CN112291778B

CN112291778B - Network optimization method and device

Info

Publication number: CN112291778B
Application number: CN202011294346.9A
Authority: CN
Inventors: 李新玥; 王伟; 张涛
Original assignee: China United Network Communications Group Co Ltd
Current assignee: China United Network Communications Group Co Ltd
Priority date: 2020-11-18
Filing date: 2020-11-18
Publication date: 2022-09-16
Anticipated expiration: 2040-11-18
Also published as: CN112291778A

Abstract

The embodiment of the invention provides a network optimization method and device, relates to the technical field of communication, and aims to improve the accuracy of network data of a determined target cell in a certain time interval and improve the frequency band utilization rate. The method comprises the following steps: the method comprises the steps that a server determines network data corresponding to a target cell in a target time interval based on a target neural network model, wherein the network data corresponding to the target time interval comprise 4G downlink PDSCH layer flow of the target cell in the target time interval, 5G downlink PDSCH layer flow of the target cell in the target time interval, the number of TM3 terminals of the target cell in the target time interval, the number of TM4 terminals of the target cell in the target time interval and the number of TM9 terminals of the target cell in the target time interval; and the server sends the network data corresponding to the target cell in the target time interval to the network equipment.

Description

Network optimization method and device

Technical Field

The embodiment of the invention relates to the technical field of communication, in particular to a network optimization method and device.

Background

At present, in order to perfect the deployment work of the 5G network, the frequency band in the 4G network can be ploughed to the 5G network.

However, if a certain frequency band of the 4G network is completely re-cultivated to the 5G network at the initial stage of deployment, some problems may be caused. For example, in the initial stage of 5G deployment, the number of 5G terminals is small, which may result in low frequency band utilization. The 4G and 5G dynamic spectrum sharing technology (DSS) can be applied to the original 4G frequency band, so that the dynamic configuration of the 4G and 5G frequency spectrum is achieved, and the utilization rate of the frequency spectrum is maximized.

Disclosure of Invention

Embodiments of the present invention provide a network optimization method and apparatus based on DSS technology application, which can improve accuracy of determining network data of a target cell in a certain time interval, and improve frequency band utilization.

In a first aspect, an embodiment of the present invention provides a network optimization method, including: the method comprises the steps that a server determines network data corresponding to a target cell in a target time interval based on a target neural network model, wherein the network data corresponding to the target time interval comprises 4G downlink Physical Downlink Shared Channel (PDSCH) layer flow of the target cell in the target time interval, 5G downlink PDSCH layer flow of the target cell in the target time interval, the number of Transmission Mode (TM) 3 terminals of the target cell in the target time interval, the number of TM4 terminals of the target cell in the target time interval and the number of TM9 terminals of the target cell in the target time interval; and the server sends the network data corresponding to the target cell in the target time interval to the network equipment.

In a second aspect, an embodiment of the present invention provides a network optimization method, including: the network equipment receives network data, corresponding to a target cell in a target time interval, sent by a server, wherein the network data corresponding to the target time interval comprises 4G downlink PDSCH layer traffic of the target cell in the target time interval, 5G downlink PDSCH layer traffic of the target cell in the target time interval, the number of TM3 terminals of the target cell in the target time interval, the number of TM4 terminals of the target cell in the target time interval and the number of TM9 terminals of the target cell in the target time interval, and the network data, corresponding to the target cell in the target time interval, is determined by the server based on a target neural network model; the network equipment determines whether the ratio of the number of TM9 terminals of the target cell to the number of 4G terminals in the target cell is smaller than a proportional threshold, wherein the number of 4G terminals in the target cell is the sum of the number of TM3 terminals of the target cell, the number of TM4 terminals of the target cell and the number of TM9 terminals of the target cell; under the condition that the ratio of the number of TM9 terminals of the target cell to the number of 4G terminals in the target cell is smaller than the proportional threshold, the network equipment determines whether the 4G downlink PDSCH layer flow of the target cell is larger than or equal to the 5G downlink PDSCH layer flow of the target cell; in a case where the 4G downlink PDSCH layer traffic of the target cell is greater than or equal to the 5G downlink PDSCH layer traffic of the target cell, the network device determines location puncturing for transmitting synchronization signals and Physical Broadcast Channel (PBCH) blocks, SSBs in the 5G network.

In a third aspect, an embodiment of the present invention provides a server, including: a determining module and a sending module; the determining module is configured to determine, based on a target neural network model, network data corresponding to a target cell in a target time interval, where the network data corresponding to the target time interval includes 4G downlink PDSCH layer traffic of the target cell in the target time interval, 5G downlink PDSCH layer traffic of the target cell in the target time interval, the number of TM3 terminals of the target cell in the target time interval, the number of TM4 terminals of the target cell in the target time interval, and the number of TM9 terminals of the target cell in the target time interval; the sending module is configured to send network data corresponding to the target cell in the target time interval to the network device.

In a fourth aspect, an embodiment of the present invention provides a network device, including: a receiving module and a determining module; the receiving module is configured to receive network data, sent by a server, corresponding to a target cell in a target time interval, where the network data corresponding to the target time interval includes 4G downlink PDSCH layer traffic of the target cell in the target time interval, 5G downlink PDSCH layer traffic of the target cell in the target time interval, the number of TM3 terminals of the target cell in the target time interval, the number of TM4 terminals of the target cell in the target time interval, and the number of TM9 terminals of the target cell in the target time interval, and the network data corresponding to the target cell in the target time interval is determined by the server based on a target neural network model; the determining module is configured to determine whether a ratio of the number of TM9 terminals of the target cell to the number of 4G terminals in the target cell is smaller than a proportional threshold, where the number of 4G terminals in the target cell is a sum of the number of TM3 terminals of the target cell, the number of TM4 terminals of the target cell, and the number of TM9 terminals of the target cell; and determining whether the 4G downlink PDSCH layer traffic of the target cell is greater than or equal to the 5G downlink PDSCH layer traffic of the target cell, if the ratio of the number of TM9 terminals of the target cell to the number of 4G terminals in the target cell is less than the proportional threshold; and determining position punching for transmitting SSB in the 5G network under the condition that the 4G downlink PDSCH layer flow of the target cell is greater than or equal to the 5G downlink PDSCH layer flow of the target cell.

