Method for establishing connection, and network device

Abstract

The present application relates to the field of communications, and discloses a method for establishing a connection, and a network device. The method for establishing a connection in the embodiments of the present application comprises: in a time dimension, determining service rules of a first network device and other network devices; on the basis of the service rules, from among other network devices, determining a second network device corresponding to the first network device in a first period of time; and sending to the second network device connection establishment negotiation information for establishing a target connection, and on the basis of connection establishment response information fed back by the second network device, executing a connection response operation corresponding to the connection establishment response information, wherein the connection establishment response information is determined by the second network device on the basis of a resource state.

Description

Method for establishing connection and network device

[0001] Cross-references

[0002] This application claims priority to a Chinese patent application filed with the China Patent Office on July 31, 2023, with application number 202310956173.X and titled “Method and network device for establishing a connection”, the entire contents of which are incorporated by reference into this application. Technical Field

[0003] The embodiments of the present application relate to the field of communications, and in particular to a method for establishing a connection and a network device. Background Art

[0004] During the target connection establishment process, for example, for an X2 or Xn connection, the basis for establishing or deleting target connection links between base stations is the number of inter-base station handoffs over the past fixed period (e.g., one day). Assuming that there are n total target connection resources between base stations, where n is a positive integer greater than or equal to 1, target connection links are established with the base stations ranked in the top n in terms of handoff counts, and established target connection links are not established or deleted with base stations ranked n+1 and later. Assuming that the traffic patterns between base station A and base stations B and C, as counted over a fixed period of one day, show that the sum of the handoff counts between base station A and base station B is greater than the sum of the handoff counts between base station A and base station C, according to the relevant method, if only one target connection resource remains, a target connection link is established between base stations A and base station B.

[0005] However, a fixed cycle can include multiple time granularities. For example, a fixed cycle of one day can include 24 time granularities, each one hour long. Between 6:00 AM and 6:00 PM, base station A and base station C experience more handoffs. During this time period, base stations A and B establish target connection links, resulting in an overall waste of target connection resources. Therefore, performing handoffs between base stations on a fixed cycle can lead to resource waste.

[0006] Summary of the Invention

[0007] The embodiments of the present application provide a method for establishing a connection and a network device, which can solve the problem that switching between base stations in a fixed period may cause waste of resources.

[0008] In a first aspect, a method for establishing a connection is provided, the method comprising: determining business rules between the first network device and other network devices in a time dimension; based on the business rules, determining a second network device corresponding to the first network device in a first time period from the other network devices; sending connection establishment negotiation information for establishing a target connection to the second network device, and performing a connection response operation corresponding to the connection establishment response information based on connection establishment response information of the second network device, wherein the connection establishment response information is determined by the second network device based on a resource status.

[0009] In a second aspect, a method for establishing a connection is provided, the method comprising: receiving connection establishment negotiation information sent by a first network device for establishing a target connection, wherein the connection establishment negotiation information carries business rules of the first network device and the second network device in a time dimension; based on the business rules, determining connection establishment response information; and sending the connection establishment response information to the first network device.

[0010] In a third aspect, a device for establishing a connection is provided, the device including: a first determination module for determining the business rules of the first network device and other network devices in a time dimension; a second determination module for determining, from the other network devices, a second network device corresponding to the first network device in a first time period based on the business rules; a connection module for sending connection establishment negotiation information for establishing a target connection to the second network device, and performing a connection response operation corresponding to the connection establishment response information based on the connection establishment response information fed back by the second network device, wherein the connection establishment response information is determined by the second network device based on a resource status.

[0011] In a fourth aspect, a device for establishing a connection is provided, which includes: a receiving module for receiving connection establishment negotiation information sent by a first network device for establishing a target connection, wherein the connection establishment negotiation information carries the business rules of the first network device and the second network device in the time dimension; a third determination module for determining connection establishment response information based on the business rules; and a sending module for sending the connection establishment response information to the first network device.

[0012] In the fifth aspect, a network side device is provided, which includes a processor, a memory, and a program or instruction stored in the memory and runnable on the processor. When the program or instruction is executed by the processor, the steps of the method for establishing a connection as described in the first aspect or the second aspect are implemented.

[0013] In a sixth aspect, a network device is provided, comprising a processor and a communication interface, wherein the processor is used to implement the steps of the method for establishing a connection as described in the first aspect; and the communication interface is used to communicate with an external device.

[0014] In a seventh aspect, a network device is provided, comprising a processor and a communication interface, wherein the processor is used to implement the steps of the method for establishing a connection as described in the second aspect; and the communication interface is used to communicate with an external device.

[0015] In an eighth aspect, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method for establishing a connection as described in the first aspect or the second aspect are implemented.

[0016] In the ninth aspect, a computer program product is provided, which includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method for establishing a connection as described in the first aspect or the second aspect.

[0017] In the tenth aspect, a chip is provided, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the method for establishing a connection as described in the first aspect or the second aspect.

[0018] In the eleventh aspect, a computer program / program product is provided, which is stored in a non-volatile storage medium and is executed by at least one processor to implement the steps of the method for establishing a connection as described in the first aspect or the second aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] FIG1 is a schematic diagram of a wireless communication system applicable to embodiments of the present application;

[0020] FIG2 is a schematic flowchart of a method for establishing a connection according to an embodiment of the present application;

[0021] FIG3 is a schematic flowchart of a method for establishing a connection according to an embodiment of the present application;

[0022] FIG4 is a schematic flowchart of a method for establishing a connection according to an embodiment of the present application;

[0023] FIG5 is a schematic diagram of a method for establishing a connection according to an embodiment of the present application;

[0024] FIG6 is a schematic structural diagram of an apparatus for establishing a connection according to an embodiment of the present application;

[0025] FIG7 is a schematic structural diagram of an apparatus for establishing a connection according to an embodiment of the present application;

[0026] FIG8 is a schematic structural diagram of a communication device according to an embodiment of the present application;

[0027] FIG9 is a schematic structural diagram of a network device according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] The following will be combined with the accompanying drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described are 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 are within the scope of protection of this application.

[0029] The terms "first," "second," and the like in the specification and claims of this application are used to distinguish similar objects and are not used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate so that the embodiments of this application can be implemented in an order other than that illustrated or described herein. In addition, the term "and / or" in the specification and claims refers to at least one of the connected objects, and the character " / " generally indicates that the objects connected are in an "or" relationship.

[0030] It is worth noting that the technology described in the embodiments of the present application is not limited to the Long Term Evolution (LTE) / LTE-Advanced (LTE-A) system, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA) and other systems. The terms "system" and "network" in the embodiments of the present application are often used interchangeably, and the technology described can be used for the systems and radio technologies mentioned above, as well as for other systems and radio technologies. The following description describes a New Radio (NR) system for illustrative purposes, and NR terminology is used in most of the following description, but these technologies can also be applied to applications other than NR system applications, such as 6th generation (6G) systems. th Generation, 6G) communication system.

