WO2023071616A1 - 业务处理的方法、装置、电子设备及介质 - Google Patents

业务处理的方法、装置、电子设备及介质 Download PDF

Info

Publication number
WO2023071616A1
WO2023071616A1 PCT/CN2022/119879 CN2022119879W WO2023071616A1 WO 2023071616 A1 WO2023071616 A1 WO 2023071616A1 CN 2022119879 W CN2022119879 W CN 2022119879W WO 2023071616 A1 WO2023071616 A1 WO 2023071616A1
Authority
WO
WIPO (PCT)
Prior art keywords
model
service processing
business processing
request
business
Prior art date
Application number
PCT/CN2022/119879
Other languages
English (en)
French (fr)
Inventor
崔琪楣
任崇万
赵博睿
梁盛源
陶小峰
Original Assignee
北京邮电大学
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京邮电大学 filed Critical 北京邮电大学
Publication of WO2023071616A1 publication Critical patent/WO2023071616A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46Multiprogramming arrangements
    • G06F9/50Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5005Allocation of resources, e.g. of the central processing unit [CPU] to service a request
    • G06F9/5027Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals

Definitions

  • This application relates to data processing technology, especially a business processing method, device, electronic equipment and media.
  • the 5G access network adopts a logical architecture in which the centralized unit CU-distributed unit DU is separated.
  • One of the base station devices gNB includes a CU and one or more DUs.
  • the CU can be connected to the DU through the F1 interface.
  • the DU is responsible for completing the protocol stack processing functions with high real-time requirements such as RLC/MAC/PHY, while the CU is responsible for completing the protocol stack processing functions with low real-time requirements such as PDCP/RRC/SDAP.
  • Embodiments of the present application provide a service processing method, device, electronic equipment, and medium, wherein, according to an aspect of the embodiments of the present application, the provided service processing method is applied to base station equipment, including:
  • the centralized unit CU in the base station equipment delivers to the DU;
  • the method before acquiring the service processing request sent by the target object associated with the base station device, the method further includes:
  • the method further includes:
  • model call request sent by the DU, where the model call request includes an ID parameter corresponding to the DU;
  • model index select the initial business processing model and model associated data corresponding to the model call request;
  • the initial service processing model and model associated data corresponding to the model invocation request are sent to the DU.
  • model evaluation module stored in the DU, perform service evaluation on the service processing model to be evaluated, and determine to generate the service processing model if it passes.
  • the method before acquiring the service processing request sent by the target object associated with the base station device, the method further includes:
  • the selection of the target service processing model matching the service processing request includes:
  • a target service processing model matching the category is selected from multiple service processing models stored in the DU, where the category includes intelligent channel coding. At least one of intelligent positioning, intelligent channel estimation, intelligent intelligent beam management, intelligent dynamic wireless resource allocation, and intelligent link adaptation.
  • the sending the service processing request to the distributed unit DU includes:
  • a service processing apparatus which is applied to base station equipment, and includes:
  • An acquisition module configured to acquire a service processing request sent by a target object associated with the base station device
  • the selection module is configured to send the service processing request to the distributed unit DU, and select a target service processing model that matches the service processing request from multiple service processing models stored in the DU,
  • the service processing model is delivered to the DU by the centralized unit CU in the base station equipment;
  • a generating module configured to use the target business processing model to perform business processing on the business processing request, and generate a business processing result
  • a sending module configured to return the service processing result to the target object.
  • an electronic device including:
  • a display configured to display with the memory to execute the executable instructions so as to complete any operation of the above-mentioned service processing method.
  • a computer-readable storage medium for storing computer-readable instructions, and when the instructions are executed, operations of any one of the business processing methods described above are performed.
  • the service processing request sent by the target object associated with the base station equipment can be obtained; the service processing request is sent to the distributed unit DU, and the service processing request is selected from the multiple service processing models stored in the DU.
  • the matching target business processing model, the business processing model is sent to the DU by the centralized unit CU in the base station equipment; use the target business processing model to perform business processing on the business processing request, and generate the business processing result; return the business processing result to the target object .
  • multiple service processing models can be deployed in the DU in the base station equipment, so that after receiving the service request sent by the physical layer or MAC layer object associated with the base station equipment, it can pass Targetedly select the corresponding business model to make a decision on the business request, and return the processing result to the physical layer or MAC layer object. Furthermore, the purpose of introducing the intelligent decision-making function into the physical layer and MAC layer functions under the 5G network is realized.