In a fifth aspect, an embodiment of the present invention provides another server, including: a processor, a memory, a bus, and a communication interface; the memory is used for storing computer execution instructions, the processor is connected with the memory through the bus, and when the server runs, the processor executes the computer execution instructions stored in the memory, so that the server executes the network optimization method provided by the first aspect.

In a sixth aspect, an embodiment of the present invention provides another network device, including: a processor, a memory, a bus, and a communication interface; the memory is used for storing computer execution instructions, the processor is connected with the memory through the bus, and when the network device runs, the processor executes the computer execution instructions stored in the memory, so that the network device executes the network optimization method provided by the second aspect.

In a seventh aspect, an embodiment of the present invention provides a computer-readable storage medium, which includes a computer program, and when the computer program runs on a computer, the computer is caused to execute a network optimization method provided in the first aspect.

In an eighth aspect, an embodiment of the present invention provides a computer-readable storage medium, which includes a computer program, and when the computer program runs on a computer, the computer is caused to execute a network optimization method provided in the second aspect.

In a ninth aspect, an embodiment of the present invention provides a computer program product containing instructions, which when run on a computer, causes the computer to execute the network optimization method of the first aspect and any one of the implementations thereof.

In a tenth aspect, an embodiment of the present invention provides a computer program product containing instructions, which when run on a computer, causes the computer to execute the network optimization method of the second aspect and any one of the implementations thereof.

In the network optimization method and apparatus provided in the embodiments of the present invention, a server determines, based on a target neural network model, network data corresponding to a target cell in a target time interval, where the network data corresponding to the target time interval includes 4G downlink PDSCH layer traffic of the target cell in the target time interval, 5G downlink PDSCH layer traffic of the target cell in the target time interval, the number of TM3 terminals of the target cell in the target time interval, the number of TM4 terminals of the target cell in the target time interval, and the number of TM9 terminals of the target cell in the target time interval; the server sends the network data corresponding to the target cell in the target time interval to the network equipment; after receiving the network data, the network device determines whether the ratio of the number of TM9 terminals of the target cell to the number of 4G terminals in the target cell (i.e., the sum of the number of TM3 terminals, TM4 terminals and TM9 terminals in the target cell) is smaller than a proportional threshold, and determines whether the 4G downlink PDSCH layer traffic is greater than or equal to the 5G downlink PDSCH layer traffic if the number of TM9 terminals is smaller than the number of 4G terminals; then, when the 4G downlink PDSCH layer traffic is greater than or equal to the 5G downlink PDSCH layer traffic, the network device determines location puncturing for transmitting SSBs in the 5G network. In the embodiment of the invention, the server determines the network data corresponding to the target cell in the target time interval based on the target neural network model, so that the accuracy of determining the network data of the target cell in a certain time interval can be improved; and after receiving the network data, the network device may determine a corresponding channel conflict solution based on the network data, that is, optimize the network, and may improve the frequency band utilization.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below.

Fig. 1 is a schematic network architecture diagram of a 5G communication system according to an embodiment of the present invention;

fig. 2 is a hardware schematic diagram of a base station according to an embodiment of the present invention;

fig. 3 is a hardware schematic diagram of a server according to an embodiment of the present invention;

fig. 4 is a first schematic diagram illustrating a network optimization method according to an embodiment of the present invention;

FIG. 5 is a diagram of a cell in an LSTM according to an embodiment of the present invention;

fig. 6 is a second schematic diagram of a network optimization method according to an embodiment of the present invention;

fig. 7 is a first schematic structural diagram of a server according to an embodiment of the present invention;

fig. 8 is a schematic structural diagram of a server according to an embodiment of the present invention;

fig. 9 is a first schematic structural diagram of a network device according to an embodiment of the present invention;

fig. 10 is a schematic structural diagram of a network device according to an embodiment of the present invention.

Detailed Description

The network optimization method and apparatus provided by the embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

Furthermore, the terms "including" and "having," and any variations thereof, as referred to in the description of the present application, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements but may alternatively include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

It should be noted that, in the embodiments of the present invention, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "e.g.," an embodiment of the present invention is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the word "exemplary" or "such as" is intended to present concepts related in a concrete fashion.

The term "and/or" as used herein includes the use of either or both of the two methods.

In the description of the present application, the meaning of "a plurality" means two or more unless otherwise specified.

Based on the problems existing in the background art, embodiments of the present invention provide a method and an apparatus for network optimization, where a server determines, based on a target neural network model, network data corresponding to a target cell in a target time interval, where the network data corresponding to the target time interval includes 4G downlink PDSCH layer traffic of the target cell in the target time interval, 5G downlink PDSCH layer traffic of the target cell in the target time interval, the number of TM3 terminals of the target cell in the target time interval, the number of TM4 terminals of the target cell in the target time interval, and the number of TM9 terminals of the target cell in the target time interval; the server sends the network data corresponding to the target cell in the target time interval to the network equipment; after receiving the network data, the network device determines whether the ratio of the number of TM9 terminals of the target cell to the number of 4G terminals in the target cell (i.e., the sum of the number of TM3 terminals, TM4 terminals and TM9 terminals in the target cell) is smaller than a proportional threshold, and determines whether the 4G downlink PDSCH layer traffic is greater than or equal to the 5G downlink PDSCH layer traffic if the number of TM9 terminals is smaller than the number of 4G terminals; then, when the 4G downlink PDSCH layer traffic is greater than or equal to the 5G downlink PDSCH layer traffic, the network device determines location puncturing for transmitting SSBs in the 5G network. In the embodiment of the invention, the server determines the network data corresponding to the target cell in the target time interval based on the target neural network model, so that the accuracy of determining the network data of the target cell in a certain time interval can be improved; and after receiving the network data, the network device may determine a corresponding channel conflict solution based on the network data, that is, optimize the network, and may improve the frequency band utilization.

The network optimization method and apparatus provided in the embodiments of the present invention can be applied to a wireless communication system, and taking the wireless communication system as a 5G communication system as an example, as shown in fig. 1, the 5G communication system includes a terminal 101, a network device 102, and a server 103. In general, in practical applications, the connections between the above-mentioned devices or service functions may be wireless connections, and fig. 1 illustrates the connections between the devices by solid lines for convenience of intuitively representing the connections between the devices.

The terminal 101 is configured to send a function (e.g., a Resource Element (RE) -level rate matching function) of the terminal to the network device 102, and the network device 102 may determine a corresponding configuration scheme based on the function of the terminal 101.

