Inter-frequency handover method and apparatus, electronic device, and storage medium

Abstract

The present disclosure provides a method and device for inter-frequency handover, electronic equipment and storage medium. The method is executed by an initial network device, and includes: obtaining target multi-dimensional data of a candidate cell sent by a terminal device, and a target inter-frequency handover model sent by a network management center server, and inputting the target multi-dimensional data into the target inter-frequency handover model to obtain a target cell identifier output by the target inter-frequency handover model, wherein the target cell identifier is used to identify a target cell for inter-frequency handover of the terminal device, and the target cell identifier is sent to the terminal device. Thus, the computational load of the initial network device can be saved, and the initial network device can efficiently determine the target cell identifier to be switched based on the target inter-frequency handover model sent by the network management center server.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of communication, and particularly relates to a frequency switching method and device, electronic equipment and storage medium. BACKGROUND

[0002] In a mobile communication system, a terminal device is usually connected to a base station with the strongest signal for communication. However, in some cases, the terminal device can be located near a base station with a weaker signal, which can cause the communication quality to decrease. In order to improve the communication quality and maintain a good user experience, the terminal device can perform inter-frequency switching to a cell served by a base station with a stronger signal.

[0003] In the related art, when the source cell and the target cell belong to different frequency points, inter-frequency measurement needs to be started. During the execution of the inter-frequency measurement, according to the 3GPP protocol, a measurement gap needs to be initiated for the terminal device, that is, a part of time (measurement gap time, usually 6 ms) is reserved, and during this period, the terminal device will not send and receive any data, thereby affecting the user experience of the terminal device.

[0004] Therefore, how to directly determine and switch to the optimal inter-frequency target cell without inter-frequency measurement has become a key research direction. SUMMARY

[0005] The present disclosure aims to at least solve one of the technical problems in the related art to some extent.

[0006] To this end, the present disclosure provides a frequency switching method and device, electronic equipment, storage medium and computer program product.

[0007] The frequency switching method provided by the first aspect of the present disclosure is executed by an initial network device, and the method comprises: obtaining target multi-dimensional data of a candidate cell sent by a terminal device, and a target inter-frequency switching model sent by a network management center server; inputting the target multi-dimensional data into the target inter-frequency switching model to obtain a target cell identifier output by the target inter-frequency switching model, wherein the target cell identifier is used to identify a target cell to which the terminal device is switched; and sending the target cell identifier to the terminal device.

[0008] The training method of the inter-frequency switching model provided by the second aspect of the present disclosure is executed by a network management center server, and the method comprises: obtaining target sample data, wherein the target sample data has a corresponding labeled cell identifier; training an initial inter-frequency switching model according to the target sample data to obtain a target inter-frequency switching model; and sending the target inter-frequency switching model to an initial network device.

[0009] The inter-frequency handover method provided by the third aspect of the present disclosure is executed by a terminal device, and the method comprises: receiving a target cell identifier sent by an initial network device; and switching communication between the initial network device and a target cell corresponding to the target cell identifier.

[0010] The inter-frequency handover device provided by the fourth aspect of the present disclosure is executed by an initial network device, and the device comprises: a first obtaining module, configured to obtain target multi-dimensional data of a candidate cell sent by a terminal device and a target inter-frequency handover model sent by a network management center server; a second obtaining module, configured to input the target multi-dimensional data into the target inter-frequency handover model to obtain a target cell identifier output by the target inter-frequency handover model, wherein the target cell identifier is used to identify a target cell to which the terminal device is to be handed over; and a first sending module, configured to send the target cell identifier to the terminal device.

[0011] The inter-frequency handover device provided by the fifth aspect of the present disclosure is executed by a network management center server, and the device comprises: a third obtaining module, configured to obtain target sample data, wherein the target sample data has a corresponding labeled cell identifier; a training module, configured to train an initial inter-frequency handover model according to the target sample data to obtain a target inter-frequency handover model; and a second sending module, configured to send the target inter-frequency handover model to an initial network device.

[0012] The inter-frequency handover device provided by the sixth aspect of the present disclosure is executed by a terminal device, and the device comprises: a receiving module, configured to receive a target cell identifier sent by an initial network device; and a switching module, configured to switch communication between the initial network device and a target cell corresponding to the target cell identifier.

[0013] The electronic device provided by the seventh aspect of the present disclosure comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the program, the inter-frequency handover method provided by the first aspect of the present disclosure is implemented, or the training method of the inter-frequency handover model provided by the second aspect of the present disclosure is implemented, or the inter-frequency handover method provided by the third aspect of the present disclosure is implemented.

[0014] The non-transitory computer-readable storage medium provided by the eighth aspect of the present disclosure has a computer program stored thereon, and when the program is executed by a processor, the inter-frequency handover method provided by the first aspect of the present disclosure is implemented, or the training method of the inter-frequency handover model provided by the second aspect of the present disclosure is implemented, or the inter-frequency handover method provided by the third aspect of the present disclosure is implemented.

[0015] The ninth aspect of the present disclosure provides a computer program product, when the processor of the computer program product executes, the processor executes the inter-frequency handover method provided by the first aspect of the present disclosure, or implements the training method of the inter-frequency handover model provided by the second aspect of the present disclosure, or implements the inter-frequency handover method provided by the third aspect of the present disclosure.

[0016] The inter-frequency handover method, device, electronic device, storage medium and computer program product provided by the present disclosure have at least the following beneficial effects: the initial network device obtains the target multi-dimensional data of the candidate cell sent by the terminal device and the target inter-frequency handover model sent by the network management center server, inputs the target multi-dimensional data into the target inter-frequency handover model to obtain the target cell identifier output by the target inter-frequency handover model, wherein the target cell identifier is used to identify the target cell to which the terminal device is inter-frequency handed over, and then the target cell identifier is sent to the terminal device. Thus, the computational load of the initial network device can be saved, and the initial network device can efficiently determine the target cell identifier to be handed over based on the target inter-frequency handover model sent by the network management center server.

[0017] The additional aspects and advantages of the present disclosure will be partially given in the following description, partially become obvious from the following description, or be known by the practice of the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0018] The above and / or additional aspects and advantages of the present disclosure will become apparent and more readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:

[0019] Figure 1 is a flowchart of an inter-frequency handover method according to an embodiment of the present disclosure;

[0020] Figure 2 is a flowchart of an inter-frequency handover method according to another embodiment of the present disclosure;

[0021] Figure 3 is a flowchart of an inter-frequency handover method according to an embodiment of the present disclosure;

[0022] Figure 4 is a flowchart of a training method of an inter-frequency handover model according to another embodiment of the present disclosure;

[0023] Figure 5 is a flowchart of an inter-frequency handover method according to an embodiment of the present disclosure;

[0024] Figure 6 is a flowchart of an inter-frequency handover method according to another embodiment of the present disclosure;

[0025] Figure 7is a structural schematic diagram of a frequency switching device according to an embodiment of the present disclosure;

[0026] Figure 8 is a structural schematic diagram of a frequency switching model training device according to an embodiment of the present disclosure;

[0027] Figure 9 is a structural schematic diagram of a frequency switching device according to an embodiment of the present disclosure;

[0028] Figure 10 A block diagram of an exemplary electronic device suitable for implementing an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0029] Embodiments of the present disclosure are described in detail below with reference to the accompanying drawings, in which examples of embodiments are shown, and wherein the same or similar reference numerals are used to represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present disclosure, and cannot be understood as a limitation of the present disclosure. On the contrary, the embodiments of the present disclosure include all changes, modifications and equivalents falling within the spirit and scope of the appended claims.