  • FIG. 1 is a schematic diagram of a business processing method proposed in this application
  • FIG. 2 is a schematic diagram of a system architecture of a base station device applied to business processing proposed by the present application
  • Figure 3- Figure 5 is a schematic flow chart of a business process proposed in this application.
  • FIG. 6 is a schematic structural diagram of an electronic device for business processing proposed in this application.
  • FIG. 7 is a schematic structural diagram of electronic equipment for service processing proposed in this application.
  • FIGS. 1-5 A method for performing service processing according to an exemplary embodiment of the present application is described below with reference to FIGS. 1-5 . It should be noted that the following application scenarios are only shown for easy understanding of the spirit and principle of the present application, and the implementation manners of the present application are not limited in this regard. On the contrary, the embodiments of the present application can be applied to any applicable scene.
  • the application also proposes a service processing method, device, base station equipment and medium.
  • Fig. 1 schematically shows a schematic flowchart of a service processing method according to an embodiment of the present application. As shown in Figure 1, the method is applied to base station equipment, including:
  • the 5G access network adopts a logical architecture of CU-DU separation, and one gNB includes one CU and one or more DUs.
  • the CU can be connected to the DU through the F1 interface.
  • the DU is responsible for completing the protocol stack processing functions with high real-time requirements such as RLC/MAC/PHY, while the CU is responsible for completing the protocol stack processing functions with low real-time requirements such as PDCP/RRC/SDAP.
  • the O-RAN architecture introduces the Near-RT RIC.
  • the near-real-time wireless intelligent controller is connected to the CU-CP, CU-UP, and DU entities through the E2 interface, and performs centralized data collection and decision-making through the E2 interface.
  • Intelligence can be introduced into Near-RT RIC, and an intelligent method can be used to solve radio resource management functions (except dynamic radio resource allocation). But the intelligent controller can only be responsible for near real-time intelligent control with real-time performance greater than 10ms.
  • 3Gpp R18 discusses the introduction of AI algorithms in physical layer and MAC layer functions, such as channel coding, positioning, channel estimation, beam management, dynamic wireless resource allocation, and link adaptation.
  • the intelligent decision-making and control of the MAC layer and the physical layer have high real-time requirements, generally less than 10ms, and the data required by the AI algorithm is located in the distributed unit DU.
  • the existing 5G network architecture and O-RAN network architecture cannot support the real-time requirements of intelligent decision-making at the physical layer and MAC layer, and lack a general AI workflow.
  • the target object associated with the base station device may be a physical layer or a MAC layer in a communication network under the base station device.
  • S102 Send the service processing request to the distributed unit DU, and select a target service processing model that matches the service processing request from multiple service processing models stored in the DU.
  • the service processing model is determined by the centralized unit in the base station equipment CU sends to DU;
  • a centralized intelligent model module can be deployed in the CU of the base station device, and the intelligent model library can include a model memory, a model manager, and a model converter.
  • the centralized intelligent model module can be deployed together with the CU or in the Edge server side.
  • the model storage is used to store the initial service processing model (for example, an AI/ML model file) and corresponding model-related information.
  • the model files include model structure files and model parameter files.
  • Model-related information includes model functions, as well as the input data types and format standards required for model training and inference.
  • the model manager is used to manage the upload and delivery of AI/ML models.
  • the model converter converts the format of the models developed by developers under different deep learning architectures to ensure that AI/ML models can be deployed on the distributed intelligent control module introduced later.
  • a distributed intelligent control module may be deployed in the DU of the base station equipment.
  • the DU may include protocol stack functions such as RLC layer, MAC layer, and PHY layer.
  • the distributed intelligent control module can use artificial intelligence to carry out intelligent decision-making and prediction of PHY layer and MAC layer functions.
  • the DU may also include a data collector for storing the data required for training and reasoning models (that is, for training the initial service processing model transmitted from the CU).
  • Model training engine providing the software environment required for model training, using the training data in the data collector for model training, and deploying the model after the model training is completed (that is, multiple business processing models used to process business processing requests) in the model inference engine.
  • the model reasoning engine provides the software environment required for model reasoning, and the deployed model uses the reasoning data in the data collector for model reasoning.