[0031] FIG1 is a schematic diagram of a wireless communication system applicable to an embodiment of the present application. The wireless communication system includes multiple network-side devices 12. The network-side device 12 may be a base station or a core network. A base station may be referred to as a node B, an evolved node B, an access point, a base transceiver station (BTS), a radio base station, a radio transceiver, a basic service set (BSS), an extended service set (ESS), a node B, an evolved node B (eNB), a home node B, a home evolved node B, a WLAN access point, a WiFi node, a transmitting receiving point (TRP), or any other appropriate term in the field. As long as the same technical effect is achieved, the base station is not limited to a specific technical term. It should be noted that in the embodiment of the present application, only NR gNB base stations and LTE eNB base stations are used as examples, but the specific type of base stations is not limited. The wireless communication system may also include a terminal 11 that communicates with the network-side device 12. The specific type of terminal 11 is not limited in the embodiment of the present application.

[0032] The following describes in detail the method for establishing a connection provided by the embodiment of the present application through some embodiments and their application scenarios in conjunction with the accompanying drawings.

[0033] As shown in FIG2 , an embodiment of the present application provides a method for establishing a connection. The method may be performed by a first network device. In other words, the method may be performed by software or hardware installed on the first network device. The method includes the following steps:

[0034] S220: Determine the service rules of the first network device and other network devices in a time dimension.

[0035] The first network device and the other network devices are devices located on the network side of the wireless communication system. The first network device can communicate with the other network devices. A traffic pattern is used to predict traffic patterns between the first network device and the other network devices. For example, a traffic pattern is predicted to occur 200 times between the first network device and the other network devices in the next 24 hours. For example, the traffic pattern can be represented by parameters such as the number of handovers.

[0036] The types of the first network device and the other network devices may be the same or different, and there is no limitation on this.

[0037] S230: Determine, from the other network devices, a second network device corresponding to the first network device in the first time period.

[0038] The first time period is a future time period, i.e., a time period after the current time. Based on service patterns, a second network device is determined from other network devices. The determined second network device represents the target connection device for the first network device within the first time period. In other words, within the first time period, the first network device is ready to establish a connection with the second network device.

[0039] Optionally, the traffic patterns between the first network device and the second network device during the first time period may satisfy the communication requirements for that time period. For example, during the first time period, the traffic volume between the first network device and the second network device is greater than the traffic volume between the first network device and the third network device. The traffic patterns between the first network device and the third network device during the first time period do not satisfy the communication requirements for that time period.

[0040] Through this step, it is possible to determine that the target connection device of the first network device within a specified time is the second network device from among multiple other network devices.

[0041] S240: Send connection establishment negotiation information for establishing a target connection to the second network device, and perform a connection response operation corresponding to the connection establishment response information according to the connection establishment response information of the second network device.

[0042] The first network device negotiates with the second network device to establish a target connection between the first and second network devices by sending connection establishment negotiation information. Connection establishment response information is determined by the second network device based on its resource status and fed back to the first network device by the second network device, indicating whether the second network device agrees to establish the target connection. Optionally, for connection establishment response information indicating agreement to establish the target connection, the connection response operation may be establishing the target connection; for connection establishment response information indicating disagreement to establish the target connection, the connection response operation may be other operations.

[0043] For example, in S220, the business rules of the first network device and other network devices are determined in the time dimension. For example, the business rule is that the first network device and network device A are predicted to have 200 communication services in the next 2 hours, and the communication services are, for example, communication switching. In S230: determine the second network device corresponding to the first network device in the first time period from the other network devices. For example, if the business rule of 200 communication services being predicted to occur in the next 24 hours meets the communication needs, then network device A is determined to be the second network device, and in S240, connection negotiation information for establishing a target connection is sent to the second network device, i.e., network device A, and the target connection is established based on the response information of agreeing to establish the connection fed back by network device A.

[0044] The connection establishment method provided in an embodiment of the present application determines the business rules of the first network device and other network devices in a time dimension; based on the business rules, determines a second network device corresponding to the first network device in a first time period from the other network devices; sends connection establishment negotiation information for establishing a target connection to the second network device, and performs a connection response operation corresponding to the connection establishment response information based on connection establishment response information fed back by the second network device. The connection establishment response information is determined by the second network device based on resource status, and can flexibly allocate target connection resources to avoid waste of target connection resources.

[0045] FIG3 is a flow chart of a method for establishing a connection according to an embodiment of the present application, which can be applied on a network device side. As shown in FIG3 , the method 300 includes the following steps:

[0046] S310: Train a first prediction model.

[0047] A first prediction model is trained based on the business patterns of the first network device and other network devices across multiple time dimensions. The business patterns across multiple time dimensions can be used to represent the business patterns of the first network device and other network devices over a historical period. Different time dimensions can correspond to time periods of varying lengths. Optionally, the prediction model is trained using a long short-term memory (LSTM) algorithm. The trained first prediction model is used to predict the business patterns of the first network device and other network devices.

[0048] S321: Determine the predicted number of switching between the first network device and the other network devices at each time granularity.

[0049] The predicted number of handoffs is a predicted value output by the first prediction model, representing the number of handoffs between the first network device and other network devices at different time granularities. A time granularity is a time unit of varying length within a first time period, where the first time period is a future time period. The predicted number of handoffs corresponds to the time granularity; in other words, for each time granularity, there is a predicted number of handoffs between the first network device and different other network devices, for example, the predicted number of handoffs between the first network device and the second network device at time granularity t, and the predicted number of handoffs between the first network device and the third network device at time granularity t.

[0050] Specifically, the predicted number of switching times may represent the number of switching times between the first network device and each other network device in each time granularity t of the first time period T in the future, for example, including the predicted number of switching times between the first network device and the second network device in the first time granularity of the first time period.

[0051] S322: Determine the service rule according to the predicted number of switching times at the time granularity included in the first time period.

[0052] The business rule determined in this step may, for example, include the predicted number of handoffs at multiple time granularities, such as the predicted number of handoffs between the first network device and the second network device at a first time granularity in a first time period, and the predicted number of handoffs between the first network device and the second network device at a second time granularity in the first time period. In one possible implementation, step S322 includes determining the first time period based on at least two consecutive time granularities, if the difference in the predicted number of handoffs in the at least two consecutive time granularities is less than a number threshold; and determining the business rule based on the predicted number of handoffs at the at least two consecutive time granularities included in the first time period.

