN node UE XnAP ID, the Target NG-RAN node UE XnAP ID, the gNB-CU UE F1AP ID, the gNB-DU UE F1AP ID, the RAN UE ID, the International Mobile Equipment Identity (IMEI), the International Mobile Subscriber Identity (IMSI), the Globally Unique Temporary UE Identity (GUTI), the Subscription Permanent Identifier (SUPI), the Subscription concealed identifier (SUCI) and the Radio Network Temporary Identity (RNTI).

[0131] (6) Downlink transmit power of the sample neighboring cell. The transmit power may be the actual transmit power and / or the maximum transmit power.

[0132] (7) Downlink transmit power of the serving beam in the sample neighboring cell. The transmit power may be the actual transmit power and / or the maximum transmit power.

[0133] (8) Downlink transmit power of the sample source cell. The transmit power may be actual transmit power and / or maximum transmit power.

[0134] (9) Downlink transmit power of the serving beam on the sample source cell. The transmit power may be the actual transmit power and / or the maximum transmit power.

[0135] (10) Uplink transmit power of the sample terminal. The transmit power may be actual transmit power and / or maximum transmit power.

[0136] (11) Number of downlink transmit antennas in the sample neighboring cell.

[0137] (12) Number of uplink receiving antennas in the sample neighborhood.

[0138] (13) Number of downlink transmit antennas of the sample source cell.

[0139] (14) Number of uplink receiving antennas of the sample source cell.

[0140] (15) Number of uplink transmit antennas of the sample terminal.

[0141] (16) Number of downlink receiving antennas of the sample terminal.

[0142] (17) The measurement result of at least one cell with a different frequency from the sample source cell reported by the sample terminal.

[0143] (18) The measurement result of at least one cell with the same frequency as the sample source cell reported by the sample terminal.

[0144] (19) The measurement results of the sample terminal measured by the sample neighboring area.

[0145] Among them, the measurement results of the sample neighboring area on the sample terminal may include at least one of the measurement results of the sample neighboring area measuring the SRS of the sample terminal, the measurement results of the sample neighboring area measuring other uplink reference signals of the sample terminal, and the measurement results of the sample neighboring area measuring the NR-U channel used by the sample terminal.

[0146] The above measurement result includes at least one of the following: RSRP, RSRQ, SINR, RSSI and CO measured in the cell.

[0147] In the case where the measurement result includes the CO measured in the cell, the measurement result may also include the EDT.

[0148] (20) The measurement result of the sample source cell on the sample terminal.

[0149] (21) CQI and / or downlink MCS Index of the sample terminal.

[0150] (22) Uplink MCS Index of the sample terminal.

[0151] (23) Load status of the sample neighboring area. The load status may include part or all of the information reported by the Resource Status Reporting process defined in the XnAP protocol in the existing mechanism.

[0152] (24) Load status of the sample source cell.

[0153] In some embodiments, the feedback information after the terminal switches to the target cell may include one or more of the following:

[0154] (1) Identification of the target cell.

[0155] (2) Identification of the serving beam on the target cell.

[0156] (3) The measurement results of the target cell on the terminal.

[0157] (4) The CQI and / or downlink MCS Index of the terminal.

[0158] (5) Uplink MCS Index of the terminal.

[0159] (6) Downlink spectrum efficiency parameters of the terminal in the target cell.

[0160] (7) Uplink spectrum efficiency parameters of the terminal in the target cell.

[0161] (8) User experience parameters of the terminal in the target cell.

[0162] In some embodiments, the input parameters of the parameter prediction model may include one or more of the following:

[0163] (1) A cell identifier of a neighboring cell, where the cell identifier may be at least one of CGI, PCI, ARFCN, TAC, RANAC and PLMN.

[0164] (2) Identification of the service beam in the neighboring cell.

[0165] (3) The cell identifier of the source cell.

[0166] (4) Identification of the serving beam on the source cell.

[0167] (5) Terminal identification.

[0168] (6) Downlink transmit power of the neighboring cell. The transmit power can be the actual transmit power and / or the maximum transmit power.

[0169] (7) Downlink transmit power of the service beam in the neighboring cell. The transmit power can be the actual transmit power and / or the maximum transmit power.

[0170] (8) Downlink transmit power of the source cell. The transmit power may be actual transmit power and / or maximum transmit power.

[0171] (9) Downlink transmit power of the serving beam on the source cell. The transmit power can be the actual transmit power and / or the maximum transmit power.

[0172] (10) Uplink transmit power of the terminal. The transmit power can be the actual transmit power and / or the maximum transmit power.

[0173] (11) Number of downlink transmit antennas in the neighboring cell.

[0174] (12) Number of uplink receiving antennas in the neighboring cell.

[0175] (13) Number of downlink transmit antennas of the source cell.

[0176] (14) Number of uplink receiving antennas of the source cell.

[0177] (15) Number of uplink transmit antennas of the terminal.

[0178] (16) Number of downlink receiving antennas of the terminal.

[0179] (17) Effective uplink bandwidth of the terminal in the neighboring cell.

[0180] (18) The effective downlink bandwidth of the terminal in the neighboring cell.

[0181] (19) Uplink idle bandwidth of the neighboring cell.

[0182] (20) Downlink idle bandwidth of the neighboring cell.

[0183] (21) The measurement result of at least one cell with a frequency different from that of the source cell reported by the terminal.

[0184] (22) The measurement result of at least one cell with the same frequency as the source cell reported by the terminal.

[0185] (23) The measurement result of the source cell on the terminal.

[0186] (24) Load status of neighboring cells. The load status can be obtained according to the existing mechanism.

[0187] (25) Load status of the source cell.

[0188] In one implementation, the uplink and downlink effective bandwidths of the neighboring cells may be estimated.

[0189] Figure 2 A flow chart of a method for estimating the uplink and downlink effective bandwidth of a neighboring cell provided in an embodiment of the present application, such as Figure 2 As shown, the method comprises the following steps:

[0190] 1. Obtain the uplink and downlink resource status of the neighboring cell, which includes the physical resource block (PRB) utilization and idle bandwidth.

[0191] 2. Calculate the uplink and downlink rates of the UE. If the uplink rate is greater than the preset threshold, the UE is judged to be an uplink heavy traffic user; if the downlink rate is greater than the preset threshold, the UE is judged to be a downlink heavy traffic user; in other cases, the UE is judged to be a non-heavy traffic user. When both the uplink rate and the downlink rate of the UE are greater than the preset threshold, the UE can be judged to be an uplink heavy traffic user or a downlink heavy traffic user according to the preset rules. For example, when both the uplink rate and the downlink rate of the UE are greater than the preset threshold, the UE is judged to be an uplink heavy traffic user; or, when both the uplink rate and the downlink rate of the UE are greater than the preset threshold, the UE is judged to be a downlink heavy traffic user.

[0192] 3. If the UE is a user with a large uplink traffic volume, compare the uplink idle bandwidth of the neighboring cell and the maximum uplink bandwidth supported by the UE, and take the smaller value as the uplink effective bandwidth. When the uplink idle bandwidth of the neighboring cell is large, in order to avoid distortion in the estimation of the uplink effective bandwidth, if the uplink PRB utilization rate of the neighboring cell is higher than the preset threshold or the number of active users is higher than the preset threshold, the uplink effective bandwidth remains unchanged; otherwise, the uplink effective bandwidth = uplink effective bandwidth / (number of active users in the candidate target cell + 1). The number of active users refers to users with uplink data or downlink data transmission. The final uplink effective bandwidth is used as the uplink effective bandwidth of the neighboring cell available to the UE, and the estimation process is exited.

[0193] 4. If the UE is a user with a large downlink traffic volume, compare the downlink idle bandwidth of the neighboring cell and the maximum downlink bandwidth supported by the UE, and take the smaller value as the downlink effective bandwidth. When the downlink idle bandwidth of the neighboring cell is large, in order to avoid distortion in the estimation of the downlink effective bandwidth, if the downlink PRB utilization rate of the neighboring cell is higher than the preset threshold or the number of active users is higher than the preset threshold, the downlink effective bandwidth remains unchanged; otherwise, the downlink effective bandwidth = downlink effective bandwidth / (number of active users in the candidate target cell + 1). Among them, the number of active users refers to users with uplink data or downlink data transmission. The final downlink effective bandwidth is used as the downlink effective bandwidth of the neighboring cell available to the UE, and the estimation process is exited.

[0194] In some embodiments, the parameter prediction result may also include one or more of the following:

[0195] Neighboring cell ID. Used to mark the cell corresponding to the parameter prediction result.

[0196] Credibility of parameter prediction results. Used to characterize the reliability of parameter prediction results. When the credibility of one or more parameters in the parameter prediction results is less than a preset threshold, the method for selecting a target cell provided in the embodiment of the present application may not be used, but the target cell may be selected according to the existing mechanism.

[0197] In some embodiments, the handover optimization request information may include one or more of the following:

[0198] (1) A cell identifier of a sample source cell, where the cell identifier may be at least one of CGI, PCI, ARFCN, TAC, RANAC and PLMN.

[0199] (2) Cell identifier of the sample neighboring cell, where the cell identifier may be at least one of CGI, PCI, ARFCN, TAC, RANAC and PLMN.

[0200] (3) First indication information, the first indication information is used to indicate the start, update or stop of collecting sample parameter information.

[0201] (4) First cycle information, the first cycle information is used to indicate a cycle for sending sample parameter information to the source network device.

[0202] (5) First direction information, where the first direction information is used to indicate uplink information and / or downlink information in the collected sample parameter information.

[0203] (6) Second indication information: The second indication information is used to indicate the type of sample parameter information to be collected, for example, indicating whether to collect spectrum efficiency parameters and / or whether to collect user experience parameters.

[0204] (7) Data granularity identification. The second network device may collect user experience parameters obtained by measuring data corresponding to the data granularity identification. The data granularity identification may be at least one of a slice identification, a 5QI identification, a QoS flow identification, a PDU session identification, and a UE identification.

[0205] (8) QoS parameter type: The QoS parameter type may be at least one of rate, packet loss rate, retransmission rate, delay, transmission queue length, and packet jitter.

[0206] (9) Service type. The second network device may collect user experience parameters corresponding to the service type. The service type may be at least one of voice, video, and a service type for application layer measurement defined in 3GPP technical specification 38.331 (transmitted using serviceType in the AppLayerMeasConfig field).

[0207] (10) Identification of the sample terminal. The second network device may determine the terminal for which information needs to be collected based on the identification of the sample terminal. The identification of the sample terminal may be an identification of the sample terminal in the neighboring cell and / or the source cell. For example, the identification of the sample terminal may be at least one of Source NG-RAN node UE XnAP ID, Target NG-RAN node UE XnAP ID, gNB-CU UEF1AP ID, gNB-DU UE F1AP ID, RAN UE ID, IMEI, IMSI, GUTI, SUPI, SUCI and RNTI.

[0208] (11) First time length information, the first time length information is used to indicate the time period for collecting sample parameter information.

[0209] (12) Third indication information, where the third indication information is used to indicate starting, updating or stopping sending the parameter prediction model to the source network device.

[0210] (13) Second cycle information, where the second cycle information is used to indicate a cycle for sending the parameter prediction model to the source network device.

[0211] (14) The cell identifier of the source cell, where the cell identifier may be at least one of CGI, PCI, ARFCN, TAC, RANAC and PLMN.

[0212] (15) The cell identifier of the target cell, where the cell identifier may be at least one of CGI, PCI, ARFCN, TAC, RANAC and PLMN.

[0213] (16) Fourth indication information, the fourth indication information is used to indicate starting, updating or stopping collecting feedback information after the terminal switches to the target cell.

[0214] (17) Third cycle information, the third cycle information is used to indicate a cycle for sending feedback information to the source network device.

[0215] (18) Second direction information, where the second direction information is used to indicate the uplink information and / or downlink information in the collected feedback information.

[0216] (19) Fifth indication information: The fifth indication information is used to indicate the type of feedback information to be collected, for example, whether to collect spectrum efficiency parameters and / or whether to collect user experience parameters.

[0217] (20) Terminal identification. The second network device may determine the terminal for which information needs to be collected based on the terminal identification. The terminal identification may be at least one of Source NG-RAN node UE XnAP ID, Target NG-RAN node UE XnAP ID, gNB-CU UE F1AP ID, gNB-DU UE F1AP ID, RAN UE ID, IMEI, IMSI, GUTI, SUPI, SUCI, and RNTI.

[0218] (21) Second time length information, where the second time length information is used to indicate a time period for collecting feedback information.

[0219] (22) Sixth indication information, the sixth indication information is used to indicate that the target cell is predicted and / or the credibility of the parameter prediction result. When the sixth indication information includes the credibility of the parameter prediction result, it can also be determined whether to switch the terminal to the target cell according to the credibility of the parameter prediction result. For example, when the credibility of one or more parameters in the parameter prediction result is less than a preset threshold, the method for selecting a target cell provided in the embodiment of the present application may not be used, but the target cell may be selected according to an existing mechanism.

[0220] In some embodiments, the method further comprises:

[0221] receiving feedback information sent by the second network device;

[0222] Based on the feedback information, the parameter prediction model is optimized.

[0223] Specifically, the prediction accuracy of the trained parameter prediction model may not be high. In this case, the feedback information after the terminal switches to the target cell can be used as a sample input parameter prediction model (for example, as a feedback (reward) parameter of reinforcement learning) to optimize the parameter prediction model and improve the prediction accuracy of the parameter prediction model.

[0224] In some embodiments, selecting a target cell to which the terminal switches based on the parameter prediction result includes:

[0225] Based on the parameter prediction result, estimate the uplink capability and / or downlink capability of the terminal in the neighboring cell;

[0226] A target cell to which the terminal switches is selected based on the uplink capability and / or downlink capability of the terminal in the neighboring cell.

[0227] Specifically, after obtaining the parameter prediction result, the source network device may estimate the uplink capability and / or downlink capability of the terminal in the neighboring cell according to the parameter prediction result.

[0228] In one implementation, when the parameter prediction result includes uplink and / or downlink spectrum efficiency parameters of the terminal in the neighboring cell, the uplink capability and / or downlink capability of the terminal in the neighboring cell can be estimated based on the uplink and / or downlink spectrum efficiency parameters of the terminal in the neighboring cell.

[0229] For example, the uplink capability and / or downlink capability of the terminal in the neighboring cell may be estimated in the following manner:

[0230] The uplink capability of the terminal in the neighboring cell = the uplink spectrum efficiency parameter of the terminal in the neighboring cell * the uplink effective bandwidth of the terminal in the neighboring cell.

[0231] The downlink capability of the terminal in the neighboring cell = the downlink spectrum efficiency parameter of the terminal in the neighboring cell * the downlink effective bandwidth of the terminal in the neighboring cell.

[0232] In one implementation, when the parameter prediction result includes the user experience parameters of the terminal in the neighboring cell, the uplink capability and / or downlink capability of the terminal in the neighboring cell may be estimated based on the user experience parameters of the terminal in the neighboring cell.

[0233] For example, the uplink capability and / or downlink capability of the terminal in the neighboring cell may be estimated in the following manner:

[0234] The uplink capability of the terminal in the neighboring cell = the uplink rate in the user experience parameters of the terminal in the neighboring cell.

[0235] The downlink capability of the terminal in the neighboring cell = the downlink rate in the user experience parameters of the terminal in the neighboring cell.

[0236] After estimating the uplink capability and / or downlink capability of the terminal in the neighboring cell, a target cell to which the terminal switches may be selected based on the uplink capability and / or downlink capability of the terminal in the neighboring cell.

[0237] In some embodiments, selecting a target cell to which the terminal switches based on the uplink capability and / or downlink capability of the terminal in the neighboring cell includes:

[0238] Select a neighboring cell with the largest uplink capacity and / or downlink capacity, and determine it as the target cell to which the terminal switches; or

[0239] A target cell to which the terminal switches is selected based on the uplink capability and / or downlink capability of the terminal in the neighboring cell and the traffic type of the terminal.

[0240] Specifically, after estimating the uplink capability and / or downlink capability of the terminal in the neighboring cell, the neighboring cell with the largest corresponding uplink capability and / or downlink capability may be selected and determined as the target cell to which the terminal switches.

[0241] Alternatively, the target cell to which the terminal switches may be selected based on the uplink capability and / or downlink capability of the terminal in the neighboring cell and the traffic type of the terminal (the terminal is a user with a large uplink traffic volume or a user with a large downlink traffic volume).

[0242] In some embodiments, based on the uplink capability and / or downlink capability of the terminal in the neighboring cell and the traffic type of the terminal, selecting a target cell to which the terminal switches includes:

[0243] In the case where the terminal is a user with a large uplink traffic volume, a target cell to which the terminal is switched is selected from a neighboring cell whose corresponding uplink capacity is the largest and whose corresponding uplink capacity is greater than the uplink capacity of the terminal in the source cell; or

[0244] When the terminal is a user with a large downlink traffic volume, a target cell to which the terminal switches is selected from a neighboring cell whose corresponding downlink capacity is the largest and whose corresponding downlink capacity is greater than the downlink capacity of the terminal in the source cell.

[0245] Specifically, when selecting the target cell to which the terminal switches based on the uplink capability and / or downlink capability of the terminal in the neighboring cell and the traffic type of the terminal (the terminal is a user with large uplink traffic or a user with large downlink traffic), the uplink and / or downlink capabilities of the source cell can be determined first.