  • the model evaluator evaluates the model, which can comprehensively evaluate the convergence speed of model training and the accuracy of the model.
  • the distributed intelligent control module obtains the network low-layer data, layer-1 layer-2 measurement data and user information sent by the target device through the MAC layer and the physical layer through the interface, and stores the information in the data collector.
  • the way of obtaining information may include the following ways: the distributed intelligent control module actively sends data request information through the interface, the distributed intelligent control module subscribes to the MAC/physical layer, and periodically or event-triggered sends the MAC layer and physical layer information to the intelligent controller. layer information.
  • the MAC layer and the physical layer of the base station equipment in this application can send service processing requests through interfaces.
  • the service processing request includes: intelligent channel coding. Intelligent positioning. Intelligent channel estimation. Smart smart beam management. Intelligent dynamic wireless resource allocation. At least one of intelligent link adaptation, etc.
  • the model reasoning engine corresponding to the request function uses the reasoning data in the data collector to make reasoning, and sends the intelligent decision/prediction result to the business processing requester through interface three.
  • the service processing request sent by the target object associated with the base station equipment can be obtained; the service processing request is sent to the distributed unit DU, and the service processing request is selected from the multiple service processing models stored in the DU.
  • the matching target business processing model, the business processing model is sent to the DU by the centralized unit CU in the base station equipment; use the target business processing model to perform business processing on the business processing request, and generate the business processing result; return the business processing result to the target object .
  • multiple service processing models can be deployed in the DU in the base station equipment, so that after receiving the service request sent by the physical layer or MAC layer object associated with the base station equipment, it can pass Targetedly select the corresponding business model to make a decision on the business request, and return the processing result to the physical layer or MAC layer object. Furthermore, the purpose of introducing the intelligent decision-making function into the physical layer and MAC layer functions under the 5G network is realized.
  • the method before acquiring the service processing request sent by the target object associated with the base station device, the method further includes:
  • the method further includes:
  • model call request sent by the DU, where the model call request includes an ID parameter corresponding to the DU;
  • model index select the initial business processing model and model associated data corresponding to the model call request;
  • the initial service processing model and model associated data corresponding to the model invocation request are sent to the DU.
  • the method further includes:
  • model evaluation module stored in the DU, perform service evaluation on the service processing model to be evaluated, and determine to generate the service processing model if it passes.
  • the method before acquiring the service processing request sent by the target object associated with the base station device, the method further includes:
  • the selecting a target service processing model that matches the service processing request includes:
  • a target service processing model matching the category is selected from multiple service processing models stored in the DU, where the category includes intelligent channel coding. At least one of intelligent positioning, intelligent channel estimation, intelligent intelligent beam management, intelligent dynamic wireless resource allocation, and intelligent link adaptation.
  • the sending the service processing request to the distributed unit DU includes:
  • the CU of the base station equipment in this application includes a centralized intelligent model module and a DU functional entity.
  • the centralized intelligent control module includes a model converter, a model manager, and a model memory.
  • the centralized intelligent model module is connected to the DU functional entity through interface 2, and the DU functional entity can send a model call request through interface 2, and the model call request includes the ID number of the DU functional entity, or Including the model function information corresponding to the called model.
  • the model manager in the CU performs model indexing through the model function, and then sends the corresponding initial business model to the corresponding in the DU functional entity.
  • the DU functional entity uses the delivered model to perform model training and model reasoning, it can obtain the business processing model to be evaluated, and then use the model evaluation module stored in the DU to conduct business evaluation on the business processing model to be evaluated, and determine the generation of business processing Model.
  • step 301 the developer uploads the model to the CU through interface 1, where the uploaded data includes model files and model-related information.
  • Step 302 the model converter in the CU converts the format of the uploaded initial service processing model, and stores them in a unified format.
  • the model manager allocates storage space for multiple initial business processing models, and maintains an index table of functions and addresses to facilitate model indexing.
  • Step 304 the model storage stores multiple initial service processing models in the storage space allocated by the model manager.
  • the implementation process of the MAC layer/physical layer intelligent function is: the MAC layer or the physical layer sends a service processing request to the distributed intelligent control module in the DU through the interface three, and the service processing request includes the intelligent channel At least one of coding, intelligent positioning, intelligent channel estimation, intelligent intelligent beam management, intelligent dynamic wireless resource allocation, intelligent link adaptation, etc.