[0053] The first time period can include multiple time granularities. For example, the first time period is one day and can include 24 time granularities, each of which is one hour. For example, the number threshold is 20 times. Between 0:00 and 1:00 in the time period, the number of handovers between base station A and base station B is 200 times, and between 1:00 and 2:00 in the time period, the number of handovers between base station A and base station B is 210 times. It can be seen that the difference in the predicted number of handovers in these two consecutive time granularities is less than the number threshold, indicating that the number of handovers between base station A and base station B is relatively stable, and the traffic patterns between network devices in multiple time granularities do not change much. In this case, 0:00 to 2:00 can be considered as a complete first time period for considering base station handovers, without having to perform handover judgments for the multiple time granularities contained therein. This avoids performing a judgment for each time granularity. If the time granularity is too large, resources will be wasted, while if the resource granularity is too small, excessive judgments will result in wasted computational costs.

[0054] Conversely, for example, between 3:00 and 4:00, the number of handoffs between base station A and base station B is 200, and between 4:00 and 5:00, the number of handoffs between base station A and base station B is 100. This indicates that the difference in the predicted number of handoffs between these two consecutive time granularities is greater than the number threshold, indicating that the number of handoffs between base station A and base station B varies significantly, and that the traffic patterns between network devices vary significantly across multiple time granularities. In this case, instead of treating 3:00 to 5:00 as a complete first time period, handoff determinations are made for 3:00 to 4:00 and 4:00 to 5:00, respectively. For example, between 4:00 and 5:00, the number of handoffs between base station A and base station C is 200, which is higher than the number between base station A and base station B. Based on this traffic pattern, the target connection can be established via base station A with base station C, rather than base station A connecting to base station B. Thus, the first time period can be rationally divided according to the traffic pattern, and handoffs between base stations can be performed based on the first time period, thereby avoiding the resource waste that may result from performing handoffs between base stations at a fixed cycle.

[0055] The determined business rule can be used to indicate the determination of a second network device from the other network devices. The second network device is determined from the other network devices based on the predicted number of handovers between the first network device and the other network devices in the first time period. Optionally, the other network devices communicating with the first network device in the first time period are sorted according to the predicted number of handovers to generate a first queue. The second network device is determined based on the first queue and the number of target connection resources. For example, if the number of target connection resources is 1, the network device ranked first in the first queue is determined to be the second network device. In other words, the device with the largest predicted number of handovers with the first network device in the first time period is determined to be the second network device.

[0056] Optionally, the predicted number of handovers between the first network device and other network devices in each time period is broadcast.

[0057] S330: Send connection establishment negotiation information for establishing a target connection to the second network device.

[0058] The connection negotiation information carries a first predicted number of handovers between the first network device and the second network device at a time granularity included in a first time period. The first predicted number of handovers is carried in the connection negotiation information, and the connection negotiation information is sent by the first network device to the second network device.

[0059] S340: Establish a connection between the first network device and the second network device.

[0060] When the connection establishment response information indicates that a connection is to be established, that is, when the second network device agrees to establish a connection with the first network device, a connection is established between the first network device and the second network device.

[0061] If the connection establishment response message indicates that the connection is not established, the connection establishment negotiation message is sent to the third network device. The second network device is ranked in the first N positions in the first queue, where N is a natural number. The first queue is sorted by the number of handovers between other network devices and the first network device in at least one time granularity within the first time period. The third network device is ranked in the N+1th position in the first queue. That is, if the second network device refuses to establish a connection with the first network device, the connection establishment negotiation message is sent to the third network device whose predicted number of handovers is second only to the second network device, to negotiate a connection with the third network device and repeat the aforementioned negotiation steps. For example, if the number of target connection resources N is 1 and the second network device is ranked first in the first queue, if the connection establishment response message fed back by the second network device indicates that the connection is not established with the first network device, the first network device sends the connection establishment negotiation message to the third network device, which is ranked second in the first queue. Optionally, if the third network device agrees to establish a connection, the connection between the first and third network devices is established; if the third network device refuses to establish a connection, the connection establishment negotiation message is sent to other devices ranked after the third network device in the first queue.

[0062] If the connection establishment response information indicates that the connection is not established, the first predicted handover number is set to 0, and the second network device is placed at the end of the first queue. This can avoid repeatedly sending connection establishment negotiation information to the second network device, which would waste resources.

[0063] The method for establishing a connection according to this embodiment can accurately determine the second network device to be connected to based on the predicted number of switching times; and according to the connection establishment response information fed back by the second network device, a corresponding response operation is performed, thereby improving the efficiency of establishing a connection with the first network device.

[0064] In a possible implementation, after step S340, it also includes: determining a fourth network device among the other network devices whose predicted number of switching with the first network device in at least one time granularity in the first time period is ranked after the Nth position in the first queue; and deleting the target connection between the fourth network device and the fourth network device.

[0065] For example, the second network device is ranked 1 in the first queue. After the connection between the first network device and the second network device is established, the network device ranked 2 or later in the first queue is determined to be the fourth network device. The number of the fourth network device can be one or more.

[0066] Because the first network device has already established a connection with the second network device, the first network device currently has no remaining resources to connect to the fourth network device. In this case, deleting the target connection between the first network device and the fourth network device can save resources and effectively ensure the service quality between the first network device and the second network device.

[0067] In one possible implementation, after step S310, it also includes: inputting the data transmitted between the first network device and the other network devices into the first prediction model; outputting a second predicted number of switching times through the first prediction model, wherein the second predicted number of switching times represents the number of switching times between the first network device and the other network devices in at least one time granularity in the first time period.

[0068] For example, the data transmitted between the first network device and the third network device is input into the first prediction model, and the first prediction model can output a second predicted number of switching times representing the first network device and the third network device in at least one time granularity in the first time period.

[0069] Specifically, the first prediction model can be trained based on historical transmission data between the first network device and the third network device. When using the first prediction model, 24*7 pieces of data transmitted between the first network device and the third network device are input into the first prediction model. Using the first prediction model, the number of second handovers between the first network device and the third network device can be predicted for each hour within the next 24 hours.

[0070] Optionally, after outputting the second predicted switching number, the method further includes broadcasting the second predicted switching number.

[0071] In one possible implementation, after outputting the second predicted number of switching times, it also includes: determining the error between the second predicted number of switching times and the actual number of switching times; when the error is greater than the error threshold, accumulating the number of errors; when the number of errors reaches the fault tolerance number, retraining the first prediction model.

[0072] Optionally, after each time granularity ends, the actual number of switches for that time granularity is compared with the second predicted number of switches for that time granularity to obtain the error of the second predicted number of switches relative to the actual number of switches. Optionally, if the error is less than the error threshold, the prediction result for that time granularity is recorded as "good"; if the error is greater than the error threshold, the prediction result is recorded as "bad". If the number of "bad" prediction results within a time period (for example, one day) is greater than or equal to the fault tolerance number, it means that the prediction accuracy of the first prediction model needs to be improved, and this triggers re-training of the model to ensure the accuracy of the prediction.