[0030] The technical solutions provided by the embodiments of the present disclosure can be applied to various systems, especially 5G systems. For example, the applicable systems can be Global System of Mobile Communication (GSM) systems, Code Division Multiple Access (CDMA) systems, Wideband Code Division Multiple Access (WCDMA) General Packet Radio Service (GPRS) systems, Long Term Evolution (LTE) systems, LTE Frequency Division Duplex (FDD) systems, LTE Time Division Duplex (TDD) systems, Long Term Evolution Advanced (LTE-A) systems, Universal Mobile Telecommunication System (UMTS), 5G New Radio (NR) systems, etc. The various systems all include terminals and network devices. The system can also include a core network part, such as an Evolved Packet System (EPS), a 5G system (5GS), etc.

[0031] Figure 1 is a flowchart of the inter-frequency handover method proposed by an embodiment of the present disclosure.

[0032] It should be noted that the execution subject of the inter-frequency handover method in this embodiment is an inter-frequency handover device, which can be implemented in software and / or hardware, and can be configured in a network device without limitation.

[0033] As shown in Figure 1 , the inter-frequency handover method comprises:

[0034] S101: Obtain the target multi-dimensional data of the candidate cell sent by the terminal device and the target inter-frequency handover model sent by the network management center server.

[0035] The inter-frequency handover method in the embodiment of the present disclosure can be executed by an initial network device, which can be, for example, a serving base station, which can serve a source cell.

[0036] In the embodiment of the present disclosure, the network management center server can be used to assist the initial network device in performing related calculations in the inter-frequency handover process, so as to effectively reduce the calculation load of the initial network device.

[0037] The target inter-frequency handover model can be an initial inter-frequency handover model pre-trained on the network management center server side based on sample data until the initial inter-frequency handover model converges to obtain the target inter-frequency handover model, which can be used to process the target multi-dimensional data to determine the cell identifier of the target cell to be inter-frequency handed over.

[0038] In the embodiment of the present disclosure, the target multi-dimensional data includes data of a fourth-generation mobile communication network type and data of a fifth-generation mobile communication network type.

[0039] The fourth-generation mobile communication network type data includes first mobile robustness optimization (MRO) data, first cell performance index data, first cell configuration parameter data, and first universal interface data.

[0040] The fourth-generation mobile communication network type data can be specifically as shown in Table 1:

[0041] Table 1

[0042]

[0043]

[0044] The data of the fifth-generation mobile communication network type includes: second MRO data; second cell performance index data; second cell configuration parameter data; and first general interface data.

[0045] The data of the fifth-generation mobile communication network type can be specifically as shown in Table 2:

[0046] Table 2

[0047]

[0048]

[0049]

[0050] S102: input the target multi-dimensional data into the target inter-frequency handover model to obtain a target cell identifier output by the target inter-frequency handover model, wherein the target cell identifier is used to identify a target cell to which the terminal device is inter-frequency handed over.

[0051] After obtaining the target multi-dimensional data of the candidate cell sent by the terminal device and the target inter-frequency handover model sent by the network management center server, the target multi-dimensional data can be input into the target inter-frequency handover model to obtain a target cell identifier output by the target inter-frequency handover model, wherein the target cell identifier is used to identify a target cell to which the terminal device is inter-frequency handed over.

[0052] In the embodiment of the present disclosure, the target inter-frequency handover model can be an initial inter-frequency handover model pre-trained based on sample data, until the initial inter-frequency handover model converges, and the initial inter-frequency handover model trained to converge is taken as the target inter-frequency handover model.

[0053] S103: send the target cell identifier to the terminal device.

[0054] After inputting the target multi-dimensional data into the target inter-frequency handover model to obtain a target cell identifier output by the target inter-frequency handover model, the target cell identifier can be sent to the terminal device, so that the terminal device can accurately learn the target cell identifier of the target cell to be handed over, thereby assisting the terminal device to subsequently hand over and establish a communication connection between the target cell based on the target cell identifier.

[0055] In the embodiment of the present disclosure, the initial network device obtains the target multi-dimensional data of the candidate cell sent by the terminal device and the target inter-frequency handover model sent by the network management center server, inputs the target multi-dimensional data into the target inter-frequency handover model, and obtains the target cell identifier output by the target inter-frequency handover model, wherein the target cell identifier is used to identify the target cell for inter-frequency handover of the terminal device, and the target cell identifier is sent to the terminal device. Thus, the computational load of the initial network device can be saved, and the initial network device can efficiently determine the target cell identifier to be switched based on the target inter-frequency handover model sent by the network management center server.

[0056] Figure 2 is a flowchart of an inter-frequency handover method according to another embodiment of the present disclosure.

[0057] As shown in Figure 2 , the inter-frequency handover method comprises the following steps.

[0058] S201: obtaining target multi-dimensional data of a candidate cell sent by a terminal device and a target inter-frequency handover model sent by a network management center server.

[0059] S202: inputting the target multi-dimensional data into the target inter-frequency handover model to obtain a target cell identifier output by the target inter-frequency handover model, wherein the target cell identifier is used to identify a target cell for inter-frequency handover of the terminal device.

[0060] S203: sending the target cell identifier to the terminal device.

[0061] The description of S201-S203 can be referred to the above embodiments, and will not be repeated here.

[0062] S204: obtaining initial sample data sent by the terminal device.

[0063] The data sent by the terminal device for training the initial inter-frequency handover model without processing is the initial sample data.

[0064] That is, in the embodiment of the present disclosure, the initial network device can obtain the initial sample data sent by the terminal device based on the communication link between the terminal device and the initial network device, and then process the initial sample data. The specific process can be referred to the subsequent embodiments, and will not be repeated here.

[0065] S205: data preprocessing of the initial sample data to obtain candidate sample data.

[0066] In the embodiments of the present disclosure, in the initial data, the MRO file contains periodic measurement data of all UEs in the cell coverage range, and part of the data has missing values; the wireless performance index data causes missing values (such as short statistical interval, failure, etc.); the MDT data has abnormal latitude and longitude data (such as missing latitude and longitude, false positives, etc.), thus, the initial sample data needs to be preprocessed to obtain candidate sample data, so as to improve the data quality of the sample data, thereby effectively guaranteeing the model training effect of the inter-frequency handover model.

[0067] In some embodiments, the data preprocessing of the initial sample data can be filling the missing values caused by the wireless performance index data, and / or removing the abnormal values of the abnormal latitude and longitude data of the MDT data, and / or normalizing the initial sample data, without limitation.

[0068] Optionally, in some embodiments, as shown in Figure 3 Figure 3 is a flowchart of an inter-frequency handover method according to another embodiment of the present disclosure, and the data preprocessing of the initial sample data to obtain candidate sample data can include:

[0069] S301: Determine whether the initial network device and the candidate network device apply the same baseband processing unit (BBU) pool.

[0070] Wherein, the candidate network device and the initial network device are adjacent.