  • a target service processing model corresponding to the category may be selected to perform corresponding service processing.
  • the business processing model of the corresponding function in the distributed intelligent control module in the DU uses the reasoning model in the data collector to perform reasoning, and sends the model reasoning result to the business processing requester (ie, the target object) through interface three.
  • the present application further provides a service processing apparatus.
  • base station equipment including:
  • An acquisition module 201 configured to acquire a service processing request sent by a target object associated with the base station device
  • the selecting module 202 is configured to send the service processing request to the distributed unit DU, and select a target service processing model matching the service processing request from multiple service processing models stored in the DU,
  • the service processing model is delivered to the DU by the centralized unit CU in the base station equipment;
  • the generating module 203 is configured to use the target business processing model to perform business processing on the business processing request, and generate a business processing result;
  • the sending module 204 is configured to return the service processing result to the target object.
  • the service processing request sent by the target object associated with the base station equipment can be obtained; the service processing request is sent to the distributed unit DU, and the service processing request is selected from the multiple service processing models stored in the DU.
  • the matching target business processing model, the business processing model is sent to the DU by the centralized unit CU in the base station equipment; use the target business processing model to perform business processing on the business processing request, and generate the business processing result; return the business processing result to the target object .
  • multiple service processing models can be deployed in the DU in the base station equipment, so that after receiving the service request sent by the physical layer or MAC layer object associated with the base station equipment, it can pass Targetedly select the corresponding business model to make a decision on the business request, and return the processing result to the physical layer or MAC layer object. Furthermore, the purpose of introducing the intelligent decision-making function into the physical layer and MAC layer functions under the 5G network is realized.
  • the acquiring module 201 further includes:
  • the obtaining module 201 is configured to receive a plurality of initial business processing models and model associated data uploaded by the development user; and,
  • the acquiring module 201 is configured to convert the multiple initial business processing models and model-related data into a preset format and store them in the CU, and store the multiple initial business processing models and model-related data in the CU Link data to generate the corresponding model index;
  • the obtaining module 201 is configured to receive multiple trained initial service processing models uploaded by the development user.
  • the acquiring module 201 further includes:
  • the acquisition module 201 is configured to receive the model call request sent by the DU, the model call request includes the ID parameter corresponding to the DU and the call model function;
  • the obtaining module 201 is configured to use the model index to select the initial business processing model and model associated data corresponding to the calling model function;
  • the obtaining module 201 is configured to send the initial service processing model and model associated data corresponding to the model calling request to the DU based on the ID parameter.
  • the acquiring module 201 further includes:
  • the acquisition module 201 is configured to use the training data stored in the DU to perform model training on the initial service processing model to generate a service processing model to be evaluated;
  • the obtaining module 201 is configured to use the model evaluation module stored in the DU to perform service evaluation on the service processing model to be evaluated, and determine to generate the service processing model if it passes.
  • the acquiring module 201 further includes:
  • the obtaining module 201 is configured to receive a plurality of initial service processing models and model associated data sent by the edge server, or receive a plurality of trained service processing models sent by the edge server.
  • the acquiring module 201 further includes:
  • the obtaining module 201 is configured to select a target service processing model matching the category from multiple service processing models stored in the DU based on the category of the service processing request, wherein the category includes an intelligent channel coding. At least one of intelligent positioning, intelligent channel estimation, intelligent intelligent beam management, intelligent dynamic wireless resource allocation, and intelligent link adaptation.
  • the acquiring module 201 further includes:
  • the obtaining module 201 is configured to select and send to the DU through the MAC layer or the physical layer according to the type of the service processing request.
  • Fig. 7 is a logical structural block diagram of an electronic device according to an exemplary embodiment.
  • the electronic device 300 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, and the like.
  • a non-transitory computer-readable storage medium including instructions, such as a memory including instructions, the instructions can be executed by the electronic device processor to complete the above-mentioned business processing method, the method includes: Acquiring a service processing request sent by a target object associated with the base station equipment; sending the service processing request to a distributed unit DU, and selecting a service processing model from multiple service processing models stored in the DU processing the target service processing model that matches the request, the service processing model is delivered to the DU by the centralized unit CU in the base station equipment; using the target service processing model to perform service processing on the service processing request, Generate a business processing result; return the business processing result to the target object.
  • the above instructions may also be executed by a processor of the electronic device to complete other steps involved in the above exemplary embodiments.