[0073] The error threshold and the number of fault tolerances can be pre-set according to business requirements, or adjusted in real time according to actual business needs.

[0074] In one possible implementation, the error between the second predicted switching number and the actual switching number is: the ratio of the first difference to the actual switching number, where the first difference is the difference between the second predicted switching number and the actual switching number.

[0075] That is, error=(second predicted number of switching times−actual number of switching times) / actual number of switching times.

[0076] In a possible implementation manner, the target connection includes: an X2 or Xn connection.

[0077] Establishing an X2 or Xn connection means establishing an X2 or Xn link between different network devices. Each network device has at least one X2 or Xn resource. Establishing an X2 or Xn link requires that the network devices have available X2 or Xn resources.

[0078] The connection establishment method provided in an embodiment of the present application determines the business rules of the first network device and other network devices in a time dimension; based on the business rules, determines the second network device corresponding to the first network device in a first time period from the other network devices; sends connection establishment negotiation information for establishing a target connection to the second network device, and performs a connection response operation corresponding to the connection establishment response information based on resource status feedback from the second network device. This method can flexibly allocate target connection resources based on the business rules and avoid waste of target connection resources.

[0079] The above describes in detail the method for establishing a connection according to an embodiment of the present application in conjunction with Figures 2-3. The following describes in detail the method for establishing a connection according to another embodiment of the present application in conjunction with Figure 4. It can be understood that the interaction between network devices described from the second network device side is the same as the description of the first network device side in the method shown in Figures 2-3. To avoid repetition, the relevant description is appropriately omitted.

[0080] FIG4 is a flow chart of a method for establishing a connection according to an embodiment of the present application, which can be applied to a second network device. As shown in FIG4 , the method 400 includes the following steps:

[0081] S410: Receive connection establishment negotiation information for establishing a target connection sent by the first network device.

[0082] The connection establishment negotiation information is used to request to establish a connection between the first network device and the second network device. The connection establishment negotiation information carries the service rules of the first network device and the second network device in the time dimension.

[0083] S420: Determine connection establishment response information based on the business rule.

[0084] The connection establishment response information is used to respond to the connection establishment negotiation information, for example, including agreeing to establish the connection or rejecting the connection establishment.

[0085] S430: Send the connection establishment response information to the first network device.

[0086] The connection establishment method provided in an embodiment of the present application receives connection establishment negotiation information sent by a first network device for establishing a target connection, wherein the connection establishment negotiation information carries business rules of the first network device and the second network device in a time dimension; determines connection establishment response information based on the business rules; and sends the connection establishment response information to the first network device, thereby flexibly allocating target connection resources based on the business rules and avoiding waste of target connection resources.

[0087] In a possible implementation, the service regularity of the first network device and the second network device in the time dimension includes: a first predicted number of switching times of the first network device and the second network device in at least one time granularity in a first time period.

[0088] The first predicted switching number is a predicted value, optionally determined by the first network device. The first predicted switching number is, for example, the number of switchings between the first network device and the second network device in at least one hour within the next day.

[0089] In a possible implementation, the first time period includes at least two consecutive time granularities, and a difference between predicted switching times corresponding to each of the at least two consecutive time granularities is less than a times threshold.

[0090] The first time period can include multiple time granularities. For example, the first time period is one day and can include 24 time granularities, each of which is one hour. For example, the number threshold is 20 times. Between 0:00 and 1:00 in the time period, the number of handovers between base station A and base station B is 200 times, and between 1:00 and 2:00 in the time period, the number of handovers between base station A and base station B is 210 times. It can be seen that the difference in the predicted number of handovers in these two consecutive time granularities is less than the number threshold, indicating that the number of handovers between base station A and base station B is relatively stable, and the traffic patterns between network devices in multiple time granularities do not change much. In this case, 0:00 to 2:00 can be considered as a complete first time period for considering base station handovers, without having to perform handover judgments for the multiple time granularities contained therein. This avoids performing a judgment for each time granularity. If the time granularity is too large, resources will be wasted, while if the resource granularity is too small, excessive judgments will result in wasted computational costs.

[0091] In a possible implementation, step S420 includes determining connection establishment response information based on the first predicted number of handovers and a remaining resource status of the second network device.

[0092] The resource remaining status is used to indicate the available resources of the current second network device, such as idle link resources in the second network device. Specifically, it can indicate whether the second network device has idle link resources and / or the number of idle link resources in the second network device.

[0093] Determining the connection establishment response information based on the first predicted number of switching times and the remaining resource status can take into account the service status of the first network device and the second network device and more accurately determine whether to establish a connection between the first network device and the second network device.

[0094] Optionally, before determining to establish a connection response message based on the first predicted number of switching times and the remaining resource status of the second network device, the method further includes waiting for a predetermined time.

[0095] For example, after receiving the connection negotiation message, the second network device waits for S seconds before sending a connection response message. This delay allows the second network device to receive all the connection negotiation messages. In other words, if multiple network devices wish to establish a connection with the second network device, by waiting for the predetermined time, the second network device can receive the connection negotiation messages from all of them.

[0096] In one possible implementation, determining the connection establishment response information based on the first predicted number of switching times and the remaining resource status of the second network device includes at least one of the following: determining that the connection establishment response information indicates agreement to display the connection establishment when it is determined that there are idle connection resources; determining that the connection establishment response information indicates agreement to display the connection establishment when the first predicted number of switching times is greater than the number of switching times corresponding to the fifth network device; wherein the number of switching times corresponding to the fifth network device is ranked Nth in the second queue, and the second queue is sorted according to the number of switching times between each network device and the second network device in at least one time granularity of the first time period; and determining that the connection establishment response information indicates agreement to display the connection establishment when the first predicted number of switching times is greater than the number of switching times corresponding to the sixth network device; wherein the number of switching times corresponding to the sixth network device is ranked Nth in the third queue, and the third queue is sorted according to the number of switching times between each network device and the second network device in at least one time granularity of the second time period, and the second time period is the next time period of the first time period.