[0071] In the embodiments of the present disclosure, determining whether the initial network device and the candidate network device apply the same baseband processing unit (BBU) pool can be checking the physical connection of the two network devices. If they are connected to the same BBU pool through a wire, it can be determined that they apply the same BBU pool, or it can also be checking the BBU related configuration information in the management interface or configuration interface of the device. For example, the BBU number, BBU pool configuration, IP address, etc. can be checked. If the configuration information of the two devices is the same, it can be determined that they apply the same BBU pool.

[0072] S302: If the initial network device and the candidate network device apply the same BBU pool, determine the first utilization rate of the BBU in the initial device and the second utilization rate of the BBU in the candidate network device adjacent to the initial network device.

[0073] ​The utilization rate of the BBU in the initial network device, i.e., can be referred to as a first utilization rate, which can be used to describe the workload of the processing and computing tasks undertaken by the BBU in the initial network device. Correspondingly, the utilization rate of the BBU in the candidate network device, i.e., can be referred to as a second utilization rate, which can be used to describe the workload of the processing and computing tasks undertaken by the BBU in the candidate network device.

[0074] In the embodiments of the present disclosure, after determining that the initial network device and the candidate network device apply the same BBU pool, the first utilization rate of the BBU in the initial network device and the second utilization rate of the BBU in the candidate network device adjacent to the initial network device can be determined.

[0075] S303: determining a target network device from the candidate network device and the initial network device according to the first utilization rate and the second utilization rate, wherein the target network device is used to perform data preprocessing on the initial sample data to obtain candidate sample data.

[0076] Optionally, in some embodiments, determining the target network device from the candidate network device and the initial network device according to the first utilization rate and the second utilization rate can be that when the first utilization rate is less than the second utilization rate, the initial network device is taken as the target network device, or when the first utilization rate is greater than or equal to the second utilization rate, the second utilization rate with the minimum value is determined from the plurality of second utilization rates, and the candidate network device corresponding to the second utilization rate with the minimum value is taken as the target network device.

[0077] That is to say, in the embodiments of the present disclosure, the first utilization rate and the second utilization rate can be compared, and when the first utilization rate is less than the second utilization rate, the initial network device is taken as the target network device, or when the first utilization rate is greater than or equal to the second utilization rate, the second utilization rate with the minimum value is determined from the plurality of second utilization rates, and the candidate network device corresponding to the second utilization rate with the minimum value is taken as the target network device.

[0078] Optionally, in some embodiments, after taking the initial network device as the target network device, the initial sample data can be preprocessed to obtain candidate sample data, and the candidate sample data can be sent to the network management center server.

[0079] The data preprocessing on the initial sample data includes but is not limited to the following modes:

[0080] 1. Missing value filling processing: processing missing values in high-dimensional data flow, including but not limited to fixed value filling, calculation result filling (minimum value, correlation value, mean value, maximum value) and other processing modes, for example:

[0081] (1) RSRP missing values can be filled with minimum values, and the RSRP missing values of the 4G cell are filled with 0 (converted to -140 dBm), and the RSRP missing values of the 5G cell are filled with 0 (converted to -156 dBm);

[0082] (2) The PCI and Arfcn missing values of the neighboring cells in the MRO are associated with and filled with the PCI and Arfcn of the corresponding neighboring cells of the cell in the neighboring cell parameter configuration table;

[0083] (3) The handover success rate and the uplink interference level are filled with the average of the last 4 15-minute granularity indicators before the performance table is reported;

[0084] (4) The uplink interference level and the uplink PRB utilization rate are filled with the maximum of the last 4 15-minute granularity indicators before the performance table is reported.

[0085] 2. Outlier processing: based on the distance from the sampling point to the service cell converted from the latitude and longitude reported by the user (the data without latitude and longitude is directly deleted), the data with a distance greater than a certain value L from the service cell is removed to ensure the reliability of the high-dimensional data stream, for example:

[0086] When the distance d between the latitude and longitude data (λA, ΦA) reported by the cell measurement report and the latitude and longitude (λB, ΦB) of the site in the cell configuration table is greater than the set value L, the outlier data is removed to avoid affecting the training result, wherein the calculation formula of the distance d between any two points is:

[0087] d = 111.12 cos1 / [sinΦAsinΦBcosΦAcosΦBcos(λB—λA)];

[0088] Wherein, the longitude and latitude of point A are λA and ΦA respectively, the longitude and latitude of point B are λB and ΦB respectively, and d is the distance.

[0089] In the embodiment of the disclosure, after the initial network device is taken as the target network device, the initial sample data can be preprocessed to obtain candidate sample data, and the candidate sample data is sent to the network management center server.

[0090] Optionally, in some embodiments, after the candidate network device corresponding to the second utilization rate with the minimum value is taken as the target network device, the initial sample data can be preprocessed by the target network device to obtain candidate sample data, and the candidate sample data is sent to the network management center server.

[0091] That is to say, in the embodiment of the disclosure, after the candidate network device corresponding to the second utilization rate with the minimum value is taken as the target network device, the initial network device can send a corresponding control instruction to the target network device to control the target network device to perform data preprocessing on the initial sample data (the specific explanation of the data preprocessing on the initial sample data can be referred to the above embodiment, which will not be described here again) to obtain candidate sample data, and send the candidate sample data to the network management center server.

[0092] Optionally, in some embodiments, sending the candidate sample data to the network management center server can include determining a utilization rate difference between the second utilization rate with the minimum value and the first utilization rate, and when the utilization rate difference is less than a difference threshold value, and after receiving the candidate sample data sent by the target network device, sending the candidate sample data to the network management center server, or when the utilization rate difference is greater than or equal to the difference threshold value, controlling the target network device to send the candidate sample data to the network management center server.

[0093] That is to say, in the embodiment of the disclosure, the utilization rate difference between the first utilization rate and the second utilization rate can be determined, and the determined utilization rate difference and the difference threshold value are compared, and when the utilization rate difference is less than the difference threshold value, the candidate sample data sent by the target network device is received, and then the initial network device can send the candidate sample data to the network management center server, or when the utilization rate difference is greater than or equal to the difference threshold value, the target network device is controlled to send the candidate sample data to the network management center server.

[0094] S304: If the initial network device and the candidate network device do not apply the same BBU pool, determining the utilization rate with the minimum value from the first utilization rate and the second utilization rate.

[0095] In the embodiment of the disclosure, when it is determined that the initial network device and the candidate network device do not apply the same BBU pool, the first utilization rate and the second utilization rate can be compared, and the utilization rate with the minimum value is determined from the first utilization rate and the second utilization rate.

[0096] S305: Taking the network device corresponding to the utilization rate with the minimum value as the target network device.

[0097] In the embodiment of the disclosure, after the utilization rate with the minimum value is determined from the first utilization rate and the second utilization rate, the network device corresponding to the utilization rate with the minimum value can be taken as the target network device.

[0098] S306: If the network device corresponding to the utilization rate with the minimum value is the initial network device, performing data preprocessing on the initial sample data to obtain candidate sample data.

[0099] After the network device corresponding to the utilization rate with the minimum value is taken as the target network device, the embodiment of the present disclosure can be that, in a case where it is determined that the network device corresponding to the utilization rate with the minimum value is the initial network device, the initial sample data is preprocessed (for specific explanation of preprocessing of the initial sample data, refer to the above embodiment, which will not be described here again) to obtain candidate sample data.

[0100] S307: sending the candidate sample data to the network management center server.