The network device 102 is configured to receive a function that the terminal 101 has, which is transmitted by the terminal 101. In this embodiment of the present invention, the network device 102 is further configured to receive network data, which is sent by the server 103 and corresponds to the target cell in the target time interval, and determine, based on the network data, position puncturing for sending the SSB in the 5G network or position puncturing for sending a cell specific reference signal (CRS) in the 4G network.

And the server 103 is used for acquiring historical data. In this embodiment of the present invention, the server 103 is further configured to perform neural network training on the historical data to obtain a target neural network model, and further determine, based on the target neural network model, network data corresponding to a target cell in a target time interval.

By way of example, taking the network device 102 in fig. 1 as a commonly used base station as an example, a hardware structure of the network device 102 provided in the embodiment of the present invention is described. As shown in fig. 2, a base station provided in an embodiment of the present invention may include:

parts

20 and 21. The 20 part is mainly used for receiving and transmitting radio frequency signals and converting the radio frequency signals and baseband signals; the 21 part is mainly used for baseband processing, base station control, and the like. Portion 20 may be generally referred to as a transceiver unit, transceiver, transceiving circuitry, or transceiver, etc. Part 21 is typically the control center of the base station and may be generally referred to as a processing unit.

The transceiver unit of part 20, which may also be referred to as a transceiver, or a transceiver, etc., includes an antenna and a radio frequency unit, or only includes a radio frequency unit or a portion thereof, where the radio frequency unit is mainly used for radio frequency processing. Alternatively, a device for implementing the receiving function in section 20 may be regarded as a receiving unit, and a device for implementing the transmitting function may be regarded as a transmitting unit, that is, section 20 includes a receiving unit and a transmitting unit. A receiving unit may also be referred to as a receiver, a receiving circuit, or the like, and a transmitting unit may be referred to as a transmitter, a transmitting circuit, or the like.

Portion 21 may comprise one or more boards or chips, each of which may comprise one or more processors and one or more memories, the processors being configured to read and execute programs in the memories to implement baseband processing functions and control of the base station. If a plurality of single boards exist, the single boards can be interconnected to increase the processing capacity. As an alternative implementation, multiple boards may share one or more processors, or multiple boards may share one or more memories. The memory and the processor may be integrated together or may be provided separately. In some embodiments, the 20 and 21 portions may be integrated or may be separate. In addition, all functions in the part 21 may be integrated in one chip, or part of the functions may be integrated in one chip to implement another part of the functions may be integrated in one or more other chips to implement, which is not limited in this embodiment of the present invention.

For example, fig. 3 is a schematic diagram of a hardware structure of a server according to an embodiment of the present invention. As shown in fig. 3, the server 30 includes a processor 301, a memory 302, a network interface 303, and the like.

The processor 301 is a core component of the server 30, and the processor 301 is configured to run an operating system of the server 30 and application programs (including a system application program and a third-party application program) on the server 30, so as to implement the network optimization method performed by the server 30.

In this embodiment, the processor 301 may be a Central Processing Unit (CPU), a microprocessor, a Digital Signal Processor (DSP), an application-specific integrated circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, a transistor logic device, a hardware component, or any combination thereof, which is capable of implementing or executing various exemplary logic blocks, modules, and circuits described in connection with the disclosure of the embodiment of the present invention; a processor may also be a combination of computing functions, e.g., comprising one or more microprocessors, a DSP and a microprocessor, or the like.

Optionally, the processor 301 of the server 30 includes one or more CPUs, which are single-core CPUs (single-CPUs) or multi-core CPUs (multi-CPUs).

The memory 302 includes, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical memory, or the like. The memory 302 holds the code for the operating system.

Optionally, the processor 301 implements the network optimization method in the embodiment of the present invention by reading the instructions stored in the memory 302, or the processor 301 implements the network optimization method provided in the embodiment of the present invention by using the instructions stored inside. In the case that the processor 301 implements the network optimization method provided by the embodiment of the present invention by reading the execution saved in the memory, the memory stores instructions for implementing the network optimization method provided by the embodiment of the present invention.

The network interface 303 is a wired interface, such as a Fiber Distributed Data Interface (FDDI) interface or a Gigabit Ethernet (GE) interface. Alternatively, the network interface 303 is a wireless interface. The network interface 303 is used for the server 30 to communicate with other devices.

The memory 302 is configured to store historical data, that is, network data corresponding to a plurality of time intervals in a historical time period and each of the plurality of time intervals of the target cell. The at least one processor 301 further performs the method according to the embodiment of the present invention according to a plurality of time intervals in the history time period saved in the memory 302 and the network data corresponding to the target cell in each of the plurality of time intervals. For more details of the processor 301 to implement the above functions, reference is made to the following description of various method embodiments.

Optionally, the server 30 further includes a bus, and the processor 301 and the memory 302 are connected to each other through the bus 304, or in other manners.

Optionally, the server 30 further includes an input/output interface 305, where the input/output interface 305 is configured to connect with an input device, and receive a network data determination request (i.e., a request for determining network data corresponding to the target cell in the target time interval) input by a user through the input device. Input devices include, but are not limited to, a keyboard, a touch screen, a microphone, and the like. The input/output interface 305 is further configured to connect with an output device, and output the network data determination result (i.e. the network data corresponding to the target cell in the target time interval) of the processor 301. Output devices include, but are not limited to, displays, printers, and the like.

The network optimization method and the network optimization device provided by the embodiment of the invention are applied to a 4G network and a 5G network under the scene of Physical Resource Block (PRB) level spectrum sharing. When the 4G network and the 5G network share the spectrum, certain channel collision may occur. In the following embodiments, the network device may allocate different solutions based on different channel conflicts for different data or functions, so as to achieve the purpose of optimizing the network.

With reference to the communication system shown in fig. 1, the network optimization method provided in the embodiment of the present invention is completely described below from the perspective of interaction among devices in the communication system, so as to describe a process in which a server determines network data corresponding to a target cell in a target time interval and a process in which a network device allocates different solutions to different channel conflicts.

As shown in fig. 4, the network optimization method provided by the embodiment of the present invention may include S101-S107.

S101, the server acquires historical data.

The historical data comprises a plurality of time intervals in a historical time period and network data corresponding to the target cell in each time interval in the time intervals. Specifically, the network data corresponding to a time interval of the target cell in a time interval of the historical time period includes 4G downlink PDSCH layer traffic of the target cell in the time interval, 5G downlink PDSCH layer traffic of the target cell in the time interval, the number of TM3 terminals of the target cell in the time interval, the number of TM4 terminals of the target cell in the time interval, and the number of TM9 terminals of the target cell in the time interval.