[0097] A first network device requests to establish a connection with a second network device. Assume that the second network device has N connection resources, and the second network device needs to use one connection resource for each connection. If the second network device has at least one idle connection resource, the second network device agrees to establish a connection with the first network device, i.e., the connection establishment response information determines that the connection has been established. If the second network device does not have idle connection resources, the first predicted number of handovers for the first network device within a first time period is compared with the number of handovers for the fifth network device. Based on the number of handovers at at least one time granularity within the first time period, the fifth network device is ranked last among the N network devices connected to the second network device, i.e., ranked Nth in the second queue. If the first predicted number of handovers is greater than the number of handovers for the fifth network device, the first predicted number of handovers can be ranked in the first N positions of the second queue within the first time period, and the second network device agrees to establish a connection with the first network device. Furthermore, the first predicted number of handovers for the first network device within a second time period can be compared with the number of handovers for the sixth network device within the second time period. The second time period is a period after the first time period. For example, if the current time is 0:00, the first time period is from 0:00 to 12:00, and the second time period is from 13:00 to 24:00. Based on the number of handoffs in at least one time granularity during the second time period, the sixth network device is ranked last among the N network devices connected to the second network device, i.e., ranked Nth in the third queue. If the first predicted number of handoffs is greater than the number of handoffs corresponding to the sixth network device, then the first predicted number of handoffs can be ranked in the first N positions of the third queue during the second time period, and the second network device agrees to establish a connection with the first network device.

[0098] In one possible implementation, determining the connection establishment response information based on the first predicted number of switching times and the remaining resource status of the second network device includes: determining that the connection establishment response information shows that no connection is established when there are no idle connection resources, the first predicted number of switching times is less than the number of switching times corresponding to the fifth network device, and the first predicted number of switching times is less than the number of switching times corresponding to the sixth network device.

[0099] When all N connection resources of the second network device are in use, a further determination is made as to whether the first switching count corresponding to the first network device can rank among the top N network device switching counts in the first time period and the subsequent second time period. In other words, when the second network device is the target connection device of the first network device, it is necessary to determine whether the first network device is also the target connection device of the second network device, taking into account the remaining resources of the second network device. If the first switching count cannot rank among the top N switching counts, then the first network device is not the target connection device of the second network device in both the first and second time periods, the second network device refuses to establish a connection with the first network device, and the connection establishment response information determined indicates that the connection is not established.

[0100] In a possible implementation, after determining to establish connection response information based on the first predicted number of switching times and the remaining resource status of the second network device, the method further includes: if the first predicted number of switching times is greater than the number of switching times corresponding to the fifth network device, deleting the connection between the second network device and the fifth network device; and if the first predicted number of switching times is greater than the number of switching times corresponding to the sixth network device, deleting the connection between the second network device and the sixth network device.

[0101] If the first predicted number of handovers is greater than the number of handovers corresponding to the fifth network device, the second network device needs to disconnect from the fifth network device to provide connection resources for connection between the first network device and the second network device. Similarly, if the first predicted number of handovers is greater than the number of handovers corresponding to the sixth network device, the second network device needs to disconnect from the sixth network device to provide connection resources for connection between the first network device and the second network device.

[0102] In a possible implementation, before determining the establishment of connection response information based on the first predicted number of switching times and the remaining resource status of the second network device, it also includes: training a second prediction model based on the number of switching times between the second network device and other network devices in multiple time granularities.

[0103] The number of handoffs between the second network device and other network devices at multiple time granularities can be historical statistical values. Optionally, a long short-term memory (LSTM) algorithm is used to train the second prediction model. The trained second prediction model is used to predict the number of handoffs between the second network device and other network devices.

[0104] In one possible implementation, after training the second prediction model, the method further includes: inputting data transmitted between the second network device and other network devices into the second prediction model; and outputting a third predicted number of switching times through the second prediction model, wherein the third predicted number of switching times represents the number of switching times between the second network device and the other network devices in at least one time granularity in the first time period.

[0105] For example, data transmitted between the first network device and the second network device is input into the second prediction model, and the second prediction model can output a predicted number of switching between the first network device and the second network device in at least one time granularity in the first time period.

[0106] Specifically, the second prediction model can be trained based on historical transmission data between the first network device and the second network device. When using the second prediction model, 24*7 pieces of data transmitted between the first network device and the second network device are input into the first prediction model. Using the second prediction model, the third number of handovers between the first network device and the second network device can be predicted for each hour within the next 24 hours.

[0107] In one possible implementation, after outputting the third predicted number of switching times, it also includes: determining the error between the third predicted number of switching times and the actual number of switching times; when the error is greater than the error threshold, accumulating the number of errors; when the number of errors reaches the fault tolerance number, retraining the second prediction model.

[0108] The steps and technical effects of retraining the second prediction model are similar to those of the first prediction model and will not be repeated here.

[0109] In a possible implementation manner, the target connection includes: an X2 or Xn connection.

[0110] The connection establishment method provided in an embodiment of the present application receives connection establishment negotiation information sent by a first network device for establishing a target connection, wherein the connection establishment negotiation information carries business rules of the first network device and the second network device in a time dimension; determines connection establishment response information based on the business rules; and sends the connection establishment response information to the first network device, thereby flexibly allocating target connection resources based on the business rules and avoiding waste of target connection resources.

[0111] 5 , a method 500 for establishing a connection according to an embodiment of the present application is described, taking a first network device as a wireless base station 501 and a second network device as a wireless base station 502. The method 500 includes predicting handover patterns between base stations and establishing and / or deleting X2 / Xn links.

[0112] Assume that there are four base stations in the radio access network: NR gNB base station A 501, LTE eNB base station B 502, NR gNB base station C (not shown), and LTE eNB base station D (not shown). Base station A 501 needs to establish an X2 link with base station B 502, an Xn link with base station C, and an Xn link with base station D. The number of X2 and Xn resources for each base station is n = 1.

[0113] The inter-base handover prediction module of base station A 501 uses t = 1 hour as the minimum time granularity for handover statistics. It uses k = 24 * 7 * 4 data points between base station A 501 and base stations B, C, and D, respectively, to train a first prediction model using the LSTM algorithm. The first prediction model, trained based on AB and AC, is fed with j = 24 * 7 data points. The first prediction model predicts the number of handovers corresponding to each hour in the first future time period (T = 24 hours), as shown in Table 1. The inter-base handover prediction module of base station A 501 sends the prediction results in Table 1 to the X2\Xn creation and deletion modules of base station A 501.

[0114] Table 1

[0115] The inter-base handover prediction module of base station B 502 uses t = 1 hour as the minimum time granularity for handover statistics. It uses k = 24 * 7 * 4 data points between base station B 502 and base stations A and C, respectively, to train a second prediction model using the LSTM algorithm. The second prediction model is fed with j = 24 * 7 data points; the model predicts the number of handovers corresponding to each hour in the first time period (T = 24 hours) in the future. This is shown in Table 2. The inter-base handover prediction module of base station B 502 sends the prediction results in Table 2 to the X2\Xn creation and deletion module of base station B 502.