[0246] In one implementation, when the uplink capability and / or downlink capability of a terminal in a neighboring cell is determined based on the spectrum efficiency parameters of the terminal in the neighboring cell, the uplink and / or downlink capability of the source cell may also be determined based on the spectrum efficiency parameters of the terminal in the source cell.

[0247] For example, the uplink and / or capability on the source cell may be determined by:

[0248] The uplink capacity of the source cell = the uplink spectrum efficiency parameter of the terminal in the source cell * the uplink bandwidth used by the terminal in the source cell.

[0249] The downlink capacity of the source cell = the downlink spectrum efficiency parameter of the terminal in the source cell * the downlink bandwidth used by the terminal in the source cell.

[0250] In one implementation, when the uplink capability and / or downlink capability of a terminal in a neighboring cell is determined based on the user experience parameters of the terminal in the neighboring cell, the uplink and / or downlink capability of the source cell may also be determined based on the user experience parameters of the terminal in the source cell.

[0251] For example, the uplink and / or capability on the source cell may be determined by:

[0252] Uplink capacity on the source cell = uplink rate in the user experience parameters of the terminal on the source cell. The uplink rate in the user experience parameters of the terminal on the source cell may be an average value or a sample value in the most recent unit time.

[0253] Downlink capacity of the source cell = downlink rate in the user experience parameters of the terminal in the source cell. The downlink rate in the user experience parameters of the terminal in the source cell may be an average value or a sample value in the most recent unit time.

[0254] When the terminal is a user with a large uplink traffic volume, the target cell to which the terminal switches can be selected from the neighboring cells whose corresponding uplink capacity is the largest and whose corresponding uplink capacity is greater than the uplink capacity of the terminal in the source cell.

[0255] In one implementation, when there are multiple neighboring cells with the largest uplink capability and the corresponding uplink capability is greater than the uplink capability of the terminal on the source cell, the cell with the largest downlink capability can be selected as the target cell from among these neighboring cells. When there are multiple cells with the largest downlink capability, the neighboring cell with the best at least one of the UE's CQI, uplink MCS Index, downlink MCS Index, and the measurement result of the UE can be selected as the target cell.

[0256] When the terminal is a user with a large downlink traffic volume, a target cell to which the terminal switches is selected from a neighboring cell whose corresponding downlink capacity is the largest and whose corresponding downlink capacity is greater than the downlink capacity of the terminal in the source cell.

[0257] In one implementation, when there are multiple neighboring cells with the largest corresponding downlink capability and whose corresponding downlink capability is greater than the downlink capability of the terminal on the source cell, the cell with the largest uplink capability can be selected as the target cell from among these neighboring cells. When there are multiple cells with the largest uplink capability, the neighboring cell with the best at least one of the CQI, uplink MCS Index, downlink MCS Index, and measurement results of the UE can be selected as the target cell.

[0258] In some embodiments, when the parameter prediction result includes the optimal neighboring cell identifier corresponding to the terminal, the optimal neighboring cell can be directly selected as the target cell to which the terminal switches.

[0259] Figure 3 A second flow chart of a method for selecting a target cell provided in an embodiment of the present application is as follows: Figure 3 As shown, the method is applied to the second network device and includes the following steps:

[0260] Step 300: Receive switching optimization request information sent by the source network device.

[0261] Step 301: Send one or more of the following to the source network device according to the handover optimization request information:

[0262] Sample parameter information used to train parameter prediction models;

[0263] Parameter prediction model;

[0264] Feedback information after the terminal switches to the target cell;

[0265] Parameter prediction results; the parameter prediction results include the performance parameters of the terminal after switching to the neighboring cell and / or the optimal neighboring cell identifier corresponding to the terminal, which are predicted based on the parameter prediction model.

[0266] Specifically, when it is necessary to select a target cell for the terminal to switch to, the second network device may receive the switching optimization request information sent by the source network device.

[0267] The second network device may be any one of a gNB, an eNB, an ng-eNB, an en-gNB, a CU of a gNB, a CUCP of a gNB, a CUUP of a gNB, a DU of a gNB, an RIC, or a newly defined network node. The source network device may be any one of a gNB, an eNB, an ng-eNB, an en-gNB, a CU of a gNB, a CUCP of a gNB, a CUUP of a gNB, an RIC, or a newly defined network node.

[0268] In one implementation, when the parameter prediction model needs to be trained, the second network device may receive the handover optimization request information sent by the source network device, and send sample parameter information to the source network device according to the handover optimization request information. At this time, the second network device may be a network device in a neighboring cell of the source cell.

[0269] In one implementation, when the parameter prediction model is stored in the second network device, the second network device may receive the switching optimization request information sent by the source network device, and send the parameter prediction model to the source network device according to the switching optimization request information.

[0270] The second network device may store a trained parameter prediction model.

[0271] In one implementation, when the target cell is within the jurisdiction of the second network device, the second network device may receive the switching optimization request information sent by the source network device, and send feedback information after the terminal switches to the target cell to the source network device according to the switching optimization request information.

[0272] In one implementation, when the parameter prediction model is stored on the second network device, the second network device may not send the parameter prediction model to the source network device, but may use the parameter prediction model to perform prediction to obtain parameter prediction results. The second network device may receive the switching optimization request information sent by the source network device, and send the parameter prediction results to the source network device according to the switching optimization request information. The second network device may obtain the input parameters of the parameter prediction model from the source network device, or directly obtain the input parameters of the parameter prediction model from the neighboring cell of the source cell, and then obtain the parameter prediction results according to the input parameters of the parameter prediction model, and send the parameter prediction results to the source network device.

[0273] In the method for selecting a target cell provided in an embodiment of the present application, the second network device receives the switching optimization request information sent by the source network device, and sends the sample parameter information, the parameter prediction model, the feedback information after the terminal switches to the target cell, and at least one of the parameter prediction results to the source network device according to the switching optimization request information, so that the source network device can determine the parameter prediction result, and then select the cell with the largest uplink and downlink capabilities as the target cell for the terminal to switch to according to the parameter prediction result, thereby improving user performance.

[0274] In some embodiments, the handover optimization request information may include one or more of the following:

[0275] (1) A cell identifier of a sample source cell, where the cell identifier may be at least one of CGI, PCI, ARFCN, TAC, RANAC and PLMN.

[0276] (2) Cell identifier of the sample neighboring cell, where the cell identifier may be at least one of CGI, PCI, ARFCN, TAC, RANAC and PLMN.

[0277] (3) First indication information, the first indication information is used to indicate the start, update or stop of collecting sample parameter information.

[0278] (4) First cycle information, the first cycle information is used to indicate a cycle for sending sample parameter information to the source network device.

[0279] (5) First direction information, where the first direction information is used to indicate uplink information and / or downlink information in the collected sample parameter information.

[0280] (6) Second indication information: The second indication information is used to indicate the type of sample parameter information to be collected, for example, indicating whether to collect spectrum efficiency parameters and / or whether to collect user experience parameters.

[0281] (7) Data granularity identification. The second network device may collect user experience parameters obtained by measuring data corresponding to the data granularity identification. The data granularity identification may be at least one of a slice identification, a 5QI identification, a QoS flow identification, a PDU session identification, and a UE identification.

[0282] (8) QoS parameter type: The QoS parameter type may be at least one of rate, packet loss rate, retransmission rate, delay, transmission queue length, and packet jitter.

[0283] (9) Service type. The second network device may collect user experience parameters corresponding to the service type. The service type may be at least one of voice, video, and a service type for application layer measurement defined in 3GPP technical specification 38.331 (transmitted using serviceType in the AppLayerMeasConfig field).

[0284] (10) Identification of the sample terminal. The second network device may determine the terminal for which information needs to be collected based on the identification of the sample terminal. The identification of the sample terminal may be an identification of the sample terminal in the neighboring cell and / or the source cell. For example, the identification of the sample terminal may be at least one of Source NG-RAN node UE XnAP ID, Target NG-RAN node UE XnAP ID, gNB-CU UEF1AP ID, gNB-DU UE F1AP ID, RAN UE ID, IMEI, IMSI, GUTI, SUPI, SUCI and RNTI.

[0285] (11) First time length information, the first time length information is used to indicate the time period for collecting sample parameter information.

[0286] (12) Third indication information, where the third indication information is used to indicate starting, updating or stopping sending the parameter prediction model to the source network device.

[0287] (13) Second cycle information, where the second cycle information is used to indicate a cycle for sending the parameter prediction model to the source network device.

[0288] (14) The cell identifier of the source cell, where the cell identifier may be at least one of CGI, PCI, ARFCN, TAC, RANAC and PLMN.

[0289] (15) The cell identifier of the target cell, where the cell identifier may be at least one of CGI, PCI, ARFCN, TAC, RANAC and PLMN.

[0290] (16) Fourth indication information, the fourth indication information is used to indicate starting, updating or stopping collecting feedback information after the terminal switches to the target cell.

[0291] (17) Third cycle information, the third cycle information is used to indicate a cycle for sending feedback information to the source network device.

[0292] (18) Second direction information, where the second direction information is used to indicate the uplink information and / or downlink information in the collected feedback information.

[0293] (19) Fifth indication information: The fifth indication information is used to indicate the type of feedback information to be collected, for example, whether to collect spectrum efficiency parameters and / or whether to collect user experience parameters.

[0294] (20) Terminal identification. The second network device may determine the terminal for which information needs to be collected based on the terminal identification. The terminal identification may be at least one of Source NG-RAN node UE XnAP ID, Target NG-RAN node UE XnAP ID, gNB-CU UE F1AP ID, gNB-DU UE F1AP ID, RAN UE ID, IMEI, IMSI, GUTI, SUPI, SUCI, and RNTI.

[0295] (21) Second time length information, where the second time length information is used to indicate a time period for collecting feedback information.

[0296] (22) Sixth indication information, the sixth indication information is used to indicate that the target cell is predicted and / or the credibility of the parameter prediction result. When the sixth indication information includes the credibility of the parameter prediction result, it can also be determined whether to switch the terminal to the target cell according to the credibility of the parameter prediction result. For example, when the credibility of one or more parameters in the parameter prediction result is less than a preset threshold, the method for selecting a target cell provided in the embodiment of the present application may not be used, but the target cell may be selected according to an existing mechanism.

[0297] In some embodiments, the sample parameter information may include one or more of the following:

[0298] (1) A cell identifier of a sample source cell, where the cell identifier may be at least one of CGI, PCI, ARFCN, TAC, RANAC and PLMN.

[0299] (2) Cell identifier of the sample neighboring cell, where the cell identifier may be at least one of CGI, PCI, ARFCN, TAC, RANAC and PLMN.

[0300] (3) Identification of the serving beam in the sample neighborhood.

[0301] (4) Identification of the serving beam on the sample source cell.

[0302] (5) Sample terminal identification. The terminal identification may be at least one of Source NG-RAN node UE XnAP ID, Target NG-RAN node UE XnAP ID, gNB-CU UE F1AP ID, gNB-DU UE F1AP ID, RAN UE ID, IMEI, IMSI, GUTI, SUPI, SUCI, and RNTI.

[0303] (6) Downlink transmit power of the sample neighboring cell. The transmit power may be the actual transmit power and / or the maximum transmit power.

[0304] (7) Downlink transmit power of the serving beam in the sample neighboring cell. The transmit power may be the actual transmit power and / or the maximum transmit power.

[0305] (8) Downlink transmit power of the sample source cell. The transmit power may be actual transmit power and / or maximum transmit power.

[0306] (9) Downlink transmit power of the serving beam on the sample source cell. The transmit power may be the actual transmit power and / or the maximum transmit power.

[0307] (10) Uplink transmit power of the sample terminal. The transmit power may be actual transmit power and / or maximum transmit power.

[0308] (11) Number of downlink transmit antennas in the sample neighboring cell.

[0309] (12) Number of uplink receiving antennas in the sample neighborhood.

[0310] (13) Number of downlink transmit antennas of the sample source cell.

[0311] (14) Number of uplink receiving antennas of the sample source cell.

[0312] (15) Number of uplink transmit antennas of the sample terminal.

[0313] (16) Number of downlink receiving antennas of the sample terminal.

[0314] (17) The measurement result of at least one cell with a different frequency from the sample source cell reported by the sample terminal.

[0315] (18) The measurement result of at least one cell with the same frequency as the sample source cell reported by the sample terminal.

[0316] (19) The measurement results of the sample terminal measured by the sample neighboring area.

[0317] Among them, the measurement results of the sample neighboring area on the sample terminal may include at least one of the measurement results of the sample neighboring area measuring the SRS of the sample terminal, the measurement results of the sample neighboring area measuring other uplink reference signals of the sample terminal, and the measurement results of the sample neighboring area measuring the NR-U channel used by the sample terminal.

[0318] The above measurement result includes at least one of the following: RSRP, RSRQ, SINR, RSSI and CO measured in the cell.

[0319] In the case where the measurement result includes the CO measured in the cell, the measurement result may also include the EDT.

[0320] (20) The measurement result of the sample source cell on the sample terminal.

[0321] (21) CQI and / or downlink MCS Index of the sample terminal.

[0322] (22) Uplink MCS Index of the sample terminal.

[0323] (23) Load status of the sample neighboring area. The load status may include part or all of the information reported by the Resource Status Reporting process defined in the XnAP protocol in the existing mechanism.

[0324] (24) Load status of the sample source cell.

[0325] (25) Uplink spectrum efficiency parameters and / or downlink spectrum efficiency parameters of the sample terminal in the sample neighboring area.

[0326] (26) The uplink bandwidth and / or downlink bandwidth of the sample terminal in the sample neighborhood.

[0327] (27) User experience parameters of sample terminals in sample neighborhood areas.

[0328] The methods provided in the embodiments of the present application are based on the same application concept, so the implementation of each method can refer to each other, and the repeated parts will not be repeated.

[0329] The following describes the methods provided in the above embodiments of the present application by using examples of specific application scenarios.

[0330] Example 1: Select the target cell to which the terminal switches.

[0331] The third network device predicts the performance parameters of the UE after switching to the neighboring cell based on the data collected in the source cell and / or the data collected in the neighboring cell of the source cell, and selects a suitable neighboring cell as the target cell for switching based on the predicted performance parameters of the UE after switching to the neighboring cell. The third network device may be the same as the base station where the source cell is located, the same as the base station where the neighboring cell is located, or different from both the base station where the source cell is located and the base station where the neighboring cell is located.

[0332] Figure 4 A third flowchart of a method for selecting a target cell provided in an embodiment of the present application is shown in FIG. Figure 4 As shown, the method comprises the following steps:

[0333] 1. Use machine learning methods to train parameter prediction models to predict performance parameters after the UE is connected to the neighboring cell.

[0334] During training, the sample information includes at least one of the following information:

[0335] The cell identifier of the source cell, where the cell identifier may be at least one of CGI, PCI, ARFCN, TAC, RANAC, and PLMN;

[0336] The cell identifier of the sample neighborhood;

[0337] The identifier of the serving beam on the sample neighborhood;

[0338] The identifier of the serving beam on the sample source cell;

[0339] The identity of the sample UE may be an identity of the sample UE in the neighboring cell and / or an identity of the sample UE in the source cell, such as at least one of Source NG-RAN node UE XnAP ID, Target NG-RAN node UE XnAP ID, gNB-CU UE F1APID, gNB-DU UE F1AP ID, RAN UE ID, IMEI, IMSI, GUTI, SUPI, SUCI and RNTI;

[0340] Downlink transmit power of the sample neighboring cells, which may be actual power and / or maximum power;

[0341] The downlink transmission power of the serving beam in the sample neighboring cell, which may be the actual power and / or the maximum power;

[0342] The downlink transmission power of the sample source cell may be actual power and / or maximum power;

[0343] The downlink transmission power of the serving beam on the sample source cell may be the actual power and / or the maximum power;

[0344] The uplink transmit power of the sample UE, which may be actual power and / or maximum power;

[0345] Number of downlink transmit antennas in the sample neighboring cell;

[0346] The number of uplink receiving antennas in the sample neighborhood;

[0347] The number of downlink transmit antennas of the sample source cell;

[0348] The number of uplink receiving antennas of the sample source cell;

[0349] The number of uplink transmit antennas of the sample UE;

[0350] The number of downlink receiving antennas of the sample UE;

[0351] Downlink bandwidth used by the sample UE;

[0352] The uplink bandwidth used by the sample UE;

[0353] The measurement result of at least one cell with a different frequency from the sample source cell reported by the sample UE;

[0354] The measurement result of at least one cell with the same frequency as the sample source cell reported by the sample UE;

[0355] The measurement result of the sample source cell on the sample UE;

[0356] CQI and / or downlink MCS Index of the sample UE;

[0357] Uplink MCS Index of the sample UE;

[0358] Load status of the sample neighborhood;

[0359] The load status of the sample source cell;

[0360] Downlink spectrum efficiency parameters of sample UEs;

[0361] Uplink spectrum efficiency parameters of sample UEs;

[0362] User experience parameters of sample UEs.

[0363] Among them, the measurement results of the sample neighboring cell on the sample UE may include at least one of the measurement results of the sample neighboring cell measuring the SRS of the sample UE, the measurement results of the sample neighboring cell measuring other uplink reference signals of the sample UE, and the measurement results of the sample neighboring cell measuring the NR-U channel used by the sample UE.

[0364] The above measurement result includes at least one of the following: RSRP, RSRQ, SINR, RSSI and CO measured in the cell.

[0365] In the case where the measurement result includes the CO measured in the cell, the measurement result may also include the EDT.

[0366] The load status of the sample neighboring area may include part or all of the information reported by the ResourceStatus Reporting process defined in the XnAP protocol in the existing mechanism.