It should be understood that the above historical time period may be 1 minute (min), 1 hour (h), 1 day, or the like, and the above one time interval may be 1 millisecond (ms), 1 second(s), 1 minute, or the like, and embodiments of the present invention are not particularly limited. Also, the time length of the historical period should be greater than the length of a time interval within the historical period, e.g., when the historical period is 1 day (or some 1 day), the time interval of the historical period should be less than 1 day (e.g., 1 s).

It is understood that the number of TM3 terminals of the target cell is used to indicate how many terminals of TM3 transmission mode are in the target cell. For example, if the number of TM3 terminals of the target cell in a certain time interval is 10, this indicates that there are 10 terminals with TM3 transmission mode in the target cell in the time interval. Similarly, the number of TM4 terminals of the target cell is used to indicate how many terminals with TM4 transmission modes the target cell has, and the number of TM9 terminals of the target cell is used to indicate how many terminals with TM9 transmission modes the target cell has.

It should be noted that TM3, TM4, and TM9 are all transmission modes in Long Term Evolution (LTE) LTE (i.e., 4G network), that is, TM3 terminal of the target cell, TM4 terminal of the target cell, and TM9 terminal of the target cell are all 4G terminals in the target cell.

In an implementation manner of the embodiment of the present invention, the server may obtain the history data from the network management device.

S102, the server determines network data corresponding to the target cell in the target time interval based on the target neural network model.

The network data corresponding to the target time interval includes 4G downlink PDSCH layer traffic of the target cell in the target time interval, 5G downlink PDSCH layer traffic of the target cell in the target time interval, the number of TM3 terminals of the target cell in the target time interval, the number of TM4 terminals of the target cell in the target time interval, and the number of TM9 terminals of the target cell in the target time interval.

It is to be understood that the target time interval is a time interval within a preset time period (or future time period). In the embodiment of the invention, the server can determine the network data corresponding to any time interval of the target cell in a certain time period in the future based on the target neural network model; the time length corresponding to the target time interval is the same as the time length corresponding to each of the plurality of time intervals.

In an implementation manner of the embodiment of the present invention, in the above S102, the server may be directly used when the target neural network model has been trained, that is, the server determines, based on the target neural network model, network data corresponding to the target cell in the target time interval.

In another implementation manner, the server may further perform neural network training based on historical data to obtain the target neural network model. Specifically, the content included in the history data is described in S101, and is not described herein again.

In the embodiment of the invention, the server can obtain the target neural network model based on historical data and Long Short Term Memory (LSTM) training.

The LSTM includes three gates for protecting and controlling the state of a cell (cell), namely a forgetting gate, an input gate, and an output gate.

Specifically, the forgetting gate is used to control the old knowledge to be merged into the main line, that is, to decide which information in the last output passes through the cell, specifically, the information can pass through siThe sigmoid function is realized by the calculation formula of

As shown in FIG. 5, the input of the forgetting gate is the output of the previous step (i.e., h) _t-1 ) And the current input (i.e. x) _t ) The output of the forgetting gate (i.e. f) _t ) Indicating the specific gravity, f, that allows the information in the last cell to pass _t Is a number between 0 and 1, where 0 means that no quantity (i.e. any information in the last cell) is allowed to pass, and 1 means that any quantity is allowed to pass. The method can be specifically realized by the following formula:

f _t ＝σ(W _f ×[h _t-1 ,x _t ]+b _f )

wherein σ is the sigmoid function, W _f And b _f The weights and intercepts in the forgetting gate layer are used for updating and optimizing the neural network model.

Further, f _t And C _t-1 The product (i.e. the state of the last cell) is the information that the point needs to be lost (or forgotten) in the mainline.

And the input gate is used for controlling the new knowledge to enter a main line, namely, deciding how much new information is added into the cell. As shown in fig. 5, the sigmoid layer determines which information that is newly input can be retained, and the tanh layer determines which information needs to be updated. The following equation can then be derived:

i _t ＝σ(W _i ×[h _t-1 ,x _t ]+b _i )

wherein i _t Indicating which information may be retained in the cell,

indicating which information needs to be updated, W _i And b _i Represents the weight and intercept, W, in the sigmoid layer _c And b _c The weight and intercept of the hanh layer are represented.

Further, i _t And

the product of (a) is the information needed to be added in the main line.

Thus, after determining the information that needs to be discarded and added, the state of the current cell can be determined, that is:

output gates and finally, the output of the model needs to be determined. The output needs to be based on the current cell state (i.e., C) _t )。

First, for h _t-1 And x _t Filtering, and calculating an output ratio through a sigmoid function, namely:

o _t ＝σ(W _o ×[h _t-1 ,x _t ]+b _o )

wherein o is _t Represents the output ratio, W _o And b _o Representing the weights and intercepts in the calculation of the output proportion.

Then, the state of the current cell (i.e. C) _t ) And (5) passing through the tanh function, and multiplying the tanh function by the output ratio to obtain the current output result. The method can be specifically realized by the following formula:

h _t ＝o _t ×tanh(C _t )

wherein h is _t Representing the final output of the cell.

In an implementation manner of the embodiment of the present invention, the server may adopt Root Mean Square Error (RMSE) as the loss function to optimize and verify the accuracy and effect of the neural network model, that is, update the plurality of ws (including W) _f 、W _i 、W _c And W _o ) And a plurality of b (including b) _f 、b _i 、b _c And b _o )。

The RMSE can measure the average magnitude of the gratuitous difference, which is the square root of the average of the squared differences between the predicted value and the actual observation, and can be specifically realized by the following formula:

s103, the server sends the network data corresponding to the target cell in the target time interval to the network equipment.

And S104, the network equipment receives the network data which is sent by the server and corresponds to the target cell in the target time interval.

The network data corresponding to the target time interval includes 4G downlink PDSCH layer traffic of the target cell in the target time interval, 5G downlink PDSCH layer traffic of the target cell in the target time interval, the number of TM3 terminals of the target cell in the target time interval, the number of TM4 terminals of the target cell in the target time interval, and the number of TM9 terminals of the target cell in the target time interval, and the network data corresponding to the target time interval is determined by the server based on a target neural network model.