[0101] In the embodiment of the present disclosure, in a case where it is determined that the target network device is the initial network device, the initial network device can send the candidate sample data to the network management center server based on a communication link between the initial network device and the network center server or a data transmission interface.

[0102] S308: if the network device corresponding to the utilization rate with the minimum value is the candidate network device, controlling the target network device to preprocess the initial sample data to obtain the candidate sample data.

[0103] After the network device corresponding to the utilization rate with the minimum value is taken as the target network device, the embodiment of the present disclosure can be that, in a case where it is determined that the network device corresponding to the utilization rate with the minimum value is the candidate network device, a control instruction is generated and sent to the target network device to control the target network device to preprocess the initial sample data (for specific explanation of preprocessing of the initial sample data, refer to the above embodiment, which will not be described here again) to obtain the candidate sample data.

[0104] S309: controlling the target network device to send the candidate sample data to the network management center server.

[0105] In a case where it is determined that the target network device is the candidate network device, the embodiment of the present disclosure can be that the initial network device generates and sends a control instruction to the target network device to control the target network device to send the candidate sample data to the network management center server.

[0106] In the embodiment of the present disclosure, whether the initial network device and the candidate network device apply the same baseband processing unit (BBU) pool is determined, and when the initial network device and the candidate network device apply the same BBU pool, the first utilization rate of the BBU in the initial device and the second utilization rate of the BBU in the candidate network device adjacent to the initial network device are determined, and the target network device is determined from the candidate network device and the initial network device according to the first utilization rate and the second utilization rate, wherein the target network device is used to perform data preprocessing on the initial sample data to obtain candidate sample data, and when the initial network device and the candidate network device do not apply the same BBU pool, the utilization rate with the minimum value is determined from the first utilization rate and the second utilization rate, and the network device corresponding to the utilization rate with the minimum value is taken as the target network device, and when the network device corresponding to the utilization rate with the minimum value is the initial network device, the initial sample data is preprocessed to obtain candidate sample data, and the candidate sample data is sent to the network management center server, and when the network device corresponding to the utilization rate with the minimum value is the candidate network device, the target network device is controlled to perform data preprocessing on the initial sample data to obtain candidate sample data, and the target network device is controlled to send the candidate sample data to the network management center server, so that the data of the busy base station can be uniformly preprocessed by the BBU with less load, thereby reducing the work load of other base stations, improving the efficiency of data preprocessing, and effectively avoiding overloading of the base station.

[0107] Figure 4 is a flow diagram of a training method of a frequency switching model according to an embodiment of the present disclosure.

[0108] It should be noted that the execution subject of the training method of the frequency switching model is a training device of the frequency switching model, and the device can be realized by software and / or hardware. The device can be configured in a network device, and no limitation is made in this regard.

[0109] As shown in Figure 4 , the training method of the frequency switching model comprises the following steps.

[0110] S401: Obtain target sample data.

[0111] The target sample data can be used to train an initial frequency switching model, and the target sample data can have a corresponding labeled cell identifier.

[0112] In the embodiment of the present disclosure, the target sample data can be received, and then a preset number of candidate sample data can be taken as target sample data, or the candidate sample data can be manually labeled to obtain target sample data and a labeled cell identifier corresponding to the sample data.

[0113] S402: training the initial inter-frequency handover model according to the target sample data to obtain a target inter-frequency handover model.

[0114] After obtaining the sample data, the embodiment of the present disclosure can train the initial inter-frequency handover model according to the target sample data to obtain the target inter-frequency handover model.

[0115] In some embodiments, training the initial inter-frequency handover model according to the target sample data to obtain the target inter-frequency handover model can be inputting the target sample data into the initial inter-frequency handover model to obtain a predicted cell identifier output by the initial inter-frequency handover model, and then determining a loss value between the predicted cell identifier and a labeled cell identifier based on a preset loss function, and determining that the initial inter-frequency handover model converges when the loss value is less than a preset loss threshold to obtain the target inter-frequency handover model.

[0116] S403: sending the target inter-frequency handover model to the initial network device.

[0117] In the embodiment of the present disclosure, the network management center server obtains the target sample data, wherein the target sample data has a corresponding labeled cell identifier, can train the initial inter-frequency handover model according to the target sample data to obtain the target inter-frequency handover model, and send the target inter-frequency handover model to the initial network device. Since the network management center server has high computing power, the training efficiency of the inter-frequency handover model can be improved, and since the inter-frequency handover model is trained based on the network management center server, the base station computing load can be reduced, thereby avoiding affecting the communication stability of the network device.

[0118] Figure 5 is a flowchart of a method for training an inter-frequency handover model according to another embodiment of the present disclosure.

[0119] As shown in Figure 5 , the method for training the inter-frequency handover model comprises:

[0120] S501: receiving candidate sample data.

[0121] The candidate sample data is sent by the initial network device controlling the target network device, or the candidate sample data is sent by the initial network device.

[0122] That is, in the embodiment of the present disclosure, the network management center server can receive the candidate sample data sent by the initial network device controlling the target network device, or receive the candidate sample data directly sent by the initial network device, and then the network management center server can process the candidate sample data to obtain target sample data for training the inter-frequency handover model. For details, please refer to the subsequent embodiments, which will not be described here.

[0123] S502: Determine a target communication network type corresponding to the candidate sample data.

[0124] In the embodiments of the present disclosure, the candidate sample data can have a corresponding target communication network type.

[0125] In the embodiments of the present disclosure, the target communication network type includes a fourth generation mobile communication network type and a fifth generation mobile communication network type.

[0126] The candidate sample data of the fourth generation mobile communication network type includes third MRO data, third cell performance index data, third cell configuration parameter data, and third general interface data.

[0127] The candidate sample data of the fifth generation mobile communication network type includes fourth MRO data, fourth cell performance index data, fourth cell configuration parameter data, and fourth general interface data.

[0128] S503: Process the candidate sample data based on a preset data association rule for the target communication network type to determine a labeled cell identifier corresponding to the candidate sample data.

[0129] After determining the target communication network type corresponding to the candidate sample data, the embodiments of the present disclosure can process the candidate sample data based on a preset data association rule for the target communication network type to determine a labeled cell identifier corresponding to the candidate sample data.

[0130] Optionally, in some embodiments, processing the candidate sample data based on the preset data association rule for the target communication network type can include, in the case that the target communication network type is the fourth generation mobile communication network type, processing the fourth MRO data and the fourth general interface data based on a first data association rule corresponding to the fourth generation mobile communication network type, or in the case that the target communication network type is the fifth generation mobile communication network type, processing the third MRO data and the third general interface data based on a second data association rule corresponding to the fifth generation mobile communication network type.

[0131] In the embodiments of the present disclosure, in the case that the target communication network type is the fourth generation mobile communication network type, the fourth MRO data and the fourth general interface data are processed based on a first data association rule corresponding to the fourth generation mobile communication network type to determine a labeled cell identifier corresponding to the candidate sample data.

[0132] The first data association rule includes:

[0133] LTE_MRO.ECI = LTE_UU.ECI

[0134] AND

[0135] LTE_MRO.MME_UE_S1AP_ID = LTE_UU.MME_UE_S1AP_ID

[0136] AND

[0137] ((LTE_UU.Procedure_Type = 7 or LTE_UU.Procedure_Type = 8) and LTE_UU.Procedure_Stat

[0138] us = 1)

[0139] AND

[0140] LTE_UU.Procedure_Start_Time between (LTE_MRO.objTimeStamp - t, LTE_MRO.bjTime

[0141] Stamp + t)

[0142] AND

[0143] LTE_MRO.NRScArfcn!= LTE_UU.Target_Arfcn.