[0367] The user experience parameter may include at least one of the following information:

[0368] Uplink QoS parameters;

[0369] Downlink QoS parameters;

[0370] QoE parameters.

[0371] The QoS parameters may include at least one of the following information:

[0372] A data granularity identifier, indicating that the remaining QoS parameters are measured based on the data corresponding to the data granularity identifier. The data granularity identifier may be at least one of a slice identifier, a 5QI identifier, a QoS flow identifier, a PDU session identifier, and a UE identifier;

[0373] rate, which may be a rate of different protocol layers, such as at least one of a MAC layer rate, an RLC layer rate, and a PDCP layer rate;

[0374] Packet loss rate, where the packet loss rate may be the number of transmission packet losses or transmission failures per unit time, such as at least one of an RLC layer packet loss rate, a PDCP packet loss rate, and a HARQ transmission failure rate;

[0375] a retransmission rate, where the retransmission rate may be the number of retransmissions per unit time, such as at least one of an RLC layer retransmission rate, a PDCP retransmission rate, and a HARQ retransmission rate;

[0376] Delay, the delay may include at least one of the following: one, multiple, or a sum of multiple components of RAN side delay (RAN part of delay) in 3GPP technical specification 38.314;

[0377] A transmission queue length, where the transmission queue length may be a transmission queue length of different protocol layers, such as an RLC layer transmission queue length and / or a PDCP layer transmission queue length;

[0378] Packet jitter, which may be packet jitter of different protocol layers, such as RLC layer packet jitter and / or PDCP layer packet jitter.

[0379] The QoE parameter may include at least one of the following information:

[0380] Service type, which may be at least one of voice, video, and a service type for application layer measurement defined in 3GPP technical specification 38.331 (transmitted using serviceType in the AppLayerMeasConfig field);

[0381] at least one information in an application layer measurement report, the application layer measurement report being consistent with the application layer measurement report used in 3GPP technical specification 38.331 (delivered using measReportAppLayerContainer);

[0382] At least one information in a RAN visible measurement report, the RAN visible measurement report is consistent with the RAN visible measurement report used in 3GPP technical specification 38.331 (delivered using RAN-VisibleMeasurements).

[0383] The spectrum efficiency parameter may be a spectrum efficiency parameter corresponding to all or part of the resources of the cell, for example, a spectrum efficiency parameter of all bandwidths of the cell, a spectrum efficiency parameter of PDSCH resources, or a spectrum efficiency parameter of PUSCH resources. The method for calculating the spectrum efficiency parameter may be any of the following methods:

[0384] Method 1: Spectral efficiency The parameter is the spectrum efficiency, which is the amount of data that can be transmitted per unit spectrum.

[0385] Method 2: Divide the minimum and maximum values ​​of the spectrum efficiency supported by the cell into multiple intervals, and each interval corresponds to a characterization value. The spectrum efficiency parameter is the characterization value of the interval to which the spectrum efficiency of the UE belongs. The characterization value can be a numerical value, for example, the score corresponding to the interval when the maximum value is 100 points and the minimum value is 0 points, the number of the interval, the maximum value, minimum value, median or average value of the spectrum efficiency in the interval, or an indication information, for example, indicating that the spectrum efficiency is high, medium or low.

[0386] Method 3: UEs with similar uplink and / or downlink signal receiving and transmitting states in the cell are divided into different groups. For example, if UE1 and UE2 have multiple identical neighboring cells and the mean square error of the uplink and / or downlink signal measurements of the two UEs in all identical neighboring cells is less than a preset threshold, UE1 and UE2 are divided into the same group. The spectrum efficiency parameter is the maximum, minimum, median or average value of the spectrum efficiency of all UEs in the group to which the UE belongs.

[0387] Machine learning methods may include, but are not limited to, reinforcement learning.

[0388] The parameter prediction model may be trained on a third network device.

[0389] The source cell and / or the neighboring cell sends the collected sample information to the third network device according to the request of the third network device.

[0390] The third network device sends handover optimization request information to the source cell and / or the neighboring cell, where the handover optimization request information includes at least one of the following information:

[0391] The cell identifier of the sample source cell;

[0392] The cell identifier of the sample neighborhood;

[0393] First indication information, the first indication information is used to indicate starting, updating or stopping collecting sample parameter information;

[0394] First cycle information, where the first cycle information is used to indicate a cycle for sending sample parameter information to the source network device;

[0395] First direction information, where the first direction information is used to indicate uplink information and / or downlink information in the collected sample parameter information;

[0396] Second indication information, where the second indication information is used to indicate the type of sample parameter information that needs to be collected;

[0397] Data granularity identification;

[0398] Quality of service QoS parameter type;

[0399] Type of business;

[0400] The identification of the sample terminal;

[0401] First time length information, the first time length information is used to indicate a time period for collecting sample parameter information;

[0402] third indication information, where the third indication information is used to indicate starting, updating or stopping sending the parameter prediction model to the source network device;

[0403] Second cycle information, where the second cycle information is used to indicate a cycle for sending the parameter prediction model to the source network device;

[0404] The cell identifier of the source cell;

[0405] The cell identifier of the target cell;

[0406] Fourth indication information, the fourth indication information is used to indicate starting, updating or stopping collecting feedback information after the terminal switches to the target cell;

[0407] third cycle information, where the third cycle information is used to indicate a cycle for sending feedback information to the source network device;

[0408] Second direction information, where the second direction information is used to indicate the uplink information and / or downlink information in the collected feedback information;

[0409] Fifth indication information, where the fifth indication information is used to indicate the type of feedback information that needs to be collected;

[0410] The terminal's identification;

[0411] Second time length information, where the second time length information is used to indicate a time period for collecting feedback information;

[0412] Sixth indication information: the sixth indication information is used to indicate that the target cell is predicted and / or the credibility of the parameter prediction result.

[0413] The source cell and / or the neighboring cell sends the collected sample information to the third network device according to the handover optimization request information.

[0414] The input parameters of the parametric prediction model include one or more of the following:

[0415] Neighboring cell ID;

[0416] The identifier of the serving beam in the neighboring cell;

[0417] The cell identifier of the source cell;

[0418] The identifier of the serving beam on the source cell;

[0419] The terminal's identification;

[0420] Downlink transmission power of neighboring cells;

[0421] Downlink transmit power of the serving beam in the neighboring cell;

[0422] Downlink transmit power of the source cell;

[0423] Downlink transmit power of the serving beam on the source cell;

[0424] The uplink transmit power of the terminal;

[0425] Number of downlink transmit antennas in the neighboring cell;

[0426] Number of uplink receiving antennas in the neighboring cell;

[0427] The number of downlink transmit antennas of the source cell;

[0428] The number of uplink receiving antennas of the source cell;

[0429] The number of uplink transmit antennas of the terminal;

[0430] The number of downlink receiving antennas of the terminal;

[0431] The effective uplink bandwidth of the terminal in the neighboring cell;

[0432] The effective downlink bandwidth of the terminal in the neighboring cell;

[0433] Uplink idle bandwidth of neighboring cells;

[0434] Downlink idle bandwidth of neighboring cells;

[0435] The measurement result of at least one cell with a different frequency from the source cell reported by the terminal;

[0436] The measurement result of at least one cell with the same frequency as the source cell reported by the terminal;

[0437] The measurement result of the source cell on the terminal;

[0438] Load status of neighboring cells;

[0439] The load status of the source cell. The uplink or downlink effective bandwidth of the neighboring cell can be estimated. The following is an estimation algorithm:

[0440] (1) Obtain the uplink and downlink resource status of the neighboring cell, which includes PRB utilization and idle bandwidth.

[0441] (2) Calculate the uplink and downlink rates of the UE. If the uplink rate is greater than a preset threshold, the UE is judged to be an uplink heavy traffic user; if the downlink rate is greater than the preset threshold, the UE is judged to be a downlink heavy traffic user; in other cases, the UE is judged to be a non-heavy traffic user. When both the uplink rate and the downlink rate of the UE are greater than the preset threshold, the UE can be judged to be an uplink heavy traffic user or a downlink heavy traffic user according to the preset rule. For example, when both the uplink rate and the downlink rate of the UE are greater than the preset threshold, the UE is judged to be an uplink heavy traffic user; or, when both the uplink rate and the downlink rate of the UE are greater than the preset threshold, the UE is judged to be a downlink heavy traffic user.

[0442] (3) If the UE is a user with a large uplink traffic volume, compare the uplink idle bandwidth of the neighboring cell and the maximum uplink bandwidth supported by the UE, and take the smaller value as the uplink effective bandwidth. When the uplink idle bandwidth of the neighboring cell is large, in order to avoid distortion in the estimation of the uplink effective bandwidth, if the uplink PRB utilization rate of the neighboring cell is higher than the preset threshold or the number of active users is higher than the preset threshold, the uplink effective bandwidth remains unchanged; otherwise, the uplink effective bandwidth = uplink effective bandwidth / (number of active users in the candidate target cell + 1). The number of active users refers to users with uplink data or downlink data transmission. The final uplink effective bandwidth is used as the uplink effective bandwidth of the neighboring cell available to the UE, and the estimation process is exited.

[0443] (4) If the UE is a user with a large downlink traffic volume, compare the downlink idle bandwidth of the neighboring cell and the maximum downlink bandwidth supported by the UE, and take the smaller value as the downlink effective bandwidth. When the downlink idle bandwidth of the neighboring cell is large, in order to avoid distortion in the estimation of the downlink effective bandwidth, if the downlink PRB utilization rate of the neighboring cell is higher than the preset threshold or the number of active users is higher than the preset threshold, the downlink effective bandwidth remains unchanged; otherwise, the downlink effective bandwidth = downlink effective bandwidth / (number of active users in the candidate target cell + 1). The number of active users refers to users with uplink data or downlink data transmission. The final downlink effective bandwidth is used as the downlink effective bandwidth of the neighboring cell available to the UE, and the estimation process is exited.

[0444] The parameter prediction results include one or more of the following:

[0445] The measurement results of the neighboring cell on the terminal;

[0446] The CQI and / or downlink MCS Index of the terminal;

[0447] Uplink MCS Index of the terminal;

[0448] Downlink spectrum efficiency parameters of the terminal in the neighboring cell;

[0449] Uplink spectrum efficiency parameters of the terminal in the neighboring cell;

[0450] User experience parameters of the terminal in the neighboring area;

[0451] Neighboring cell ID;

[0452] The credibility of parameter prediction results;

[0453] The cell identifier of the best neighboring cell.

[0454] The parameter prediction result is a prediction of some performance parameters assuming that the UE is connected to a neighboring cell.

[0455] During the training process, a portion of sample information can be selected as feedback information of the model prediction results and input into the model, for example, as a reward parameter of reinforcement learning to help improve the prediction accuracy of the parameter prediction model.

[0456] The source cell can obtain the parameter prediction result in any of the following two ways.

[0457] Method 1:

[0458] The source cell sends a handover optimization request message to the neighboring cell, and the neighboring cell sends the collected sample information to the source cell according to the handover optimization request message. The source cell generates input parameters of the parameter prediction model according to one or more of the received sample information and its own collected information (for example, the measurement result of at least one cell with the same frequency point as the source cell reported by the UE).

[0459] The source cell sends a first message to the third network device, where the first message includes input parameters of the parameter prediction model.

[0460] The third network device uses the parameter prediction model to infer the parameter prediction result according to the input parameters of the parameter prediction model.

[0461] The third network device sends a second message to the source cell, where the second message includes the parameter prediction result.

[0462] Method 2:

[0463] The source cell sends a third message to the third network device, where the third message includes at least one of the following information:

[0464] third indication information, where the third indication information is used to indicate starting, updating or stopping sending the parameter prediction model to the source network device;

[0465] The second cycle information is used to indicate a cycle for sending the parameter prediction model to the source network device.

[0466] The third network device sends a fourth message to the source cell according to the third message, where the fourth message includes a parameter prediction model.

[0467] The source cell generates input parameters of the parameter prediction model according to the method in the first approach.

[0468] The source cell uses the parameter prediction model to infer parameter prediction results according to the input parameters of the parameter prediction model.

[0469] 2. The source cell selects the UE to be handed over. The selection conditions include: the signal strength of the source cell measured by the UE is less than a preset threshold, the UE is judged to have a large uplink traffic volume or a large downlink traffic volume, or a UE that needs to be handed over in other existing mechanisms.

[0470] The source cell can select one or more neighboring cells with good enough signals according to the existing mechanism. If there is only one neighboring cell selected, this cell is used as the target cell and the handover is performed; otherwise, the subsequent process is performed.

[0471] 3. If the source cell selects multiple neighboring cells with good enough signals, the source cell also needs to determine the target cell based on the uplink and downlink capabilities. After the target cell is selected, the handover is performed.

[0472] The source cell can estimate the uplink and downlink capabilities of the neighboring cells based on the parameter prediction results.

[0473] Figure 5 A schematic diagram of a process for estimating the uplink and downlink capabilities of a neighboring cell and selecting a target cell according to a parameter prediction result provided in an embodiment of the present application, such as Figure 5 As shown, the method comprises the following steps:

[0474] A. Estimate the uplink capacity and / or downlink capacity of each neighboring cell based on the parameter prediction results.

[0475] If the parameter prediction result includes the UE's downlink spectrum efficiency parameter and / or the UE's uplink spectrum efficiency parameter, the uplink capacity and / or downlink capacity of each neighboring cell is estimated according to the following method:

[0476] Select each neighboring cell in turn, and estimate the uplink capability and / or downlink capability of the UE in this neighboring cell.

[0477] The uplink capability of the terminal in the neighboring cell = the uplink spectrum efficiency parameter of the terminal in the neighboring cell * the uplink effective bandwidth of the terminal in the neighboring cell.

[0478] The downlink capability of the terminal in the neighboring cell = the downlink spectrum efficiency parameter of the terminal in the neighboring cell * the downlink effective bandwidth of the terminal in the neighboring cell.

[0479] If the parameter prediction result includes the UE user experience parameter, the uplink capacity and / or downlink capacity of each neighboring cell is estimated according to the following method:

[0480] Select each neighboring cell in turn, and estimate the uplink capability and / or downlink capability of the UE in this neighboring cell.

[0481] The uplink capability of the terminal in the neighboring cell = the uplink rate in the user experience parameters of the terminal in the neighboring cell.

[0482] The downlink capability of the terminal in the neighboring cell = the downlink rate in the user experience parameters of the terminal in the neighboring cell.

[0483] B. Select the cell with the largest uplink and / or downlink capacity among all neighboring cells.

[0484] C. Estimate the uplink capability and / or downlink capability of the UE on the source cell.

[0485] When the uplink capability and / or downlink capability of the terminal in the neighboring cell is determined based on the spectrum efficiency parameter of the terminal in the neighboring cell, the uplink and / or downlink capability of the source cell may also be determined according to the spectrum efficiency parameter of the terminal in the source cell.

[0486] For example, the uplink and / or capability on the source cell may be determined by:

[0487] The uplink capacity of the source cell = the uplink spectrum efficiency parameter of the terminal in the source cell * the uplink bandwidth used by the terminal in the source cell.

[0488] The downlink capacity of the source cell = the downlink spectrum efficiency parameter of the terminal in the source cell * the downlink bandwidth used by the terminal in the source cell.

[0489] When the uplink capability and / or downlink capability of the terminal in the neighboring cell is determined based on the user experience parameters of the terminal in the neighboring cell, the uplink and / or downlink capability of the source cell may also be determined according to the user experience parameters of the terminal in the source cell.

[0490] For example, the uplink and / or capability on the source cell may be determined by:

[0491] Uplink capacity on the source cell = uplink rate in the user experience parameters of the terminal on the source cell. The uplink rate in the user experience parameters of the terminal on the source cell may be an average value or a sample value in the most recent unit time.

[0492] Downlink capacity of the source cell = downlink rate in the user experience parameters of the terminal in the source cell. The downlink rate in the user experience parameters of the terminal in the source cell may be an average value or a sample value in the most recent unit time.

[0493] The calculation method of the spectrum efficiency parameter of the source cell is the same as the calculation method of the spectrum efficiency parameter in the sample information.

[0494] D. If the UE is a user with a large uplink traffic volume, select the cell with the largest uplink capability in the neighboring cell and greater than the uplink capability of the source cell. If there is more than one, select the cell with the largest downlink capability in the remaining neighboring cells. If there is more than one, consider the cell with the best CQI, uplink MCS Index, downlink MCS Index of the UE in the remaining neighboring cells, and at least one of the measurement results of the UE measured; If the UE is a user with a large downlink traffic volume, select the cell with the largest downlink capability in the neighboring cell and greater than the downlink capability of the source cell. If there is more than one, select the cell with the largest uplink capability in the remaining neighboring cells. If there is more than one, consider the cell with the best CQI, uplink MCS Index, downlink MCS Index of the UE in the remaining neighboring cells, and at least one of the measurement results of the UE measured.

[0495] In other cases, select the cell selected in step B.

[0496] The selected cell is used as the target cell and handover is performed.

[0497] E. If the parameter prediction model is trained in the source cell, the source cell may request the target cell to send feedback information. The feedback information may include one or more of the following:

[0498] The identifier of the target cell;

[0499] The measurement result of the target cell on the terminal;

[0500] The identifier of the serving beam on the target cell;

[0501] The CQI and / or downlink MCS Index of the terminal;

[0502] Uplink MCS Index of the terminal;

[0503] Downlink spectrum efficiency parameters of the terminal in the target cell;

[0504] Uplink spectrum efficiency parameters of the terminal in the target cell;

[0505] User experience parameters of the terminal in the target cell.

