Base station parameter control method and communication apparatus

Abstract

The embodiments of the present application relate to the technical field of wireless communications. Provided are a base station parameter control method and a communication apparatus. The method comprises: acquiring first geographic location information of a target control region and traffic statistics data in the target control region, wherein the traffic statistics data comprises statistical values of a plurality of traffic statistics items within a first duration; matching the first geographic location information and the traffic statistics data with a plurality of preset scenarios, and determining a target scenario corresponding to the target control region; inputting into a prediction model at least one piece of target geographic location information and at least one target traffic statistics item that correspond to the target scenario and a target statistical value range that corresponds to the at least one target traffic statistics item, and determining, on the basis of output data of the prediction model, a configuration parameter of a base station in the target control region. By means of the embodiments of the present application, a base station can provide a communication service which better meets the communication requirements of a user.

Description

Base station parameter control method and communication apparatus

[0001] Cross-reference to Related Applications

[0002] This application claims priority to the Chinese Patent Application No. 202410411702.2, filed on April 7, 2024, and entitled “Base station parameter control method and communication apparatus”, the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0003] The present application relates to the technical field of wireless communication, and in particular to a base station parameter control method and a communication apparatus. BACKGROUND

[0004] In a communication network, different configuration parameters of a base station determine the signal coverage range, signal strength and other indicators of the base station. The advantages and disadvantages of these indicators have a significant impact on the quality of the communication network and the user experience. Therefore, in order to improve the user experience, it is necessary to adjust the configuration parameters of the base station in the communication network to better meet the needs of users. SUMMARY

[0005] Embodiments of the present application provide a base station parameter control method and a communication apparatus to better meet the communication needs of users by setting the configuration parameters of the base station.

[0006] In a first aspect, embodiments of the present application provide a base station parameter control method. The base station parameter control method can be executed by a network device, such as a base station, a relay station, or an access point, or a chip in these devices, and the present application does not limit this. The base station parameter control method includes: obtaining first geographic location information of a target control area and traffic statistical data in the target control area, the traffic statistical data including statistical values of a plurality of traffic statistical items within a first time length; matching the first geographic location information and the traffic statistical data with a plurality of preset scenes to determine a target scene corresponding to the target control area; each scene in the plurality of preset scenes includes at least one geographic location information corresponding to each scene, at least one traffic statistical item corresponding to each scene, and a statistical value range corresponding to the at least one traffic statistical item; inputting at least one target geographic location information, at least one target traffic statistical item, and a target statistical value range corresponding to the at least one target traffic statistical item corresponding to the target scene into a prediction model, and determining configuration parameters of a base station in the target control area according to output data of the prediction model, the configuration parameters being used to configure the base station in the target control area within a second time length, the second time length being after the first time length.

[0007] By using the method, the network device can determine the configuration parameters of the base stations in the target control area in the next time length according to the traffic statistical data and the geographic location information obtained in the last time length in the target control area, thereby dynamically adjusting the configuration parameters according to the geographic location information and the traffic statistical data in the target control area, improving the regulation and control effect of the configuration parameters of the base stations, and enabling the base stations to provide communication services that better meet the communication needs of users.

[0008] In an implementation, the method further includes obtaining a first historical record, the first historical record including at least one statistical value corresponding to at least one of the traffic statistical items respectively, and second geographic location information corresponding to the at least one statistical value, the at least one statistical value corresponding to at least one of the traffic statistical items respectively, and second geographic location information corresponding to the at least one statistical value, the third time length being located before the first time length; determining a plurality of frequent item sets based on the first historical record, each of the frequent item sets including one or more of the at least one traffic statistical item, a statistical value range corresponding to each of the one or more, and second geographic location information corresponding to the one or more in the first historical record; the statistical value range corresponding to the one or more being obtained according to the statistical values corresponding to the one or more, and the ratio of the number of times that the one or more in each of the frequent item sets appear together in the third time length to the total number of item sets in the third time length exceeding a preset threshold; and taking each of the frequent item sets as a scene to obtain the plurality of preset scenes.

[0009] By using the method, the frequent item sets that frequently appear are obtained from the historical record of the traffic statistical data and the geographic location information, the frequent item sets are taken as preset scenes, the configuration parameters of the base stations are determined according to the target scene matching the preset scene, thereby improving the adaptability of the configuration parameters to the actual preset scene, and enabling the configuration parameters of the base stations to meet the traffic demand in the target control area.

[0010] In an implementation, the prediction model is obtained by training a prediction classifier, the prediction classifier being used to predict whether the output data of the prediction model can optimize the traffic statistical data in the second time length, and the prediction classifier is obtained by training a second historical record. Accordingly, the method further includes obtaining a second historical record, the second historical record including at least one statistical value corresponding to at least one traffic statistical item respectively, third geographic location information corresponding to the at least one statistical value, and a configuration parameter scheme corresponding to the at least one statistical value, the fourth time length being located before the first time length; determining the prediction model based on the second historical record, the prediction model being used to describe the relationship between different geographic location information, at least one traffic statistical item corresponding to the different geographic location information, a statistical value range corresponding to the at least one traffic statistical item, and a configuration parameter.

[0011] The method can use the prediction model to process a large amount of traffic statistical data and geographical position information, improve the calculation speed of the configuration parameters, and timely adjust the configuration parameters of the base station when the traffic statistical data changes. In addition, the prediction model is determined according to the historical records of the traffic statistical data, the geographical position information, and the configuration parameters, so that the prediction model can obtain the relationship between the configuration parameters and the traffic statistical data and the geographical position information from the historical data, and more accurately determine the configuration parameters of the base station according to the traffic statistical data and the geographical position information.

[0012] In an embodiment, the output data of the prediction model can be used as the configuration parameters of the base station in the target control area. The method can directly use the output data of the prediction model as the configuration parameters of the base station in the target control area, so that the configuration parameters can be quickly transmitted to the base station, and the response speed can be improved.

[0013] In an embodiment, the output data of the prediction model can be adjusted according to a preset adjustment rule to obtain the configuration parameters of the base station in the target control area. The method can adjust the output data of the prediction model according to the adjustment rule to obtain the configuration parameters, so that more optimized configuration parameters that meet the adjustment rule can be obtained on the basis of the output data of the prediction model.

[0014] In an embodiment, after the output data of the prediction model is adjusted according to the preset adjustment rule to obtain the configuration parameters of the base station in the target control area, the method further includes: adjusting the configuration parameters for multiple rounds before a preset stop condition is met; and using the configuration parameters adjusted in each round as the configuration parameters of the base station in the target control area at different time points. The method can adjust the configuration parameters for multiple rounds, so that the configuration parameters can be optimized multiple times based on the adjustment rule.

[0015] In an embodiment, after it is determined that the preset stop condition is met, the first geographical position information of the target control area and the traffic statistical data in the target control area can be reacquired, and a new round of process of predicting the configuration parameters of the base station can be started. The method can stop adjusting the configuration parameters when it is determined that the preset stop condition is met, and start a new round of process of predicting the configuration parameters of the base station, so that unnecessary adjustments can be reduced, and system resources can be saved.

[0016] In an embodiment, the method of adjusting the configuration parameters for multiple rounds includes: determining adjustment data for optimizing the configuration parameters obtained in the last round according to a preset adjustment rule; the adjustment data is used to adjust the configuration parameters to be adjusted currently, and the adjustment data is less than a preset threshold; and adjusting the configuration parameters to be adjusted currently according to the adjustment data.

[0017] By using the above method, in multiple rounds of adjustment, the adjustment data of this time is determined according to the adjustment data used for adjustment last time, and the generated adjustment data is taken as a reference, which is beneficial to constantly find more optimized adjustment data according to the adjustment record.

[0018] In an implementation, the stop condition comprises that the modulation round number of the configuration parameter reaches a preset round threshold. By using the above method, when the adjustment round number is large, the adjustment of the configuration parameter is stopped, which is beneficial to effectively reduce unnecessary adjustment.

[0019] In an implementation, the preset adjustment rule is used to describe the relationship between different output data, different optimization indexes, and adjustment amounts of different optimization indexes. By using the above method, the relationship between different output data, different optimization indexes, and adjustment amounts of different optimization indexes is expressed through the preset adjustment rule, which can limit the adjustment within a reasonable rule range and avoid large errors in the adjustment of the configuration parameter.

[0020] In an implementation, the base station configuration parameter control method further comprises: determining a probability that the configuration parameter can optimize the traffic statistical data; if the probability is greater than a probability requirement value corresponding to the target scenario, sending the configuration parameter to the base station in the target control area; or if the probability is less than the probability requirement value corresponding to the target scenario, refusing to send the configuration parameter to the base station in the target control area.

[0021] By using the above method, by setting the probability requirement value, the probability of configuring the configuration parameter to the base station in the target control area can be controlled, and the performance stability of the base station in the target control area can be better maintained. If it is desired that the performance stability of the base station in the target control area is high, a higher probability requirement value can be set, and vice versa, so that the configuration parameter of the base station is adjusted according to different requirements for stability in the target control area.

[0022] In an implementation, the target control area is one of multiple areas obtained by dividing a controllable area, and each area in the multiple areas includes at least one base station. By using the above method, the controllable area is divided into multiple areas, and one of the multiple areas is controlled separately, which can reduce the control granularity of the configuration parameter of the base station, realize fine control, and improve the adaptation degree of the configuration parameter and the geographic location information.

[0023] In an implementation, the third time length is greater than the first time length, and the third time length is greater than the second time length. With the above method, the third time length is greater than any one of the first time length and the second time length, so that the first historical record in the third time length can be used to more accurately and comprehensively obtain various possible frequent item sets, and then more comprehensive multiple preset scenes are obtained, and the application range of the method of the embodiment of the present application is improved.

[0024] In a second aspect, an embodiment of the present application provides a base station parameter control device, comprising a transceiver module and a processing module; the transceiver module is configured to: obtain first geographic location information of a target control area, and traffic statistical data in the target control area, the traffic statistical data comprising statistical values of a plurality of traffic statistical items in a first time length; the processing module is configured to: match the first geographic location information and the traffic statistical data with a plurality of preset scenes to determine a target scene corresponding to the target control area; each scene in the plurality of preset scenes comprises: at least one geographic location information corresponding to each scene, at least one traffic statistical item corresponding to each scene, and a statistical value range corresponding to the at least one traffic statistical item; input at least one target geographic location information, at least one target traffic statistical item, and a target statistical value range corresponding to the at least one target traffic statistical item corresponding to the target scene into a prediction model, and determine a configuration parameter of a base station in the target control area according to output data of the prediction model, the configuration parameter being used to configure the base station in the target control area in a second time length, the second time length being after the first time length.

[0025] In a third aspect, an embodiment of the present application provides a communication device, comprising units for performing each step of the method provided in the first aspect. For example, the communication device can comprise a processing unit and a transceiver unit.

[0026] In an optional implementation, the device can comprise a module corresponding to each of the methods / operations / steps / actions of any possible implementation of the first aspect, which can be a hardware circuit, software, or a combination of hardware circuit and software. In an optional implementation, the device comprises a processing unit (sometimes also referred to as a processing module) and a communication unit (sometimes also referred to as a transceiver module, a communication module, etc.). The transceiver unit can implement the sending function and the receiving function. When the transceiver unit implements the sending function, it can be referred to as a sending unit (sometimes also referred to as a sending module). When the transceiver unit implements the receiving function, it can be referred to as a receiving unit (sometimes also referred to as a receiving module). The sending unit and the receiving unit can be the same functional module, which is referred to as a transceiver unit, and the functional module can implement the sending function and the receiving function. Alternatively, the sending unit and the receiving unit can be different functional modules, and the transceiver unit is a general term for these functional modules.

[0027] In a fourth aspect, an embodiment of the present application further provides a communication apparatus, including a processor configured to execute a computer program (or computer executable instructions) stored in a memory, when the computer program (or computer executable instructions) is executed, the apparatus performs the method according to the first aspect and any possible implementation manner thereof.

[0028] In a possible implementation, the processor and the memory can be integrated together; in another possible implementation, the memory can also be located outside the communication apparatus.

[0029] The communication apparatus can further include a communication interface configured to enable the communication apparatus to communicate with other devices, such as transmitting or receiving data and / or signals. For example, the communication interface can be a transceiver, a circuit, a bus, a module or other types of communication interfaces.

[0030] In a fifth aspect, an embodiment of the present application provides a chip, the chip is configured to read a computer program stored in a memory, and execute the method according to the first aspect. Optionally, the chip can include a processor, the processor is coupled with the memory, and is configured to read the computer program stored in the memory, and implement the method according to the first aspect and any possible implementation manner thereof. Optionally, the chip can further include a memory, a communication interface, a power supply module and the like. The memory is configured to store the computer program, the communication interface is configured to receive and send data, and the power supply unit is configured to supply power for the processor.