[0144] The related field introduction in the first data association rule can be as shown in Table 3.

[0145] Table 3

[0146]

[0147] That is to say, in the embodiment of the disclosure, the fourth MRO data and the fourth general interface data can be associated based on the first data association rule corresponding to the fourth generation mobile communication network type, to determine the labeled cell identifier corresponding to the candidate sample data.

[0148] In the embodiment of the disclosure, in the case where the target communication network type is the fifth generation mobile communication network type, the third MRO data and the third general interface data are processed based on the second data association rule corresponding to the fifth generation mobile communication network type, to determine the labeled cell identifier corresponding to the candidate sample data.

[0149] The second data association rule includes:

[0150] NR_MRO.ECI = N1N2_Interface.ECI

[0151] AND

[0152] NR MRO. objAMFUENGAPID = N1N2_Interface. objAMFUENGAPID

[0153] AND

[0154] NR MRO. objAMFRegionID = N1N2_Interface. objAMFRegionID

[0155] AND

[0156] NR MRO. objAMFSetID = N1N2_Interface. objAMFSetID

[0157] AND

[0158] NR MRO. objAMFPointer = N1N2_Interface. objAMFPointer

[0159] AND

[0160] ((N1N2_Interface. Procedure_Type = 16 or N1N2_Interface. Procedure_Type = 19) and N1N2

[0161] _Interface. Procedure_Status = 1))

[0162] AND

[0163] N1N2_Interface. Procedure_Start_Time between (NR_MRO. objTimeStamp - t, NR_MRO.

[0164] bjTimeStamp + t)

[0165] AND

[0166] NR MRO. NRScArfcn! = N1N2_Interface. Target_Arfcn.

[0167] The related field introduction in the second data association rule can be as shown in Table 4:

[0168] Table 4

[0169]

[0170] S504: The candidate sample data and the labeled cell identifier corresponding to the candidate sample data are taken as target sample data together.

[0171] After the candidate sample data is processed based on the data association rule preset for the target communication network type to determine the labeled cell identifier corresponding to the candidate sample data, the embodiment of the present disclosure can take the candidate sample data and the labeled cell identifier corresponding to the candidate sample data as target sample data together.

[0172] In the embodiment of the present disclosure, the target sample data of the fourth generation mobile communication network type can be, for example:

[0173]

[0174] Wherein "ECI, LTE_ScSSRSRP_1, LTE_ScSSRSRQ_1, LTE_ScSSSINR_1,..." is the feature data, "inter_cell" is the labeled cell identifier, indicating the target cell of the ECI handover of the serving cell, and the labeled cell identifier not associated with the inter-frequency handover target cell is "not handover".

[0175] In the embodiment of the present disclosure, the target sample data of the fifth generation mobile communication network type can be, for example:

[0176]

[0177] Wherein "NCI, NRScSSRSRP_1, NRScSSRSRQ_1, NRScSSSINR_1,..." is the feature data, "inter_cell" is the labeled cell identifier, indicating the inter-frequency target cell of the ECI handover of the serving cell, and the labeled cell identifier not associated with the inter-frequency handover target cell is "not handover".

[0178] S505: Training the initial inter-frequency handover model according to the target sample data to obtain a target inter-frequency handover model.

[0179] S506: Sending the target inter-frequency handover model to the initial network device.

[0180] The description of S505-S506 can be referred to the above-mentioned embodiments, and will not be repeated here.

[0181] In the embodiment of the present disclosure, candidate sample data is received, a target communication network type corresponding to the candidate sample data is determined, and the target communication network type corresponding to the candidate sample data is determined. Then, the candidate sample data is processed based on a preset data association rule for the target communication network type to determine a labeled cell identifier corresponding to the candidate sample data. Then, the candidate sample data and the labeled cell identifier corresponding to the candidate sample data are jointly used as target sample data. The initial inter-frequency handover model is trained according to the target sample data to obtain a target inter-frequency handover model. The target inter-frequency handover model is sent to the initial network device. Since the network management center server has high computing power, the training efficiency of the inter-frequency handover model can be improved. Since the inter-frequency handover model is trained based on the network management center server, the computing load of the base station can be reduced, thereby avoiding affecting the communication stability of the network device.

[0182] Figure 6 FIG. 1 is a flowchart of an inter-frequency handover method according to an embodiment of the present disclosure.

[0183] It should be noted that the execution subject of the inter-frequency handover method in this embodiment is an inter-frequency handover device. The device can be implemented by software and / or hardware. The device can be configured in a network device, and the present disclosure does not limit the device.

[0184] As shown in FIG. 1, the inter-frequency handover method includes the following steps. Figure 6

[0185] S601: Receiving target cell identifier sent by initial network device.

[0186] In the embodiment of the present disclosure, the terminal device can receive the target cell identifier sent by the initial network device based on the communication link between the terminal device and the initial network device.

[0187] S602: Switching the communication between the target cell corresponding to the target cell identifier.

[0188] In the embodiment of the present disclosure, after receiving the target cell identifier sent by the initial network device, the terminal device can switch the communication between the target cell corresponding to the target cell identifier. Thus, the inter-frequency handover can be triggered directly based on the target cell identifier sent by the initial network device, thereby effectively simplifying the operation logic of the inter-frequency handover and improving the efficiency of the inter-frequency handover, thereby effectively improving the user experience.

[0189] Figure 7 FIG. 2 is a structural diagram of an inter-frequency handover device according to an embodiment of the present disclosure.

[0190] As shown in FIG. 2, the inter-frequency handover device 70 is executed by the initial network device. The device includes the following components. Figure 7

[0191] ​​The first obtaining module 701 is configured to obtain target multi-dimensional data of a candidate cell sent by a terminal device and a target inter-frequency handover model sent by a network management center server.

[0192] The second obtaining module 702 is configured to input the target multi-dimensional data into the target inter-frequency handover model to obtain a target cell identifier output by the target inter-frequency handover model, wherein the target cell identifier is used to identify a target cell to which the terminal device is inter-frequency handed over.

[0193] The first sending module 703 is configured to send the target cell identifier to the terminal device.

[0194] In some embodiments of the present disclosure, the target multi-dimensional data includes data of a fourth-generation mobile communication network type and data of a fifth-generation mobile communication network type.

[0195] The data of the fourth-generation mobile communication network type includes:

[0196] First mobile robustness optimization (MRO) data, first cell performance index data, first cell configuration parameter data, and first general interface data.

[0197] The data of the fifth-generation mobile communication network type includes:

[0198] Second MRO data, second cell performance index data, second cell configuration parameter data, and first general interface data.

[0199] In some embodiments of the present disclosure, the inter-frequency handover device 70 is specifically used for:

[0200] Obtaining initial sample data sent by a terminal device.

[0201] Performing data preprocessing on the initial sample data to obtain candidate sample data, wherein the candidate sample data is used to train an initial inter-frequency handover model to obtain a target inter-frequency handover model.