[0116] Table 2

[0117] According to the prediction results shown in Table 1, between 0 and 1, the predicted number of handovers between base stations AB is the highest (200 times). The X2\Xn establishment and deletion module of base station A 501 determines that an X2 link should be established between base stations AB between 0 and 1. Based on this, base station A 501 sends a connection establishment request to base station B. After receiving the request, base station B 502 waits for 5 seconds and also receives a link establishment request from base station C. According to the prediction results shown in Table 2, between 0 and 1, the predicted number of BC handovers (300) is higher than the predicted number of BA handovers (200). Base station B 502 determines that it is more appropriate to establish an Xn link between BC between 0 and 1 and refuses to establish a link with base station A 501. Base station A 501 receives a response message indicating that the connection is not established. Afterwards, base station A 501 sends a link establishment request to base station D, which ranks second in the predicted number of handovers.

[0118] At the same time, starting from 0 o'clock, base station A 501 counts the actual number of handovers between base stations AB and AC, as shown in Table 3 below.

[0119] Table 3

[0120] According to the formula, error = (predicted number of handovers - actual number of handovers) / actual number of handovers. Assuming a tolerance of 4 and a 30% error threshold, the prediction model between base stations AB requires retraining by midnight on the same day, while the prediction model between base stations AC does not. Base station A 501's X2 / Xn establishment and deletion module sends a base station AB model retraining message to its inter-base station handover prediction module to repeat model training.

[0121] Through the connection establishment method provided in the embodiment of the present application, the X2 / Xn link can be configured multiple times within a time period, and X2 / Xn resources can be flexibly allocated to improve the utilization of X2 / Xn resources.

[0122] It should be noted that the method for establishing a connection provided in the embodiments of the present application can be performed by a device for establishing a connection, or a control module in the device for executing and loading the above method. In the embodiments of the present application, the method for establishing a connection provided in the embodiments of the present application is described by taking the method for loading and establishing a connection performed by a device for establishing a connection as an example.

[0123] FIG6 is a schematic diagram of a device for establishing a connection according to an embodiment of the present application. As shown in FIG6 , the device 600 for establishing a connection includes: a first determining module 601 , a second determining module 602 , and a connecting module 603 .

[0124] The first determination module 601 is used to determine the business rules of the first network device and other network devices in the time dimension; the second determination module 602 is used to determine, from the other network devices, a second network device corresponding to the first network device in the first time period based on the business rules; the connection module 603 is used to send connection establishment negotiation information for establishing a target connection to the second network device, and perform a connection response operation corresponding to the connection establishment response information based on the connection establishment response information fed back by the second network device, where the connection establishment response information is determined by the second network device based on the resource status.

[0125] In a possible implementation, the first determination module 601 is used to determine the predicted number of switching between the first network device and the other network devices at each time granularity; and determine the business rule based on the predicted number of switching at the time granularity included in the first time period.

[0126] In one possible implementation, the connection module 603 is used to send connection establishment negotiation information for establishing a target connection to the second network device, where the connection establishment negotiation information carries a first predicted number of switching times between the first network device and the second network device at a time granularity included in a first time period.

[0127] In one possible implementation, the first determination module 601 is used to determine the first time period based on the at least two consecutive time granularities when the difference between the predicted number of switching times in at least two consecutive time granularities is less than a number threshold; and determine the business rule based on the first predicted number of switching times on the at least two consecutive time granularities included in the first time period.

[0128] In one possible implementation, the connection module 603 is used to establish a connection between the first network device and the second network device when the connection establishment response information indicates that the connection is established; and send the connection establishment negotiation information to the third network device when the connection establishment response information indicates that the connection is not established, wherein the second network device is ranked in the first N positions in the first queue, N is a natural number, and the first queue is ranked according to the number of switches between the other network devices and the first network device in at least one time granularity in the first time period; wherein the third network device is ranked in the first queue as the N+1th position; and when the connection establishment response information indicates that the connection is not established, the first predicted number of switches is set to 0, and the second network device is placed at the end of the first queue.

[0129] In one possible implementation, the device for establishing a connection is also used to determine a fourth network device among the other network devices whose predicted number of switching with the first network device in at least one time granularity in the first time period is ranked after the Nth position in the first queue; and delete the target connection between the fourth network device and the fourth network device.

[0130] In a possible implementation, the device for establishing a connection is further used to train a first prediction model based on business rules between the first network device and other network devices in multiple time dimensions.

[0131] In one possible implementation, the device for establishing a connection is also used to input data transmitted between the first network device and the other network devices into the first prediction model; through the first prediction model, a second predicted number of switching times is output, wherein the second predicted number of switching times represents the number of switching times between the first network device and the other network devices in at least one time granularity in a first time period.

[0132] In one possible implementation, the device for establishing a connection is also used to determine the error between the second predicted number of switching times and the actual number of switching times; when the error is greater than an error threshold, the number of errors is accumulated; when the number of errors reaches the fault tolerance number, the first prediction model is retrained.

[0133] In one possible implementation, the error between the first predicted switching number and the actual switching number is: the ratio of the first difference to the actual switching number, where the first difference is the difference between the second predicted switching number and the actual switching number.

[0134] In a possible implementation manner, the target connection includes: an X2 or Xn connection.

[0135] The device for establishing a connection in the embodiments of the present application can be a device, a device or electronic device with an operating system, or a component, integrated circuit, or chip in a terminal. The device or electronic device can be a mobile electronic device or a non-mobile electronic device, and the embodiments of the present application do not specifically limit this.

[0136] According to the device 600 of the embodiment of the present application, the process of the method corresponding to the embodiments of Figures 2 to 3 can be referred to, and the various units / modules in the device 600 and the above-mentioned other operations and / or functions are respectively for implementing the corresponding processes of the methods of the embodiments of Figures 2 to 3, and can achieve the same or equivalent technical effects. For the sake of brevity, they will not be repeated here.

[0137] FIG7 is another schematic diagram of the structure of an apparatus for establishing a connection according to an embodiment of the present application. As shown in FIG7 , the apparatus for establishing a connection 700 includes: a receiving module 701 , a third determining module 702 , and a sending module 703 .

[0138] The receiving module 701 is used to receive connection establishment negotiation information sent by the first network device for establishing a target connection, wherein the connection establishment negotiation information carries the business rules of the first network device and the second network device in the time dimension; the third determination module 702 is used to determine the connection establishment response information based on the business rules; the sending module 703 is used to send the connection establishment response information to the first network device.

[0139] In a possible implementation, the service regularity of the first network device and the second network device in the time dimension includes: a first predicted number of switching times of the first network device and the second network device in at least one time granularity in a first time period.

[0140] In a possible implementation, the first time period includes at least two consecutive time granularities, and a difference between predicted switching times corresponding to each of the at least two consecutive time granularities is less than a times threshold.

[0141] In a possible implementation, the third determining module 702 is configured to determine connection establishment response information based on the first predicted number of handovers and a remaining resource status of the second network device.