[0031] In a sixth aspect, an embodiment of the present application further provides a chip system, the chip system can include a logic circuit (or understood as, the chip system includes a processor, the processor can include a logic circuit and the like), and can further include an input / output interface. The input / output interface can be configured to input a message, and can also be configured to output a message. The input / output interface can be the same interface, that is, the same interface can implement the sending function and the receiving function; or the input / output interface can include an input interface and an output interface, the input interface is configured to implement the receiving function, that is, configured to receive a message, and the output interface is configured to implement the sending function, that is, configured to send a message. The logic circuit can be configured to perform operations other than the transceiving function in the method according to any one of the first aspect to the second aspect and any possible implementation manner thereof; the logic circuit can also be configured to transmit a message to the input / output interface, or receive a message from the input / output interface from other communication apparatuses. The chip system can be configured to implement the method according to the first aspect and any possible implementation manner thereof. The chip system can be composed of a chip, or can include a chip and other discrete devices.

[0032] Optionally, the chip system can further include a memory, the memory can be used to store instructions, and the logic circuit can invoke the instructions stored in the memory to implement corresponding functions.

[0033] In a seventh aspect, an embodiment of the present application provides a computer storage medium, which stores a program, and when the program is executed on a communication device, the communication device is caused to execute the method provided in the first aspect.

[0034] In an eighth aspect, an embodiment of the present application provides a program product, which contains a program or instructions; and when the program or instructions are executed on a computer, the computer is caused to execute the method provided in the first aspect.

[0035] In a ninth aspect, a communication system is provided, which can include a base station parameter control device and at least one base station; the base station parameter control device is configured to execute the method in the first aspect and any possible implementation thereof, so as to configure parameters for the at least one base station.

[0036] The technical effects brought by the second aspect to the ninth aspect can be referred to the description of the beneficial effects of the corresponding solutions in the first aspect, and will not be described here. BRIEF DESCRIPTION OF DRAWINGS

[0037] FIG. 1 is a schematic diagram of a communication system architecture suitable for embodiments of the present application;

[0038] FIG. 2 is a schematic diagram of a system suitable for the method of embodiments of the present application;

[0039] FIG. 3 is a schematic diagram of a flow of a base station parameter configuration control method provided by embodiments of the present application;

[0040] FIG. 4 is a schematic diagram of a region division method in the base station parameter configuration control method provided by embodiments of the present application;

[0041] FIG. 5 is a schematic diagram of another region division method provided by embodiments of the present application;

[0042] FIG. 6 is a schematic diagram of a flow of a base station parameter configuration control method provided by an example of the present application;

[0043] FIG. 7 is a schematic diagram of a head pointer provided by an example of the present application;

[0044] FIG. 8 is a schematic diagram of a frequent pattern tree provided by an example of the present application;

[0045] FIG. 9 is a schematic diagram of a flow of a base station parameter configuration control method provided by another example of the present application;

[0046] FIG. 10 is a schematic diagram of a flow of a base station parameter configuration control method provided by yet another example of the present application;

[0047] Fig. 11 is a flow chart of a method for controlling configuration parameters of a base station according to another example of the present application;

[0048] Fig. 12A is a flow chart of a method for controlling configuration parameters of a base station according to another example of the present application;

[0049] Fig. 12B is a schematic diagram of an interface according to an example of the present application;

[0050] Fig. 12C is a schematic diagram of an adjustment data optimization process according to an example of the present application;

[0051] Fig. 13 is a schematic diagram of a communication device according to an example of the present application;

[0052] Fig. 14 is a schematic diagram of a communication device according to another example of the present application. DETAILED DESCRIPTION

[0053] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the drawings.

[0054] In the embodiments of the present application, the number of a noun, unless otherwise specified, represents "a singular noun or a plural noun", i.e. "one or more". "At least one" means one or more, and "a plurality of" means two or more. "Or" describes the association relationship of the associated objects, and means that there can be two kinds of relationships, for example, A or B, which means that A exists alone, B exists alone, and A, B can be singular or plural. The character " " generally represents that the associated objects before and after it are in a "or" relationship. For example, A / B means A or B. In the description of the present application, unless otherwise specified, the meaning of "a plurality of" is two or more.

[0055] The ordinal numbers "first", "second", etc. mentioned in the embodiments of the present application are used to distinguish a plurality of objects, and are not used to limit the size, content, order, time sequence, priority or importance of the plurality of objects. For example, the first information and the second information can be the same information or different information, and such names do not mean that the two pieces of information occupy different resources, transmission order, sending / receiving end, content, size, application scenario, priority or importance, etc. In addition, the numbering of the steps in each embodiment introduced in the present application is only used to distinguish different steps, and is not used to limit the order between the steps.

[0056] The application scenarios of the embodiments of the present application will be introduced first.

[0057] The technical solutions in the embodiments of the present application can be applied to various communication systems, for example, a universal mobile telecommunications system (UMTS), a wireless local area network (WLAN), a wireless fidelity (Wi-Fi) system, a 4th generation (4G) communication system such as a long term evolution (LTE) system, a 5G communication system such as a new radio (NR) system, and a future evolved communication system such as a 6th generation (6G) mobile communication system.

[0058] To facilitate understanding of the embodiments of the present application, first, a communication system shown in FIG. 1 is taken as an example to specifically describe a communication system applicable to the embodiments of the present application. As shown in FIG. 1, the communication system 1000 includes a radio access network 100 and a core network 200. Optionally, the communication system 1000 can also include an Internet 300. The radio access network 100 can include at least one network device, such as 110a and 110b in FIG. 1, and can also include at least one terminal device, such as 120a-120j in FIG. 1. Among them, 110a is a base station, 110b is a micro station, 120a, 120e, 120f and 120j are mobile phones, 120b is a car, 120c is a fuel dispenser, 120d is a home access point (HAP) arranged indoors or outdoors, 120g is a notebook computer, 120h is a printer, and 120i is a drone.

[0059] In FIG. 1, the terminal device can be connected with the network device, and the network device can be connected with the core network device in the core network. The core network device and the network device can be independent and different physical devices, can be integrated with the functions of the core network device and the logical functions of the network device on the same physical device, and can also be a physical device integrated with part of the functions of the core network device and part of the functions of the network device. The terminal device and the terminal device, and the network device and the network device can be connected with each other through a wired or wireless manner. FIG. 1 is only a schematic diagram, and the communication system can also include other devices, such as a wireless relay device and a wireless backhaul device, which are not shown in FIG. 1.

[0060] The network device and the terminal device are introduced as follows.

[0061] (1) Network device

[0062] A network device is a device that connects terminal devices to a wireless network in a mobile communication system. The network device, as a node in a radio access network, can also be referred to as a base station, a radio access network (RAN) node (or device), an access point (AP), or an access network (AN) device.

[0063] Currently, some examples of network devices are: a new generation Node B (gNB), a transmission reception point (TRP), an evolved Node B (eNB), a radio network controller (RNC), a Node B (NB), a base station controller (BSC), a base transceiver station (BTS), a transmitting and receiving point (TRP), a transmitting point (TP), a mobile switching center, a home base station (for example, a home evolved NodeB, or home Node B, HNB), or a base band unit (BBU), and the like.

[0064] In addition, in a network structure, a network device can include a centralized unit (CU) node and a distributed unit (DU). This structure splits the protocol layers of the network device, with some protocol layer functions being centrally controlled by the CU, and the rest of the protocol layer functions being distributed in the DU and controlled by the CU. For example, the CU is responsible for processing non-real-time protocols and services, and implements the functions of the RRC layer and the PDCP layer. The DU is responsible for processing physical layer protocols and real-time services, and implements the functions of the RLC layer, the MAC layer, and the PHY layer.

[0065] Optionally, the network device can also include an active antenna unit (AAU). The AAU implements some physical layer processing functions, radio frequency processing, and related functions of active antennas. Since the information of the RRC layer ultimately becomes or is converted from the information of the PHY layer, in this architecture, high layer signaling, such as RRC layer signaling, can also be considered as being sent by the DU, or by the DU+AAU.

[0066] It can be understood that the network device can include one or more of the CU, the DU, and the AAU. In addition, the CU can be divided into a network device in an access network, or the CU can be divided into a network device in a core network, which is not limited in the present application.

[0067] The embodiments of the present application do not limit the specific technology and specific device form adopted by the network device. In the embodiments of the present application, the apparatus for implementing the function of the network device can be the network device; or can be an apparatus capable of supporting the network device to implement the function, such as a chip system, which can be installed in the network device. The chip system can be composed of a chip, or can include a chip and other discrete devices. In the embodiments of the present application, the function of the network device can also be implemented by multiple network function entities, each of which is used to implement part of the function of the network device. These network function entities can be network elements in a hardware device, can be software functions running on a dedicated hardware, or can be virtualized functions instantiated on a platform (such as a cloud platform). In the technical solutions provided in the embodiments of the present application, the apparatus for implementing the function of the network device is taken as an example to describe the technical solutions provided in the embodiments of the present application.

[0068] (2) Terminal device

[0069] A terminal device is a device that provides voice and / or data connectivity to users. The terminal device can also be referred to as user equipment (UE), terminal, access terminal, terminal unit, terminal station, mobile station (MS), remote station, remote terminal, mobile terminal (MT), wireless communication device, terminal agent, or terminal device, etc.

[0070] For example, the terminal device can be a handheld device with wireless connection function, or a vehicle with communication function, a vehicle-mounted device (such as a vehicle-mounted communication device, a vehicle-mounted communication chip), etc. Currently, some examples of terminal devices are: a mobile phone, a cordless phone, a session initiation protocol (SIP) phone, a wireless local loop (WLL) station, a personal digital assistant (PDA) device, a handheld device with wireless communication function, a computing device or other processing device connected to a wireless modem, a tablet computer, a computer with wireless transceiver function, a notebook computer, a palm computer, a mobile internet device (MID), a wearable device, a virtual reality (VR) device, an augmented reality (AR) device, a wireless terminal in industrial control, a wireless terminal in self driving, a wireless terminal in remote medical surgery, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home, etc.

[0071] In the embodiments of the present application, the device for implementing the function of the terminal device can be a terminal device, or a device capable of supporting the terminal device to implement the function, such as a chip or a chip system or a module, which can be installed in the terminal device. In the technical solutions provided in the embodiments of the present application, the device for implementing the function of the terminal device is taken as an example to describe the technical solutions provided in the embodiments of the present application.

[0072] In addition, the same terminal device or network device can provide different functions in different application scenarios. For example, the mobile phone in FIG. 1 includes 120a, 120e, 120f and 120j. Among them, the mobile phone 120a can access the base station 110a, connect the car 120b, communicate directly with the mobile phone 120e and access the HAP; the mobile phone 120e can access the HAP and communicate directly with the mobile phone 120a; the mobile phone 120f can access the micro station 110b, connect the notebook computer 120g and connect the printer 120h; the mobile phone 120j can control the unmanned aerial vehicle 120i.

[0073] The roles of the network device and the terminal device can be relative. For example, the helicopter or the drone 120i in FIG. 1 can be configured as a mobile base station, and for the terminal device 120j that accesses the wireless access network 100 through the 120i, the terminal device 120i is a base station; but for the base station 110a, the 120i is a terminal device, that is, the 110a and the 120i communicate through a wireless air interface protocol. Of course, the 110a and the 120i can also communicate through a base station-to-base station interface protocol, and in this case, the 120i is also a base station relative to the 110a. Therefore, the wireless access network and the terminal device can be collectively referred to as a communication apparatus, the 110a and the 110b in FIG. 1 can be referred to as a communication apparatus with a base station function, and the 120a-120j in FIG. 1 can be referred to as a communication apparatus with a terminal device function.

[0074] The network device and the terminal device can be in a fixed position or can be movable. The network device and the terminal device can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; can be deployed on the water surface; and can be deployed on an airplane, a balloon, and a man-made satellite in the air. Embodiments of the present application do not limit the application scenarios of the network device and the terminal device.

[0075] The network device and the terminal device, the network device and the network device, and the terminal device and the terminal device can communicate through a licensed spectrum, can communicate through an unlicensed spectrum, or can simultaneously communicate through the licensed spectrum and the unlicensed spectrum; can communicate through a spectrum below 6 gigahertz (GHz), can communicate through a spectrum above 6 GHz, or can simultaneously use the spectrum below 6 GHz and the spectrum above 6 GHz. Embodiments of the present application do not limit the spectrum resources used for wireless communication.

[0076] In the embodiments of the present application, “sending information to (a terminal device or a module)” and “sending information to (a terminal device or a module)” can be understood as that the destination of the information is the terminal device or the module. This can include directly or indirectly sending information to the terminal device. “Receiving information from (a terminal device or a module)” and “receiving information of (a terminal device or a module)” can be understood as that the source of the information is the terminal device, and can include directly or indirectly receiving information from the terminal device. The information can be processed as necessary between the source and the destination, for example, format change, etc., but the destination can understand the valid information from the source. Similar expressions in the present application can be understood similarly, and will not be described here.