[0202] In some embodiments of the present disclosure, the inter-frequency handover device 70 is specifically used for:

[0203] Determining whether an initial network device and a candidate network device apply a same baseband processing unit (BBU) pool, wherein the candidate network device and the initial network device are adjacent.

[0204] If the initial network device and the candidate network device apply the same BBU pool, determining a first utilization rate of a BBU in the initial device and a second utilization rate of a BBU in the candidate network device adjacent to the initial network device.

[0205] According to the first utilization rate and the second utilization rate, a target network device is determined from the candidate network device and the initial network device, wherein the target network device is used to perform data preprocessing on the initial sample data to obtain candidate sample data.

[0206] In some embodiments of the present disclosure, the inter-frequency handover apparatus 70 is specifically used for:

[0207] If the initial network device and the candidate network device do not apply the same BBU pool, a utilization rate with a minimum value is determined from the first utilization rate and the second utilization rate;

[0208] The network device corresponding to the utilization rate with the minimum value is taken as the target network device.

[0209] In some embodiments of the present disclosure, the inter-frequency handover apparatus 70 is specifically used for:

[0210] If the network device corresponding to the utilization rate with the minimum value is the initial network device, the initial sample data is preprocessed to obtain the candidate sample data;

[0211] The candidate sample data is sent to the network management center server.

[0212] In some embodiments of the present disclosure, the inter-frequency handover apparatus 70 is specifically used for:

[0213] If the first utilization rate is less than the second utilization rate, the initial network device is taken as the target network device.

[0214] If the first utilization rate is greater than or equal to the second utilization rate, a second utilization rate with a minimum value is determined from the plurality of second utilization rates, and the candidate network device corresponding to the second utilization rate with the minimum value is taken as the target network device.

[0215] In some embodiments of the present disclosure, the inter-frequency handover apparatus 70 is specifically used for:

[0216] After the initial network device is taken as the target network device, the initial sample data is preprocessed to obtain the candidate sample data;

[0217] The candidate sample data is sent to the network management center server.

[0218] In some embodiments of the present disclosure, the inter-frequency handover apparatus 70 is specifically used for:

[0219] After the candidate network device corresponding to the second utilization rate with the minimum value is taken as the target network device, the target network device is controlled to preprocess the initial sample data to obtain the candidate sample data;

[0220] The candidate sample data is sent to the network management center server.

[0221] In some embodiments of the present disclosure, the inter-frequency handover device 70 is specifically used for:

[0222] determining a utilization difference between the second utilization and the first utilization with the minimum value;

[0223] if the utilization difference is less than the difference threshold, sending the candidate sample data to the network management center server after receiving the candidate sample data sent by the target network device;

[0224] if the utilization difference is greater than or equal to the difference threshold, controlling the target network device to send the candidate sample data to the network management center server.

[0225] Corresponding to the inter-frequency handover method provided by the above-mentioned Figures 1 to 3 embodiments, the present disclosure also provides an inter-frequency handover device. Since the inter-frequency handover device provided by the embodiments of the present disclosure corresponds to the inter-frequency handover method provided by the above-mentioned Figures 1 to 3 embodiments, the implementation of the inter-frequency handover method is also applicable to the inter-frequency handover device proposed by the embodiments of the present disclosure, and will not be described in detail in the embodiments of the present disclosure.

[0226] In the present embodiment, the initial network device obtains the target multi-dimensional data of the candidate cell sent by the terminal device and the target inter-frequency handover model sent by the network management center server, inputs the target multi-dimensional data into the target inter-frequency handover model, and obtains the target cell identifier output by the target inter-frequency handover model, wherein the target cell identifier is used to identify the target cell to which the terminal device is inter-frequency handed over, and then the target cell identifier is sent to the terminal device. Thus, the computational load of the initial network device can be saved, and the initial network device can efficiently determine the target cell identifier to be handed over based on the target inter-frequency handover model sent by the network management center server.

[0227] Figure 8 is a structural schematic diagram of the training device of the inter-frequency handover model proposed by an embodiment of the present disclosure.

[0228] As Figure 8 shown, the training device 80 of the inter-frequency handover model is executed by the network management center server, and the device comprises:

[0229] The third acquisition module 801 is configured to acquire target sample data, wherein the target sample data has a corresponding labeled cell identifier.

[0230] The training module 802 is configured to train the initial inter-frequency handover model according to the target sample data to obtain a target inter-frequency handover model.

[0231] The second sending module 803 is configured to send the target inter-frequency handover model to the initial network device.

[0232] In some embodiments of the present disclosure, the third obtaining module 801 is further configured to:

[0233] receive candidate sample data, wherein the candidate sample data is sent by the initial network device to the target network device, or the candidate sample data is sent by the initial network device;

[0234] determine a target communication network type corresponding to the candidate sample data;

[0235] process the candidate sample data based on a preset data association rule for the target communication network type to determine a labeled cell identifier corresponding to the candidate sample data;

[0236] collect the candidate sample data and the labeled cell identifier corresponding to the candidate sample data as target sample data.

[0237] In some embodiments of the present disclosure, the target communication network type includes a fourth generation mobile communication network type and a fifth generation mobile communication network type.

[0238] The candidate sample data of the fourth generation mobile communication network type includes:

[0239] third MRO data, third cell performance index data, third cell configuration parameter data, and third general interface data;

[0240] The candidate sample data of the fifth generation mobile communication network type includes:

[0241] fourth MRO data, fourth cell performance index data, fourth cell configuration parameter data, and fourth general interface data.

[0242] In some embodiments of the present disclosure, the third obtaining module 801 is further configured to:

[0243] if the target communication network type is the fourth generation mobile communication network type, then process the fourth MRO data and the fourth general interface data based on a first data association rule corresponding to the fourth generation mobile communication network type;

[0244] if the target communication network type is the fifth generation mobile communication network type, then process the third MRO data and the third general interface data based on a second data association rule corresponding to the fifth generation mobile communication network type.

[0245] The training method of the inter-frequency handover model provided in the above Figures 4 to 5 Embodiments provides a training device of an inter-frequency handover model. The training device of the inter-frequency handover model provided in the above Figures 4 to 5The training method for the inter-frequency handover model provided in the embodiments corresponds to the training device for the inter-frequency handover model proposed in the embodiments of this disclosure, and will not be described in detail in the embodiments of this disclosure.

[0246] In this embodiment, the network management center server acquires target sample data, which has a corresponding labeled cell identifier. It can train an initial inter-frequency handover model based on the target sample data to obtain a target inter-frequency handover model, and then send the target inter-frequency handover model to the initial network device. Since the network management center server has high computing power, the training efficiency of the inter-frequency handover model can be improved. Furthermore, since the inter-frequency handover model is trained based on the network management center server, the computational load on the base station can be reduced, thereby avoiding affecting the communication stability of the network device.

[0247] Figure 9 This is a schematic diagram of the structure of a frequency switching device proposed in an embodiment of this disclosure.

[0248] like Figure 9 As shown, the inter-frequency switching device 90 is executed by the terminal equipment, and the device includes:

[0249] Receiver module 901 is used to receive the target cell identifier sent by the initial network device;

[0250] The switching module 902 is used to switch the communication between the target cells corresponding to the target cell identifier.