[0506] F. The source cell optimizes the parameter prediction model according to the feedback information, for example, by using the feedback information as a reward parameter input of the parameter prediction model to improve the prediction accuracy of the parameter prediction model.

[0507] Steps EF are not necessary.

[0508] The credibility of parameter prediction may be considered in the process of selecting the target cell. For example, if the credibility of one or more output parameters in the parameter prediction result is less than a preset threshold, the method is exited and the target cell is determined according to the existing mechanism.

[0509] If the parameter prediction result includes the optimal neighboring cell identifier corresponding to the terminal, steps AD are ignored, the optimal neighboring cell is used as the target cell, and the handover is performed. Then, the remaining steps are performed according to the actual situation.

[0510] Example 2: Node 1 sends a switching optimization request message to Node 2, and Node 2 sends a message to Node 1 according to the switching optimization request message.

[0511] Node 1 can be any one of gNB, eNB, ng-eNB, en-gNB, CU of gNB, CUCP of gNB, CUUP of gNB, DU of gNB, RIC, or a newly defined network node. Node 2 can be any one of gNB, eNB, ng-eNB, en-gNB, CU of gNB, CUCP of gNB, CUUP of gNB, DU of gNB, RIC, or a newly defined network node.

[0512] Figure 6 A schematic diagram of a process in which node 1 sends a switching optimization request message to node 2 to obtain information provided in an embodiment of the present application, such as Figure 6 As shown, the process includes the following steps:

[0513] 1. Node 1 sends message 1 to node 2. Message 1 includes switching optimization request information.

[0514] Among them, message one can be an Xn interface message, an X2 interface message, an F1 interface message, an E1 interface message or a message supported by RIC.

[0515] If the message one is an Xn interface message, the Xn interface message may be at least one of RESOURCE STATUS REQUEST, HANDOVER REQUEST, NG-RAN NODE CONFIGURATION UPDATE, and a newly defined Xn interface message (eg, AI / ML INFORMATION REQUEST).

[0516] If the first message is an X2 interface message, the X2 interface message may be at least one of RESOURCE STATUS REQUEST, HANDOVER REQUEST, ENB CONFIGURATION UPDATE, and a newly defined X2 interface message.

[0517] If the message one is an F1 interface message, the F1 interface message may be at least one of RESOURCE STATUS REQUEST, UECONTEXT SETUP REQUEST, UE CONTEXT SETUP REQUEST, UE CONTEXT MODIFICATION REQUEST, GNB-CU CONFIGURATION UPDATE, and a newly defined F1 interface message.

[0518] If the message one is an E1 interface message, the E1 interface message may be at least one of RESOURCE STATUS REQUEST, GNB-CU-CP CONFIGURATION UPDATE, BEARER CONTEXT SETUP REQUEST, BEARER CONTEXT MODIFICATION REQUEST, and a newly defined E1 interface message.

[0519] Node 2 generates the information required by node 1 according to the switching optimization request information.

[0520] For example, the node 1 includes indication information of starting or updating collection of sample information of the sample neighboring area in the handover optimization request information, and:

[0521] If the direction information of the downlink related information in the collected sample information and the indication information of the collected spectrum efficiency parameter are included, the node 2 starts to collect the sample information related to the downlink. For example, the information may include at least one of the following information:

[0522] Downlink transmit power of the sample neighboring cells, which may be actual power and / or maximum power;

[0523] The downlink transmission power of the serving beam in the sample neighboring cell, which may be the actual power and / or the maximum power;

[0524] Number of downlink transmit antennas in the sample neighboring cell;

[0525] The downlink transmission power of the sample source cell may be actual power and / or maximum power;

[0526] The downlink transmission power of the serving beam on the sample source cell may be the actual power and / or the maximum power;

[0527] The number of downlink transmit antennas of the sample source cell;

[0528] The number of downlink receiving antennas of the sample UE;

[0529] Downlink bandwidth used by the sample UE;

[0530] The measurement result of at least one cell with the same frequency as the sample source cell reported by the sample UE;

[0531] The measurement result of at least one cell with a different frequency from the sample source cell reported by the sample UE;

[0532] CQI and / or downlink MCS Index of the sample UE;

[0533] Load status of the sample neighborhood;

[0534] The load status of the sample source cell;

[0535] Downlink spectrum efficiency parameters of sample UE.

[0536] If the direction information of the uplink related information in the collected sample information and the indication information of collecting the spectrum efficiency parameter are included, the node 2 starts to collect the sample information related to the uplink. For example, the information may include at least one of the following information:

[0537] The uplink transmit power of the sample UE, which may be actual power and / or maximum power;

[0538] The number of uplink receiving antennas in the sample neighborhood;

[0539] The uplink transmit power of the sample source cell, which may be actual power and / or maximum power;

[0540] The number of uplink receiving antennas of the sample source cell;

[0541] The number of uplink transmit antennas of the sample UE;

[0542] The uplink bandwidth used by the sample UE;

[0543] The measurement result of at least one cell with the same frequency as the sample source cell reported by the sample UE;

[0544] The measurement result of at least one cell with a different frequency from the sample source cell reported by the sample UE;

[0545] The measurement result of the sample neighboring cell on the sample UE;

[0546] The measurement result of the sample source cell on the sample UE;

[0547] Uplink MCS Index of the sample UE;

[0548] Load status of the sample neighborhood;

[0549] The load status of the sample source cell;

[0550] Uplink spectrum efficiency parameters of sample UEs.

[0551] If the indication information for collecting user experience parameters is included, and the data granularity identifier and / or the QoS parameter type are included, for example, the data granularity identifier including the 5QI identifier of 1 and the QoS parameter type of the rate value are included, the node 2 starts to collect the user experience parameters. For example, the information may include at least one of the following information:

[0552] Uplink QoS parameters;

[0553] Downstream QoS parameters.

[0554] The QoS parameter includes at least one of the following information:

[0555] Data granularity identifier, for example, 5QI identifier is 1;

[0556] Rate, for example, the rate of data with a 5QI identifier of 1.

[0557] If the indication information for collecting the user experience parameter is included and the service type is included, for example, the service type having a value of streaming is included, the node 2 selects a UE, for example, a UE configured with an application layer measurement report corresponding to the service type, and starts collecting the user experience parameter. For example, the information may include at least one of the following information:

[0558] QoE parameters.

[0559] The QoE parameter includes at least one of the following information:

[0560] Business type, for example, the value is streaming;

[0561] At least one piece of information in the application layer measurement report of the corresponding service, such as Initial Playout Delay and / or Buffer Level.

[0562] At least one information in the RAN visible measurement report corresponding to the service, such as initialPlayoutDelay.

[0563] 2. Node 2 sends message 2 to node 1.

[0564] The second message may be an Xn interface message, an X2 message, an F1 interface message, an E1 interface message or a message supported by RIC.

[0565] If message two is an Xn interface message, the Xn interface message may be at least one of RESOURCE STATUS UPDATE, RESOURCE STATUS RESPONSE, HANDOVER REPORT, ACCESS AND MOBILITY INDICATION, NG-RAN NODE CONFIGURATION UPDATE ACKNOWLEDGE, ENB CONFIGURATION UPDATEACKNOWLEDGE, XN SETUP REQUEST, XN SETUP RESPONSE and a newly defined Xn interface message (e.g., AI / MLINFORMATION UPDATE).

[0566] If the second message is an X2 interface message, the X2 interface message may be at least one of RESOURCE STATUS RESPONSE, RESOURCE STATUS UPDATE, HANDOVER REPORT, and a newly defined X2 interface message.

[0567] If message two is an F1 interface message, the F1 interface message may be at least one of RESOURCE STATUS RESPONSE, RESOURCE STATUS UPDATE, ACCESS AND MOBILITY INDICATION, GNB-DU CONFIGURATION UPDATE, GNB-CU CONFIGURATION UPDATE ACKNOWLEDGE, F1 SETUP REQUEST, UE CONTEXT SETUP RESPONSE, UE CONTEXT MODIFICATION RESPONSE and a newly defined F1 interface message.

[0568] If message two is an E1 interface message, the E1 interface message may be at least one of RESOURCE STATUS RESPONSE, RESOURCE STATUS UPDATE, GNB-CU-UP CONFIGURATION UPDATE ACKNOWLEDGE, BEARERCONTEXT SETUP RESPONSE, BEARER CONTEXT MODIFICATION RESPONSE, GNB-CU-CPMEASUREMENT RESULTS INFORMATION, BEARER CONTEXT MODIFICATION REQUIRED and a newly defined F1 interface message.

[0569] In one example, node one includes indication information of the start or update of sample collection in the cell in the switching optimization request information, and includes first cycle information, message two includes sample information collected by node two, and message two is periodically sent to node one according to the indication of the first cycle information.

[0570] Example 3: gNB1 requires gNB2 to provide sample information.

[0571] Among them, gNB2 consists of gNB-CUCP2, gNB-CUUP2 and gNB-DU2.

[0572] Figure 7 A flow chart of gNB1 requiring gNB2 to provide sample information provided in an embodiment of the present application, such as Figure 7 As shown, the process includes the following steps:

[0573] 1. gNB-DU2 sends an F1 SETUP REQUEST message to gNB-CUCP2, including at least one of the following information:

[0574] The cell identifier of the managed cell;

[0575] The identifier of the serving beam on the managed cell;

[0576] The maximum downlink transmit power of the managed cell;

[0577] The maximum downlink transmit power of the service beam in the managed cell;

[0578] The number of downlink transmit antennas of the managed cell;

[0579] The number of uplink receive antennas of the managed cell.

[0580] 2. gNB-CUCP2 sends an F1 message setup request response (F1SETUP RESPONSE) to gNB-DU2.

[0581] Through steps 1-2, gNB-CUCP2 obtains the downlink transmission power information and / or antenna information of the beam of the cell managed by gNB-DU2.

[0582] The information received by gNB-CUCP2 can be sent to gNB1 using an Xn message, such as NG-RAN NODE CONFIGURATION UPDATE, or can be sent to gNB1 in step 11 as part of sample information.

[0583] 3. gNB1 finds that there is a neighboring cell of the cell on gNB1 on gNB2. If the cell on gNB1 is used as the source cell for handover, the neighboring cell may become the target cell. gNB1 decides to train the parameter prediction model. gNB1 requires gNB2 to report sample information.

[0584] gNB1 sends an Xn message RESOURCE STATUS REQUEST to gNB-CUCP2, including handover optimization request information, including the cell ID of the source cell and the cell ID of the neighboring cell. The handover optimization request information may also include at least one of the other information in the handover optimization request information.

[0585] The sample UE can be selected by gNB-CUCP2, gNB-DU2, or gNB-CUUP2.

[0586] If gNB-CUCP2 selects a sample UE, when selecting, priority is given to UEs that can receive the source cell signal in the neighboring cell. In addition, if the switching optimization request information includes a data granularity identifier and / or a service type, priority is given to UEs that are transmitting data corresponding to the data granularity identifier and / or service type, and / or UEs that have been configured with application layer measurements corresponding to the same service type.

[0587] 4. gNB-CUCP2 sends an F1 message RESOURCE STATUS REQUEST to gNB-DU2, including at least one of the handover optimization request information in step 3, and if gNB-CUCP2 selects a sample UE, also includes the UE identifier of the sample UE.

[0588] 5. gNB-DU2 sends an F1 message RESOURCE STATUS RESPONSE to gNB-CUCP2. If gNB-DU2 selects a sample UE, it also includes the UE identity of the sample UE.

[0589] 6. gNB-CUCP2 sends an E1 message RESOURCE STATUS REQUEST to gNB-CUUP2, including at least one of the handover optimization request information in step 3, and if gNB-CUCP2 selects a sample UE, also includes the UE identifier of the sample UE.

[0590] 7. gNB-CUUP2 sends an F1 message RESOURCE STATUS RESPONSE to gNB-CUCP2, including the UE identity of the sample UE if gNB-CUUP2 selected the sample UE.

[0591] 8. gNB-CUCP2 sends an Xn message RESOURCE STATUS RESPONSE to gNB1.

[0592] gNB-CUCP2 may use the F1 message RESOURCE STATUS REQUEST to notify gNB-DU2 to update the handover optimization request information, and / or use the E1 message RESOURCE STATUS REQUEST to notify gNB-CUUP2 to update the handover optimization request information. For example, if the sample UE selected by gNB-CUUP2 and / or gNB-DU2 is different from the sample UE selected by gNB-CUCP2, gNB-CUCP2 notifies gNB-CUUP2 and / or gNB-DU2 to update the sample UE.

[0593] Through the above steps, gNB-CUCP2 determines the selected sample UE. According to the existing mechanism, gNB-CUCP2 configures the measurement of the frequency point of the source cell and / or the frequency point of the neighboring cell for the selected sample UE and obtains the corresponding measurement report.

[0594] If the handover optimization request information received by gNB-DU2 includes indication information for starting or updating sample information collection, gNB-DU2 collects sample information of the sample UE according to the handover optimization request information. For example, the handover optimization request information includes indication information for collecting spectrum efficiency parameters, and gNB-DU2 collects spectrum efficiency parameters of the sample UE.

[0595] 9. gNB-DU2 sends an F1 message RESOURCE STATUS UPDATE to gNB-CUCP2 according to the requirements of the handover optimization request information, for example, according to the first cycle information, including the sample information collected by gNB-DU2, where the identifier of the sample UE is used by gNB-CUCP2 to find the corresponding UE context.

[0596] If the handover optimization request information received by gNB-CUUP2 includes indication information for starting or updating sample information collection, gNB-CUUP2 collects sample information of the sample UE according to the handover optimization request information. For example, the handover optimization request information includes indication information for collecting user experience parameters, and gNB-CUUP2 collects user experience parameters of the sample UE on gNB-CUUP2.

[0597] 10. According to the requirements of the handover optimization request information, for example, according to the first cycle information, gNB-CUUP2 sends an E1 message RESOURCE STATUS UPDATE to gNB-CUCP2, including the sample information collected by gNB-CUUP2, wherein the identifier of the sample UE is used by gNB-CUCP2 to find the corresponding UE context.

[0598] 11. If the handover optimization request information received by gNB-CUCP2 includes indication information for starting or updating sample information collection, gNB-CUCP2 sends an Xn message resource status update (RESOURCE STATUS UPDATE) to gNB1 according to the requirements of the handover optimization request information, for example, according to the first cycle information, including the sample information collected by gNB2.

[0599] Through the above steps, gNB1 can obtain the sample information collected by gNB2 and train the parameter prediction model.

[0600] 12. gNB1 sends an Xn message RESOURCE STATUS REQUEST to gNB-CUCP2, including handover optimization request information, including an instruction to stop collecting sample information.

[0601] 13. gNB-CUCP2 sends an F1 message RESOURCE STATUS REQUEST to gNB-DU2, including handover optimization request information, including an instruction to stop collecting sample information.

[0602] 14. gNB-DU2 sends F1 message RESOURCE STATUS RESPONSE to gNB-CUCP2. gNB-DU2 stops collecting sample information.

[0603] 15. gNB-CUCP2 sends an E1 message RESOURCE STATUS REQUEST to gNB-CUUP2, including handover optimization request information, including instruction information to stop collecting sample information.

[0604] 16. gNB-CUUP2 sends an E1 message RESOURCE STATUS RESPONSE to gNB-CUCP2. gNB-CUUP2 stops collecting sample information.

[0605] 17. gNB-CUCP2 sends an Xn message RESOURCE STATUS RESPONSE to gNB1.

[0606] gNB1 can use the parameter prediction model to select a suitable target cell for the UE, optimize the performance of the UE after switching to the greatest extent, and improve the user experience.

[0607] In this example, the order of messages can be Figure 7 Different than shown.

[0608] Example 4: gNB3 uses the parameter prediction model to select a target cell for the UE.

[0609] The source cell of the UE is on gNB3, and the target cell is on gNB4. gNB3 consists of gNB-CUCP3, gNB-CUUP3, and gNB-DU3, and gNB4 consists of gNB-CUCP4, gNB-CUUP4, and gNB-DU4.

[0610] Figure 8 A schematic diagram of a process for gNB3 to select a target cell for a UE using a parameter prediction model provided in an embodiment of the present application, such as Figure 8As shown, the process includes the following steps:

[0611] The source cell determines that the UE needs to be handed over to another cell.

[0612] 1. gNB-CUCP3 sends an F1 message RESOURCE STATUS REQUEST to gNB-DU3, including handover optimization request information. The information includes the UE identifier and indication information for collecting user experience parameters.

[0613] 2. gNB-DU3 sends F1 message RESOURCE STATUS RESPONSE to gNB-CUCP3.

[0614] 3. gNB-DU3 collects sample information according to the handover optimization request information. gNB-DU3 sends an F1 message RESOURCE STATUS UPDATE to gNB-CUCP3, including the collected sample information. The sample information includes the user experience parameters collected by gNB-DU3.

[0615] 4. gNB-CUCP3 sends an E1 message RESOURCE STATUS REQUEST to gNB-CUUP3, including handover optimization request information. The information includes UE identification and indication information for collecting user experience parameters.

[0616] 5. gNB-CUUP3 sends an E1 message RESOURCE STATUS RESPONSE to gNB-CUCP3.

[0617] 6. gNB-CUUP3 collects sample information according to the handover optimization request information. gNB-CUUP3 sends an E1 message RESOURCE STATUS UPDATE to gNB-CUCP3, including the collected sample information. The sample information includes the user experience parameters collected by gNB-CUUP3.