S105, the network equipment determines whether the ratio of the number of TM9 terminals of the target cell to the number of 4G terminals in the target cell is smaller than a proportional threshold.

Wherein the number of 4G terminals in the target cell is the sum of the number of TM3 terminals of the target cell, the number of TM4 terminals of the target cell and the number of TM9 terminals of the target cell.

In conjunction with the description of the above embodiments, it should be understood that the TM3 terminal of the target cell, the TM4 terminal of the target cell, and the TM9 terminal of the target cell are all 4G terminals in the target cell, and the number of 4G terminals in the target cell is the sum of the three numbers of terminals.

It can be understood that when the ratio of the number of TM9 terminals in the target cell to the number of 4G terminals in the target cell is smaller than the ratio threshold, the ratio of TM9 terminals in the target cell is smaller, otherwise the ratio of TM9 terminals in the target cell is larger (i.e., the ratio of TM9 terminals is larger in the 4G terminals included in the target cell).

S106, under the condition that the ratio of the number of TM9 terminals of the target cell to the number of 4G terminals in the target cell is smaller than a proportional threshold, the network equipment determines whether the 4G downlink PDSCH layer flow of the target cell is larger than or equal to the 5G downlink PDSCH layer flow of the target cell.

It should be understood that 4G downlink PDSCH layer traffic represents 4G network traffic and 5G downlink PDSCH layer traffic represents 5G network traffic. In the embodiment of the invention, the network equipment can allocate one channel conflict solution for larger 4G network traffic and can also allocate another channel conflict solution for larger 5G network traffic.

S107, under the condition that the 4G downlink PDSCH layer flow of the target cell is larger than or equal to the 5G downlink PDSCH layer flow of the target cell, the network equipment determines the position punching for sending the SSB in the 5G network.

It can be understood that, the 4G downlink PDSCH layer traffic of the target cell is greater than or equal to the 5G downlink PDSCH layer traffic of the target cell, which indicates that the traffic of the 4G network is greater than or equal to the traffic of the 5G network in the target time interval, so that the network device may determine puncturing at the position where the SSB is transmitted in the 5G network, so that the punctured position can transmit the CRS in the 4G network. In this way, channel collisions between CRS in a 4G network and SSBs in a 5G network can be resolved.

It should be understood that the position of the original SSB is the resource used by the 5G network to send the SSB, and the position of the SSB sent in the 5G network is punctured, specifically, a part of the position of the SSB sent is punctured, that is, a part of the resource originally used to send the SSB is separated, so that the 4G network can send the CRS.

In an implementation manner of the embodiment of the present invention, when the 4G downlink PDSCH layer traffic of the target cell is smaller than the 5G downlink PDSCH layer traffic of the target cell, the network device determines to puncture the positions where the CRS is transmitted in the 4G network.

It should be understood that the 4G downlink PDSCH layer traffic of the target cell is smaller than the 5G downlink PDSCH layer traffic of the target cell, which means that the traffic of the 4G network is smaller than the traffic of the 5G network in the target time interval, and thus, the network device may determine the puncturing position at which the CRS is transmitted in the 4G network, so that the punctured position can transmit the SSB in the 5G network, that is, part of the resources originally used for transmitting the CRS is separated, so that the 5G network can transmit the SSB. In this way, channel collisions between CRS in a 4G network and SSBs in a 5G network can also be resolved.

In an implementation manner of the embodiment of the present invention, when a ratio of the number of TM9 terminals in the target cell to the number of 4G terminals in the target cell is greater than or equal to a proportional threshold, a network device determines that a multicast single frequency network (MBSFN) subframe is configured for a 4G network.

The MBSFN subframe is used to transmit a Physical Control Format Indicator Channel (PCFICH), a physical hybrid automatic repeat indicator channel (PHICH), and a Physical Downlink Control Channel (PDCCH).

Specifically, the 4G network may not transmit CRS, and only needs 1-2 symbols to transmit PCFICH, PHICH, and PDCCH.

In the network optimization method provided in the embodiment of the present invention, a server determines, based on a target neural network model, network data corresponding to a target cell in a target time interval, where the network data corresponding to the target time interval includes a 4G downlink PDSCH layer traffic of the target cell in the target time interval, a 5G downlink PDSCH layer traffic of the target cell in the target time interval, a number of TM3 terminals of the target cell in the target time interval, a number of TM4 terminals of the target cell in the target time interval, and a number of TM9 terminals of the target cell in the target time interval; the server sends the network data corresponding to the target cell in the target time interval to the network equipment; after receiving the network data, the network device determines whether the ratio of the number of TM9 terminals of the target cell to the number of 4G terminals in the target cell (i.e., the sum of the number of TM3 terminals, TM4 terminals and TM9 terminals in the target cell) is smaller than a proportional threshold, and determines whether the 4G downlink PDSCH layer traffic is greater than or equal to the 5G downlink PDSCH layer traffic if the number of TM9 terminals is smaller than the number of 4G terminals; then, when the 4G downlink PDSCH layer traffic is greater than or equal to the 5G downlink PDSCH layer traffic, the network device determines puncturing of the location where the SSB is transmitted in the 5G network. In the embodiment of the invention, the server determines the network data corresponding to the target cell in the target time interval based on the target neural network model, so that the accuracy of determining the network data of the target cell in a certain time interval can be improved; and after receiving the network data, the network device may determine a corresponding channel conflict solution based on the network data, that is, optimize the network, and may improve the frequency band utilization.

As shown in fig. 6, the network optimization method provided in the embodiment of the present invention may include S201 to S204.

S201, the network equipment acquires the function information of the target 5G terminal.

The function information of the target 5G terminal includes functions of the target 5G terminal, where the functions may include an RE-level rate matching function and/or a Resource Block (RB), that is, a rate matching function, and the target 5G terminal is one of a plurality of 5G terminals included in the target cell.

It should be understood that when the target 5G terminal establishes a communication relationship with the network device, the target 5G terminal may send the function information to the network device, and thus, the network device may allocate a corresponding channel conflict solution to the target 5G terminal based on the function of the target 5G terminal.

S202, the network equipment determines whether the target 5G terminal has the RE level rate matching function.

It can be understood that the network device determines whether the target 5G terminal has the RE-level rate matching function, i.e., determines whether the RE-level rate matching function is included in the function information of the target 5G terminal.

S203, in case that the target 5G terminal does not have the RE-level rate matching function, the network device determines whether the target 5G terminal has the RB-level rate matching function.