[0251] With the above Figure 6 Corresponding to the inter-frequency switching method provided in the embodiments, this disclosure also provides an inter-frequency switching device. Because the inter-frequency switching device provided in the embodiments of this disclosure is similar to the one described above... Figure 6 The frequency switching method provided in the embodiments corresponds to the frequency switching method, and therefore the implementation of the frequency switching method is also applicable to the frequency switching device proposed in the embodiments of this disclosure, which will not be described in detail in the embodiments of this disclosure.

[0252] In this embodiment of the disclosure, after receiving the target cell identifier sent by the initial network device, the terminal device may switch to communication between the target cell corresponding to the target cell identifier. Thus, based on the target cell identifier sent by the initial network device, inter-frequency handover can be directly triggered, thereby effectively simplifying the operation logic of inter-frequency handover, improving the efficiency of inter-frequency handover, and thus effectively improving the user experience.

[0253] To implement the above embodiments, this disclosure also proposes an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the frequency switching method proposed in the foregoing embodiments of this disclosure.

[0254] To implement the above embodiments, this disclosure also proposes a non-transitory computer-readable storage medium storing a computer program that, when executed by a processor, implements the frequency switching method proposed in the foregoing embodiments of this disclosure.

[0255] To implement the above embodiments, this disclosure also proposes a computer program product that, when the instruction processor in the computer program product is executed, performs the frequency switching method proposed in the foregoing embodiments of this disclosure.

[0256] Figure 10 A block diagram of an exemplary electronic device suitable for implementing embodiments of the present disclosure is shown. Figure 10 The electronic device 12 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0257] like Figure 10 As shown, the electronic device 12 is represented in the form of a general-purpose computing device. The components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and bus 18 connecting different system components (including system memory 28 and processing unit 16).

[0258] Bus 18 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. Examples of these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0259] Electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by electronic device 12, including volatile and non-volatile media, removable and non-removable media.

[0260] Memory 28 can include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Electronic device 12 can further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 can be provided for reading from and writing to a non-removable, non-volatile magnetic media (not shown and typically called a "hard drive"). Figure 10

[0261] Although Figure 10 not shown in FIG. 1, a disk drive, an optical disk drive and / or a tape drive, a flash memory or other similar medium can also be used. In these instances, each can also be connected to bus 18 by one or more data media interfaces. The drives and their associated computer-readable media provide nonvolatile storage of data, data structures, computer-executable instructions and so on for electronic device 12. For example, a hard disk can used for non-volatile memory according to some embodiments. Although

[0262] Program / utility 40 having a set (at least one) of program modules 42 can be stored in memory 28 by way of example, such as an operating system, one or more application programs, other program modules, and program data, each or some combination thereof, which may

[0263] ​The electronic device 12 can also communicate with one or more external devices 14 such as a keyboard or a pointing device, a display 24, etc.; other devices that enable a user to interact with the electronic device 12; and / or any devices (e.g., a networking module, a modem, etc.) that enable the electronic device 12 to communicate with one or more other computing devices. Such communication can occur via an input / output (I / O) interface 22. Still yet, the electronic device 12 can communicate with one or more networks, such as a local area network (LAN), a wide area network (WAN), and / or the Internet, through a network adapter 20. As depicted, the network adapter 20 communicates with the other components of the electronic device 12 through the bus 18. It should be appreciated that although not shown, other hardware and / or software modules could be used in conjunction with the electronic device 12. Such modules include, but are not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data archival storage systems, etc.

[0264] The processing unit 16 executes various functional applications and handovers by running programs stored in the system memory 28, such as the handover methods mentioned in the foregoing embodiments.

[0265] Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the features disclosed herein. The disclosure is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure that come within known or customary practice in the art to which the disclosure pertains. The specification and examples are to be regarded as illustrative only, and the true scope and spirit of the disclosure are indicated by the following claims.

[0266] It should be understood that the present disclosure is not limited to the precise structures described and shown in the drawings, and that various modifications and changes can be made to the embodiments without departing from the scope of the present disclosure. The scope of the present disclosure is limited only by the claims that follow.

[0267] It can be noted that in the description of the present disclosure, the terms "first", "second", etc. are used only for descriptive purposes and not to be construed as indicating or implying relative importance. In addition, in the description of the present disclosure, the meaning of "a plurality of" is two or more unless otherwise specified.

[0268] Any procedural or methodological descriptions in flow charts or otherwise described herein can be understood to represent modules, segments, or portions of code that include executable instructions for implementing the specific logical functions or steps, and the scope of preferred embodiments of the present disclosure includes additional implementations in which the functions are performed in an order different from that shown or discussed, including substantially simultaneously, or in reverse order, as will be understood by those skilled in the art to which the embodiments of the present disclosure pertain.

[0269] It should be understood that portions of the present disclosure can be implemented in hardware, software, firmware, or combinations thereof. In the above-described embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, and as in another embodiment, it can be implemented using any or a combination of the following technologies, which are known in the art: discrete logic circuitry having logic gates for implementing logic functions upon data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), etc.

[0270] Those skilled in the art of the present technology can understand that all or part of the steps carried out by the above-described embodiments can be completed by programs instructing related hardware, and the programs can be stored in a computer-readable storage medium, and when executed, include one or a combination of steps of the method embodiments.

[0271] In addition, each functional unit in various embodiments of the present disclosure can be integrated into one processing module, or each unit can be physically present separately, or two or more units can be integrated into one module. The above-mentioned integrated module can be realized in the form of hardware or in the form of a software functional module. When the integrated module is realized in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0272] The above-mentioned storage medium can be a read-only memory, a magnetic disk or an optical disk, etc.

[0273] In the description of the present specification, the description referring to the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present disclosure. In the present specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0274] Although the embodiments of the present disclosure have been shown and described above, it is understood that the above-described embodiments are exemplary, and it is not construed that the present disclosure is limited to the above-described embodiments, and a person of ordinary skill in the art can make changes, modifications, replacements, and variations to the above-described embodiments within the scope of the present disclosure.

Claims

1. A method of inter-frequency handover, the method comprising: The method is executed by an initial network device, and the method comprises: obtaining target multi-dimensional data of a candidate cell sent by a terminal device and a target inter-frequency handover model sent by a network management center server; wherein the target multi-dimensional data comprises: fourth-generation mobile communication network type data and fifth-generation mobile communication network type data, the fourth-generation mobile communication network type data comprises: first mobile robustness optimization (MRO) data, first cell performance index data, first cell configuration parameter data and first universal interface data, and the fifth-generation mobile communication network type data comprises: second MRO data, second cell performance index data, second cell configuration parameter data and first universal interface data; inputting the target multi-dimensional data into the target inter-frequency handover model to obtain a target cell identifier output by the target inter-frequency handover model, wherein the target cell identifier is used to identify a target cell to which the terminal device is inter-frequency handed over; sending the target cell identifier to the terminal device; the method further comprises: obtaining initial sample data sent by the terminal device; determining whether the initial network device and the candidate network device apply a same baseband processing unit (BBU) pool, if the initial network device and the candidate network device apply the same BBU pool, determining a first utilization rate of a BBU in the initial network device and a second utilization rate of a BBU in a candidate network device adjacent to the initial network device; wherein the candidate network device is adjacent to the initial network device; determining a target network device from the candidate network device and the initial network device according to the first utilization rate and the second utilization rate; performing data preprocessing on the initial sample data by the target network device to obtain candidate sample data, wherein the candidate sample data is used to train an initial inter-frequency handover model to obtain the target inter-frequency handover model.