  • the non-transitory computer readable storage medium may be ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, and the like.
  • an application program/computer program product including one or more instructions, the one or more instructions can be executed by the processor of the electronic device to complete the above business processing method, the The method includes: obtaining a service processing request sent by a target object associated with the base station equipment; sending the service processing request to a distributed unit DU, and selecting a service processing model from a plurality of service processing models stored in the DU The target service processing model matched with the service processing request, the service processing model is sent to the DU by the centralized unit CU in the base station equipment; the service processing request is processed by using the target service processing model Business processing, generating a business processing result; returning the business processing result to the target object.
  • the above instructions may also be executed by a processor of the electronic device to complete other steps involved in the above exemplary embodiments.
  • FIG. 7 is a diagram of an example of a computer device 30 .
  • the schematic diagram 7 is only an example of the computer device 30, and does not constitute a limitation to the computer device 30, and may include more or less components than those shown in the figure, or combine certain components, or different components
  • the computer device 30 may also include an input and output device, a network access device, a bus, and the like.
  • the so-called processor 302 may be a central processing unit (Central Processing Unit, CPU), and may also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
  • the general-purpose processor can be a microprocessor or the processor 302 can also be any conventional processor, etc.
  • the processor 302 is the control center of the computer device 30 and uses various interfaces and lines to connect various parts of the entire computer device 30 .
  • the memory 301 can be used to store computer-readable instructions 303 , and the processor 302 implements various functions of the computer device 30 by running or executing computer-readable instructions or modules stored in the memory 301 and calling data stored in the memory 301 .
  • the memory 301 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application program required by a function (such as a sound playback function, an image playback function, etc.); Data created using the computer device 30 and the like.