In an implementation manner of the embodiment of the present invention, in a case that the target 5G terminal has the RE-level rate matching function, the network device may determine at least one target RE symbol.

Wherein the at least one target RE symbol is used for transmitting CRS in a 4G network.

It should be appreciated that CRS in a 4G network and PDSCH in a 5G network may generate channel collisions during the spectrum resource sharing process. When the 5G network transmits the PDSCH, if the target 5G terminal has an RE-level rate matching function, the network device may determine to perform RE-level rate matching in the 5G network, specifically, the network device may determine the at least one target RE symbol through the RE-level rate matching, where the at least one target RE symbol no longer transmits the PDSCH in the 5G network but transmits the CRS in the 4G network.

S204, under the condition that the target 5G terminal has the RB level rate matching function, the network equipment determines at least one target RB symbol.

Wherein the at least one target RB symbol is used for transmitting CRS in a 4G network.

It can be understood that, when the 5G network transmits the PDSCH, if the target 5G terminal does not have the RE-level rate matching function but has the RB-level rate matching function, the network device may determine to perform RB-level rate matching in the 5G network, and specifically, through the RB-level rate matching, the network device may determine the at least one target RB symbol, where the at least one target RB symbol no longer transmits the PDSCH in the 5G network but transmits the CRS in the 4G network.

In an implementation manner of the embodiment of the present invention, when the 5G network transmits the PDSCH, if the target 5G terminal has an RB-level rate matching function, the network device may further determine other RB symbols, where the other RB symbols are used to transmit Primary Synchronization Signals (PSS), Secondary Synchronization Signals (SSS) or PBCH in the 4G network.

In this embodiment of the present invention, after 203, the network optimization method provided in this embodiment of the present invention further includes: in the case that the target 5G terminal does not have the RB-level rate matching function, the network device configures a zero power channel state information-reference signal (ZP CSI-RS) in the 5G network.

It should be understood that the network device configures the ZP CSI-RS in the 5G network to correspond to a symbol for transmitting CRS in the 4G network, the network device needs multiple sets of CSI-RS to perform rate matching in a ZP CSI-RS manner, and the network device configures the ZP CSI-RS at a position where the 4G CRS is transmitted.

According to the network optimization method provided by the embodiment of the invention, the network equipment acquires the function information of the target 5G terminal, and determines whether the target 5G terminal has the RE-level rate matching function or not; then, in case that the target 5G terminal does not have the RE-level rate matching function, the network device determines again whether the target 5G terminal has the RB-level rate matching function, and in case that the target 5G terminal has the RB-level rate matching function, the network device determines at least one target RB symbol, wherein the at least one target RB symbol is used for transmitting the CRS in the 4G network. In the embodiment of the invention, the network equipment can acquire the function information from the signaling reported by a certain 5G terminal, and based on the functions of the network equipment, the corresponding channel conflict solution method is distributed to the 5G terminal, so that the network is optimized, and the transmission efficiency between the network equipment and the 5G terminal is improved.

In an implementation manner of the embodiment of the present invention, the network device may further determine whether the target 5G terminal supports a demodulation reference signal (DMRS) additional symbol moving function, and in a case that the target 5G terminal supports the DMRS additional symbol moving function, the network device may move a position at which the DMRS additional is transmitted from a symbol 11 to a symbol 12.

It should be understood that in a high speed scenario, the 5G network may enhance mobility performance through DMRS addition, but its symbol position collides with the pilot of LTE, i.e., DMRS addition in the 5G network collides with CRS in the 4G network, and therefore, the network device may move the position where DMRS addition is transmitted from symbol 11 to symbol 12.

Optionally, the network device may also configure ZP CRS-RS for the 4G network (or 5G network) to avoid interference by PDSCH of the 4G network (or 5G network) when the 5G network (or 4G network) configures CSI-RS.

It should be understood that the CSI-RS is important for reporting a Channel Quality Indicator (CQI) or a Rank Indication (RI) periodically, and in order to overlap the NZP CSI-RS in the 5G network (or the 4G network) and the ZP CSI-RS in the 4G network (or the 5G network), a non-zero power state information-reference signal (NZP CSI-RS) with multiple ports may need to be configured.

In another implementation manner of the embodiment of the present invention, the network device may send the PDCCH in the 4G network through the first symbol, and then send the PDCCH in the 5G network through a plurality of symbols thereafter.

In the embodiment of the present invention, the server, the network device, and the like may be divided into functional modules according to the above method examples, for example, each functional module may be divided corresponding to each function, or two or more functions may be integrated into one processing module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. It should be noted that, the division of the modules in the embodiment of the present invention is schematic, and is only a logic function division, and there may be another division manner in actual implementation.

In the case of dividing each functional module by corresponding functions, fig. 7 shows a possible structural diagram of the server involved in the above embodiment, and as shown in fig. 7, the server 40 may include: a determination module 401 and a sending module 402.

A determining module 401, configured to determine network data corresponding to a target cell in a target time interval based on a target neural network model, where the network data corresponding to the target time interval includes 4G downlink PDSCH layer traffic of the target cell in the target time interval, 5G downlink PDSCH layer traffic of the target cell in the target time interval, the number of TM3 terminals of the target cell in the target time interval, the number of TM4 terminals of the target cell in the target time interval, and the number of TM9 terminals of the target cell in the target time interval.

A sending module 402, configured to send network data corresponding to the target cell in the target time interval to the network device.

Optionally, the determining module 401 is further configured to perform neural network training on the historical data to obtain the target neural network model; the history data includes a plurality of time intervals within a history time period and network data corresponding to each time interval of the target cell within the plurality of time intervals, where the network data corresponding to one time interval of the target cell within the history time period includes 4G downlink PDSCH layer traffic of the target cell within the time interval, 5G downlink PDSCH layer traffic of the target cell within the time interval, the number of TM3 terminals of the target cell within the time interval, the number of TM4 terminals of the target cell within the time interval, and the number of TM9 terminals of the target cell within the time interval.

In the case of integrated units, fig. 8 shows a possible structural diagram of the server involved in the above-described embodiment. The server 50 as shown in fig. 8 may include: a processing module 501 and a communication module 502. The processing module 501 may be used to control and manage the actions of the server 50. The communication module 502 may be used to support communication of the server 50 with other entities. Optionally, as shown in fig. 8, the server 50 may further include a storage module 503 for storing program codes and data of the server 50.