[0142] In one possible implementation, the third determination module 702 is used to determine that, when it is determined that there are idle connection resources, the connection establishment response information indicates that the connection establishment is agreed to be displayed; when the first predicted number of switching times is greater than the number of switching times corresponding to the fifth network device, the connection establishment response information indicates that the connection establishment is agreed to be displayed; wherein, the number of switching times corresponding to the fifth network device is ranked Nth in the second queue, and the second queue is sorted according to the number of switching times between each network device and the second network device in at least one time granularity of the first time period; when the first predicted number of switching times is greater than the number of switching times corresponding to the sixth network device, the connection establishment response information indicates that the connection establishment is agreed to be displayed; wherein, the number of switching times corresponding to the sixth network device is ranked Nth in the third queue, and the third queue is sorted according to the number of switching times between each network device and the second network device in at least one time granularity of the second time period, and the second time period is the next time period of the first time period.

[0143] In one possible implementation, the third determination module 702 is used to determine that the connection establishment response information table shows that no connection is established when there are no idle connection resources, the first predicted switching number is less than the switching number corresponding to the fifth network device, and the first predicted switching number is less than the switching number corresponding to the sixth network device.

[0144] In one possible implementation, the device for establishing a connection is further used to delete the connection between the second network device and the fifth network device when the first predicted number of switching times is greater than the number of switching times corresponding to the fifth network device; and to delete the connection between the second network device and the sixth network device when the first predicted number of switching times is greater than the number of switching times corresponding to the sixth network device.

[0145] In a possible implementation, the device for establishing a connection is further configured to train a second prediction model based on the number of handovers between the second network device and other network devices in multiple time granularities.

[0146] In one possible implementation, the device for establishing a connection is also used to input data transmitted between the second network device and the other network devices into the second prediction model; through the second prediction model, a third predicted number of switching times is output, wherein the third predicted number of switching times represents the number of switching times between the second network device and the other network devices in at least one time granularity in the first time period.

[0147] In one possible implementation, the device for establishing a connection is also used to determine the error between the third predicted number of switching times and the actual number of switching times that occurred; when the error is greater than the error threshold, the number of errors is accumulated; when the number of errors reaches the fault tolerance number, the second prediction model is retrained.

[0148] In a possible implementation manner, the target connection includes: an X2 or Xn connection.

[0149] According to the device 700 of the embodiment of the present application, the process of the method corresponding to the embodiment of Figure 4 can be referred to, and the various units / modules in the device 700 and the above-mentioned other operations and / or functions are respectively for implementing the corresponding process of the method of the embodiment of Figure 4, and can achieve the same or equivalent technical effects. For the sake of brevity, they will not be repeated here.

[0150] Optionally, as shown in Figure 8, an embodiment of the present application further provides a network-side device 800, including a processor 801, a memory 802, and a program or instruction stored in the memory 802 and executable on the processor 801. For example, when the communication device 800 is a first network device, the program or instruction, when executed by the processor 801, implements the various processes of the embodiment of the method for establishing a connection in Figures 2 to 3 above, and can achieve the same technical effect. When the network-side device 800 is a first network device, the program or instruction, when executed by the processor 801, implements the various processes of the embodiment of the method for establishing a connection in Figure 4 above, and can achieve the same technical effect. To avoid repetition, they will not be described here.

[0151] An embodiment of the present application also provides a network device, including a processor and a communication interface, where the processor is used to determine the business rules of the first network device and other network devices in a time dimension; based on the business rules, determine a second network device corresponding to the first network device in a first time period from the other network devices, send connection establishment negotiation information for establishing a target connection to the second network device, and perform a connection response operation corresponding to the connection establishment response information based on the second network device, where the connection establishment response information is determined by the second network device based on a resource status; and the communication interface is used to communicate with an external device.

[0152] An embodiment of the present application also provides another network device, including a processor and a communication interface, the processor being configured to receive connection establishment negotiation information sent by a first network device for establishing a target connection, wherein the connection establishment negotiation information carries the business rules of the first network device and the second network device in the time dimension; and to send the connection establishment response information to the first network device; the processor being configured to determine the connection establishment response information based on the business rules; and the communication interface being configured to communicate with an external device.

[0153] Specifically, embodiments of the present application also provide a network-side device. As shown in Figure 9, the network device 900 includes an antenna 901, a radio frequency device 902, and a baseband device 903. Antenna 901 is connected to radio frequency device 902. In the uplink direction, radio frequency device 902 receives information via antenna 901 and sends the received information to baseband device 903 for processing. In the downlink direction, baseband device 903 processes the information to be sent and sends it to radio frequency device 902. Radio frequency device 902 processes the received information and sends it through antenna 901.

[0154] The frequency band processing device may be located in the baseband device 903 . The method performed by the network-side device in the above embodiment may be implemented in the baseband device 903 . The baseband device 903 includes a processor 904 and a memory 905 .

[0155] The baseband device 903 may include, for example, at least one baseband board, on which multiple chips are arranged, as shown in the figure, one of the chips is, for example, a processor 904, which is connected to the memory 905 to call the program in the memory 905 and execute the network device operations shown in the above method embodiment.

[0156] The baseband device 903 may further include a network interface 906 for exchanging information with the radio frequency device 902 . The interface may be, for example, a common public radio interface (CPRI).

[0157] Specifically, the network side device in the embodiment of the present application further includes: instructions or programs stored in the memory 905 and executable on the processor 904, and the processor 904 calls the instructions or programs in the memory 905 to execute:

[0158] The processor 904 calls the instructions or programs in the memory 905 to execute the methods executed by the modules shown in Figure 6 or Figure 7, and achieves the same technical effects. To avoid repetition, they are not described here.

[0159] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each process of the above-mentioned method embodiment for establishing a connection is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0160] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer-readable storage medium, such as a computer read-only memory (ROM), random access memory (RAM), a magnetic disk, or an optical disk.

[0161] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned method embodiment for establishing a connection, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0162] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0163] An embodiment of the present application further provides a computer program product, which includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method described in the first aspect.

[0164] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, it should be noted that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0165] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), including a number of instructions for enabling a terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0166] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms without departing from the purpose of this application and the scope of protection of the claims, all of which are within the protection of this application.

Claims

1. A method for establishing a connection, performed by a first network device, comprising: Determine the service rules of the first network device and other network devices in the time dimension; Based on the service rule, determining a second network device corresponding to the first network device in the first time period from the other network devices; Sending connection establishment negotiation information for establishing a target connection to the second network device, and performing a connection response operation corresponding to the connection establishment response information fed back by the second network device, wherein the connection establishment response information is determined by the second network device based on a resource status.

2. The method according to claim 1, wherein: The determining the service rules of the first network device and other network devices in the time dimension includes: Determining the predicted number of switching between the first network device and the other network devices at each time granularity; The business rule is determined according to the predicted number of switching times at a time granularity included in the first time period.