2. The method of claim 1, wherein, the method further comprises: if the initial network device and the candidate network device do not apply the same BBU pool, determining a utilization rate with a minimum value from the first utilization rate and the second utilization rate; taking a network device corresponding to the utilization rate with the minimum value as the target network device.

3. The method of claim 2, wherein, the method further comprises: if the network device corresponding to the utilization rate with the minimum value is the initial network device, performing data preprocessing on the initial sample data to obtain the candidate sample data; sending the candidate sample data to the network management center server.

4. The method of claim 3, wherein, the method further comprises: if the network device corresponding to the utilization rate with the minimum value is the candidate network device, controlling the target network device to perform data preprocessing on the initial sample data to obtain the candidate sample data; controlling the target network device to send the candidate sample data to the network management center server.

5. The method of claim 1, wherein, the determining of the target network device from the candidate network device and the initial network device according to the first utilization rate and the second utilization rate comprises: if the first utilization rate is less than the second utilization rate, taking the initial network device as the target network device. If the first utilization rate is greater than or equal to the second utilization rate, a second utilization rate with a minimum value is determined from the plurality of second utilization rates, and the candidate network device corresponding to the second utilization rate with the minimum value is taken as the target network device.

6. The method of claim 5, wherein, After the initial network device is taken as the target network device, the method further includes: performing data preprocessing on the initial sample data to obtain the candidate sample data; sending the candidate sample data to the network management center server.

7. The method of claim 5, wherein, After the candidate network device corresponding to the second utilization rate with the minimum value is taken as the target network device, the method further includes: controlling the target network device to perform data preprocessing on the initial sample data to obtain the candidate sample data; sending the candidate sample data to the network management center server.

8. The method of claim 7, wherein, The sending of the candidate sample data to the network management center server includes: determining a utilization rate difference between the second utilization rate with the minimum value and the first utilization rate; if the utilization rate difference is less than the difference threshold value, after receiving the candidate sample data sent by the target network device, sending the candidate sample data to the network management center server; if the utilization rate difference is greater than or equal to the difference threshold value, controlling the target network device to send the candidate sample data to the network management center server. 9.A method for training a model of inter-frequency handover, characterized in that, The method is performed by a network management center server, and the method includes: receiving candidate sample data sent by an initial network device controlling a target network device or candidate sample data sent by the initial network device; determining a target communication network type corresponding to the candidate sample data; processing the candidate sample data based on a data association rule preset for the target communication network type to determine a labeled cell identifier corresponding to the candidate sample data; taking the candidate sample data and the labeled cell identifier together as target sample data, and obtaining the target sample data, wherein the target sample data has a corresponding labeled cell identifier, the target multi-dimensional data includes fourth-generation mobile communication network type data and fifth-generation mobile communication network type data, the fourth-generation mobile communication network type data includes first mobile robustness optimization (MRO) data, first cell performance index data, first cell configuration parameter data, and first universal interface data, and the fifth-generation mobile communication network type data includes second MRO data, second cell performance index data, second cell configuration parameter data, and first universal interface data; training an initial inter-frequency handover model based on the target sample data to obtain a target inter-frequency handover model; sending the target inter-frequency handover model to the initial network device, wherein the initial network device is configured to perform the method according to any one of claims 1-8.

10. The method of claim 9, wherein, The processing of the candidate sample data based on the data association rule preset for the target communication network type includes: In a case that the target communication network type is the fourth generation mobile communication network type, the fourth MRO data and the fourth general interface data are processed based on a first data association rule corresponding to the fourth generation mobile communication network type; In a case that the target communication network type is the fifth generation mobile communication network type, the third MRO data and the third general interface data are processed based on a second data association rule corresponding to the fifth generation mobile communication network type.

11. A method of inter-frequency handover, the method comprising: The method is executed by a terminal device, and the method comprises: receiving target cell identification sent by an initial network device, wherein the target cell identification is determined by the initial network device executing the method in any one of claims 1-8; switching connection between communications to a target cell corresponding to the target cell identification.

12. A frequency switching device, characterized in that, The apparatus is executed by an initial network device, and the apparatus comprises: a first obtaining module, configured to obtain target multi-dimensional data of a candidate cell sent by a terminal device and target inter-frequency handover model sent by a network management center server; wherein the target multi-dimensional data comprises: data of a fourth generation mobile communication network type and data of a fifth generation mobile communication network type, the data of the fourth generation mobile communication network type comprises: first mobile robustness optimization (MRO) data, first cell performance index data, first cell configuration parameter data and first general interface data, and the data of the fifth generation mobile communication network type comprises: second MRO data, second cell performance index data, second cell configuration parameter data and first general interface data; a second obtaining module, configured to input the target multi-dimensional data into the target inter-frequency handover model to obtain target cell identification output by the target inter-frequency handover model, wherein the target cell identification is used to identify a target cell for inter-frequency handover of the terminal device; a first sending module, configured to send the target cell identification to the terminal device. The apparatus further comprises: obtaining initial sample data sent by the terminal device; determining whether an initial network device and a candidate network device apply a same baseband processing unit (BBU) pool, if the initial network device and the candidate network device apply the same BBU pool, determining a first utilization rate of a BBU in the initial network device and a second utilization rate of a BBU in a candidate network device adjacent to the initial network device; wherein the candidate network device is adjacent to the initial network device; determining a target network device from the candidate network device and the initial network device according to the first utilization rate and the second utilization rate; performing data preprocessing on the initial sample data by the target network device to obtain candidate sample data, wherein the candidate sample data is used to train an initial inter-frequency handover model to obtain the target inter-frequency handover model.

13. A training device of a frequency handover model, characterized in that, The apparatus is executed by a network management center server, and the apparatus comprises: The third obtaining module is configured to receive candidate sample data sent by the initial network device controlling the target network device, or candidate sample data sent by the initial network device; determine a target communication network type corresponding to the candidate sample data; process the candidate sample data based on a data association rule preset for the target communication network type, to determine a labeled cell identifier corresponding to the candidate sample data; jointly take the candidate sample data and the labeled cell identifier as target sample data, and obtain the target sample data, wherein the target sample data has a corresponding labeled cell identifier, and the target multi-dimensional data includes fourth-generation mobile communication network type data and fifth-generation mobile communication network type data, the fourth-generation mobile communication network type data includes first mobile robustness optimization (MRO) data, first cell performance index data, first cell configuration parameter data, and first universal interface data, and the fifth-generation mobile communication network type data includes second MRO data, second cell performance index data, second cell configuration parameter data, and first universal interface data. The training module is configured to train an initial inter-frequency handover model based on the target sample data, to obtain a target inter-frequency handover model. The second sending module is configured to send the target inter-frequency handover model to the initial network device, wherein the initial network device is configured to perform the method according to any one of claims 1-8.

14. A frequency switching device, characterized in that, The terminal device is configured to execute the apparatus, and the apparatus comprises: The receiving module is configured to receive a target cell identifier sent by an initial network device, wherein the target cell identifier is determined by the initial network device performing the method according to any one of claims 1-8. The switching module is configured to switch communication between the target cell corresponding to the target cell identifier.

15. An electronic device comprising: at least one processor; and a memory connected with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1-11.

16. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to enable the computer to perform the method according to any one of claims 1-11.

Images