[0618] Through steps 1-6, gNB-CUCP3 obtains the user experience parameters of the UE in the source cell. Steps 1-6 are not mandatory.

[0619] 7. gNB-CUCP3 obtains the measurement results of the UE and determines the candidate target cell based on the measurement results.

[0620] 8. gNB-CUCP3 obtains sample information of neighboring cells. gNB-CUCP3 uses information in the sample information and / or information obtained by gNB-CUCP3, such as at least one of the UE's intra-frequency measurement results, inter-frequency measurement results, and user experience parameters of the UE in the source cell, as input parameters of the parameter prediction model, and infers the parameter prediction results.

[0621] 9. gNB-CUCP3 determines the target cell based on the parameter prediction results.

[0622] 10. gNB-CUCP3 sends an Xn message HANDOVER REQUEST to gNB-CUCP4, including handover optimization request information. The handover optimization request information includes at least one of the following information:

[0623] The cell identifier of the source cell;

[0624] The cell identifier of the candidate target cell;

[0625] UE identification;

[0626] Indication information, indicating the collection of spectrum efficiency parameters and / or the collection of user experience parameters;

[0627] Time length, collecting sample information within a time period specified by the time length after receiving the switching optimization request information;

[0628] Indication information, indicating that the target cell is predicted, and / or including the credibility of the prediction, wherein the prediction may be a prediction of a user experience parameter on the target cell and / or a prediction of the target cell;

[0629] Switch any one or more of the other information in the optimization request information.

[0630] If the target cell in the Xn message HANDOVER REQUEST received by gNB-CUCP4 is selected based on the predicted user experience parameters on the target cell and / or the target cell is predicted and includes the credibility of the prediction, gNB-CUCP4 can decide whether to accept the handover based on the credibility. For example, when the credibility is lower than the preset threshold value, gNB-CUCP4 rejects the handover.

[0631] 11. gNB-CUCP4 sends an E1 message BEARER CONTEXT SETUP REQUEST to gNB-CUUP4, including at least one of the received handover optimization request messages.

[0632] 12. gNB-CUUP4 sends an E1 message BEARER CONTEXTSETUP RESPONSE to gNB-CUCP4.

[0633] 13. gNB-CUCP4 sends an F1 message UE CONTEXT SETUP REQUEST to gNB-DU4, including at least one of the received handover optimization request messages.

[0634] 14. gNB-DU4 sends F1 message UE CONTEXT SETUP RESPONSE to gNB-CUCP4.

[0635] 15. gNB-CUCP4 sends an Xn message HANDOVER REQUESTACKNOWLEDGE to gNB-CUCP3.

[0636] gNB-CUUP4 collects sample information of the UE based on the received switching optimization request information. For example, if the switching optimization request information includes indication information and time length for collecting user experience parameters, gNB-CUUP4 collects the user experience parameters of the UE within the time length.

[0637] 16. gNB-CUUP4 sends an E1 message base station centralized unit control plane measurement result information (GNB-CU-CP MEASUREMENT RESULTS INFORMATION) to gNB-CUCP4, including the sample information of the UE collected by gNB-CUUP4.

[0638] gNB-DU4 collects sample information of the UE based on the received switching optimization request information. For example, if the switching optimization request information includes indication information and time length for collecting spectrum efficiency parameters, gNB-CUUP4 collects the spectrum efficiency parameters of the UE within the time length.

[0639] 17. gNB-DU4 sends an F1 message ACCESS AND MOBILITY INDICATION to gNB-CUCP4, including the sample information of the UE collected by gNB-DU4.

[0640] 18. gNB-CUCP4 sends an Xn message access and mobility indication (ACCESS AND MOBILITY INDICATION) to gNB-CUCP3, including the sample information of the UE collected by gNB4.

[0641] According to the above steps, gNB3 obtains sample information of the UE after switching to the target cell selected according to the parameter prediction model, such as the spectrum efficiency parameter and / or user experience parameter of the UE when switching to the target cell. The sample information reflects the changes of some performance parameters of the UE when switching to the target cell, such as the improvement or deterioration of the spectrum efficiency, or the improvement or deterioration of the user experience.

[0642] gNB3 can use the information in the sample information as feedback parameters of the parameter prediction model to help improve the accuracy of the parameter prediction model. In this way, in the subsequent handover process, the source cell can select the optimal target cell to ensure that the user gets the best user experience, thereby improving the performance of the entire network.

[0643] In this example, the order of messages can be Figure 8 different.

[0644] Example 5: An algorithm for selecting a target cell using parameter prediction results in the source cell.

[0645] The conditions for selecting the target cell in this algorithm include the QoE parameters, QoS parameters and spectrum efficiency parameters predicted by the parameter prediction model after the UE is connected to the neighboring cell. One or more of the conditions are also selected during implementation, and the order of judgment may be different from that in this algorithm.

[0646] In this algorithm, the QoE parameters are taken as an example of the QoE parameters of the service type being streaming, and the QoS parameters are taken as an example of the uplink and downlink rates of the UE.

[0647] Fig. 9 A flow chart of an algorithm for selecting a target cell using parameter prediction results provided in an embodiment of the present application is shown in FIG. Fig. 9 As shown, the algorithm includes the following steps:

[0648] 1. The source cell determines whether the UE has established a designated service. The service may be executed by a service type configured by Operation Administration and Maintenance (OAM). For example, in this example, the designated service is streaming.

[0649] 2. If the UE has established a designated service, determine whether the source cell can obtain the QoE parameters of the designated service of the UE and whether the QoE parameters of the designated service in at least one neighboring cell can be inferred through a parameter prediction model.

[0650] If the source cell can obtain the QoE parameters of the designated service of the UE and can infer the QoE parameters of the designated service of at least one neighboring cell through the parameter prediction model, execute step 3.

[0651] If the source cell cannot obtain the QoE parameters of the designated service of the UE or cannot infer the QoE parameters of the designated service in at least one neighboring cell through the parameter prediction model, or the UE has not established the designated service, execute step 4.

[0652] 3. Estimate the service experience parameters of the UE in the source cell and in the neighboring cell according to the QoE parameters. In this example, the estimation method may be, for example, an estimation method for the audio and video mean subjective opinion score (MOS) score specified in 3GPP technical specification 26.247. In this example, the audio and video MOS score is the service experience parameter.

[0653] 3a. Determine whether there is a neighboring cell whose service experience parameter is better than that of the source cell. If so, proceed to step 3b. If not, proceed to step 4.

[0654] 3b. Select the neighboring cell with the best service experience parameter as the target cell and execute step 8.

[0655] 4. Determine whether the source cell can obtain the QoS parameters of the UE and whether the QoS parameters of at least one neighboring cell can be inferred through the parameter prediction model. In this example, the QoS parameters are the uplink and downlink rates of the UE.

[0656] If the source cell can obtain the QoS parameters of the UE and can infer the QoS parameters of at least one neighboring cell through the parameter prediction model, execute step 4a.

[0657] If the source cell cannot obtain the QoS parameters of the UE or cannot infer the QoS parameters of at least one neighboring cell through the parameter prediction model, execute step 5.

[0658] 4a. Estimate the uplink capability and downlink capability of the UE in the source cell and in the neighboring cell according to the QoS parameters, and execute step 6.

[0659] 5. Estimate the uplink and downlink capabilities of the UE in the source cell and in the neighboring cell based on the spectrum efficiency parameters of the UE obtained by the source cell and the spectrum efficiency parameters of at least one neighboring cell inferred by the parameter prediction model, and execute step 6.

[0660] If the source cell cannot obtain the spectrum efficiency parameters of the UE or infer the spectrum efficiency parameters of at least one neighboring cell through the parameter prediction model, the existing mechanism is used to select the target cell and the algorithm is exited.

[0661] 6. Determine the heavy traffic state of the UE based on the traffic volume of the UE.

[0662] 6a. If the UE is a user with a large uplink traffic volume, select the cell with the largest uplink capacity in the neighboring cell and greater than the uplink capacity of the source cell. If there is more than one, select the cell with the largest downlink capacity among the above cells. If there is more than one, select the cell with the best CQI, uplink MCS Index, downlink MCS Index of the UE in the above cells and at least one of the measurement results of the neighboring cell on the UE.

[0663] 6b. If the UE is a downlink heavy traffic user or a non-heavy traffic user, select the cell with the largest downlink capacity in the neighboring cell and greater than the downlink capacity of the source cell. If there is more than one, select the cell with the largest uplink capacity among the above cells. If there is more than one, select the cell with the best CQI, uplink MCS Index, downlink MCS Index of the UE in the above cells and at least one of the measurement results of the neighboring cell on the UE.

[0664] 7. If a suitable neighboring cell is selected, the neighboring cell is used as the target cell and step 8 is executed. If no suitable target cell is selected, step 7a is executed.

[0665] 7a. Determine whether handover is necessary. For example, if the UE's co-frequency measurement result in the source cell is less than a preset threshold, it is considered that handover is necessary. If handover is not necessary, exit this algorithm. If handover is necessary, execute step 7b.

[0666] 7b. If the UE is a user with a large uplink traffic volume, select the cell with the largest uplink capacity in the neighboring cells. If there is more than one, select the cell with the largest downlink capacity among the above cells. If there is more than one, select a cell randomly among the above cells. If the UE is another user, select the cell with the largest downlink capacity in the neighboring cells. If there is more than one, select the cell with the largest uplink capacity among the above cells. If there is more than one, select a cell randomly among the above cells. Use the selected cell as the target cell. Execute step 8.

[0667] 8. Perform handover to the target cell and exit this algorithm.

[0668] According to this algorithm, the source cell can select the best target cell to perform handover, ensuring that the UE gets the best user experience after handover.

[0669] Example 6: Node 3 sends the input parameters of the parameter prediction model to node 4, and node 4 sends the parameter prediction results to node 3.

[0670] Node 3 may be any one of gNB, eNB, ng-eNB, en-gNB, CU of gNB, CUCP of gNB, CUUP of gNB, DU of gNB, RIC or a newly defined network node. Node 4 may be any one of gNB, eNB, ng-eNB, en-gNB, CU of gNB, CUCP of gNB, CUUP of gNB, DU of gNB, RIC or a newly defined network node, and node 4 is a network device capable of executing model reasoning.

[0671] Fig.10 A schematic diagram of a process in which node three sends input parameters of a parameter prediction model to node four and node four sends parameter prediction results to node three provided in an embodiment of the present application, such as Fig.10 As shown, the process includes the following steps:

[0672] 1. Node 3 generates input parameters of the parameter prediction model based on one or more of the received sample information and the information collected by itself. Node 3 sends message 3 to node 4. Message 3 includes the input parameters of the parameter prediction model.

[0673] 2. Node 4 has obtained the parameter prediction model. Node 4 uses the parameter prediction model to infer the parameter prediction result according to the input parameters of the parameter prediction model. Node 4 sends message 4 to node 3, and the message includes the parameter prediction result.

[0674] Node three selects the optimal target cell based on the parameter prediction results.

[0675] Example 7: Node 5 obtains the parameter prediction model from node 6.

[0676] The node five can be any one of a gNB, an eNB, an ng-eNB, an en-gNB, a CU of a gNB, a CUCP of a gNB, a CUUP of a gNB, a DU of a gNB, a RIC, or a newly defined network node. The node six can be any one of a gNB, an eNB, an ng-eNB, an en-gNB, a CU of a gNB, a CUCP of a gNB, a CUUP of a gNB, a DU of a gNB, a RIC, or a newly defined network node, and the node six is ​​a network device capable of executing model reasoning.

[0677] Fig.11 A schematic diagram of a process for obtaining a parameter prediction model from node 6 by node 5 provided in an embodiment of the present application is shown in FIG. Fig.11 As shown, the process includes the following steps:

[0678] 1. Node 5 sends message 5 to node 6. Message 5 includes at least one of the following information:

[0679] An indication message, indicating to start, update or stop sending the trained parameter prediction model to node five;

[0680] The second period information indicates that the trained parameter prediction model is sent every time indicated by the second period information.

[0681] 2. Node 6 sends message 6 to node 5 according to the requirements of message 5, for example, according to the second cycle information, including the parameter prediction model trained by node 6.

[0682] Node five infers parameter prediction results according to the received parameter prediction model, and selects the optimal target cell according to the parameter prediction results.

[0683] The prior art does not consider the performance of the UE after switching when selecting a target cell for the UE. The embodiment of the present application supports the source cell to predict the performance of the UE after switching, and selects the best target cell accordingly, ensuring that the UE obtains the best user experience after switching.

[0684] The methods and devices provided in the various embodiments of the present application are based on the same application concept. Since the methods and devices solve problems based on similar principles, the implementation of the devices and methods can refer to each other, and the repeated parts will not be repeated.

[0685] Fig.12 A schematic diagram of the structure of the source network device provided in the embodiment of the present application, such as Fig.12 As shown, the source network device includes a memory 1220, a transceiver 1210 and a processor 1200; wherein the processor 1200 and the memory 1220 may also be arranged physically separately.

[0686] The memory 1220 is used to store computer programs; the transceiver 1210 is used to send and receive data under the control of the processor 1200.

[0687] Specifically, the transceiver 1210 is used to receive and send data under the control of the processor 1200 .

[0688] Among them, Fig.12 In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically linking together various circuits of one or more processors represented by processor 1200 and memory represented by memory 1220. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described in this application. The bus interface provides an interface. The transceiver 1210 may be a plurality of components, namely, a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium, which may include a wireless channel, a wired channel, an optical cable, and other transmission media.

[0689] The processor 1200 is responsible for managing the bus architecture and general processing, and the memory 1220 can store data used by the processor 1200 when performing operations.

[0690] The processor 1200 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or a complex programmable logic device (CPLD). The processor may also adopt a multi-core architecture.

[0691] The processor 1200 is configured to execute any of the methods provided in the embodiments of the present application according to the obtained executable instructions by calling the computer program stored in the memory 1220, for example: obtaining a parameter prediction result; the parameter prediction result includes a performance parameter after the terminal switches to a neighboring area and / or an optimal neighboring area identifier corresponding to the terminal predicted based on a parameter prediction model;

[0692] Based on the parameter prediction result, selecting a target cell to which the terminal switches;

[0693] The parameter prediction model is obtained through training based on sample parameter information, and the sample parameter information at least includes parameters for characterizing the uplink capability and / or downlink capability of the sample terminal in the sample neighboring area.

[0694] In some embodiments, obtaining parameter prediction results includes:

[0695] Acquire parameter prediction results from the first network device; or,

[0696] The parameter prediction results are obtained based on the parameter prediction model.

[0697] In some embodiments, the operations further include:

[0698] Sending a handover optimization request message to the second network device, where the handover optimization request message is used to obtain one or more of the following:

[0699] Sample parameter information;

[0700] Parameter prediction model;

[0701] Feedback information after the terminal switches to the target cell;

[0702] Parameter prediction results.

[0703] In some embodiments, the parameters used to characterize the uplink capability and / or downlink capability of the sample terminal in the sample neighboring area include one or more of the following:

[0704] Uplink spectrum efficiency parameters and / or downlink spectrum efficiency parameters of the sample terminal in the sample neighboring area;

[0705] The uplink bandwidth and / or downlink bandwidth of the sample terminal in the sample neighboring area;

[0706] User experience parameters of sample terminals in sample neighborhoods.

[0707] In some embodiments, the sample parameter information further includes one or more of the following:

[0708] The cell identifier of the sample source cell;

[0709] The cell identifier of the sample neighborhood;

[0710] The identifier of the serving beam on the sample neighborhood;

[0711] The identifier of the serving beam on the sample source cell;

[0712] The identification of the sample terminal;

[0713] Downlink transmission power of sample neighboring cells;

[0714] Downlink transmit power of the serving beam in the sample neighboring cell;

[0715] Downlink transmission power of the sample source cell;

[0716] Downlink transmit power of the serving beam on the sample source cell;

[0717] Uplink transmit power of the sample terminal;

[0718] Number of downlink transmit antennas in the sample neighboring cell;

[0719] The number of uplink receiving antennas in the sample neighborhood;

[0720] The number of downlink transmit antennas of the sample source cell;

[0721] The number of uplink receiving antennas of the sample source cell;

[0722] The number of uplink transmit antennas of the sample terminal;

[0723] The number of downlink receiving antennas of the sample terminal;

[0724] The measurement result of at least one cell with a different frequency from the sample source cell reported by the sample terminal;

[0725] The measurement result of at least one cell with the same frequency as the sample source cell reported by the sample terminal;

[0726] The measurement results of the sample terminal measured by the sample neighboring area;

[0727] The measurement result of the sample source cell on the sample terminal;

[0728] Channel quality indicator CQI and / or downlink modulation and coding scheme index MCS Index of the sample terminal;

[0729] Uplink MCS Index of the sample terminal;

[0730] Load status of the sample neighborhood;

[0731] The load status of the sample source cell.