The processing module 501 may be a processor or a controller (for example, the processor 301 shown in fig. 3 may be mentioned above). The communication module 502 may be a transceiver, a transceiver circuit, or a communication interface, etc. (e.g., may be the network interface 303 as shown in fig. 3 described above). The storage module 503 may be a memory (e.g., may be the memory 302 described above with reference to fig. 3).

When the processing module 501 is a processor, the communication module 502 is a transceiver, and the storage module 503 is a memory, the processor, the transceiver, and the memory may be connected by a bus. The bus may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc.

In the case of dividing each functional module by corresponding functions, fig. 9 shows a schematic diagram of a possible structure of the network device in the foregoing embodiment, as shown in fig. 9, the network device 60 may include: a receiving module 601 and a determining module 602.

A receiving module 601, configured to receive network data, sent by a server, corresponding to a target cell in a target time interval, where the network data corresponding to the target time interval includes 4G downlink PDSCH layer traffic of the target cell in the target time interval, 5G downlink PDSCH layer traffic of the target cell in the target time interval, the number of TM3 terminals of the target cell in the target time interval, the number of TM4 terminals of the target cell in the target time interval, and the number of TM9 terminals of the target cell in the target time interval, and the network data corresponding to the target cell in the target time interval is determined by the server based on a target neural network model.

A determining module 602, configured to determine whether a ratio of the number of TM9 terminals of the target cell to the number of 4G terminals in the target cell is smaller than a ratio threshold, where the number of 4G terminals in the target cell is a sum of the number of TM3 terminals of the target cell, the number of TM4 terminals of the target cell, and the number of TM9 terminals of the target cell; and determining whether the 4G downlink PDSCH layer traffic of the target cell is greater than or equal to the 5G downlink PDSCH layer traffic of the target cell, if the ratio of the number of TM9 terminals of the target cell to the number of 4G terminals in the target cell is less than the proportional threshold; and determining position punching for transmitting SSB in the 5G network under the condition that the 4G downlink PDSCH layer flow of the target cell is greater than or equal to the 5G downlink PDSCH layer flow of the target cell.

Optionally, the determining module 602 is further configured to determine to configure an MBSFN subframe for the 4G network, where a ratio of the number of TM9 terminals of the target cell to the number of 4G terminals in the target cell is greater than or equal to the ratio threshold, and the MBSFN subframe is used to transmit the PCFICH, the PHICH, and the PDCCH.

Optionally, the determining module 602 is further configured to determine whether a target 5G terminal has an RE-level rate matching function, where the target 5G terminal is one of multiple 5G terminals included in the target cell; and, in case the target 5G terminal does not have the RE-level rate matching function, determining whether the target 5G terminal has an RB-level rate matching function; and determining at least one target RB symbol for transmitting CRS in the 4G network if the target 5G terminal has the RB level rate matching function.

In the case of an integrated unit, fig. 10 shows a schematic diagram of a possible structure of the network device involved in the above-described embodiment. As shown in fig. 10, the network device 70 may include: a processing module 701 and a communication module 702. Processing module 701 may be used to control and manage the actions of network device 70. Communication module 702 may be used to support communication of network device 70 with other entities. Optionally, as shown in fig. 10, the network device 70 may further include a storage module 703 for storing program codes and data of the network device 70.

The processing module 701 may be a processor or a controller (for example, the processor 301 shown in fig. 3). The communication module 702 may be a transceiver, a transceiver circuit or a communication interface, etc. (e.g., may be the network interface 303 as shown in fig. 3 described above). The storage module 703 may be a memory (e.g., may be the memory 302 described above with reference to fig. 3).

When the processing module 701 is a processor, the communication module 702 is a transceiver, and the storage module 703 is a memory, the processor, the transceiver, and the memory may be connected by a bus. The bus may be a PCI bus or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc.

It should be understood that, in various embodiments of the present invention, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In the above embodiments, all or part of the implementation may be realized by software, hardware, firmware, or any combination thereof. When implemented using a software program, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. The procedures or functions described in accordance with the embodiments of the invention may be carried out in whole or in part when the computer program instructions are loaded and executed on a computer. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored on a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website, computer, server, or data center to another website, computer, server, or data center via wire (e.g., coaxial cable, fiber optics, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or can comprise one or more data storage devices, such as a server, a data center, etc., that can be integrated with the medium. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.

The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily think of the changes or substitutions within the technical scope of the present invention, and shall cover the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for network optimization, comprising:

the method comprises the steps that a server determines network data corresponding to a target cell in a target time interval based on a target neural network model, wherein the network data corresponding to the target time interval comprise 4G downlink Physical Downlink Shared Channel (PDSCH) layer traffic of the target cell in the target time interval, 5G downlink PDSCH layer traffic of the target cell in the target time interval, the number of transmission mode (TM 3) terminals of the target cell in the target time interval, the number of TM4 terminals of the target cell in the target time interval and the number of TM9 terminals of the target cell in the target time interval;

the server sends network data corresponding to a target time interval of the target cell to network equipment, so that the network equipment determines position punching for sending a synchronization signal and a physical broadcast channel block SSB in a 5G network under the condition that the ratio of the number of TM9 terminals of the target cell to the number of 4G terminals in the target cell is smaller than a proportional threshold, and the 4G downlink PDSCH layer flow of the target cell is larger than or equal to the 5G downlink PDSCH layer flow of the target cell, wherein the number of 4G terminals in the target cell is the sum of the number of TM3 terminals of the target cell, the number of TM4 terminals of the target cell and the number of TM9 terminals of the target cell.

2. The method of claim 1, further comprising:

the server carries out neural network training on historical data to obtain the target neural network model; the historical data comprises a plurality of time intervals in a historical time period and network data corresponding to the target cell in each time interval in the plurality of time intervals, wherein the network data corresponding to one time interval in the historical time period of the target cell comprises 4G downlink PDSCH layer traffic of the target cell in the time interval, 5G downlink PDSCH layer traffic of the target cell in the time interval, the number of TM3 terminals of the target cell in the time interval, the number of TM4 terminals of the target cell in the time interval and the number of TM9 terminals of the target cell in the time interval.