  • the memory 301 may include a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash memory card (Flash Card), at least one magnetic disk storage device, a flash memory device, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), or other non-volatile/volatile storage devices.
  • a hard disk a memory
  • a plug-in hard disk a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash memory card (Flash Card), at least one magnetic disk storage device, a flash memory device, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), or other non-volatile/volatile storage devices.
  • a smart memory card Smart Media Card, SMC
  • the integrated modules of the computer device 30 are realized in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the present invention realizes all or part of the processes in the methods of the above embodiments, and can also use computer-readable instructions to instruct related hardware to complete, and the computer-readable instructions can be stored in a computer-readable storage medium. When the computer-readable instructions are executed by the processor, the steps of the above-mentioned various method embodiments can be realized.

Landscapes

  • Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本申请公开了一种业务处理的方法、装置、电子设备及介质。本申请中,本申请中,可以获取与基站设备相关联的目标对象发送的业务处理请求;将业务处理请求发送给分布式单元DU,并从DU中存储的多个业务处理模型中,选取与业务处理请求相匹配的目标业务处理模型,业务处理模型由基站设备中的集中式单元CU下发至DU;利用目标业务处理模型对业务处理请求进行业务处理,生成业务处理结果;将业务处理结果返回给目标对象。

Description

业务处理的方法、装置、电子设备及介质 技术领域
本申请中涉及数据处理技术,尤其是一种业务处理的方法、装置、电子设备及介质。
背景技术
5G接入网采用集中式单元CU-分布式单元DU分离的逻辑架构。其中一个基站设备gNB包括一个CU和一个或者多个DU。CU可以通过F1接口与DU相连。DU负责完成RLC/MAC/PHY等实时性要求较高的协议栈处理功能,而CU负责完成PDCP/RRC/SDAP等实时性要求较低的协议栈处理功能。
针对未来业务需求的多样性,需要在接入网中内嵌智能,但是5G网络架构不支持智能的部署。因此,如何在现有的5G网络架构中设计一种可以支持物理层和MAC层智能决策的实时性要求的方案,成为了需要解决的问题。
发明内容
本申请实施例提供一种业务处理的方法、装置、电子设备及介质,其中,根据本申请实施例的一个方面,提供的一种业务处理的方法,应用于基站设备,包括:
获取与所述基站设备相关联的目标对象发送的业务处理请求;
将所述业务处理请求发送给分布式单元DU,并从所述DU中存储的多个业务处理模型中,选取与所述业务处理请求相匹配的目标业务处理模型,所述业务处理模型由所述基站设备中的集中式单元CU下发至所述DU;
利用所述目标业务处理模型对所述业务处理请求进行业务处理,生成业务处理结果;
将所述业务处理结果返回给所述目标对象。
可选地,在基于本申请上述方法的另一个实施例中,在所述获取与所述基站设备相关联的目标对象发送的业务处理请求之前,还包括:
接收开发用户上传的多个初始业务处理模型以及模型关联数据;以及,
将所述多个初始业务处理模型以及模型关联数据转换成预设格式后存储到所述CU中,以及在所述CU中为所述多个初始业务处理模型以及模型关联数据生成对应的模型索引;
或,
接收所述开发用户上传的多个已训练完毕的初始业务处理模型。
可选地,在基于本申请上述方法的另一个实施例中,在所述在所述CU中为所述多个初始业务处理模型以及模型关联数据生成对应的模型索引之后,还包括:
接收所述DU发送的模型调取请求,所述模型调取请求中包含有所述DU对应的ID参数;
利用所述模型索引,选取所述模型调取请求对应的初始业务处理模型以及模型关联数据;
基于所述ID参数,将所述模型调取请求对应的初始业务处理模型以及模型关联数据发送给所述DU。
可选地,在基于本申请上述方法的另一个实施例中,在所述将所述模型调取请求对应的初始业务处理模型以及模型关联数据发送给所述DU之后,还包括:
利用所述DU中存储的训练数据,对所述初始业务处理模型进行模型训练,生成待评估业务处理模型;
利用所述DU中存储的模型评估模块,对所述待评估业务处理模型进行业务评估,若通过,确定生成所述业务处理模型。
可选地,在基于本申请上述方法的另一个实施例中,在所述获取与所述基站设备相关联的目标对象发送的业务处理请求之前,还包括:
接收所述边缘服务器发送的多个初始业务处理模型以及模型关联数据,或,接收所述边缘服务器发送的多个已训练完毕的业务处理模型。