[0732] In some embodiments, the input parameters of the parameter prediction model include one or more of the following:

[0733] Neighboring cell ID;

[0734] The identifier of the serving beam in the neighboring cell;

[0735] The cell identifier of the source cell;

[0736] The identifier of the serving beam on the source cell;

[0737] The terminal's identification;

[0738] Downlink transmission power of neighboring cells;

[0739] Downlink transmit power of the serving beam in the neighboring cell;

[0740] Downlink transmit power of the source cell;

[0741] Downlink transmit power of the serving beam on the source cell;

[0742] The uplink transmit power of the terminal;

[0743] Number of downlink transmit antennas in the neighboring cell;

[0744] Number of uplink receiving antennas in the neighboring cell;

[0745] The number of downlink transmit antennas of the source cell;

[0746] The number of uplink receiving antennas of the source cell;

[0747] The number of uplink transmit antennas of the terminal;

[0748] The number of downlink receiving antennas of the terminal;

[0749] The effective uplink bandwidth of the terminal in the neighboring cell;

[0750] The effective downlink bandwidth of the terminal in the neighboring cell;

[0751] Uplink idle bandwidth of neighboring cells;

[0752] Downlink idle bandwidth of neighboring cells;

[0753] The measurement result of at least one cell with a different frequency from the source cell reported by the terminal;

[0754] The measurement result of at least one cell with the same frequency as the source cell reported by the terminal;

[0755] The measurement result of the source cell on the terminal;

[0756] Load status of neighboring cells;

[0757] Load status of the source cell.

[0758] In some embodiments, the performance parameters after the terminal switches to the neighboring cell include one or more of the following:

[0759] The measurement results of the neighboring cell on the terminal;

[0760] The CQI and / or downlink MCS Index of the terminal;

[0761] Uplink MCS Index of the terminal;

[0762] Downlink spectrum efficiency parameters of the terminal in the neighboring cell;

[0763] Uplink spectrum efficiency parameters of the terminal in the neighboring cell;

[0764] User experience parameters of the terminal in the neighboring cell.

[0765] In some embodiments, the parameter prediction result further includes one or more of the following:

[0766] Neighboring cell ID;

[0767] The reliability of parameter prediction results.

[0768] In some embodiments, the handover optimization request information includes one or more of the following:

[0769] The cell identifier of the sample source cell;

[0770] The cell identifier of the sample neighborhood;

[0771] First indication information, the first indication information is used to indicate starting, updating or stopping collecting sample parameter information;

[0772] First cycle information, where the first cycle information is used to indicate a cycle for sending sample parameter information to the source network device;

[0773] First direction information, where the first direction information is used to indicate uplink information and / or downlink information in the collected sample parameter information;

[0774] Second indication information, where the second indication information is used to indicate the type of sample parameter information that needs to be collected;

[0775] Data granularity identification;

[0776] Quality of service QoS parameter type;

[0777] Type of business;

[0778] The identification of the sample terminal;

[0779] First time length information, the first time length information is used to indicate a time period for collecting sample parameter information;

[0780] third indication information, where the third indication information is used to indicate starting, updating or stopping sending the parameter prediction model to the source network device;

[0781] Second cycle information, where the second cycle information is used to indicate a cycle for sending the parameter prediction model to the source network device;

[0782] The cell identifier of the source cell;

[0783] The cell identifier of the target cell;

[0784] Fourth indication information, the fourth indication information is used to indicate starting, updating or stopping collecting feedback information after the terminal switches to the target cell;

[0785] third cycle information, where the third cycle information is used to indicate a cycle for sending feedback information to the source network device;

[0786] Second direction information, where the second direction information is used to indicate the uplink information and / or downlink information in the collected feedback information;

[0787] Fifth indication information, where the fifth indication information is used to indicate the type of feedback information that needs to be collected;

[0788] The terminal's identification;

[0789] Second time length information, where the second time length information is used to indicate a time period for collecting feedback information;

[0790] Sixth indication information: the sixth indication information is used to indicate that the target cell is predicted and / or the credibility of the parameter prediction result.

[0791] In some embodiments, selecting a target cell to which the terminal switches based on the parameter prediction result includes:

[0792] Based on the parameter prediction result, estimate the uplink capability and / or downlink capability of the terminal in the neighboring cell;

[0793] A target cell to which the terminal switches is selected based on the uplink capability and / or downlink capability of the terminal in the neighboring cell.

[0794] In some embodiments, selecting a target cell to which the terminal switches based on the uplink capability and / or downlink capability of the terminal in the neighboring cell includes:

[0795] Select a neighboring cell with the largest uplink capacity and / or downlink capacity, and determine it as the target cell to which the terminal switches; or

[0796] A target cell to which the terminal switches is selected based on the uplink capability and / or downlink capability of the terminal in the neighboring cell and the traffic type of the terminal.

[0797] In some embodiments, based on the uplink capability and / or downlink capability of the terminal in the neighboring cell and the traffic type of the terminal, selecting a target cell to which the terminal switches includes:

[0798] In the case where the terminal is a user with a large uplink traffic volume, a target cell to which the terminal is switched is selected from a neighboring cell whose corresponding uplink capacity is the largest and whose corresponding uplink capacity is greater than the uplink capacity of the terminal in the source cell; or

[0799] When the terminal is a user with a large downlink traffic volume, a target cell to which the terminal switches is selected from a neighboring cell whose corresponding downlink capacity is the largest and whose corresponding downlink capacity is greater than the downlink capacity of the terminal in the source cell.

[0800] In some embodiments, the operations further include:

[0801] receiving feedback information sent by the second network device;

[0802] Based on the feedback information, the parameter prediction model is optimized.

[0803] Fig.13 A schematic diagram of the structure of the second network device provided in the embodiment of the present application, such as Fig.13 As shown, the second network device includes a memory 1320, a transceiver 1310 and a processor 1300; wherein the processor 1300 and the memory 1320 may also be arranged physically separately.

[0804] The memory 1320 is used to store computer programs; the transceiver 1310 is used to send and receive data under the control of the processor 1300.

[0805] Specifically, the transceiver 1310 is used to receive and send data under the control of the processor 1300 .

[0806] Among them, Fig.13 In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically linking together various circuits of one or more processors represented by processor 1300 and memory represented by memory 1320. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described in this application. The bus interface provides an interface. The transceiver 1310 may be a plurality of components, namely, a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium, which may include a wireless channel, a wired channel, an optical cable, and other transmission media.

[0807] The processor 1300 is responsible for managing the bus architecture and general processing, and the memory 1320 can store data used by the processor 1300 when performing operations.

[0808] The processor 1300 may be a CPU, an ASIC, an FPGA or a CPLD, and the processor may also adopt a multi-core architecture.

[0809] The processor 1300 is configured to execute any of the methods provided in the embodiments of the present application according to the obtained executable instructions by calling the computer program stored in the memory 1320, for example: receiving the switching optimization request information sent by the source network device;

[0810] According to the handover optimization request information, one or more of the following is sent to the source network device:

[0811] Sample parameter information used to train parameter prediction models;

[0812] Parameter prediction model;

[0813] Feedback information after the terminal switches to the target cell;

[0814] Parameter prediction results; the parameter prediction results include the performance parameters of the terminal after switching to the neighboring cell and / or the optimal neighboring cell identifier corresponding to the terminal, which are predicted based on the parameter prediction model.

[0815] In some embodiments, the handover optimization request information includes one or more of the following:

[0816] The cell identifier of the sample source cell;

[0817] The cell identifier of the sample neighborhood;

[0818] First indication information, the first indication information is used to indicate starting, updating or stopping collecting sample parameter information;

[0819] First cycle information, where the first cycle information is used to indicate a cycle for sending sample parameter information to the source network device;

[0820] First direction information, where the first direction information is used to indicate uplink information and / or downlink information in the collected sample parameter information;

[0821] Second indication information, where the second indication information is used to indicate the type of sample parameter information that needs to be collected;

[0822] Data granularity identification;

[0823] Quality of service QoS parameter type;

[0824] Type of business;

[0825] The identification of the sample terminal;

[0826] First time length information, the first time length information is used to indicate a time period for collecting sample parameter information;

[0827] third indication information, where the third indication information is used to indicate starting, updating or stopping sending the parameter prediction model to the source network device;

[0828] Second cycle information, where the second cycle information is used to indicate a cycle for sending the parameter prediction model to the source network device;

[0829] The cell identifier of the source cell;

[0830] The cell identifier of the target cell;

[0831] Fourth indication information, the fourth indication information is used to indicate starting, updating or stopping collecting feedback information after the terminal switches to the target cell;

[0832] third cycle information, where the third cycle information is used to indicate a cycle for sending feedback information to the source network device;

[0833] Second direction information, where the second direction information is used to indicate the uplink information and / or downlink information in the collected feedback information;

[0834] Fifth indication information, where the fifth indication information is used to indicate the type of feedback information that needs to be collected;

[0835] The terminal's identification;

[0836] Second time length information, where the second time length information is used to indicate a time period for collecting feedback information;

[0837] Sixth indication information: the sixth indication information is used to indicate that the target cell is predicted and / or the credibility of the parameter prediction result.

[0838] In some embodiments, the sample parameter information includes one or more of the following:

[0839] The cell identifier of the sample source cell;

[0840] The cell identifier of the sample neighborhood;

[0841] The identifier of the serving beam on the sample neighborhood;

[0842] The identifier of the serving beam on the sample source cell;

[0843] The identification of the sample terminal;

[0844] Downlink transmission power of sample neighboring cells;

[0845] Downlink transmit power of the serving beam in the sample neighboring cell;

[0846] Downlink transmission power of the sample source cell;

[0847] Downlink transmit power of the serving beam on the sample source cell;

[0848] Uplink transmit power of the sample terminal;

[0849] Number of downlink transmit antennas in the sample neighboring cell;

[0850] The number of uplink receiving antennas in the sample neighborhood;

[0851] The number of downlink transmit antennas of the sample source cell;

[0852] The number of uplink receiving antennas of the sample source cell;

[0853] The number of uplink transmit antennas of the sample terminal;

[0854] The number of downlink receiving antennas of the sample terminal;

[0855] The measurement result of at least one cell with a different frequency from the sample source cell reported by the sample terminal;

[0856] The measurement result of at least one cell with the same frequency as the sample source cell reported by the sample terminal;

[0857] The measurement results of the sample terminal measured by the sample neighboring area;

[0858] The measurement result of the sample source cell on the sample terminal;

[0859] Channel quality indicator CQI and / or downlink modulation and coding scheme index MCS Index of the sample terminal;

[0860] Uplink MCS Index of the sample terminal;

[0861] Load status of the sample neighborhood;

[0862] The load status of the sample source cell;

[0863] Uplink spectrum efficiency parameters and / or downlink spectrum efficiency parameters of the sample terminal in the sample neighboring area;

[0864] The uplink bandwidth and / or downlink bandwidth of the sample terminal in the sample neighboring area;

[0865] User experience parameters of sample terminals in sample neighborhoods.

[0866] It should be noted here that the above-mentioned source network device and the second network device provided in the embodiment of the present application can implement all the method steps implemented in the above-mentioned method embodiment, and can achieve the same technical effect. The parts and beneficial effects that are the same as those in the method embodiment will not be described in detail here.

[0867] Fig.14 One of the structural diagrams of the device for selecting a target cell provided in an embodiment of the present application is as follows: Fig.14 As shown, the device comprises:

[0868] The acquisition unit 1400 is used to acquire a parameter prediction result; the parameter prediction result includes a performance parameter after the terminal switches to a neighboring cell and / or an optimal neighboring cell identifier corresponding to the terminal, which is predicted based on the parameter prediction model;

[0869] A selection unit 1410 is configured to select a target cell to which the terminal switches based on the parameter prediction result;

[0870] The parameter prediction model is obtained through training based on sample parameter information, and the sample parameter information at least includes parameters for characterizing the uplink capability and / or downlink capability of the sample terminal in the sample neighboring area.

[0871] In some embodiments, obtaining parameter prediction results includes:

[0872] Acquire parameter prediction results from the first network device; or,

[0873] The parameter prediction results are obtained based on the parameter prediction model.

[0874] In some embodiments, the apparatus further comprises:

[0875] The first sending unit is configured to send handover optimization request information to the second network device, where the handover optimization request information is used to obtain one or more of the following:

[0876] Sample parameter information;

[0877] Parameter prediction model;

[0878] Feedback information after the terminal switches to the target cell;

[0879] Parameter prediction results.

[0880] In some embodiments, the parameters used to characterize the uplink capability and / or downlink capability of the sample terminal in the sample neighboring area include one or more of the following:

[0881] Uplink spectrum efficiency parameters and / or downlink spectrum efficiency parameters of the sample terminal in the sample neighboring area;

[0882] The uplink bandwidth and / or downlink bandwidth of the sample terminal in the sample neighboring area;

[0883] User experience parameters of sample terminals in sample neighborhoods.

[0884] In some embodiments, the sample parameter information further includes one or more of the following:

[0885] The cell identifier of the sample source cell;

[0886] The cell identifier of the sample neighborhood;

[0887] The identifier of the serving beam on the sample neighborhood;

[0888] The identifier of the serving beam on the sample source cell;

[0889] The identification of the sample terminal;

[0890] Downlink transmission power of sample neighboring cells;

[0891] Downlink transmit power of the serving beam in the sample neighboring cell;

[0892] Downlink transmission power of the sample source cell;

[0893] Downlink transmit power of the serving beam on the sample source cell;

[0894] Uplink transmit power of the sample terminal;

[0895] Number of downlink transmit antennas in the sample neighboring cell;

[0896] The number of uplink receiving antennas in the sample neighborhood;

[0897] The number of downlink transmit antennas of the sample source cell;

[0898] The number of uplink receiving antennas of the sample source cell;

[0899] The number of uplink transmit antennas of the sample terminal;

[0900] The number of downlink receiving antennas of the sample terminal;

[0901] The measurement result of at least one cell with a different frequency from the sample source cell reported by the sample terminal;

[0902] The measurement result of at least one cell with the same frequency as the sample source cell reported by the sample terminal;

[0903] The measurement results of the sample terminal measured by the sample neighboring area;

[0904] The measurement result of the sample source cell on the sample terminal;

[0905] Channel quality indicator CQI and / or downlink modulation and coding scheme index MCS Index of the sample terminal;

[0906] Uplink MCS Index of the sample terminal;

[0907] Load status of the sample neighborhood;

[0908] The load status of the sample source cell.

[0909] In some embodiments, the input parameters of the parameter prediction model include one or more of the following:

[0910] Neighboring cell ID;

[0911] The identifier of the serving beam in the neighboring cell;

[0912] The cell identifier of the source cell;

[0913] The identifier of the serving beam on the source cell;

[0914] The terminal's identification;

[0915] Downlink transmission power of neighboring cells;

[0916] Downlink transmit power of the serving beam in the neighboring cell;

[0917] Downlink transmit power of the source cell;

[0918] Downlink transmit power of the serving beam on the source cell;

[0919] The uplink transmit power of the terminal;

[0920] Number of downlink transmit antennas in the neighboring cell;

[0921] Number of uplink receiving antennas in the neighboring cell;

[0922] The number of downlink transmit antennas of the source cell;

[0923] The number of uplink receiving antennas of the source cell;

[0924] The number of uplink transmit antennas of the terminal;

[0925] The number of downlink receiving antennas of the terminal;

[0926] The effective uplink bandwidth of the terminal in the neighboring cell;

[0927] The effective downlink bandwidth of the terminal in the neighboring cell;

[0928] Uplink idle bandwidth of neighboring cells;

[0929] Downlink idle bandwidth of neighboring cells;

[0930] The measurement result of at least one cell with a different frequency from the source cell reported by the terminal;

[0931] The measurement result of at least one cell with the same frequency as the source cell reported by the terminal;

[0932] The measurement result of the source cell on the terminal;

[0933] Load status of neighboring cells;

[0934] Load status of the source cell.

[0935] In some embodiments, the performance parameters after the terminal switches to the neighboring cell include one or more of the following:

[0936] The measurement results of the neighboring cell on the terminal;

[0937] The CQI and / or downlink MCS Index of the terminal;

[0938] Uplink MCS Index of the terminal;

[0939] Downlink spectrum efficiency parameters of the terminal in the neighboring cell;

[0940] Uplink spectrum efficiency parameters of the terminal in the neighboring cell;

[0941] User experience parameters of the terminal in the neighboring cell.

[0942] In some embodiments, the parameter prediction result further includes one or more of the following:

[0943] Neighboring cell ID;

[0944] The reliability of parameter prediction results.

[0945] In some embodiments, the handover optimization request information includes one or more of the following:

[0946] The cell identifier of the sample source cell;

[0947] The cell identifier of the sample neighborhood;

[0948] First indication information, the first indication information is used to indicate starting, updating or stopping collecting sample parameter information;

[0949] First cycle information, where the first cycle information is used to indicate a cycle for sending sample parameter information to the source network device;

[0950] First direction information, where the first direction information is used to indicate uplink information and / or downlink information in the collected sample parameter information;

[0951] Second indication information, where the second indication information is used to indicate the type of sample parameter information that needs to be collected;

[0952] Data granularity identification;

[0953] Quality of service QoS parameter type;

[0954] Type of business;

[0955] The identification of the sample terminal;

[0956] First time length information, the first time length information is used to indicate a time period for collecting sample parameter information;

[0957] third indication information, where the third indication information is used to indicate starting, updating or stopping sending the parameter prediction model to the source network device;

[0958] Second cycle information, where the second cycle information is used to indicate a cycle for sending the parameter prediction model to the source network device;

[0959] The cell identifier of the source cell;

[0960] The cell identifier of the target cell;

[0961] Fourth indication information, the fourth indication information is used to indicate starting, updating or stopping collecting feedback information after the terminal switches to the target cell;

[0962] third cycle information, where the third cycle information is used to indicate a cycle for sending feedback information to the source network device;

[0963] Second direction information, where the second direction information is used to indicate the uplink information and / or downlink information in the collected feedback information;

[0964] Fifth indication information, where the fifth indication information is used to indicate the type of feedback information that needs to be collected;

[0965] The terminal's identification;

[0966] Second time length information, where the second time length information is used to indicate a time period for collecting feedback information;

[0967] Sixth indication information: the sixth indication information is used to indicate that the target cell is predicted and / or the credibility of the parameter prediction result.