[0077] It can be understood that the technical solutions in the embodiments of the present application can also be applied to other communication systems, and the corresponding names can also be replaced by the names of the corresponding functions in other communication systems. FIG. 1 is a simplified schematic diagram for ease of understanding, and the communication system can also include other devices, which are not shown in FIG. 1.

[0078] In the following, some terms or concepts in the embodiments of the present application are explained and described to facilitate understanding by those skilled in the art.

[0079] (1) Model

[0080] The model in the embodiments of the present application can be a general model, including an artificial intelligence model, and the artificial intelligence model includes a deep learning model and a machine learning model. Further, the model can also include a set algorithm or a pre-set database (also referred to as a pre-set storage) for storing a corresponding relationship.

[0081] The possible types of the artificial intelligence model in the embodiments of the present application are as follows.

[0082] From the type of internal data processing operation, the artificial intelligence model in the embodiments of the present application can specifically include a convolutional neural network model (CNN), a support vector machine model (SVM), a long short-term memory network model (LSTM), an artificial neural network model (ANN), a recurrent neural network model (RNN), a generative adversarial network model (GAN), a logical regression model (LR), etc. The artificial intelligence model in the embodiments of the present application can be used to process specific input data to obtain output data (also referred to as output).

[0083] From the training mode (or generation mode), the artificial intelligence model in the embodiments of the present application can specifically include a rule model, a self-supervised learning model, an unsupervised model, etc.

[0084] The set algorithm or the set corresponding relationship in the embodiments of the present application can be stored in a certain storage space, such as a database or a pre-set storage. Correspondingly, the model in the embodiments of the present application is a corresponding relationship table stored in the pre-set storage. After inputting the input data into the model, the corresponding relationship table can be searched, and the model output data can be obtained according to the search result.

[0085] (2) Geographical position information

[0086] In the embodiments of the present application, the geographical position information can be used to describe the information of the spatial relationship of geographical objects, which include all naturally existing objects and man-made objects. Therefore, in the embodiments of the present application, the geographical position information at least includes spatial information.

[0087] According to the relativity of the geographical position information, the geographical position information can be divided into relative geographical position information and absolute geographical position information. The relative geographical position information is determined by taking one reference geographical object and a time point as a reference. The absolute geographical position information can be longitude and latitude information or coordinate information in the earth coordinate system.

[0088] For example, the relative geographical position information can include information of the time dimension, such as A farmland, B shopping mall, and C market, which exist only at a specific time. At other times, A farmland can become D road, B shopping mall can become E park, and C market can have been cancelled.

[0089] In the embodiments of the present application, the geographical position information of the base station can also include the grid number or grid identifier to which the base station belongs.

[0090] (3) Traffic statistics data

[0091] In the embodiments of the present application, the traffic statistics data is the data generated when the user uses the communication traffic function. The traffic statistics data is obtained by collecting and arranging the original data generated when the user uses the communication traffic function. In the traffic statistics data, the statistical values of a plurality of traffic statistics items can be included, but are not limited thereto.

[0092] (4) Traffic statistics item

[0093] In the embodiments of the present application, the traffic statistics item can also be referred to as a traffic index or a traffic indicator. The traffic statistics item can include traffic volume, traffic distribution, traffic duration, delay, call drop rate, user rate, dotting data, engineering parameter, weak coverage ratio, and edge user rate, etc. The traffic volume is the number of calls or the call duration in a unit of time in the communication network. The traffic distribution refers to the traffic distribution in different regions and at different times. The traffic duration is the call duration. The delay is the time delay from the start of the call to the success of the call. The call drop rate is the proportion of the communication connection disconnection in the call process in a unit of time. The dotting data is the data obtained by using the counter to count the behavior of the user in the set category. The engineering parameter, also referred to as the work parameter, is the wireless cell parameter and the traffic position parameter used to help the communication system engineer to understand the network condition. The weak coverage ratio can be the proportion of the weak coverage cell to the total number of cells. The edge user rate can be the user rate at the edge of the cell coverage.

[0094] In the embodiments of the present application, according to different angles, the traffic statistics items can be divided into key performance indicators (KPI) and key quality indicators (KQI). The key performance indicators include user distribution, capacity, interference and / or coverage, and other indicators objectively counted from the perspective of the whole network. The key quality indicators include user rate, and edge user rate, and other indicators perceived from the perspective of the user. Exemplarily,

[0095] (5) Frequent item set

[0096] In the embodiments of the present application, the frequent item set is an item set with a relatively high frequency of occurrence. The support of the frequent item set can be greater than or equal to the minimum support. The support is the frequency of occurrence of an item set in all item sets. The item set is a set of at least one traffic statistics item.

[0097] In the embodiments of the present application, in addition to the at least one traffic statistics item, the item set also includes the range of each traffic statistics item. The traffic statistics items in the frequent item set, and the ranges of the traffic statistics items, have a relatively high frequency of occurrence. Further, in addition to the at least one traffic statistics item and the range of each traffic statistics item, the item set can also include geographic location information. The at least one traffic statistics item in the frequent item set, the range of each traffic statistics item, and the geographic location information of each traffic statistics item, have a relatively high frequency of occurrence.

[0098] (6) Configuration parameters of base station

[0099] In the embodiments of the present application, the configuration parameters of the base station are parameters that can be adjusted and set for the base station itself. The base station is an important element of a wireless network. In the area covered by the wireless network, each base station covers multiple wireless cells. Each base station provides communication services for users in the wireless cells covered by itself. The configuration parameters of the base station affect the signal coverage range, signal strength, and antenna settings of the base station, and these indicators further affect the communication quality and user experience.

[0100] In the embodiments of the present application, the configuration parameters of the base station can belong to at least one of the following three categories.

[0101] a. Scheduling type parameters

[0102] The scheduling type parameters are configuration parameters related to the scheduling of wireless air interface resources.

[0103] When a large number of users access a wireless cell, the wireless cell needs to allocate wireless resources among multiple users, which is referred to as scheduling of wireless air interface resources. The scheduling strategy of wireless air interface resources usually involves various algorithms, such as a user channel estimation algorithm, a multi-user fairness algorithm, a power control algorithm, and the like.

[0104] b, a handover type parameter

[0105] In an embodiment of the present application, the handover type parameter can be a parameter related to performing a handover operation.

[0106] The "handover" in the "handover type parameter" refers to an operation of changing the connection of a user from a current cell to another cell. When a user moves between different areas or different cell loads are unbalanced, the user needs to be handed over to transfer the connection relationship of the user to a cell with better signal or more idle resources, so as to achieve load balancing among multiple cells of a wireless network and improve wireless resource utilization efficiency and user experience.

[0107] c, a radio frequency type parameter

[0108] The radio frequency type parameter is a parameter related to the radio frequency of the antenna array of the base station.

[0109] The base station includes multiple antenna arrays. Compared with a traditional antenna, the antenna array of a 5G (5th generation mobile communication technology) base station generates a wireless signal that can be enhanced in transmission according to a set direction in a three-dimensional space, so that the signal strength received by a user in the set direction is higher. In the base station, the weight of each antenna array can be flexibly adjusted, which can improve the beam pointing accuracy of the wireless signal of the base station, concentrate the wireless signal with high strength on a specific area and a specific user group, enhance the received signal of the specific user group, reduce signal interference in the wireless cell, and also reduce interference between adjacent wireless cells, thereby affecting the service handover effect between multiple cells and the service experience rate of the user.

[0110] (7) grid

[0111] A grid refers to dividing geographic spatial data into grids or pixels, each of which has its own attribute value to represent the characteristics or attributes of the location. Grid data is a type of data based on spatial analysis, commonly used in geographic information systems (GIS), which can be used to represent terrain, climate, land use, vegetation, population distribution, and other spatial features. In the embodiments of the present application, the grid can also be referred to as a control area. The control area is formed by dividing the entire network in a predetermined manner. The entire network includes a controllable communication network, that is, the entire network includes all controllable areas.

[0112] (8) Preset scenario

[0113] In the embodiments of the present application, the preset scenario includes the sum of the geographical location information and the time characteristics of the traffic statistics data. Different preset scenarios can be used to describe different traffic variation characteristics in different control areas.

[0114] In the embodiments of the present application, the preset scenario can be obtained by mining and analyzing historical data, for example, by counting the traffic statistics items in the historical data to obtain a frequent item set.

[0115] In one embodiment, each preset scenario includes at least one geographical location information corresponding to the preset scenario, at least one traffic statistics item corresponding to each preset scenario, and at least one statistical value range of each traffic statistics item corresponding to each preset scenario.

[0116] Due to the increasing demand of wireless communication users, it is necessary to more reasonably allocate limited resources and provide users with more good experience.

[0117] To solve the above problems, the embodiments of the present application provide a communication method. FIG. 2 is a system schematic diagram applicable to the base station parameter control method flow provided by the embodiments of the present application, which is used to optimize the configuration parameters of the base station.

[0118] The system shown in FIG. 2 includes a network management control module 21, a perception engine 22, an analysis engine 23, a decision engine 24, and a closed loop engine 25. Among them, the network management control module 21 is connected with the base station in the controllable area, and the connection mode can include direct connection or indirect connection, and can also include wired connection and wireless connection.

[0119] The system shown in FIG. 2 can be implemented in at least the following five ways.

[0120] First, the network management control module 21, the perception engine 22, the analysis engine 23, the decision engine 24 and the closed loop engine 25 can be implemented by at least one server connected to the base station shown in FIG. 1 or a module on the at least one server.

[0121] Second, the network management control module 21, the perception engine 22, the analysis engine 23, the decision engine 24 and the closed loop engine 25 can be implemented by at least one device in the core network shown in FIG. 1 or a module on the at least one device.

[0122] Third, the network management control module 21, the perception engine 22, the analysis engine 23, the decision engine 24 and the closed loop engine 25 can be implemented by at least one network device shown in FIG. 1 or at least one module on the network device.

[0123] Fourth, the network management control module 21, the perception engine 22, the analysis engine 23, the decision engine 24 and the closed loop engine 25 can be implemented by at least one device in the Internet shown in FIG. 1 or a module on the at least one device.

[0124] Fifth, the network management control module 21, the perception engine 22, the analysis engine 23, the decision engine 24 and the closed loop engine 25 can be implemented by different devices in at least two networks shown in FIG. 1, and the at least two networks can be at least two of the wireless access network 100, the core network 200 and the Internet 300.

[0125] The network management control module 21 can be used to obtain two types of data, and the perception engine 22 receives and processes the two types of data obtained by the network management control module 21. The first type is that the network management control module 21 obtains the original data of the traffic statistics data through the base station.

[0126] The network management control module 21 first obtains the original data of the traffic statistics data. It should be noted that the data obtained by the network management control module 21 in the embodiment of the present application is all data obtained with the permission of the user. The data obtained by the perception engine 22 when the user uses the network is processed through some basic data processing to obtain the traffic statistics data. The traffic statistics data obtained by the perception engine 22 through the base station can include at least one statistical value corresponding to each traffic statistics item at a time.

[0127] The second type is that the network management control module 21 obtains the location-related information through the base station.

[0128] The working principles of each module or engine included in the system shown in FIG. 2 are described below.

[0129] The network management control module 21 obtains the location-related information through the base station first. The location-related information includes the base station measurement report (MR), the data related to the base station in the map, the base station attribute, and the base station interactive experience data.

[0130] The base station MR can refer to the report file generated by the base station or the terminal based on a certain period or event triggering.

[0131] The data related to the base station in the map can include the positioning information of the base station in the map.

[0132] The base station attribute can include the base station model number, the serial number, and other attribute information of the base station itself.

[0133] The base station interactive experience data can include the interactive data between the base station and the terminal, which can be used to determine whether the base station belongs to the target control area when the base station is located at the edge of the target control area. For example, when the base station is located at the edge of the target control area, the data of the terminal interacting with one sector of the base station exists in the target control area, and the data of the terminal interacting with the other sectors of the base station exists outside the target control area. Then it can be determined that part of the base station belongs to the target control area, and the other part belongs to other areas outside the target control area.

[0134] Meanwhile, the network management control module 21 also obtains the raw data generated by the user when using the communication traffic function through the traffic statistics module.

[0135] After the perception engine 22 obtains the location-related information and the raw data generated by the user when using the communication traffic function from the network management control module 21, the perception engine 22 performs traffic autonomous zone (TAZ) calculation according to the location-related information to determine the geographical position information of the base station. The perception engine 22 also performs traffic statistics operation to convert the raw data into traffic statistics data.

[0136] The analysis engine 23 is deployed with a prediction model. After the analysis engine 23 obtains the geographical position information and the traffic statistics data of the base station from the perception engine 22, the geographical position information and the traffic statistics data are input into the prediction model to obtain the output data of the prediction model, which is used to determine the configuration parameters of the base station. The prediction model of the analysis engine 23 is trained according to the preset rules stored in the experience knowledge database.