3. The method according to claim 2, wherein: Sending connection establishment negotiation information for establishing a target connection to the second network device includes: Sending connection establishment negotiation information for establishing a target connection to the second network device, wherein the connection establishment negotiation information carries a first predicted number of switching times between the first network device and the second network device at a time granularity included in a first time period.

4. The method according to claim 3, wherein: The determining the service rule according to the predicted number of switching times at the time granularity included in the first time period includes: When the difference between the predicted switching times in at least two consecutive time granularities is less than a times threshold, determining the first time period according to the at least two consecutive time granularities; The business rule is determined according to the first predicted number of switching times at the at least two consecutive time granularities included in the first time period.

5. The method according to claim 1, wherein: The performing of the connection response operation corresponding to the connection establishment response information includes: When the connection establishment response information indicates that a connection is established, establishing a connection between the first network device and the second network device; When the connection establishment response information shows that the connection is not established, the connection establishment negotiation information is sent to the third network device, wherein the second network device is ranked in the first N positions in the first queue, N is a natural number, and the first queue is ranked according to the number of switching times between the other network devices and the first network device in at least one time granularity in the first time period; wherein the third network device is ranked in the first queue at the N+1th position; When the connection establishment response information shows that the connection is not established, the first predicted switching number is set to 0, and the second network device is placed at the end of the first queue.

6. The method according to claim 5, wherein: After executing the connection response operation corresponding to the connection establishment response information, the method further includes: Determine a fourth network device among the other network devices, the fourth network device being ranked after the Nth position in the first queue in terms of the predicted number of handovers with the first network device in at least one time granularity in the first time period; The target connection with the fourth network device is deleted.

7. The method according to claim 1, wherein: Before sending the connection establishment negotiation information for establishing the target connection to the second network device, the method further includes: Based on the business rules of the first network device and other network devices in multiple time dimensions, a first prediction model is trained.

8. The method according to claim 7, wherein: After the training of the first prediction model, the method further includes: inputting data transmitted between the first network device and other network devices into the first prediction model; Outputting a second predicted switching number through the first prediction model, wherein the second predicted The measured switching times represent the switching times between the first network device and the other network devices in at least one time granularity in the first time period.

9. The method according to claim 8, wherein: After outputting the second predicted switching number, the method further includes: determining an error between the second predicted number of switching times and the number of switching times that actually occurred; In the case where the error is greater than the error threshold, accumulating the number of errors; When the number of errors reaches the error tolerance number, the first prediction model is retrained.

10. The method according to claim 9, wherein: The error between the second predicted switching number and the actual switching number is: the ratio of the first difference to the actual switching number, and the first difference is the difference between the second predicted switching number and the actual switching number.

11. The method according to claim 1, wherein: The target connection includes: X2 or Xn connection.

12. A method for establishing a connection, performed by a second network device, comprising: Receiving connection establishment negotiation information for establishing a target connection sent by the first network device, wherein the connection establishment negotiation information carries a service rule between the first network device and the second network device in a time dimension; Based on the business rule, determine to establish a connection response information; Send the connection establishment response information to the first network device.

13. The method according to claim 12, wherein: The service rules of the first network device and the second network device in the time dimension include: A first predicted number of switchings between the first network device and the second network device in at least one time granularity of a first time period.

14. The method according to claim 12, wherein: The first time period includes at least two consecutive time granularities, and a difference between predicted switching times corresponding to each of the at least two consecutive time granularities is less than a times threshold.

15. The method according to claim 13, wherein: The determining, based on the business rule, to establish connection response information includes: The connection establishment response information is determined based on the first predicted number of switching times and a remaining resource state of the second network device.

16. The method according to claim 15, wherein: The determining, based on the first predicted number of switching times and the remaining resource state of the second network device, to establish a connection response information includes at least one of the following: In the case of determining that there are idle connection resources, determining that the connection establishment response information indicates that the connection is established; In the case where the first predicted switching number is greater than the switching number corresponding to the fifth network device, determining that the connection establishment response information indicates that a connection is established; wherein the switching number corresponding to the fifth network device is ranked Nth in the second queue, and the second queue is sorted according to the switching number between each network device and the second network device in at least one time granularity of the first time period; When the first predicted number of switching times is greater than the number of switching times corresponding to the sixth network device, it is determined that the connection establishment response information shows that the connection is established; wherein the number of switching times corresponding to the sixth network device is ranked Nth in the third queue, and the third queue is sorted according to the number of switching times between each network device and the second network device in at least one time granularity of the second time period, and the second time period is the next time period of the first time period.

17. The method according to claim 15, wherein: The determining, based on the first predicted number of switching times and the remaining resource state of the second network device, to establish a connection response information includes: When there are no idle connection resources, the first predicted switching number is less than the switching number corresponding to the fifth network device, and the first predicted switching number is less than the switching number corresponding to the sixth network device, it is determined that the connection establishment response information shows that the connection is not established.

18. The method according to claim 15, wherein: After determining to establish connection response information based on the first predicted number of switching times and the remaining resource state of the second network device, the method further includes: When the first predicted switching number is greater than the switching number corresponding to the fifth network device, deleting the connection between the second network device and the fifth network device; When the first predicted switching number is greater than the switching number corresponding to the sixth network device, the connection between the second network device and the sixth network device is deleted.

19. The method according to claim 15, wherein: Before determining to establish connection response information based on the first predicted number of switching times and the remaining resource state of the second network device, the method further includes: Based on the number of switchings between the second network device and other network devices in multiple time granularities, a second prediction model is trained.

20. The method according to claim 19, wherein: After the training of the second prediction model, the method further includes: inputting data transmitted between the second network device and other network devices into the second prediction model; A third predicted switching number is outputted through the second prediction model, wherein the third predicted switching number represents the switching number between the second network device and the other network devices in at least one time granularity of the first time period.

21. The method according to claim 20, wherein: After outputting the third predicted switching number, the method further includes: Determining an error between the third predicted number of switching times and the number of switching times that actually occurred; In the case where the error is greater than the error threshold, accumulating the number of errors; When the number of errors reaches the error tolerance number, the second prediction model is retrained.

22. The method according to claim 12, wherein: The target connection includes: X2 or Xn connection.

23. A network side device, comprising a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the method for establishing a connection as described in any one of claims 1 to 11 are implemented; or the steps of the method for establishing a connection as described in any one of claims 12 to 22 are implemented.

24. A readable storage medium storing a program or instruction, wherein the program or instruction, when executed by a processor, implements the steps of the method for establishing a connection as described in any one of claims 1 to 11, or implements the steps of the method for establishing a connection as described in any one of claims 12 to 22.

Images