3. A method for network optimization, comprising:

the network equipment receives network data, corresponding to a target cell in a target time interval, sent by a server, wherein the network data corresponding to the target time interval comprises 4G downlink Physical Downlink Shared Channel (PDSCH) layer traffic of the target cell in the target time interval, 5G downlink PDSCH layer traffic of the target cell in the target time interval, the number of transmission mode (TM 3) terminals of the target cell in the target time interval, the number of TM4 terminals of the target cell in the target time interval and the number of TM9 terminals of the target cell in the target time interval, and the network data, corresponding to the target cell in the target time interval, is determined by the server based on a target neural network model;

the network equipment determines whether the ratio of the number of TM9 terminals of the target cell to the number of 4G terminals in the target cell is smaller than a ratio threshold, wherein the number of 4G terminals in the target cell is the sum of the number of TM3 terminals of the target cell, the number of TM4 terminals of the target cell and the number of TM9 terminals of the target cell;

under the condition that the ratio of the number of TM9 terminals of the target cell to the number of 4G terminals in the target cell is smaller than the proportional threshold, the network equipment determines whether the 4G downlink PDSCH layer traffic of the target cell is larger than or equal to the 5G downlink PDSCH layer traffic of the target cell;

and under the condition that the 4G downlink PDSCH layer flow of the target cell is greater than or equal to the 5G downlink PDSCH layer flow of the target cell, the network equipment determines the position punching for sending the synchronous signal and the physical broadcast channel block SSB in the 5G network.

4. The method of claim 3, further comprising:

under the condition that the ratio of the number of TM9 terminals of the target cell to the number of 4G terminals in the target cell is greater than or equal to the ratio threshold, the network equipment determines that a multicast single frequency network (MBSFN) subframe is configured for the 4G network, and the MBSFN subframe is used for sending a Physical Control Format Indicator Channel (PCFICH), a physical hybrid automatic repeat indicator channel (PHICH) and a Physical Downlink Control Channel (PDCCH).

5. The method of claim 4, further comprising:

the network equipment determines whether a target 5G terminal has a resource element RE level rate matching function, wherein the target 5G terminal is one of a plurality of 5G terminals included in the target cell;

in the case that the target 5G terminal does not have the RE level rate matching function, the network device determines whether the target 5G terminal has a Resource Block (RB) level rate matching function;

in a case where the target 5G terminal has the RB level rate matching function, the network device determines at least one target RB symbol for transmitting a cell-specific reference signal, CRS, in the 4G network.

6. A server, characterized in that the server comprises: a determining module and a sending module;

the determining module is configured to determine, based on a target neural network model, network data corresponding to a target cell in a target time interval, where the network data corresponding to the target time interval includes PDSCH layer traffic of 4G downlink physical downlink shared channel of the target cell in the target time interval, PDSCH layer traffic of 5G downlink of the target cell in the target time interval, the number of TM3 terminals in a transmission mode of the target cell in the target time interval, the number of TM4 terminals of the target cell in the target time interval, and the number of TM9 terminals of the target cell in the target time interval;

the sending module is configured to send network data corresponding to the target cell in a target time interval to a network device, so that when a ratio of the number of TM9 terminals of the target cell to the number of 4G terminals in the target cell is smaller than a proportional threshold, and a 4G downlink PDSCH layer traffic of the target cell is greater than or equal to a 5G downlink PDSCH layer traffic of the target cell, the network device determines to send a synchronization signal and a position puncture of a physical broadcast channel block SSB in a 5G network, where the number of 4G terminals in the target cell is a sum of the number of TM3 terminals of the target cell, the number of TM4 terminals of the target cell, and the number of TM9 terminals of the target cell.

7. The server according to claim 6,

the determining module is further configured to perform neural network training on historical data to obtain the target neural network model; the historical data comprises a plurality of time intervals in a historical time period and network data corresponding to the target cell in each time interval in the plurality of time intervals, wherein the network data corresponding to one time interval in the historical time period of the target cell comprises 4G downlink PDSCH layer traffic of the target cell in the time interval, 5G downlink PDSCH layer traffic of the target cell in the time interval, the number of TM3 terminals of the target cell in the time interval, the number of TM4 terminals of the target cell in the time interval and the number of TM9 terminals of the target cell in the time interval.

8. A network device, comprising a receiving module and a determining module;

the receiving module is configured to receive network data, sent by a server, corresponding to a target cell in a target time interval, where the network data corresponding to the target time interval includes PDSCH layer traffic of a 4G downlink physical downlink shared channel of the target cell in the target time interval, PDSCH layer traffic of a 5G downlink of the target cell in the target time interval, the number of TM3 terminals in a transmission mode of the target cell in the target time interval, the number of TM4 terminals of the target cell in the target time interval, and the number of TM9 terminals of the target cell in the target time interval, and the network data corresponding to the target cell in the target time interval is determined by the server based on a target neural network model;

the determining module is configured to determine whether a ratio of the number of TM9 terminals of the target cell to the number of 4G terminals in the target cell is smaller than a ratio threshold, where the number of 4G terminals in the target cell is a sum of the number of TM3 terminals of the target cell, the number of TM4 terminals of the target cell, and the number of TM9 terminals of the target cell; and determining whether the 4G downlink PDSCH layer flow of the target cell is greater than or equal to the 5G downlink PDSCH layer flow of the target cell under the condition that the ratio of the number of TM9 terminals of the target cell to the number of 4G terminals in the target cell is less than the proportional threshold; and determining position punching for transmitting a synchronization signal and a physical broadcast channel block (SSB) in a 5G network under the condition that the 4G downlink PDSCH layer flow of the target cell is greater than or equal to the 5G downlink PDSCH layer flow of the target cell.

9. The network device of claim 8,

the determining module is further configured to determine that a multicast single frequency network MBSFN subframe is configured for the 4G network, where the MBSFN subframe is used to send a physical control format indicator channel PCFICH, a physical hybrid automatic repeat indicator channel PHICH, and a physical downlink control channel PDCCH, when a ratio of the number of TM9 terminals of the target cell to the number of 4G terminals in the target cell is greater than or equal to the ratio threshold.

10. The network device of claim 9,

the determining module is further configured to determine whether a target 5G terminal has a resource element RE-level rate matching function, where the target 5G terminal is one of multiple 5G terminals included in the target cell; and, in case the target 5G terminal does not have the RE-level rate matching function, determining whether the target 5G terminal has a resource block RB-level rate matching function; and determining at least one target RB symbol for transmitting a cell-specific reference signal, CRS, in the 4G network, in case the target 5G terminal has the RB-level rate matching function.