[0137] The decision engine 24 is used to obtain the output data from the analysis engine 23, and to perform small-scale optimization on the output data according to the optimization algorithm preset in the decision engine 24 to obtain the optimized output data, which is used as the configuration data of the base station. The optimization algorithm is constrained by the preset rules stored in the experience knowledge database.

[0138] The closed loop engine 25 is configured to obtain the configuration data from the decision engine 24, and then decide whether to issue the configuration data to the base station according to the target control area where the base station is located. If the optimized configuration data needs to be issued to the base station, the configuration data is issued to the base station in the target control area. Otherwise, the optimized output data is not issued.

[0139] The system shown in FIG. 2 further includes a knowledge database for the analysis engine 23 to build the prediction model, or for the decision engine 24 to optimize the configuration data.

[0140] The system shown in FIG. 2 further includes an interface for displaying the system operation, setting the optimization target, or the probability requirement value of the traffic statistics data in the target control area.

[0141] Although not shown, other possible components can be included in the system structure described above, such as a data cleaning module for noise cleaning of the original traffic statistics data. For example, the network architecture described above can further include a transceiver interface for data transmission and reception with other platforms. The data obtained from other platforms by the transceiver interface can be used to further optimize the prediction model, or to realize other related functions.

[0142] It can be understood that FIG. 2 is an example of optimizing the configuration parameters of the base station in the target control area once. In other possible implementations, real-time optimization of the configuration parameters of the base station in the target control area can be performed. The network management control module 21 obtains the traffic statistics data reflecting the quality of service in the communication network according to the set time interval, and then optimizes the configuration parameters of the base station in combination with the geographical location information of the base station to which the traffic statistics data corresponds. The functions of the network management control module 21, the perception engine 22, the analysis engine 23, the decision engine 24, and the closed loop engine 25 shown in FIG. 2 can be implemented by independent devices respectively, or can be implemented by multiple devices together, or can be different functional modules in one device. In different communication systems, including a fourth generation (4th generation, 4G) communication system, a fifth generation (5th generation, 5G) communication system or a sixth generation (6th generation, 6G) communication system, the components of the system shown in FIG. 2 can be named in other ways, which are not limited in the embodiments of the present application.

[0143] The various possible modules or engines mentioned above can be components in hardware devices, software functions running on dedicated hardware, or virtualization functions instantiated on a platform (e.g., a cloud platform). In actual deployment, any two or more of the above modules and engines can be merged. For example, the network management control module 21 is merged with the perception engine 22, the perception engine 22 is merged with the analysis engine 23, and the decision engine 24 is merged with the closed-loop engine 25. When two or more of the modules and engines shown in Figure 2 are merged, the interaction between the merged parts in the embodiment of the present application becomes the internal operation of the merged part or can be omitted.

[0144] The system architecture and business scenarios described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Ordinary technicians in this field will know that with the evolution of communication system architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0145] The base station configuration parameter control method provided by the embodiment of the present application is described in detail below in conjunction with specific embodiments. In the specific embodiments, the method provided by the embodiment of the present application is used to optimize the base station in the communication system shown in Figure 1 as an example. In other possible implementations, the base station configuration parameter control method provided by the embodiment of the present application can also be applied to other types of network systems, such as optimizing the configuration parameters of the network equipment accessed by a terminal device in a wireless local area network. Alternatively, it can be applied to a subsystem of a communication system. Alternatively, it can be applied to a network composed of multiple different communication systems.

[0146] Figure 3 is a flow chart of a method for controlling base station configuration parameters provided by an embodiment of the present application. As shown in Figure 3, the method includes steps S31 to S33.

[0147] Step S31: The optimization platform obtains the first geographic location information of the target control area and traffic statistics data within the target control area through the base station within the target control area, and the traffic statistics data include statistical values ​​of multiple traffic statistics items within a first time period.

[0148] In one embodiment, the optimization platform can utilize the system shown in FIG2 , or can be implemented by a server with equivalent functionality. Alternatively, the optimization platform can utilize at least one portion of the system shown in FIG2 . For example, step S31 can be performed by the network management control module 21 or the perception engine 22 shown in FIG2 , step S32 can be performed by the perception engine 22 shown in FIG2 , and step S33 can be performed by the analysis engine 23 shown in FIG2 .

[0149] In an embodiment, the setting of the target control region includes at least two manners.

[0150] (1) The target control region is one of a plurality of regions obtained by dividing the controllable region, and each of the plurality of regions includes at least one base station.

[0151] For example, as shown in FIG. 4, the controllable region is divided according to the roads in the controllable region 401, and a plurality of regions 402 defined by the roads are obtained. Each region includes at least one base station, which can include two cases. Case one: the region uses at least one base station independently. Case two: the edge of the region includes at least one base station, and the region shares the base station arranged at the edge with the adjacent region at the edge.

[0152] (2) The target control region is a plurality of regions of the same type, and the plurality of regions of the same type are regions of the same type in the plurality of regions obtained by dividing the controllable region.

[0153] For example, as shown in FIG. 5, on the basis of the plurality of regions shown in FIG. 4, the plurality of regions 402 are divided according to different attributes (or categories or types), and the plurality of regions are divided into a plurality of categories. The plurality of categories can include, for example, office area, factory area, transportation hub area, educational institution area, residential area, other, life service area, culture and sports area, medical institution area, and government institution area.

[0154] According to the manner shown in FIG. 4 and FIG. 5, the controllable region is divided to obtain a plurality of regions, and in the determination of the configuration parameters, a single region is controlled in a fine-grained manner, so that the configuration parameters of the base station adapt to the space where the base station is located, the configuration parameters of the base stations in different spaces are different, and the effect of the parameter configuration of the base station is improved.

[0155] The first geographic location information can have at least three implementation manners.

[0156] Implementation manner (1)

[0157] The first geographic location information includes geographic location information of a plurality of base stations arranged in the target control region. The geographic location information of the base station can further include at least one of the earth coordinates of the base station, the address of the base station in the map, and the latitude and longitude of the base station.

[0158] Implementation manner (2)

[0159] The first geographic location information can also be equivalent to the geographic location information of the target control region.

[0160] Implementation manner (3)

[0161] The first geographic position information can include midpoint position information of geographic position information of a plurality of base stations disposed in the target control area. The aforementioned midpoint position information can be a geometric midpoint or a fitted position of an intersection of base station connecting lines.

[0162] The geographic position information of the target control area can include at least one of geographic position information of a center point of the target control area, positions of vertices of a polygon when the target control area is fitted as a polygon, positions of edges of the target control area, a category to which the target control area belongs in a plurality of categories, positions of points of interest (POI) included in the target control area, a TAZ corresponding to the target control area, and an address of the target control area in a map.

[0163] In a possible implementation, the traffic statistical data in the target control area can include traffic statistical data of at least one base station disposed in the target control area.

[0164] In a possible implementation, the first time length can include a plurality of time points at which the traffic statistical data is acquired, and different traffic statistical items can be counted at different time points. Table 1 shows the different time points at which the statistical values are acquired. The different time points at which the statistical values are acquired can include time points at which a set interval is reached, and can also include time points at which communication information is received. In Table 1, the different time points at which the statistical values are acquired include time points at which a set interval (30 minutes) is reached (for example, 15 minutes, 30 minutes, and 60 minutes in Table 1), time points at which communication information is received (for example, 45 minutes and 75 minutes in Table 1), and the first time length is 75 minutes. The statistical values in Table 1 are only for example. Table 1 only shows some traffic statistical items, and the traffic statistical items in Table 1 include traffic volume, weak coverage ratio, time delay, call drop rate, user rate, short message service, and antenna angle. In other implementations, the traffic statistical data can include more traffic statistical items, which are not listed one by one in the embodiments of the present application. In Table 1, the short message service is taken as an example of the traffic statistical item obtained according to dotting data, and the antenna angle is taken as an example of the traffic statistical data obtained according to engineering parameters.

[0165] Table 1

[0166] It can be seen that not every traffic statistical item appears at every time point at which the statistical values are acquired in the first time length in all traffic statistical items. For example, in Table 1, the time delay, the call drop rate, and the short message service do not have statistical values if there are no events of time delay, call drop, and short message service usage.

[0167] It should be understood that Table 1 only shows the statistical values corresponding to some traffic statistics, and in other possible implementation manners, the traffic statistics can also include more traffic statistics. The statistical values in Table 1 are only for example, and in other possible implementation manners, the statistical values can also be other numerical values or use other units.

[0168] In an implementation manner of the present application, in the first time length, there are multiple time points for obtaining statistical values, and the statistical value obtained at each time point is the statistical value of at least one traffic statistic. The time points in Table 1 refer to the 15th minute and the 30th minute calculated from the relative time zero point, and the unit of the time point can also be hours or days.

[0169] In step S32, the optimization platform matches the first geographic location information and the traffic statistics with multiple preset scenes to determine the target scene corresponding to the target control area. Each preset scene in the multiple preset scenes includes at least one geographic location information corresponding to each preset scene, at least one traffic statistic corresponding to each preset scene, and a statistical value range corresponding to the at least one traffic statistic.

[0170] In an implementation manner, the scene matching can be performed locally on the optimization platform, or the first geographic location information and the traffic statistics can be sent to a remote device to obtain the target scene from the remote device.

[0171] In the matching process, on one hand, the first geographic location information is compared with the geographic location information of each preset scene to determine the matching degree of the first geographic location information and the geographic location information of each preset scene, and when the matching degree is higher than a set threshold, it is determined that the first geographic location information matches the geographic location information of each preset scene. On the other hand, the traffic statistics are compared with the statistical value range of the at least one traffic statistic corresponding to each preset scene to determine the matching degree, and when the matching degree is higher than a set threshold, it is determined that the traffic statistics match the statistical value range of the at least one traffic statistic corresponding to the preset scene.

[0172] When the traffic statistic matches the statistical value range corresponding to one preset scene, and the first geographic location information matches the geographic location information corresponding to the preset scene, the preset scene is determined as the target preset scene. Taking an example in which each preset scene includes one geographic location information, the correspondence between the preset scene and the geographic location information, the traffic statistic, and the statistical value range is shown in Table 2.

[0173] Table 2

[0174] The above Table 2 is only illustrative, in other implementations, the scenario identification can also be in words, other characters, or a combination of words and other characters, such as: office area weekday scenario, factory area high delay scenario, transportation hub area high traffic scenario, medical institution area busy scenario, or residential area low rate scenario, etc. In Table 2, “[” means greater than or equal to the first item in the brackets; “]” means less than or equal to the second item in the brackets; “(” means greater than the first item in the brackets; “)” means less than the second item in the brackets. For example: [first item, second item), means the range is: greater than or equal to the first item, and less than the second item.

[0175] The geographic location information in the above Table 2 is only illustrative, in other implementations, the geographic location information can include attribute numbers. Alternatively, the geographic location information can include at least one main classification of a geographic location and at least one sub-classification corresponding to each main classification of the geographic location. Alternatively, the geographic location information can include at least one dimensional classification of a geographic location.

[0176] The traffic statistics items corresponding to each preset scenario in the above Table 2, and the statistical value range of the traffic statistics items are only illustrative, in other implementations, each preset scenario can include more or less traffic statistics items, or include completely different at least one traffic statistics item. In other implementations, the statistical value range corresponding to each traffic statistics item in each preset scenario can be other numerical ranges.

[0177] Taking each preset scenario including one geographic location information as an example, when matching the first geographic location information, the traffic statistics data, and the multiple preset scenarios, it can be determined whether the geographic location information of each preset scenario is consistent with the first geographic location information, then whether the traffic statistics items in the traffic statistics data are consistent with the traffic statistics items of each preset scenario, and then whether the statistical values in the traffic statistics data fall within the statistical value range corresponding to each preset scenario. If the first geographic location information is consistent with the geographic location information of the preset scenario, and the traffic statistics items in the traffic statistics data are consistent with the traffic statistics items of the preset scenario, and then the statistical values in the traffic statistics data fall within the statistical value range corresponding to the preset scenario, the first geographic location information and the traffic statistics data match the preset scenario.

[0178] In one implementation, when matching the first geographic location information and the traffic statistics data with the multiple preset scenarios, the average value of the statistical values of the same traffic statistics items of the same geographic location information within the first time period can be calculated according to the traffic statistics data, and the first geographic location information and the average value of the statistical values are matched with the multiple preset scenarios.

[0179] In another implementation, when matching the first geographic location information and the traffic statistical data with the plurality of preset scenes, the statistical values collected at each time point in the first time length, the traffic statistical items corresponding to the statistical values, and the geographic location information corresponding to the statistical values are respectively matched with the statistical value range corresponding to the preset scenes, the traffic statistical items corresponding to the preset scenes, and the geographic location information corresponding to the preset scenes. Thus, the traffic statistical data at different time points can be matched with different preset scenes, and the preset scene with the largest number of matches can be selected as the target scene.