[0968] In some embodiments, selecting a target cell to which the terminal switches based on the parameter prediction result includes:

[0969] Based on the parameter prediction result, estimate the uplink capability and / or downlink capability of the terminal in the neighboring cell;

[0970] A target cell to which the terminal switches is selected based on the uplink capability and / or downlink capability of the terminal in the neighboring cell.

[0971] In some embodiments, selecting a target cell to which the terminal switches based on the uplink capability and / or downlink capability of the terminal in the neighboring cell includes:

[0972] Select a neighboring cell with the largest uplink capacity and / or downlink capacity, and determine it as the target cell to which the terminal switches; or

[0973] A target cell to which the terminal switches is selected based on the uplink capability and / or downlink capability of the terminal in the neighboring cell and the traffic type of the terminal.

[0974] In some embodiments, based on the uplink capability and / or downlink capability of the terminal in the neighboring cell and the traffic type of the terminal, selecting a target cell to which the terminal switches includes:

[0975] In the case where the terminal is a user with a large uplink traffic volume, a target cell to which the terminal is switched is selected from a neighboring cell whose corresponding uplink capacity is the largest and whose corresponding uplink capacity is greater than the uplink capacity of the terminal in the source cell; or

[0976] When the terminal is a user with a large downlink traffic volume, a target cell to which the terminal switches is selected from a neighboring cell whose corresponding downlink capacity is the largest and whose corresponding downlink capacity is greater than the downlink capacity of the terminal in the source cell.

[0977] In some embodiments, the apparatus further comprises:

[0978] A first receiving unit, configured to receive feedback information sent by a second network device;

[0979] The optimization unit is used to optimize the parameter prediction model based on the feedback information.

[0980] Fig.15 The second structural diagram of the device for selecting a target cell provided in the embodiment of the present application is as follows: Fig.15 As shown, the device comprises:

[0981] The second receiving unit 1500 is used to receive the switching optimization request information sent by the source network device;

[0982] The second sending unit 1510 is configured to send one or more of the following to the source network device according to the handover optimization request information:

[0983] Sample parameter information used to train parameter prediction models;

[0984] Parameter prediction model;

[0985] Feedback information after the terminal switches to the target cell;

[0986] Parameter prediction results; the parameter prediction results include the performance parameters of the terminal after switching to the neighboring cell and / or the optimal neighboring cell identifier corresponding to the terminal, which are predicted based on the parameter prediction model.

[0987] In some embodiments, the handover optimization request information includes one or more of the following:

[0988] The cell identifier of the sample source cell;

[0989] The cell identifier of the sample neighborhood;

[0990] First indication information, the first indication information is used to indicate starting, updating or stopping collecting sample parameter information;

[0991] First cycle information, where the first cycle information is used to indicate a cycle for sending sample parameter information to the source network device;

[0992] First direction information, where the first direction information is used to indicate uplink information and / or downlink information in the collected sample parameter information;

[0993] Second indication information, where the second indication information is used to indicate the type of sample parameter information that needs to be collected;

[0994] Data granularity identification;

[0995] Quality of service QoS parameter type;

[0996] Type of business;

[0997] The identification of the sample terminal;

[0998] First time length information, the first time length information is used to indicate a time period for collecting sample parameter information;

[0999] third indication information, where the third indication information is used to indicate starting, updating or stopping sending the parameter prediction model to the source network device;

[1000] Second cycle information, where the second cycle information is used to indicate a cycle for sending the parameter prediction model to the source network device;

[1001] The cell identifier of the source cell;

[1002] The cell identifier of the target cell;

[1003] Fourth indication information, the fourth indication information is used to indicate starting, updating or stopping collecting feedback information after the terminal switches to the target cell;

[1004] third cycle information, where the third cycle information is used to indicate a cycle for sending feedback information to the source network device;

[1005] Second direction information, where the second direction information is used to indicate the uplink information and / or downlink information in the collected feedback information;

[1006] Fifth indication information, where the fifth indication information is used to indicate the type of feedback information that needs to be collected;

[1007] The terminal's identification;

[1008] Second time length information, where the second time length information is used to indicate a time period for collecting feedback information;

[1009] Sixth indication information: the sixth indication information is used to indicate that the target cell is predicted and / or the credibility of the parameter prediction result.

[1010] In some embodiments, the sample parameter information includes one or more of the following:

[1011] The cell identifier of the sample source cell;

[1012] The cell identifier of the sample neighborhood;

[1013] The identifier of the serving beam on the sample neighborhood;

[1014] The identifier of the serving beam on the sample source cell;

[1015] The identification of the sample terminal;

[1016] Downlink transmission power of sample neighboring cells;

[1017] Downlink transmit power of the serving beam in the sample neighboring cell;

[1018] Downlink transmission power of the sample source cell;

[1019] Downlink transmit power of the serving beam on the sample source cell;

[1020] Uplink transmit power of the sample terminal;

[1021] Number of downlink transmit antennas in the sample neighboring cell;

[1022] The number of uplink receiving antennas in the sample neighborhood;

[1023] The number of downlink transmit antennas of the sample source cell;

[1024] The number of uplink receiving antennas of the sample source cell;

[1025] The number of uplink transmit antennas of the sample terminal;

[1026] The number of downlink receiving antennas of the sample terminal;

[1027] The measurement result of at least one cell with a different frequency from the sample source cell reported by the sample terminal;

[1028] The measurement result of at least one cell with the same frequency as the sample source cell reported by the sample terminal;

[1029] The measurement results of the sample terminal measured by the sample neighboring area;

[1030] The measurement result of the sample source cell on the sample terminal;

[1031] Channel quality indicator CQI and / or downlink modulation and coding scheme index MCS Index of the sample terminal;

[1032] Uplink MCS Index of the sample terminal;

[1033] Load status of the sample neighborhood;

[1034] The load status of the sample source cell;

[1035] Uplink spectrum efficiency parameters and / or downlink spectrum efficiency parameters of the sample terminal in the sample neighboring area;

[1036] The uplink bandwidth and / or downlink bandwidth of the sample terminal in the sample neighboring area;

[1037] User experience parameters of sample terminals in sample neighborhoods.

[1038] It should be noted that the division of units in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional unit in each embodiment of the present application may be integrated into a processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[1039] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a processor-readable storage medium. Based on this understanding, the technical solution of the present application is essentially 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, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[1040] It should be noted here that the above-mentioned device provided in the embodiment of the present application can implement all the method steps implemented in the above-mentioned method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as those in the method embodiment will not be described in detail here.

[1041] On the other hand, an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is used to enable a computer to execute the method for selecting a target cell provided in the above embodiments.

[1042] It should be noted here that the computer-readable storage medium provided in the embodiment of the present application can implement all the method steps implemented in the above-mentioned method embodiment and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as those in the method embodiment will not be described in detail here.

[1043] The computer-readable storage medium can be any available medium or data storage device that can be accessed by a computer, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (such as CD, DVD, BD, HVD, etc.), and semiconductor storage (such as ROM, EPROM, EEPROM, non-volatile memory (NANDFLASH), solid-state drive (SSD)), etc.

[1044] The technical solution provided in the embodiment of the present application can be applicable to a variety of systems, especially 5G systems. For example, the applicable system can be a global system of mobile communication (GSM) system, a code division multiple access (CDMA) system, a wideband code division multiple access (WCDMA) general packet radio service (GPRS) system, a long term evolution (LTE) system, a LTE frequency division duplex (FDD) system, a LTE time division duplex (TDD) system, an advanced long term evolution (LTE-A) system, a universal mobile telecommunication system (UMTS), a world-wide interoperability for microwave access (WiMAX) system, a 5G new air interface (NR) system, etc. These various systems include terminal equipment and network equipment. The system may also include a core network part, such as an evolved packet system (EPS), a 5G system (5GS), etc.

[1045] The terminal involved in the embodiment of the present application may be a device that provides voice and / or data connectivity to a user, a handheld device with a wireless connection function, or other processing devices connected to a wireless modem. In different systems, the name of the terminal may also be different. For example, in a 5G system, the terminal may be called a user equipment (UE). A wireless terminal device can communicate with one or more core networks (CN) via a radio access network (RAN). The wireless terminal device may be a mobile terminal device, such as a mobile phone (or a "cellular" phone) and a computer with a mobile terminal device. For example, it may be a portable, pocket-sized, handheld, computer-built-in or vehicle-mounted mobile device that exchanges language and / or data with a wireless access network. For example, personal communication service (PCS) phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs) and other devices. The wireless terminal device may also be referred to as a system, a subscriber unit, a subscriber station, a mobile station, a mobile station, a remote station, an access point, a remote terminal device, an access terminal device, a user terminal device, a user agent, and a user device, but is not limited in the embodiments of the present application.

[1046] The network device involved in the embodiment of the present application may be a base station, which may include multiple cells providing services for the terminal. Depending on the specific application scenario, the base station may also be called an access point, or may be a device in the access network that communicates with the wireless terminal device through one or more sectors on the air interface, or other names. The network device may be used to interchange received air frames with Internet Protocol (IP) packets, and serve as a router between the wireless terminal device and the rest of the access network, wherein the rest of the access network may include an Internet Protocol (IP) communication network. The network device may also coordinate the attribute management of the air interface. For example, the network device involved in the embodiments of the present application may be a network device (Base Transceiver Station, BTS) in the Global System for Mobile communications (Global System for Mobile communications, GSM) or Code Division Multiple Access (Code Division Multiple Access, CDMA), or a network device (NodeB) in Wide-band Code Division Multiple Access (WCDMA), or an evolutionary network device (evolutional Node B, eNB or e-NodeB) in the long term evolution (long term evolution, LTE) system, a 5G base station (gNB) in the 5G network architecture (next generation system), or a home evolved Node B (Home evolved Node B, HeNB), a relay node, a home base station (femto), a pico base station (pico), etc., which is not limited in the embodiments of the present application. In some network structures, the network device may include a centralized unit (CU) node and a distributed unit (DU) node, and the centralized unit and the distributed unit may also be arranged geographically separately.

[1047] Network devices and terminals can each use one or more antennas for multiple-input multiple-output (MIMO) transmission. MIMO transmission can be single-user MIMO (SU-MIMO) or multi-user MIMO (MU-MIMO). Depending on the form and number of antenna combinations, MIMO transmission can be 2D-MIMO, 3D-MIMO, FD-MIMO or massive-MIMO, or it can be diversity transmission, precoded transmission or beamforming transmission, etc.

[1048] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) that contain computer-usable program code.

[1049] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer executable instructions. These computer executable instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[1050] These processor executable instructions may also be stored in a processor readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the processor readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[1051] These processor-executable instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[1052] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for selecting a target cell, characterized in that: Applied to source network devices, including: Obtaining parameter prediction results; the parameter prediction results include performance parameters of the terminal after switching to a neighboring cell and / or an optimal neighboring cell identifier corresponding to the terminal, which are predicted based on a parameter prediction model; Based on the parameter prediction result, selecting a target cell to which the terminal switches; The parameter prediction model is obtained through training based on sample parameter information, and the sample parameter information at least includes parameters for characterizing the uplink capability and / or downlink capability of the sample terminal in the sample neighboring area.

2. The method for selecting a target cell according to claim 1, characterized in that: The obtaining of parameter prediction results includes: Acquire the parameter prediction result from the first network device; or, The parameter prediction result is obtained based on the parameter prediction model.

3. The method for selecting a target cell according to claim 2, characterized in that: The method further comprises: Sending handover optimization request information to the second network device, where the handover optimization request information is used to obtain one or more of the following: The sample parameter information; The parameter prediction model; Feedback information after the terminal switches to the target cell; The parameters predict the outcome.

4. The method for selecting a target cell according to claim 1, characterized in that: The parameters used to characterize the uplink capability and / or downlink capability of the sample terminal in the sample neighboring area include one or more of the following: Uplink spectrum efficiency parameters and / or downlink spectrum efficiency parameters of the sample terminal in the sample neighboring area; The uplink bandwidth and / or downlink bandwidth of the sample terminal in the sample neighboring area; User experience parameters of sample terminals in sample neighborhoods.

5. The method for selecting a target cell according to any one of claims 1 to 4, characterized in that: The sample parameter information may also include one or more of the following: The cell identifier of the sample source cell; The cell identifier of the sample neighborhood; The identifier of the serving beam on the sample neighborhood; The identifier of the serving beam on the sample source cell; The identification of the sample terminal; Downlink transmission power of sample neighboring cells; Downlink transmit power of the serving beam in the sample neighboring cell; Downlink transmission power of the sample source cell; Downlink transmit power of the serving beam on the sample source cell; Uplink transmit power of the sample terminal; Number of downlink transmit antennas in the sample neighboring cell; The number of uplink receiving antennas in the sample neighborhood; The number of downlink transmit antennas of the sample source cell; The number of uplink receiving antennas of the sample source cell; The number of uplink transmit antennas of the sample terminal; The number of downlink receiving antennas of the sample terminal; The measurement result of at least one cell with a different frequency from the sample source cell reported by the sample terminal; The measurement result of at least one cell with the same frequency as the sample source cell reported by the sample terminal; The measurement results of the sample terminal measured by the sample neighboring area; The measurement result of the sample source cell on the sample terminal; Channel quality indicator CQI and / or downlink modulation and coding scheme index MCS Index of the sample terminal; Uplink MCS Index of the sample terminal; Load status of the sample neighborhood; The load status of the sample source cell.

6. The method for selecting a target cell according to claim 1, characterized in that: The input parameters of the parameter prediction model include one or more of the following: The cell identifier of the neighboring cell; An identifier of a serving beam on the neighboring cell; The cell identifier of the source cell; The identifier of the serving beam on the source cell; an identification of the terminal; Downlink transmission power of the neighboring cell; The downlink transmission power of the serving beam in the neighboring cell; Downlink transmit power of the source cell; Downlink transmit power of the serving beam on the source cell; The uplink transmission power of the terminal; The number of downlink transmitting antennas of the neighboring cell; The number of uplink receiving antennas of the neighboring cell; Number of downlink transmit antennas of the source cell; The number of uplink receiving antennas of the source cell; The number of uplink transmit antennas of the terminal; The number of downlink receiving antennas of the terminal; The effective uplink bandwidth of the terminal in the neighboring cell; The downlink effective bandwidth of the terminal in the neighboring cell; The uplink idle bandwidth of the neighboring cell; downlink idle bandwidth of the neighboring cell; The measurement result of at least one cell having a frequency different from that of the source cell reported by the terminal; The measurement result of at least one cell having the same frequency as the source cell reported by the terminal; a measurement result of the source cell measuring the terminal; The load status of the neighboring cell; Load status of the source cell.

7. The method for selecting a target cell according to claim 1, characterized in that: The performance parameters after the terminal switches to the neighboring cell include one or more of the following: A measurement result of the neighboring cell measuring the terminal; CQI and / or downlink MCSIndex of the terminal; An uplink MCS Index of the terminal; A downlink spectrum efficiency parameter of the terminal in the neighboring cell; An uplink spectrum efficiency parameter of the terminal in the neighboring cell; User experience parameters of the terminal in the neighboring cell.

8. The method for selecting a target cell according to claim 1 or 7, characterized in that: The parameter prediction results may also include one or more of the following: The cell identifier of the neighboring cell; The reliability of the parameter prediction results.

9. The method for selecting a target cell according to claim 3, characterized in that: The switching optimization request information includes one or more of the following: The cell identifier of the sample source cell; The cell identifier of the sample neighborhood; first indication information, where the first indication information is used to indicate starting, updating or stopping collecting the sample parameter information; first cycle information, where the first cycle information is used to indicate a cycle for sending the sample parameter information to the source network device; first direction information, where the first direction information is used to indicate the collection of uplink information and / or downlink information in the sample parameter information; second indication information, where the second indication information is used to indicate the type of the sample parameter information that needs to be collected; Data granularity identification; Quality of service QoS parameter type; Type of business; The identification of the sample terminal; first time length information, where the first time length information is used to indicate a time period for collecting the sample parameter information; third indication information, where the third indication information is used to indicate starting, updating or stopping sending the parameter prediction model to the source network device; second cycle information, where the second cycle information is used to indicate a cycle for sending the parameter prediction model to the source network device; The cell identifier of the source cell; The cell identifier of the target cell; Fourth indication information, where the fourth indication information is used to indicate starting, updating or stopping collecting feedback information after the terminal switches to the target cell; third cycle information, where the third cycle information is used to indicate a cycle for sending the feedback information to the source network device; second direction information, where the second direction information is used to indicate the collection of uplink information and / or downlink information in the feedback information; fifth indication information, where the fifth indication information is used to indicate the type of the feedback information to be collected; an identification of the terminal; second time length information, where the second time length information is used to indicate a time period for collecting the feedback information; Sixth indication information, the sixth indication information is used to indicate that the target cell is predicted and / or the credibility of the parameter prediction result.

10. The method for selecting a target cell according to claim 1, characterized in that: The selecting, based on the parameter prediction result, a target cell to which the terminal switches, includes: Based on the parameter prediction result, estimating the uplink capability and / or downlink capability of the terminal in the neighboring cell; A target cell to which the terminal switches is selected based on the uplink capability and / or downlink capability of the terminal in the neighboring cell.