[0180] For example, assuming that the geographic location information of the statistical values of the traffic statistical items obtained at 15 minutes in Table 1 is a core city, a government agency area, and the five preset scenes in Table 2 are matched, the matching results are shown in Table 3.

[0181] Table 3

[0182] According to Table 3, it can be concluded that the traffic statistical data obtained at 15 minutes is not matched with any of the five preset scenes, and thus there is no target scene in the preset scene 1 to the preset scene 5, and the target scene can be further searched from other preset scenes.

[0183] The data in Table 3 is only used for example description, and in other implementations, the first geographic location information and the traffic statistical data corresponding to the first geographic location information can be other geographic location information and other traffic statistical data. The preset scenes can include other preset scenes in addition to the preset scenes shown in Table 3.

[0184] Step S33: The optimization platform inputs at least one target geographic location information corresponding to the target scene, at least one target traffic statistical item, and a target statistical value range corresponding to the at least one target traffic statistical item into a prediction model, determines a configuration parameter of a base station in the target control area according to output data of the prediction model, and the configuration parameter is used for configuring the base station in the target control area in a second time length, and the second time length is after the first time length.

[0185] In an implementation, the first time length is a time length before the second time length, for example, the first time length is from the 15th minute to the 75th minute, and the second time length is from the 100th minute to the 300th minute. Alternatively, the second time length is a time length after the first time length.

[0186] In the embodiment of the present application, the configuration parameter of the base station in the target control area is used for configuring all base stations in the target control area in the second time length, or is used for configuring at least one base station in the target control area.

[0187] In one embodiment, the prediction model can be obtained in at least four ways.

[0188] Way one: the prediction model is an artificial intelligence model. The prediction model is obtained by training according to a first output data of a prediction classifier. The prediction classifier is another artificial intelligence model other than the prediction model. The output result of the prediction classifier indicates whether the output data of the prediction model optimizes the traffic statistics data in the second time length. Before training the prediction model, the prediction classifier is trained according to the second historical record.

[0189] In the above way one, the prediction classifier can be trained by using training samples.

[0190] For example, the prediction classifier can be trained by using a knowledge database, labeled cell samples and unlabeled cell samples. The knowledge database can include empirical rules of base station configuration parameter settings, labeled TAZ data and optimization goals. Further, the labeled TAZ data can be TAZ data with POI labels; and the optimization goal can be that the traffic feature data in the next time length is optimized in terms of the traffic feature data in the current time length after the configuration parameters are applied to the base station, such as rate improvement or latency reduction.

[0191] The process of training the prediction classifier can include:

[0192] 1) training the to-be-trained classifier by using the labeled cell samples to obtain an initially trained classifier.

[0193] The set of labeled cell samples can be represented as {(x1, y1), (x2, y2)…(xn, yn)}, where xi represents the ith labeled cell sample, and yi represents the label corresponding to the labeled cell sample. By using {(x1, y1), (x2, y2)…(xn, yn)} and a learning function f, the function f inside the classifier is used to predict samples with unknown labels.

[0194] 2) inputting the labeled cell samples into the initially trained classifier to obtain the output data of the initially trained classifier.

[0195] The set of unlabeled cell samples can be represented as {(xn+1), (xn+2)…(xn+m)}. Wherein, xn+i represents the ith unlabeled cell sample.

[0196] 3) using the output data of the initially trained classifier as the pseudo label of the unlabeled cell samples.

[0197] The set of pseudo-labeled unlabeled cell samples can be represented as {(xn+1, yn+1), (xn+2, yn+2)…(xn+m, yn+m)}. Wherein, yn+i represents the pseudo-label of the i-th unlabeled cell sample.

[0198] 4) Convert the pseudo-label into a pseudo-rule, which is a language expression of the knowledge information stored in the knowledge database.

[0199] 5) Determine whether the pseudo-rule is consistent with the knowledge information in the knowledge database. If not, optimize the pseudo-rule according to the knowledge information in the knowledge database, and optimize the initially trained classifier according to the optimized pseudo-rule.

[0200] Through 3)-5), the abductive learning of the initially trained classifier is realized. In the abductive learning process, the function f needs to be further optimized, so that:

[0201] {(xn+1), (xn+2)…(xn+m)}, s.t.KB|=O, or, KB|=△(O), f←Ψ(f,△(O)).

[0202] Wherein, Indicates consistent, O represents the knowledge information in the knowledge base. KB represents the knowledge base, which can also be called the knowledge database. s.t. represents the premise; △(O) represents a function with O as the independent variable, and △(O) is consistent with the knowledge information in the knowledge base; f←Ψ(f,△(O)) represents updating the function f through Ψ(f,△(O)) to obtain the updated f.

[0203] In an implementation mode, the knowledge database stores constraint rules, which can be used to optimize the prediction model, can be used to constrain the output data of the prediction model, and can also be used to adjust the output data of the prediction model.

[0204] For example, the knowledge information stored in the knowledge database can include the rules shown in Table 4.

[0205] Table 4

[0206] In Table 4, each constraint rule corresponds to a rule summary, and each constraint rule corresponds to a constraint parameter. For example, the constraint rule corresponding to the rule summary 1 constrains the azimuth angle, and the parameter number of the azimuth angle is “number 1”. In Table 4, “rule summary 1”-“rule summary 4” are used instead of the specific summary content. The parameter number is the number of the configuration parameter. The relationship between parameters is the relationship between one configuration parameter and another configuration parameter.

[0207] In Table 4, the parameter interrelation represents the relationship between the parameter constrained by the corresponding constraint rule and other parameters. The service interruption range and the service interruption time represent the range and the time of the communication service interruption when the corresponding parameter changes, respectively. For example, according to the constraint rule corresponding to rule 3, when the uplink intermediate frequency channel receiving gain changes, the service in the cell range where the base station is located is interrupted, and the interruption time is 1 minute.

[0208] According to the parameter interrelation, the service interruption range, the service interruption time and the influence on the wireless network performance of the configuration parameter corresponding to the target scenario in Table 4, it can be determined whether the corresponding configuration parameter should be adjusted. Thus, according to the constraint rules in the knowledge database, it can be determined whether the change of the configuration parameter corresponding to the pseudo label is consistent with the constraint rules in the knowledge database.

[0209] 6) When all pseudo rules are consistent with the knowledge information in the knowledge database, or the number of inconsistent rules is less than a threshold (for example, the number of inconsistent rules accounts for less than 5%, or the number of inconsistent rules accounts for less than 10%, or the number of inconsistent rules accounts for less than other proportion thresholds, etc.), a prediction classifier is obtained.

[0210] Method two: the prediction model is an artificial intelligence model. The prediction model is obtained by training according to the third historical record. The third historical record can be the same as or different from the second historical record.

[0211] Method three: the prediction model is a database. The database stores the corresponding relationship between the preset scenarios and the configuration parameters. After the target scenario is determined, the configuration parameter corresponding to the target scenario can be obtained by searching the database.

[0212] Method four: the prediction model is a preset formula. The target scenario corresponding number is calculated according to the preset formula, and the configuration parameter corresponding to the target scenario is obtained.

[0213] Method five: the prediction model includes an artificial intelligence model and a database. When a preset scenario becomes a target scenario for the first time, the corresponding relationship between the preset scenario and the configuration parameter is determined by the artificial intelligence model, and the corresponding relationship between the preset scenario and the configuration parameter is stored in the database. When a preset scenario becomes a target scenario again, the corresponding configuration parameter is searched from the database.

[0214] In the embodiments of the present application, the geographical position parameters of the base stations in the target control area and the traffic statistical data in the target control area are obtained to determine the target scenario corresponding to the target control area, and then the prediction model is used to determine the configuration parameter of the base station in the target control area in the future second time length according to the target scenario, so that the configuration parameter of the base station can adapt to the geographical position and the actual traffic condition, thereby providing better communication service for the users in the target control area.

[0215] Example (1)

[0216] Before step S31 shown in FIG. 3 is executed, a plurality of preset scenes need to be determined first, which can be determined locally on the optimization platform or on a remote device connected to the optimization platform by wire or wireless.

[0217] In example (1), the plurality of preset scenes are determined on a remote device connected to the optimization platform by wire or wireless, as shown in FIG. 6.

[0218] Step S61: The first remote device obtains a first historical record, which includes at least one statistical value corresponding to at least one traffic statistical item respectively in a third time length, and second geographical location information corresponding to the at least one statistical value, the third time length being located before the first time length.

[0219] In an implementation manner, the first historical record is a historical record obtained by all base stations in the controllable area between the third time length. The first historical record can be the same as or different from the second historical record or the third historical record.

[0220] In an implementation manner, the third time length is longer than the first time length. The third time length can include at least one of at least one hour, at least one natural month, at least one natural year, and at least one natural day.

[0221] In the third time length, the first historical record includes a plurality of records, each record corresponding to at least one traffic statistical item, a statistical value of the at least one traffic statistical item at a time point when the record is generated, and second geographical location information of the record, for example, the statistical value of the traffic statistical item corresponding to each time point in Table 1 belongs to a record. One time point can generate a plurality of records, and the plurality of records can be obtained by different base stations and correspond to different second geographical location information.

[0222] Step S62: The first remote device determines a plurality of frequent item sets based on the first historical record, each of the frequent item sets including one or more of the at least one traffic statistical item, a statistical value range corresponding to each of the one or more, and second geographical location information corresponding to the one or more in the first historical record; the statistical value range corresponding to the one or more is obtained according to the statistical value corresponding to the one or more, and the ratio of the number of times that the one or more in each of the frequent item sets appears together in the third time length to the total number of item sets in the third time length exceeds a preset threshold.

[0223] For example, the first historical record includes geographical location information of each region, traffic statistics of each region, and configuration parameters corresponding to each traffic statistics, as shown in Table 5.

[0224] Table 5

[0225] It should be noted that the records in Table 5 are only used for example, in other embodiments, each record can include different traffic statistics, and corresponding different statistical values, or different geographical location information, or different configuration parameters.

[0226] After obtaining the first historical record of all regions in the third time length, according to the first historical record, a set of items of the first historical record is obtained, each set of items corresponds to a record, and each set of items includes at least one traffic statistics in the record, a statistical value range corresponding to the at least one traffic statistics, and geographical location information corresponding to the record.

[0227] In an embodiment, the set of items in the first historical record with a number of occurrences less than a minimum scale can be removed. For example, the same set of items can be counted to determine the number of the same set of items, and the same set of items can refer to a set of items with the same traffic statistics, the same statistical value range corresponding to the traffic statistics, and the same geographical location information. For example, each record in Table 5 corresponds to a set of items, and according to the 5 records in Table 5, 5 sets of items can be obtained, and the geographical location information of each set of items is different. Therefore, according to the records in Table 5, the number of sets of items with the same traffic statistics, the same statistical value range corresponding to the traffic statistics, and the same geographical location information is 1.

[0228] For example, before determining whether the statistical value corresponding to the traffic statistics belongs to the same range, the range of the statistical value of the traffic statistics can be divided to obtain a plurality of ranges of the statistical value. For example, the range of the statistical value of the call drop rate can be divided to obtain a plurality of statistical value ranges of the call drop rate, including [0, 10%], [10%, 20%], [20%, 30%], and [30%, 100%].

[0229] In an example, the first historical record can be mined by using a frequent item growth (FP-growth) algorithm, an association rule algorithm (apriori), or an equivalence class cluster and bottom up lattice traversal (Elact) algorithm to obtain a frequent item set.

[0230] Alternatively, a direct calculation method can also be used to obtain all item sets and the total number of the same item sets, and then divide the total number of the same item sets by the total number of all item sets to obtain the frequency of the same item sets.

[0231] For example, when the FP-growth algorithm is used to determine the frequent item sets from the first historical record, the following steps are performed.

[0232] Step 1: Scan the first historical record to determine all item sets.

[0233] In order to discretize the continuous data, taking the example shown in Table 5, it is assumed that the traffic volume is divided into two statistical value ranges of [0, 10) and [10, +∞); the weak coverage ratio is divided into two statistical value ranges of [0, 10%) and [10%, 100%]; the delay is divided into two statistical value ranges of 0 seconds and (0 seconds, +∞); the call drop rate is divided into two statistical value ranges of 0 and (0, 100%]; the user rate is divided into three statistical value ranges of [0, 200 megabytes), [200 megabytes, 500 megabytes], and (500 megabytes, +∞); the short message service is divided into two statistical value ranges of (0, 10] and (10, +∞); the antenna angle is divided into two statistical value ranges of [110°, 120°] and (120°, 130°]; and the geographic location information is divided into ranges. +∞ represents positive infinity.

[0234] Step 2: Count the number of the same item sets, build an initial tree, and create a head pointer table.

[0235] For example, for the records in Table 5, the corresponding head pointer table created is shown in FIG. 7. In FIG. 7, the number after each traffic statistic item and the corresponding statistical value range represents the number of occurrences in Table 5. The pointers of the head pointer table in FIG. 7 point to each node in the initial tree. Each pointer performs a corresponding node in the initial tree. The root node in the initial tree is empty. In FIG. 7, only the nodes corresponding to record 1 in the initial FP tree are shown for illustration.

[0236] Step 3: Remove the traffic statistic items that do not meet the minimum scale in the head pointer table to obtain filtered item sets.

[0237] The minimum scale can refer to the minimum scale of the proportion of the total number of occurrences of the traffic statistic item in the total number of item sets, which can also be referred to as the minimum support.

[0238] For example, according to the 5 records shown in Table 5, the traffic statistics item of short message service appears once in the 5 records, but in other records, the traffic statistics item of short message service has no data record, and the number of appearances is 0. The total number of item sets shown in Table 5 is 5, the traffic statistics item of short message service appears 1 time in the full item set, and the proportion is the number of appearances ÷ the total number of item sets = 20%. Then, under the condition that the minimum scale is 21%, the traffic statistics item of short message service can be removed.

[0239] Based on the above minimum scale, in Table 5, the traffic statistics items of call rate, short message service, and geographic location information are removed, and the statistical value of the deletion time delay is 0 seconds. The collection time point and the configuration parameter are not elements in the item set, and the item set table shown in Table 6 is obtained, and each record in Table 6 corresponds to an item set.

[0240] Table 6

[0241] Step 4: Create a frequency pattern (FP) tree according to the filtered item set.

[0242] Among them, one descendant node of the FP tree corresponds to one traffic statistics item, and each descendant node includes at least three pieces of information: (1) item set identifier, (2) the number of appearances of the traffic statistics item and the relationship between the node and (3) other nodes. The item set identifier can be represented by the name of the traffic statistics item.

[0243] The relationship between the node and other nodes refers to: when a traffic statistics item appears in the same item set as other traffic statistics items, the relationship between the node corresponding to the traffic statistics item and other nodes corresponding to other traffic statistics items is represented by the connection between the node and other nodes.

[0244] When creating the FP tree, in combination with the head pointer table, for each node in the FP tree, a traversal operation is performed, starting from the root node of the FP tree, and the child nodes of the FP tree are created one by one.

[0245] The traversal operation performed for the node of the FP tree includes: (1) setting the root node to null, so that the pointer in the head pointer table points to each element in the filtered item set in Table 6 one by one, if the first element item of the current item set exists in the child node of the current node of the FP tree, update the count value of this child node. Otherwise, create a new child node and update the head pointer table. (2) repeatedly perform operation (1) until the FP tree is updated according to the last element of record 5.

[0246] The FP tree obtained according to Table 6 is shown in FIG. 8.

[0247] Step 5: Obtain frequent item sets according to the FP tree.

[0248] After the FP-tree is constructed, a conditional pattern base is constructed from the leaf nodes of the FP-tree. The conditional pattern base refers to all prefix paths ending with the traffic statistics item corresponding to the node and the nodes corresponding to the prefix paths. After a conditional pattern base is constructed, the number of nodes corresponding to the conditional pattern base is reduced by 1, and if the number is 0 after the reduction, the node is deleted and the FP-tree is updated. The FP-tree is traversed from the leaf nodes to find the conditional pattern base until the number of nodes corresponding to the conditional pattern base in the FP-tree is 0.

[0249] All the conditional pattern bases are converted into item sets to obtain the final frequent item sets.

[0250] Step S63: The first remote device obtains the multiple preset scenes by taking each of the frequent item sets as a preset scene.

[0251] The execution manner of step S64 can refer to step S31 shown in FIG. 3 and any one of the related implementation manners corresponding to step S31.

[0252] Step S65: The optimization platform sends the first geographic location information and the traffic statistics data to the first remote device when matching the first geographic location information and the traffic statistics data with the multiple preset scenes.

[0253] Correspondingly, the first remote device receives the first geographic location information and the traffic statistics data.

[0254] Step S66: The first remote device determines a target scene from the multiple preset scenes according to the first geographic location information and the traffic statistics data.

[0255] The manner in which the first remote device performs scene matching can refer to the manner in which the optimization platform performs scene matching in step S32.

[0256] Step S67: The first remote device sends the target scene to the optimization platform.

[0257] Correspondingly, the optimization platform receives the target scene.

[0258] The execution manner of step S68 can refer to step S33 and the related implementation manners.

[0259] In another implementation, if the optimization platform determines multiple preset scenes locally, and matches the first geographic location information, the traffic statistics data and the target scene locally, and the optimization platform is the system shown in FIG. 2, correspondingly, step S61 is performed by the network management control module 21, or the perception engine 22 obtains the first historical record from the network management control module 21. Steps S62 and S63 can be performed by the perception engine 22. Step S64 is performed by the network management control module 21, or the perception engine 22 obtains the first geographic location information and the traffic statistics data from the network management control module 21. The preset scene matching operation of steps S65 and S66 can be performed by the perception engine 22. After determining the target scene, the perception engine 22 sends the target scene to the analysis engine 23 of the optimization platform, and the corresponding operation of determining the configuration parameters of steps S67 and S68 can be performed by the analysis engine 23.

[0260] In example (1), the historical data in all controllable areas is analyzed to mine traffic feature items that often appear together, geographic location information, and a statistical value range of the traffic feature items in the area corresponding to the geographic location information. The traffic statistics items that often appear together, the geographic location information, and the statistical value range of the traffic statistics items are used as preset scenes, so that the preset scenes can summarize the traffic tide characteristics in the controllable area. The traffic tide characteristics are characteristics of the appearance of the peaks and troughs of the traffic volume in a specific type of area in a certain period of time. Furthermore, example (1) can make the performance of the base station in the target control area adapt to the traffic tide characteristics in the target control area when determining the configuration parameters of the base station according to the target scene of the target control area, and provide better communication services for mobile network users in the target control area.

[0261] Example (2)

[0262] The prediction model is an artificial intelligence model. Before step S31 shown in FIG. 3 is performed, the prediction model is trained. The training of the prediction model can be performed on a remote device or locally on the optimization platform. Taking the training of the prediction model on a remote device as an example, the present example method includes the steps shown in FIG. 9.

[0263] Step S91: The second remote device obtains a second historical record, the second historical record including at least one statistical value corresponding to at least one traffic statistics item respectively in a fourth time length, third geographic location information corresponding to the at least one statistical value, and configuration parameters corresponding to the at least one statistical value, the fourth time length being located before the first time length.

[0264] Step S92: The second remote device determines the prediction model based on the second historical record, the prediction model being used to describe the relationship between the different geographical location information, the at least one traffic statistical item corresponding to the different geographical location information, the statistical value range corresponding to the at least one traffic statistical item, and the configuration parameter.

[0265] The implementation of step S93 can refer to step S31 and the related embodiments.

[0266] The implementation of step S94 can refer to step S32 and the related embodiments, or example (1).

[0267] Step S95: The optimization platform sends the at least one target geographical location information corresponding to the target scenario, the at least one target traffic statistical item, and the target statistical value range corresponding to the at least one target traffic statistical item to the second remote device.

[0268] Correspondingly, the second remote device receives the at least one target geographical location information corresponding to the target scenario, the at least one target traffic statistical item, and the target statistical value range corresponding to the at least one target traffic statistical item.

[0269] In another implementation, the target platform can send the information of the target scenario to the second remote device, and the second remote device can determine the at least one target geographical location information corresponding to the target scenario, the at least one target traffic statistical item, and the target statistical value range corresponding to the at least one target traffic statistical item according to the information of the target scenario. The information of the target scenario can be a number corresponding to the target scenario or a name of the target scenario.

[0270] Step S96: The second remote device inputs the at least one target geographical location information corresponding to the target scenario, the at least one target traffic statistical item, and the target statistical value range corresponding to the at least one target traffic statistical item into the prediction model to obtain output data.

[0271] Step S97: The second remote device sends the output data to the optimization platform.

[0272] Correspondingly, the optimization platform receives the output data.

[0273] Step S98: The optimization platform determines the configuration parameter according to the output data.

[0274] Alternatively, the second remote device can determine the configuration parameter according to the output data, and then send the configuration parameter to the optimization platform.

[0275] In an embodiment, the training of the prediction model is performed locally on the optimization platform, and the optimization platform adopts the system shown in FIG. 2. Accordingly, step S91 is performed by the network management module 21 shown in FIG. 2, and step S92 is performed by the analysis engine 23. The implementation of step S93 and step S94 is described with reference to step S31, step S32 or example (1). In step S95, the perception engine 22 sends at least one target geographical location information corresponding to the target scenario, at least one target traffic statistical item, and a target statistical value range corresponding to the at least one target traffic statistical item to the analysis engine 23, and step S96 is performed by the analysis engine 23. The operation of sending the output data to the optimization platform in step S97 is not performed. Step S98 can be performed by at least one of the decision engine 24, the closed-loop engine 25, and the network management control module 21.

[0276] In another embodiment, the prediction model can be trained on a remote device of the optimization platform. After the training is completed, the prediction model is deployed on the optimization platform, and then at least one target geographical location information, at least one target traffic statistical item, and a target statistical value range corresponding to the at least one target traffic statistical item are input to the prediction model locally on the optimization platform to obtain the output data of the prediction model.

[0277] In example (2), the configuration parameter is determined by the prediction model, which can quickly determine the configuration parameter of the base station according to the latest traffic statistical data and geographical location information in the case of a large number of base stations and a large number of cells corresponding to the base stations. The adjusted configuration parameter can be provided in time when the base station needs to adjust the configuration parameter, and efficient regulation and control of the base stations in the target control area can be achieved.

[0278] Example (3)

[0279] In step S33 shown in FIG. 3, the configuration parameter is determined according to the output data, which can be achieved by at least two ways.

[0280] Way one: taking the output data as the configuration parameter.

[0281] Way two: adjusting the output data according to a preset adjustment rule, and taking the adjusted output data as the configuration parameter.

[0282] In this example, the configuration parameter is determined by way two, which includes the steps shown in FIG. 10.

[0283] The implementation of step S101 and step S102 is described with reference to step S31 and step S32 shown in FIG. 3 and the corresponding embodiments, respectively.

[0284] Step S103: The optimization platform inputs at least one target geographical position information corresponding to the target scene, at least one target traffic statistical item, and a target statistical value range corresponding to the at least one target traffic statistical item into a prediction model.

[0285] Step S104: The optimization platform adjusts output data of the prediction model according to a preset adjustment rule to obtain a configuration parameter of a base station in the target control area, the configuration parameter being used for configuring the base station in the target control area in a second time length, the second time length being located after the first time length.

[0286] Step S103 and step S104 are implementation manners of step S33 in the present example (3) shown in FIG. 3.

[0287] In an implementation manner, the optimization platform is the system shown in FIG. 2, and step S104 is performed by the decision engine 24.

[0288] In an implementation manner, the preset adjustment rule is used to describe a relationship among different output data, different optimization indexes, and adjustment amounts of different optimization indexes.

[0289] For example, the preset adjustment rule can be determined according to a setting experience of the configuration parameter or a historically used configuration parameter. The setting experience of the configuration parameter can be generated according to the received business experience information. The historically used configuration parameter can be generated according to historical records.

[0290] For example, a process of adjusting the configuration parameter according to the preset adjustment rule is as follows.

[0291] Suppose a kernel function of mapping discrete geographical position information, discrete configuration parameters, and discrete statistical value ranges of traffic statistical data into continuous data is as follows:

[0292] Suppose that the geographical position information, the configuration parameter, and the traffic statistical data in the currently obtained historical records are denoted as x1:t, the sample covariance matrix of x1:t is obtained by using the kernel function, and a fitting curve f1:t corresponding to the continuous data mapped by x1:t is obtained.

[0293] Wherein, k is the kernel function. is noise data, that is, data deviation caused by accidental environmental factors. I is a unit matrix.

[0294] Suppose that unknown geographical position information, a statistical value range of traffic statistical data, and a configuration parameter are denoted as xt+1, a corresponding fitting function is denoted as ft+1, x1:t, f1:t, xt+1, and ft+1 conform to a joint Gaussian distribution, and is denoted as:

[0295] wherein k1 = [k(xt+1, x1), k(xt+1, x2), …, k(xt+1, xt)].

[0296] The following can be obtained

[0297] wherein yt+1 represents the gain obtained by the traffic statistics in the next time length, i.e. the optimization effect. D1:t is the data set selected from x1:t to obtain the gain. P(yt+1|D1:t, xt+1) represents the probability of obtaining the gain yt+1 by the traffic statistics in the next time length under the condition that the statistical value range and the geographical location information of the traffic statistics are xt+1 and the gain data set in the last time length is D1:t. N represents a normal distribution (also known as a Gaussian distribution). μ t (xt+1) is an expectation function of xt+1, (xt+1) is a variance function of xt+1, which can be determined according to the optimization target of the traffic statistics.