11. The method for selecting a target cell according to claim 10, characterized in that: The selecting, based on the uplink capability and / or downlink capability of the terminal in the neighboring cell, a target cell to which the terminal switches, includes: Select a neighboring cell with the largest uplink capacity and / or downlink capacity, and determine it as the target cell to which the terminal switches; or A target cell to which the terminal switches is selected based on the uplink capability and / or downlink capability of the terminal in the neighboring cell and the traffic type of the terminal.

12. The method for selecting a target cell according to claim 11, characterized in that: The selecting a target cell to which the terminal switches based on the uplink capability and / or downlink capability of the terminal in the neighboring cell and the traffic type of the terminal includes: In the case where the terminal is a user with a large uplink traffic volume, selecting a target cell to which the terminal is switched from a neighboring cell having the largest corresponding uplink capacity and a corresponding uplink capacity greater than the uplink capacity of the terminal in the source cell; or In the case that the terminal is a user with a large downlink traffic volume, a target cell to which the terminal switches is selected from a neighboring cell whose corresponding downlink capacity is the largest and whose corresponding downlink capacity is greater than the downlink capacity of the terminal in the source cell.

13. The method for selecting a target cell according to claim 3 or 9, characterized in that: The method further comprises: receiving the feedback information sent by the second network device; Based on the feedback information, the parameter prediction model is optimized.

14. A method for selecting a target cell, characterized in that: Applied to the second network device, comprising: Receiving switching optimization request information sent by the source network device; According to the handover optimization request information, one or more of the following is sent to the source network device: Sample parameter information used to train parameter prediction models; The parameter prediction model; Feedback information after the terminal switches to the target cell; Parameter prediction results; the parameter prediction results include performance parameters of the terminal after switching to a neighboring cell predicted based on a parameter prediction model and / or an optimal neighboring cell identifier corresponding to the terminal.

15. The method for selecting a target cell according to claim 14, characterized in that: The switching optimization request information includes one or more of the following: The cell identifier of the sample source cell; The cell identifier of the sample neighborhood; first indication information, where the first indication information is used to indicate starting, updating or stopping collecting the sample parameter information; first cycle information, where the first cycle information is used to indicate a cycle for sending the sample parameter information to the source network device; first direction information, where the first direction information is used to indicate the collection of uplink information and / or downlink information in the sample parameter information; second indication information, where the second indication information is used to indicate the type of the sample parameter information that needs to be collected; Data granularity identification; Quality of service QoS parameter type; Type of business; The identification of the sample terminal; first time length information, where the first time length information is used to indicate a time period for collecting the sample parameter information; third indication information, where the third indication information is used to indicate starting, updating or stopping sending the parameter prediction model to the source network device; second cycle information, where the second cycle information is used to indicate a cycle for sending the parameter prediction model to the source network device; The cell identifier of the source cell; The cell identifier of the target cell; Fourth indication information, where the fourth indication information is used to indicate starting, updating or stopping collecting feedback information after the terminal switches to the target cell; third cycle information, where the third cycle information is used to indicate a cycle for sending the feedback information to the source network device; second direction information, where the second direction information is used to indicate the collection of uplink information and / or downlink information in the feedback information; fifth indication information, where the fifth indication information is used to indicate the type of the feedback information to be collected; an identification of the terminal; second time length information, where the second time length information is used to indicate a time period for collecting the feedback information; Sixth indication information, the sixth indication information is used to indicate that the target cell is predicted and / or the credibility of the parameter prediction result.

16. The method for selecting a target cell according to claim 14, characterized in that: The sample parameter information includes one or more of the following: The cell identifier of the sample source cell; The cell identifier of the sample neighborhood; The identifier of the serving beam on the sample neighborhood; The identifier of the serving beam on the sample source cell; The identification of the sample terminal; Downlink transmission power of sample neighboring cells; Downlink transmit power of the serving beam in the sample neighboring cell; Downlink transmission power of the sample source cell; Downlink transmit power of the serving beam on the sample source cell; Uplink transmit power of the sample terminal; Number of downlink transmit antennas in the sample neighboring cell; The number of uplink receiving antennas in the sample neighborhood; The number of downlink transmit antennas of the sample source cell; The number of uplink receiving antennas of the sample source cell; The number of uplink transmit antennas of the sample terminal; The number of downlink receiving antennas of the sample terminal; The measurement result of at least one cell with a different frequency from the sample source cell reported by the sample terminal; The measurement result of at least one cell with the same frequency as the sample source cell reported by the sample terminal; The measurement results of the sample terminal measured by the sample neighboring area; The measurement result of the sample source cell on the sample terminal; Channel quality indicator CQI and / or downlink modulation and coding scheme index MCS Index of the sample terminal; Uplink MCS Index of the sample terminal; Load status of the sample neighborhood; The load status of the sample source cell; Uplink spectrum efficiency parameters and / or downlink spectrum efficiency parameters of the sample terminal in the sample neighboring area; The uplink bandwidth and / or downlink bandwidth of the sample terminal in the sample neighboring area; User experience parameters of sample terminals in sample neighborhoods.

17. A source network device, characterized in that: Including memory, transceiver, processor; A memory for storing a computer program; a transceiver for transmitting and receiving data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations: Obtaining parameter prediction results; the parameter prediction results include performance parameters of the terminal after switching to a neighboring cell and / or an optimal neighboring cell identifier corresponding to the terminal, which are predicted based on a parameter prediction model; Based on the parameter prediction result, selecting a target cell to which the terminal switches; The parameter prediction model is obtained through training based on sample parameter information, and the sample parameter information at least includes parameters for characterizing the uplink capability and / or downlink capability of the sample terminal in the sample neighboring area.

18. The source network device according to claim 17, characterized in that: The obtaining of parameter prediction results includes: Acquire the parameter prediction result from the first network device; or, The parameter prediction result is obtained based on the parameter prediction model.

19. The source network device according to claim 18, characterized in that: The operations also include: Sending handover optimization request information to the second network device, where the handover optimization request information is used to obtain one or more of the following: The sample parameter information; The parameter prediction model; Feedback information after the terminal switches to the target cell; The parameters predict the outcome.

20. The source network device according to claim 17, characterized in that: The parameters used to characterize the uplink capability and / or downlink capability of the sample terminal in the sample neighboring area include one or more of the following: Uplink spectrum efficiency parameters and / or downlink spectrum efficiency parameters of the sample terminal in the sample neighboring area; The uplink bandwidth and / or downlink bandwidth of the sample terminal in the sample neighboring area; User experience parameters of sample terminals in sample neighborhoods.

21. The source network device according to any one of claims 17 to 20, characterized in that: The sample parameter information may also include one or more of the following: The cell identifier of the sample source cell; The cell identifier of the sample neighborhood; The identifier of the serving beam on the sample neighborhood; The identifier of the serving beam on the sample source cell; The identification of the sample terminal; Downlink transmission power of sample neighboring cells; Downlink transmit power of the serving beam in the sample neighboring cell; Downlink transmission power of the sample source cell; Downlink transmit power of the serving beam on the sample source cell; Uplink transmit power of the sample terminal; Number of downlink transmit antennas in the sample neighboring cell; The number of uplink receiving antennas in the sample neighborhood; The number of downlink transmit antennas of the sample source cell; The number of uplink receiving antennas of the sample source cell; The number of uplink transmit antennas of the sample terminal; The number of downlink receiving antennas of the sample terminal; The measurement result of at least one cell with a different frequency from the sample source cell reported by the sample terminal; The measurement result of at least one cell with the same frequency as the sample source cell reported by the sample terminal; The measurement results of the sample terminal measured by the sample neighboring area; The measurement result of the sample source cell on the sample terminal; Channel quality indicator CQI and / or downlink modulation and coding scheme index MCS Index of the sample terminal; Uplink MCS Index of the sample terminal; Load status of the sample neighborhood; The load status of the sample source cell.

22. The source network device according to claim 17, characterized in that: The input parameters of the parameter prediction model include one or more of the following: The cell identifier of the neighboring cell; An identifier of a serving beam on the neighboring cell; The cell identifier of the source cell; The identifier of the serving beam on the source cell; an identification of the terminal; Downlink transmission power of the neighboring cell; The downlink transmission power of the serving beam in the neighboring cell; Downlink transmit power of the source cell; Downlink transmit power of the serving beam on the source cell; The uplink transmission power of the terminal; The number of downlink transmitting antennas of the neighboring cell; The number of uplink receiving antennas of the neighboring cell; Number of downlink transmit antennas of the source cell; The number of uplink receiving antennas of the source cell; The number of uplink transmit antennas of the terminal; The number of downlink receiving antennas of the terminal; The effective uplink bandwidth of the terminal in the neighboring cell; The downlink effective bandwidth of the terminal in the neighboring cell; The uplink idle bandwidth of the neighboring cell; downlink idle bandwidth of the neighboring cell; The measurement result of at least one cell having a frequency different from that of the source cell reported by the terminal; The measurement result of at least one cell having the same frequency as the source cell reported by the terminal; a measurement result of the source cell measuring the terminal; The load status of the neighboring cell; Load status of the source cell.

23. The source network device according to claim 17, characterized in that: The performance parameters after the terminal switches to the neighboring cell include one or more of the following: A measurement result of the neighboring cell measuring the terminal; CQI and / or downlink MCSIndex of the terminal; An uplink MCS Index of the terminal; A downlink spectrum efficiency parameter of the terminal in the neighboring cell; An uplink spectrum efficiency parameter of the terminal in the neighboring cell; User experience parameters of the terminal in the neighboring cell.

24. The source network device according to claim 17 or 23, characterized in that: The parameter prediction results may also include one or more of the following: The cell identifier of the neighboring cell; The reliability of the parameter prediction results.

25. The source network device according to claim 19, characterized in that: The switching optimization request information includes one or more of the following: The cell identifier of the sample source cell; The cell identifier of the sample neighborhood; first indication information, where the first indication information is used to indicate starting, updating or stopping collecting the sample parameter information; first cycle information, where the first cycle information is used to indicate a cycle for sending the sample parameter information to the source network device; first direction information, where the first direction information is used to indicate the collection of uplink information and / or downlink information in the sample parameter information; second indication information, where the second indication information is used to indicate the type of the sample parameter information that needs to be collected; Data granularity identification; Quality of service QoS parameter type; Type of business; The identification of the sample terminal; first time length information, where the first time length information is used to indicate a time period for collecting the sample parameter information; third indication information, where the third indication information is used to indicate starting, updating or stopping sending the parameter prediction model to the source network device; second cycle information, where the second cycle information is used to indicate a cycle for sending the parameter prediction model to the source network device; The cell identifier of the source cell; The cell identifier of the target cell; Fourth indication information, where the fourth indication information is used to indicate starting, updating or stopping collecting feedback information after the terminal switches to the target cell; third cycle information, where the third cycle information is used to indicate a cycle for sending the feedback information to the source network device; second direction information, where the second direction information is used to indicate the collection of uplink information and / or downlink information in the feedback information; fifth indication information, where the fifth indication information is used to indicate the type of the feedback information to be collected; an identification of the terminal; second time length information, where the second time length information is used to indicate a time period for collecting the feedback information; Sixth indication information, the sixth indication information is used to indicate that the target cell is predicted and / or the credibility of the parameter prediction result.

26. The source network device according to claim 17, characterized in that: The selecting, based on the parameter prediction result, a target cell to which the terminal switches, includes: Based on the parameter prediction result, estimating the uplink capability and / or downlink capability of the terminal in the neighboring cell; A target cell to which the terminal switches is selected based on the uplink capability and / or downlink capability of the terminal in the neighboring cell.

27. The source network device according to claim 26, characterized in that: The selecting, based on the uplink capability and / or downlink capability of the terminal in the neighboring cell, a target cell to which the terminal switches, includes: Select a neighboring cell with the largest uplink capacity and / or downlink capacity, and determine it as the target cell to which the terminal switches; or A target cell to which the terminal switches is selected based on the uplink capability and / or downlink capability of the terminal in the neighboring cell and the traffic type of the terminal.

28. The source network device according to claim 27, characterized in that: The selecting a target cell to which the terminal switches based on the uplink capability and / or downlink capability of the terminal in the neighboring cell and the traffic type of the terminal includes: In the case where the terminal is a user with a large uplink traffic volume, selecting a target cell to which the terminal is switched from a neighboring cell having the largest corresponding uplink capacity and a corresponding uplink capacity greater than the uplink capacity of the terminal in the source cell; or In the case that the terminal is a user with a large downlink traffic volume, a target cell to which the terminal switches is selected from a neighboring cell whose corresponding downlink capacity is the largest and whose corresponding downlink capacity is greater than the downlink capacity of the terminal in the source cell.

29. The source network device according to claim 19 or 25, characterized in that: The operations also include: receiving the feedback information sent by the second network device; Based on the feedback information, the parameter prediction model is optimized.

30. A second network device, characterized in that: Including memory, transceiver, processor; A memory for storing a computer program; a transceiver for transmitting and receiving data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations: Receiving switching optimization request information sent by the source network device; According to the handover optimization request information, one or more of the following is sent to the source network device: Sample parameter information used to train parameter prediction models; The parameter prediction model; Feedback information after the terminal switches to the target cell; Parameter prediction results; the parameter prediction results include performance parameters of the terminal after switching to a neighboring cell predicted based on a parameter prediction model and / or an optimal neighboring cell identifier corresponding to the terminal.

31. The second network device according to claim 30, characterized in that: The switching optimization request information includes one or more of the following: The cell identifier of the sample source cell; The cell identifier of the sample neighborhood; first indication information, where the first indication information is used to indicate starting, updating or stopping collecting the sample parameter information; first cycle information, where the first cycle information is used to indicate a cycle for sending the sample parameter information to the source network device; first direction information, where the first direction information is used to indicate the collection of uplink information and / or downlink information in the sample parameter information; second indication information, where the second indication information is used to indicate the type of the sample parameter information that needs to be collected; Data granularity identification; Quality of service QoS parameter type; Type of business; The identification of the sample terminal; first time length information, where the first time length information is used to indicate a time period for collecting the sample parameter information; third indication information, where the third indication information is used to indicate starting, updating or stopping sending the parameter prediction model to the source network device; second cycle information, where the second cycle information is used to indicate a cycle for sending the parameter prediction model to the source network device; The cell identifier of the source cell; The cell identifier of the target cell; Fourth indication information, where the fourth indication information is used to indicate starting, updating or stopping collecting feedback information after the terminal switches to the target cell; third cycle information, where the third cycle information is used to indicate a cycle for sending the feedback information to the source network device; second direction information, where the second direction information is used to indicate the collection of uplink information and / or downlink information in the feedback information; fifth indication information, where the fifth indication information is used to indicate the type of the feedback information to be collected; an identification of the terminal; second time length information, where the second time length information is used to indicate a time period for collecting the feedback information; Sixth indication information, the sixth indication information is used to indicate that the target cell is predicted and / or the credibility of the parameter prediction result.

32. The second network device according to claim 30, characterized in that: The sample parameter information includes one or more of the following: The cell identifier of the sample source cell; The cell identifier of the sample neighborhood; The identifier of the serving beam on the sample neighborhood; The identifier of the serving beam on the sample source cell; The identification of the sample terminal; Downlink transmission power of sample neighboring cells; Downlink transmit power of the serving beam in the sample neighboring cell; Downlink transmission power of the sample source cell; Downlink transmit power of the serving beam on the sample source cell; Uplink transmit power of the sample terminal; Number of downlink transmit antennas in the sample neighboring cell; The number of uplink receiving antennas in the sample neighborhood; The number of downlink transmit antennas of the sample source cell; The number of uplink receiving antennas of the sample source cell; The number of uplink transmit antennas of the sample terminal; The number of downlink receiving antennas of the sample terminal; The measurement result of at least one cell with a different frequency from the sample source cell reported by the sample terminal; The measurement result of at least one cell with the same frequency as the sample source cell reported by the sample terminal; The measurement results of the sample terminal measured by the sample neighboring area; The measurement result of the sample source cell on the sample terminal; Channel quality indicator CQI and / or downlink modulation and coding scheme index MCS Index of the sample terminal; Uplink MCS Index of the sample terminal; Load status of the sample neighborhood; The load status of the sample source cell; Uplink spectrum efficiency parameters and / or downlink spectrum efficiency parameters of the sample terminal in the sample neighboring area; The uplink bandwidth and / or downlink bandwidth of the sample terminal in the sample neighboring area; User experience parameters of sample terminals in sample neighborhoods.

33. A device for selecting a target cell, characterized in that: include: An acquisition unit, configured to acquire a parameter prediction result; the parameter prediction result includes a performance parameter after the terminal switches to a neighboring cell and / or an optimal neighboring cell identifier corresponding to the terminal, which is predicted based on a parameter prediction model; A selection unit, configured to select a target cell to which the terminal switches based on the parameter prediction result; The parameter prediction model is obtained through training based on sample parameter information, and the sample parameter information at least includes parameters for characterizing the uplink capability and / or downlink capability of the sample terminal in the sample neighboring area.

34. A device for selecting a target cell, characterized in that: include: A second receiving unit, configured to receive the switching optimization request information sent by the source network device; A second sending unit is configured to send one or more of the following to the source network device according to the handover optimization request information: Sample parameter information used to train parameter prediction models; The parameter prediction model; Feedback information after the terminal switches to the target cell; Parameter prediction results; the parameter prediction results include performance parameters of the terminal after switching to a neighboring cell predicted based on a parameter prediction model and / or an optimal neighboring cell identifier corresponding to the terminal.

35. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is used to make a computer execute the method according to any one of claims 1 to 13.

36. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is used to make a computer execute the method according to any one of claims 14 to 16.

Images