[0298] Based on the fitted function, the configuration parameter adjustment amount is determined as follows:

[0299] wherein ξ is a hyperparameter, i.e. a fixed parameter in the artificial intelligence model. When adjusting the configuration parameter, ξ is first determined from large to small, so that EI approximates the optimal solution of the configuration parameter in the next round. x represents the statistical value range and the geographical location information of the traffic statistics currently obtained, which is equivalent to the statistical value range and the first geographical location information of the traffic statistics in the first time length in the embodiment shown in FIG. 3. f(x + ) represents the error of the change value of the traffic statistics and the geographical location information in the prediction time length, and the prediction time length is equivalent to the second time length in the embodiment shown in FIG. 3. f(x + ) can be determined according to the probability requirement value of the optimization of the traffic statistics of the target control area. μ(x) is the expectation of the traffic statistics and the geographical location information in the prediction time length, and σ(x) is the variance of the traffic statistics and the geographical location information in the prediction time length. represents a standard normal distribution.

[0300] Correspondingly, the probability of EI(x) to optimize the traffic statistics in the next time length is:

[0301] In step S103, when adjusting the configuration parameter, a small range adjustment is performed, and the adjustment amplitude is less than a preset amplitude threshold.

[0302] In another possible implementation, step S103 can be executed on the third remote device, and the adjusted configuration parameter is sent to the optimization platform by the third remote device.

[0303] In the example (3), the empirical rule for determining the base station configuration parameter is converted into the adjustment rule, which can realize real-time adjustment of the configuration parameter online, and improve the optimization effect of the traffic statistical data in the time dimension.

[0304] Example (4)

[0305] As shown in FIG. 11, in the example shown in FIG. 10, after step S104, step S115 is further performed. On the basis of the embodiment shown in FIG. 3, after step S33, the step S115 shown in FIG. 11 is further performed.

[0306] The steps S111-S114 in FIG. 11 refer to the steps S101-S104 shown in FIG. 10 in sequence respectively.

[0307] Step S115: The optimization platform adjusts the configuration parameter in multiple rounds according to the preset time interval before meeting the preset stop condition; after each round of adjustment, the optimization platform takes the configuration parameter after each round of adjustment as the configuration parameter of the base station in the target control area at different time points.

[0308] In an implementation, the stop condition includes that the number of modulation rounds of the configuration parameter reaches a preset round threshold.

[0309] In an implementation, in any one of the multiple rounds of adjustment, the following steps are performed:

[0310] Step 1: According to at least one of the preset adjustment rule, the network feedback in the target control area and the constraint rule, determine the adjustment data for optimizing the configuration parameter obtained in the last time; the adjustment data is used to adjust the current configuration parameter to be adjusted, and the adjustment data is less than a preset threshold.

[0311] In an implementation, the network feedback includes at least one of positive feedback and negative feedback. The positive feedback is used to indicate that the configuration parameter optimizes the traffic statistical data, and the negative feedback is used to indicate that the configuration parameter does not optimize the traffic statistical data.

[0312] Step 2: Adjust the current configuration parameter to be adjusted according to the adjustment data.

[0313] Through the example (4), the configuration parameter can be updated iteratively according to the configuration parameter optimization result of the network feedback, and the configuration parameter adjustment effect of the base station is further improved.

[0314] Example (5)

[0315] In this example, when the trigger condition is met, the relevant steps in FIG. 3 and the steps of any relevant embodiments are re-executed to achieve cyclic updating of the configuration parameters.

[0316] The trigger condition can include at least one of the following:

[0317] a) A preset repeated execution time is reached, and steps S31-S33 in FIG. 3 and the steps of the relevant embodiments are repeatedly executed.

[0318] b) Changes in traffic statistics of the target control area are detected, and steps S31-S33 in FIG. 3 and the steps of the relevant embodiments are repeatedly executed.

[0319] In the target control area, the mean value of the traffic statistics collected at different time points can be calculated, and whether the change in the mean value in different time periods exceeds a preset proportion can be determined to determine whether there are changes in the traffic statistics of the target control area.

[0320] c) Feedback information about traffic quality from users is obtained through active acquisition or passive reception, and steps S31-S33 in FIG. 3 and the steps of the relevant embodiments are repeatedly executed.

[0321] d) Steps S31-S32 shown in FIG. 3 are repeatedly executed according to a preset time length, and each time step S32 is executed, if it is detected that the target scene newly determined is different from the target scene determined when step S32 was executed in the previous time length, step S33 is executed.

[0322] Through example (5), the configuration parameters issued to the base station can be repeatedly determined under certain conditions, so that the configuration parameters of the base station can be adjusted according to the changes in the traffic characteristic data in the target control area, so that the configuration parameters of the base station change with the changes in the traffic demand in the target control area.

[0323] Example (6)

[0324] After steps S31-S33 shown in FIG. 3, it is also necessary to determine whether to use the configuration parameters to control the base station in the target control area, as shown in FIG. 12A.

[0325] Steps S121-S123 refer to steps S31-S33 and the corresponding embodiments, respectively.

[0326] Step S124: The optimization platform determines the probability that the configuration parameters can optimize the traffic statistics.

[0327] If the currently calculated configuration parameter is changed compared to the configuration parameter of the base station in the target control area in the last time length of the first time length, it is determined that the configuration parameter can optimize the probability of the traffic statistical data. Otherwise, step S124-step S125 are not performed.

[0328] When the optimization platform is implemented by the system shown in FIG. 2, step S124 can be performed by the closed-loop engine 25 or the management control module 21.

[0329] Step S125: If the probability is greater than the probability requirement value corresponding to the target scenario, the optimization platform sends the configuration parameter to the base station in the target control area.

[0330] In an embodiment, the closed-loop engine 25 converts the configuration parameter into a corresponding man-machine language (MML), and sends the MML to all base stations in the target control area. Alternatively, the closed-loop engine 25 displays the MML corresponding to the configuration parameter to the control personnel, and the control personnel adjusts the configuration parameter of the base station according to the MML.

[0331] For example, the configuration interface can have a style as shown in FIG. 12B. The identification information of the text, symbol or text combined with symbol corresponding to the preset area can be filled in or selected in the box corresponding to the preset area; and the probability requirement value can be filled in or the identification information of the text, symbol or text combined with symbol corresponding to the probability requirement value can be selected in the box corresponding to the probability requirement value.

[0332] In an embodiment, during the process of multiple rounds of optimization of the configuration parameter, the adjustment data for optimizing the configuration parameter obtained in the last round is determined according to the probability requirement value, the network feedback in the target control area and the constraint rule. For example, the process of determining the adjustment data is shown in FIG. 12C. First, a risk assessment model is generated according to the preset probability requirement value (which can also be referred to as a risk tolerance coefficient) and the constraint rule. The risk assessment model can be a model different from the prediction model and the prediction classifier. The risk assessment model can be an artificial intelligence model, a formula or a database. The risk assessment model can determine whether the configuration parameter corresponding to the constraint rule can meet the probability requirement value after adjustment. Then, the result of the new round of optimization is determined according to the network feedback. The optimization result of the new round includes whether to adjust the configuration parameter of the last round or whether to send the adjusted configuration parameter to the base station. If the adjusted configuration parameter is not sent to the base station, the base station always maintains the configuration parameter of the last time length.

[0333] In an embodiment, after obtaining the output data of the prediction model, the configuration parameter is obtained according to the output data, and then the change amount of the configuration parameter is determined according to the configuration parameter of the last time length. The risk assessment model is used to determine whether to send the configuration parameter to the base station according to the change amount.

[0334] In an embodiment, different preset scenarios can be provided with different probability requirement values. Lower probability requirement values can be set for some preset scenarios to reduce the risk of poor user experience caused by unstable communication network due to the change of the configuration parameter. Some other preset scenarios can have higher risk tolerance for unstable communication network, and higher probability requirement values can be set for some other preset scenarios.

[0335] After step S124, if the probability is less than the probability requirement value corresponding to the target scenario, the configuration parameter is refused to be sent to the base station in the target control area.

[0336] The above mainly introduces the method provided by the present application. Correspondingly, the present application also provides a communication device for implementing various methods in the above method embodiments. The communication device can be a system in the above method embodiments, or a device containing a system, or a component such as a chip or a chip system that can be used in a system. Alternatively, the communication device can be an optimization platform in the above method embodiments, or a device containing an optimization platform, or a component such as a chip or a chip system that can be used in an optimization platform.

[0337] In some embodiments, the communication device contains hardware structures and / or software modules corresponding to the implementation of various functions in order to realize the above functions. Those skilled in the art should easily realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized in the form of hardware or a combination of hardware and computer software. Whether a certain function is realized in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods for each specific application to realize the described functions, but such implementation should not be considered beyond the scope of the present application.

[0338] The embodiments of the present application can divide the functional modules of the communication device according to the above method embodiments, for example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above integrated module can be realized in the form of hardware or software functional module. It should be noted that the division of modules in the embodiments of the present application is illustrative, and is only a logical functional division. There can be another division method when actually implemented.

[0339] FIG. 13 and FIG. 14 are structural schematic diagrams of possible apparatuses provided by embodiments of the present application. The apparatuses can be used to implement the functions of the optimization platform or system in the above-mentioned method embodiments, and thus can also achieve the beneficial effects of the above-mentioned method embodiments. In embodiments of the present application, the apparatus can be a system as shown in FIG. 2, or an optimization platform as shown in FIG. 3-FIG. 12A, or a module (such as a chip) applied to the optimization platform or base station.

[0340] As shown in FIG. 13, the base station parameter control apparatus 1300 includes a processing unit 1310 and a transceiver unit 1320. The base station parameter control apparatus 1300 is used to implement the functions of the optimization platform in the above-mentioned method embodiments of FIG. 3.

[0341] When the base station parameter control apparatus 1300 is used to implement the functions of the optimization platform in the method embodiments of FIG. 3, the transceiver unit 1320 is configured to: obtain first geographic location information of a target control area, and traffic statistical data in the target control area, the traffic statistical data including statistical values of a plurality of traffic statistical items within a first time length. The processing unit 1310 is configured to: match the first geographic location information and the traffic statistical data with a plurality of preset scenes, to determine a target scene corresponding to the target control area; each scene in the plurality of preset scenes including: at least one geographic location information corresponding to each scene, at least one traffic statistical item corresponding to each scene, and a statistical value range corresponding to the at least one traffic statistical item; input at least one target geographic location information, at least one target traffic statistical item, and a target statistical value range corresponding to the at least one target traffic statistical item corresponding to the target scene into a prediction model, and determine configuration parameters of base stations in the target control area according to output data of the prediction model, the configuration parameters being used to configure the base stations in the target control area within a second time length, the second time length being located after the first time length.

[0342] In an embodiment, the transceiving unit 1320 is further configured to obtain a first historical record, the first historical record comprising at least one statistical value corresponding to each of the at least one traffic statistic item in a third time period, the third time period being prior to the first time period, and second geographical location information corresponding to the at least one statistical value; and the processing unit 1310 is further configured to determine, based on the first historical record, a plurality of frequent item sets, each of the frequent item sets comprising one or more of the at least one traffic statistic item, a statistical value range corresponding to each of the one or more traffic statistic items, and second geographical location information corresponding to the one or more traffic statistic items in the first historical record, the statistical value range corresponding to each of the one or more traffic statistic items being obtained according to the statistical value corresponding to each of the one or more traffic statistic items, and a ratio of a number of times that the one or more traffic statistic items in each of the frequent item sets co-occur in the third time period to a total number of item sets in the third time period exceeding a preset threshold, and obtain the plurality of preset scenarios by taking each of the frequent item sets as a scenario.

[0343] In an embodiment, the prediction model is obtained according to training of a prediction classifier, the prediction classifier being configured to predict whether output data of the prediction model optimizes traffic statistic data in the second time period, and the prediction classifier is obtained according to a second historical record.

[0344] In an embodiment, the transceiving unit 1320 is further configured to obtain a second historical record, the second historical record comprising at least one statistical value corresponding to each of the at least one traffic statistic item in a fourth time period, the fourth time period being prior to the first time period, third geographical location information corresponding to the at least one statistical value, and configuration parameters corresponding to the at least one statistical value; and the processing unit 1310 is further configured to determine, based on the second historical record, the prediction model, the prediction model being configured to describe a relationship between different geographical location information, the at least one traffic statistic item corresponding to different geographical location information, a statistical value range corresponding to the at least one traffic statistic item, and the configuration parameters.

[0345] In an embodiment, the processing unit 1310 is further configured to take the output data of the prediction model as the configuration parameters of the base stations in the target control area.

[0346] In an embodiment, the processing unit 1310 is further configured to adjust the output data of the prediction model according to a preset adjustment rule to obtain the configuration parameters of the base stations in the target control area.

[0347] In an embodiment, the processing unit 1310 is further configured to: adjust the output data of the prediction model according to a preset adjustment rule, and obtain the configuration parameter of the base station in the target control area; and before a preset stop condition is met, perform multiple rounds of adjustment on the configuration parameter; and use the configuration parameter after each round of adjustment as the configuration parameter of the base station in the target control area at different time points.

[0348] In an embodiment, the transceiver unit 1320 is further configured to: before obtaining the first geographical location information of the target control area and the traffic statistical data in the target control area, determine that the preset stop condition is met.

[0349] In an embodiment, the processing unit 1310 is further configured to: determine adjustment data for optimizing the configuration parameter obtained last time according to a preset adjustment rule; the adjustment data is used to adjust the current configuration parameter to be adjusted, and the adjustment data is less than a preset threshold; and adjust the current configuration parameter to be adjusted according to the adjustment data.

[0350] In an embodiment, the stop condition comprises: a modulation round number of the configuration parameter reaches a preset round threshold.

[0351] In an embodiment, the preset adjustment rule is used to describe the relationship among different output data, different optimization indicators, and adjustment amounts of different optimization indicators.

[0352] In an embodiment, the transceiver unit 1320 is further configured to: determine a probability that the configuration parameter can optimize the traffic statistical data; if the probability is greater than a probability requirement value corresponding to the target scenario, send the configuration parameter to the base station in the target control area; or if the probability is less than the probability requirement value corresponding to the target scenario, refuse to send the configuration parameter to the base station in the target control area.

[0353] In an embodiment, the target control area is one of a plurality of areas obtained by dividing a controllable area, and each area in the plurality of areas includes at least one base station.

[0354] In an embodiment, the third time length is greater than the first time length, and the third time length is greater than the second time length.

[0355] For more detailed descriptions of the processing unit 1310 and the transceiver unit 1320, refer to the related descriptions in the method embodiments shown in FIGS. 3 to 12A, which will not be repeated here.

[0356] As shown in FIG. 14, the communication apparatus 1400 includes a processor 1410 and an interface circuit 1420. The processor 1410 and the interface circuit 1420 are coupled to each other. It can be understood that the interface circuit 1420 can be a transceiver or an input / output interface. Optionally, the communication apparatus 1400 can further include a memory 1430 for storing instructions executed by the processor 1410 or storing input data required by the processor 1410 to execute instructions or storing data generated after the processor 1410 executes instructions.

[0357] When the communication apparatus 1400 is used to implement the methods shown in FIGS. 3 to 12A, the processor 1410 is configured to implement the functions of the processing unit 1310, and the interface circuit 1420 is configured to implement the functions of the transceiver unit 1320.

[0358] When the communication apparatus is a module applied to a network device, the network device module implements the functions of the optimization platform in the method embodiments. The network device module receives information from other modules (such as a radio frequency module or an antenna) in the network device, and the information is sent by a terminal to the network device; or the network device module sends information to other modules (such as a radio frequency module or an antenna) in the network device, and the information is sent by the network device to the terminal. The network device module herein can be a baseband chip of the network device, or a DU or other module. The DU herein can be a DU under the open radio access network (O-RAN) architecture.

[0359] It can be understood that the processor in the embodiments of the present application can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. The general-purpose processor can be a microprocessor or any conventional processor.

[0360] In the present application, another example of a communication device is provided, which comprises at least one processor and at least one memory coupled to the at least one processor, the at least one memory configured to store instructions that, when executed by the at least one processor, cause the communication device to perform the method in the above embodiments. For example, the communication device comprises one processor and one memory, as shown in FIG. 14, the communication device 1400 comprises one processor 1410 and one memory 1430. The processor 1410 and the memory 1430 are coupled, and the memory 1430 stores instructions, when the instructions stored in the memory 1430 are executed by the processor 1410, the communication device 1400 performs the method executed by the platform in the above embodiments.

[0361] It should be understood that the processor 1410 and the memory 1430 can also be integrated together, such as integrated in one chip.

[0362] The method steps in the embodiments of the present application can be implemented in hardware, or in software instructions executable by a processor. The software instructions can be composed of corresponding software modules, which can be stored in a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an electrically programmable read-only memory, a register, a hard disk, a mobile hard disk, a CD-ROM, or any other form of storage medium well known in the art. An exemplary storage medium is coupled to the processor, so that the processor can read information from, and write information to, the storage medium. The storage medium can also be an integral part of the processor. The processor and the storage medium can be located in an ASIC. In addition, the ASIC can be located in a network device or a terminal. The processor and the storage medium can also exist as discrete components in the network device or the terminal.

[0363] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer programs or instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments are performed. The computer can be a general purpose computer, a special purpose computer, a computer network, a network device, a user equipment or other programmable apparatus. The computer programs or instructions can be stored in a computer readable storage medium or transferred from one computer readable storage medium to another computer readable storage medium, for example, the computer programs or instructions can be transferred from one website site, computer, server or data center to another website site, computer, server or data center through wired or wireless manner. The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center and the like integrated with one or more available media. The available media can be a magnetic medium, such as a floppy disk, a hard disk, a magnetic tape; or an optical medium, such as a digital video disc; or a semiconductor medium, such as a solid state disk. The computer readable storage medium can be a volatile or non-volatile storage medium, or can include both volatile and non-volatile storage media.

[0364] In various embodiments of the present application, the terms and / or descriptions of different embodiments are consistent and can be referred to each other if there is no special description and logical conflict, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0365] In the present application, "at least one" means one or more, and "multiple" means two or more. The association relationship between the associated objects is described, which means that there can be three relationships, for example, A and / or B, which can mean that A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. In the literal description of the present application, the character " / ", generally indicates that the associated objects before and after are in an "or" relationship; in the formula of the present application, the character " / ", indicates that the associated objects before and after are in a "division" relationship. "Including at least one of A, B and C" can mean: including A; including B; including C; including A and B; including A and C; including B and C; including A, B and C.

[0366] It can be understood that various numerical numbers involved in the embodiments of the present application are only distinguished for convenience of description, and are not used to limit the scope of the embodiments of the present application. The size of the serial number of the above processes does not mean the order of execution, and the execution order of the processes should be determined according to its function and inherent logic.

Claims

1. A base station parameter control method, characterized in that: include: Acquire first geographic location information of a target control area and traffic statistics data within the target control area, wherein the traffic statistics data include statistical values ​​of a plurality of traffic statistics items within a first time period; matching the first geographic location information and the traffic statistics data with a plurality of preset scenarios to determine a target scenario corresponding to the target control area; Each of the plurality of preset scenarios includes: at least one geographical location information corresponding to each scenario, at least one traffic statistic item corresponding to each scenario, and a statistical value range corresponding to the at least one traffic statistic item; At least one target geographic location information, at least one target traffic statistic item, and a target statistical value range corresponding to the at least one target traffic statistic item corresponding to the target scenario are input into a prediction model. Based on the output data of the prediction model, configuration parameters of the base stations within the target control area are determined. The configuration parameters are used to be configured to the base stations within the target control area within a second time period, and the second time period is located after the first time period.

2. The method according to claim 1, characterized in that The method further comprises: Obtaining a first historical record, the first historical record including at least one statistical value corresponding to at least one of the traffic statistics items within a third time period, and second geographical location information corresponding to the at least one statistical value, wherein the third time period is before the first time period; Determining, based on the first historical record, a plurality of frequent itemsets, each of the frequent itemsets including one or more of the at least one traffic statistical item, a statistical value range corresponding to each of the one or more items, and second geographic location information corresponding to the one or more items in the first historical record; the statistical value range corresponding to the one or more items being obtained based on the statistical values ​​corresponding to the one or more items; and a ratio of a number of co-occurrences of the one or more items in each of the frequent itemsets within the third time period to a total number of itemsets in the third time period exceeding a preset threshold; Each of the frequent itemsets is taken as a scene to obtain the multiple preset scenes.

3. The method according to claim 1 or 2, characterized in that The prediction model is trained based on the first output data of the prediction classifier, and the prediction classifier is used to predict whether the output data of the prediction model optimizes the traffic statistics data within the second time period; the prediction classifier is trained based on the second historical records.

4. The method according to any one of claims 1 to 3, characterized in that The method further comprises: Obtaining a second historical record, the second historical record including at least one statistical value corresponding to at least one traffic statistic item within a fourth time period, third geographic location information corresponding to the at least one statistical value, and a configuration parameter corresponding to the at least one statistical value, wherein the fourth time period is before the first time period; Based on the second historical records, the prediction model is determined, where the prediction model is used to describe the relationship between different geographic location information, at least one traffic statistic item corresponding to the different geographic location information, a statistical value range corresponding to at least one traffic statistic item, and configuration parameters.

5. The method according to any one of claims 1 to 4, characterized in that Determining the configuration parameters of the base stations within the target control area based on the output data of the prediction model includes: The output data of the prediction model is used as the configuration parameters of the base stations in the target control area.

6. The method according to any one of claims 1 to 4, characterized in that: Determining the configuration parameters of the base stations within the target control area based on the output data of the prediction model includes: According to a preset adjustment rule, the output data of the prediction model is adjusted to obtain the configuration parameters of the base stations in the target control area.

7. The method according to claim 6, characterized in that After adjusting the output data of the prediction model according to a preset adjustment rule to obtain the configuration parameters of the base stations in the target control area, the method further includes: Before a preset stopping condition is met, the configuration parameters are adjusted for multiple rounds; The configuration parameters adjusted in each round are used as configuration parameters of the base stations in the target control area at different time points.

8. The method according to claim 7, characterized in that Before acquiring the first geographical location information of the target control area and the traffic statistics data within the target control area, the method further includes: It is determined that the preset stop condition is met.

9. The method according to claim 7 or 8, characterized in that The adjusting the configuration parameters for multiple rounds includes: Determining, according to a preset adjustment rule, adjustment data for optimizing the configuration parameters obtained last time; the adjustment data is used to adjust the configuration parameters currently to be adjusted, and the adjustment data is less than a preset threshold; The configuration parameter currently to be adjusted is adjusted according to the adjustment data.

10. The method according to any one of claims 7 to 9, characterized in that: The stopping condition includes: the number of modulation rounds of the configuration parameter reaches a preset round number threshold.

11. The method according to claim 9 or 10, characterized in that The preset adjustment rules are used to describe: The relationship between different output data, different optimization indicators, and the adjustment amounts of different optimization indicators.

12. The method according to any one of claims 1 to 11, characterized in that The method further comprises: determining a probability that the configuration parameters can optimize the traffic statistics; If the probability is greater than the required probability value corresponding to the target scenario, the configuration parameters are sent to the base stations within the target control area; or, if the probability is less than the required probability value corresponding to the target scenario, the configuration parameters are refused to be sent to the base stations within the target control area.

13. The method according to any one of claims 1 to 12, characterized in that: The target control area is one of a plurality of areas obtained by dividing the controllable area, and each of the plurality of areas includes at least one base station.

14. The method according to claim 2, characterized in that The third duration is greater than the first duration, and the third duration is greater than the second duration.

15. A base station parameter control device, characterized in that: including an interface module and a processing module; The interface module is configured to: obtain first geographical location information of a target control area and traffic statistics data within the target control area, wherein the traffic statistics data include statistical values ​​of a plurality of traffic statistics items within a first time period; The processing module is configured to: match the first geographic location information and the traffic statistics data with a plurality of preset scenarios to determine a target scenario corresponding to the target control area; Each of the plurality of preset scenarios includes: at least one geographical location information corresponding to each scenario, at least one traffic statistic item corresponding to each scenario, and a statistical value range corresponding to the at least one traffic statistic item; At least one target geographic location information, at least one target traffic statistic item, and a target statistical value range corresponding to the at least one target traffic statistic item corresponding to the target scenario are input into a prediction model. Based on the output data of the prediction model, configuration parameters of the base stations within the target control area are determined. The configuration parameters are used to be configured to the base stations within the target control area within a second time period, and the second time period is located after the first time period.

16. A communication device, characterized in that: The method comprises a unit or module for executing the method according to any one of claims 1 to 14.

17. A communication device, characterized in that: include: One or more processors configured to execute the method of any one of claims 1-14.

18. A readable storage medium, characterized in that The readable storage medium stores a program or instruction, and when the program or instruction is executed on the communication device, the communication device is caused to execute the method according to any one of claims 1 to 14.

19. A chip system, characterized in that: The device comprises a processor, wherein the processor is coupled to a memory to execute a computer program or instruction stored in the memory, so that the method according to any one of claims 1 to 14 is performed.

20. A program product, characterized in that Contains a program; when the program is run on a computer, the computer is caused to execute the method according to any one of claims 1 to 14.

21. A base station parameter control system, characterized in that: It includes a base station parameter control device and at least one base station; The base station parameter control device is used to execute the method according to any one of claims 1 to 14 to configure parameters for the at least one base station.

Images