可选地,在基于本申请上述方法的另一个实施例中,所述选取与所述业务处理请求相匹配的目标业务处理模型,包括:
基于所述业务处理请求的类别,从所述DU中存储的多个业务处理模型中,选取与所述类别相匹配的目标业务处理模型,其中所述类别包括智能信道编码。智能定位、智能信道估计、智能智能波束管理、智能动态无线资源分配以及智能链路自适应的至少一种。
可选地,在基于本申请上述方法的另一个实施例中,所述将所述业务处理请求发送给分布式单元DU,包括:
根据所述业务处理请求的类别,选择通过MAC层或物理层发送给所述DU。
其中,根据本申请实施例的又一个方面,提供的一种业务处理的装置,应用于基站设备,包括:
获取模块,被配置为获取与所述基站设备相关联的目标对象发送的业务处理请求;
选取模块,被配置为将所述业务处理请求发送给分布式单元DU,并从所述DU中存储的多个业务处理模型中,选取与所述业务处理请求相匹配的目标业务处理模型,所述业务处理模型由所述基站设备中的集中式单元CU下发至所述DU;
生成模块,被配置为利用所述目标业务处理模型对所述业务处理请求进行业务处理,生成业务处理结果;
发送模块,被配置为将所述业务处理结果返回给所述目标对象。
根据本申请实施例的又一个方面,提供的一种电子设备,包括:
存储器,用于存储可执行指令;以及
显示器,用于与所述存储器显示以执行所述可执行指令从而完成上述任一所述业务处理的方法的操作。
根据本申请实施例的还一个方面,提供的一种计算机可读存储介质,用于存储计算机可读取的指令,所述指令被执行时执行上述任一所述业务处理的方法的操作。
本申请中,可以获取与基站设备相关联的目标对象发送的业务处理请求;将业务处理请求发送给分布式单元DU,并从DU中存储的多个业务处理模型中,选取与业务处理请求相匹配的目标业务处理模型,业务处理模型由基站设备中的集中式单元CU下发至DU;利用目标业务处理模型对业务处理请求进行业务处理,生成业务处理结果;将业务处理结果返回给目标对象。通过应用本申请的技术方案,可以在基站设备中的DU中部署有多个业务处理模型,从而在接收到与该基站设备相关联的物理层或是MAC层对象发送的业务请求后,可以通过针对性的选取对应的业务模型对该业务请求进行决策处理,并将处理结果返还给物理层或是MAC层对象。进而实现了将智能决策功能引入到5G网络下的物理层和MAC层功能中的目的。
下面通过附图和实施例,对本申请的技术方案做进一步的详细描述。
附图说明
构成说明书的一部分的附图描述了本申请的实施例,并且连同描述一起用于解释本申请的原理。
参照附图,根据下面的详细描述,可以更加清楚地理解本申请,其中:
图1为本申请提出的一种业务处理的方法示意图;
图2为本申请提出的应用于业务处理的基站设备的系统架构示意图;
图3-图5为本申请提出的一种业务处理的流程示意图;
图6为本申请提出的业务处理的电子装置的结构示意图;
图7为本申请提出的业务处理的电子设备结构示意图。
具体实施方式
现在将参照附图来详细描述本申请的各种示例性实施例。应注意到:除非另外具体说明,否则在这些实施例中阐述的部件和步骤的相对布置、数字表达式和数值不限制本申请的范围。
同时,应当明白,为了便于描述,附图中所示出的各个部分的尺寸并不是按照实际的比例关系绘制的。
以下对至少一个示例性实施例的描述实际上仅仅是说明性的,不作为对本申请及其应用或使用的任何限制。
对于相关领域普通技术人员已知的技术、方法和设备可能不作详细讨论,但在适当情况下,所述技术、方法和设备应当被视为说明书的一部分。
应注意到:相似的标号和字母在下面的附图中表示类似项,因此,一旦某一项在一个附图中被定义,则在随后的附图中不需要对其进行进一步讨论。
另外,本申请各个实施例之间的技术方案可以相互结合,但是必须是以本领域普通技术人员能够实现为基础,当技术方案的结合出现相互矛盾或无法实现时应当认为这种技术方案的结合不存在,也不在本申请要求的保护范围之内。
需要说明的是,本申请实施例中所有方向性指示(诸如上、下、左、右、前、后……)仅用于解释在某一特定姿态(如附图所示)下各部件之间的相对位置关系、运动情况等,如果该特定姿态发生改变时,则该方向性指示也相应地随之改变。
下面结合图1-图5来描述根据本申请示例性实施方式的用于进行业务处理的方法。需要注意的是,下述应用场景仅是为了便于理解本申请的精神和原理而示出,本申请的实施方式在此方面不受任何限制。相反,本申请的实施方式可以应用于适用的任何场景。
本申请还提出一种业务处理的方法、装置、基站设备及介质。
图1示意性地示出了根据本申请实施方式的一种业务处理的方法的流程示意图。如图1所示,该方法应用于基站设备,包括:
S101,获取与基站设备相关联的目标对象发送的业务处理请求。
相关技术中,5G接入网采用CU-DU分离的逻辑架构,一个gNB包括一个CU 和一个或者多个DU。CU可以通过F1接口与DU相连。DU负责完成RLC/MAC/PHY等实时性要求较高的协议栈处理功能,而CU负责完成PDCP/RRC/SDAP等实时性要求较低的协议栈处理功能。
针对未来业务需求的多样性,需要在接入网中内嵌智能,但是5G网络架构不支持智能的部署。O-RAN架构引入了Near-RT RIC,该近实时无线智能控制器通过E2接口与CU-CP、CU-UP、DU实体相连接,通过E2接口进行集中式数据收集和决策下发。在Near-RT RIC中可以引入智能,采用智能的方法解决无线资源管理功能(除动态无线资源分配)。但是该智能控制器只能负责实时性大于10ms的近实时智能控制。
其中,3Gpp R18中讨论了在物理层和MAC层功能中引入AI算法,如信道编码、定位、信道估计、波束管理、动态无线资源分配以及链路自适应等。MAC层和物理层的智能决策和控制对实时性要求较高一般小于10ms且AI算法所需的数据位于分布式单元DU中。现有的5G网络架构和O-RAN的网络架构不能支持物理层和MAC层智能决策的实时性要求,并且缺乏通用的AI工作流程。
其中,该与基站设备相关联的目标对象可以为该基站设备下的通信网络中的物理层或是MAC层。
S102,将业务处理请求发送给分布式单元DU,并从DU中存储的多个业务处理模型中,选取与业务处理请求相匹配的目标业务处理模型,业务处理模型由基站设备中的集中式单元CU下发至DU;
S103,利用目标业务处理模型对业务处理请求进行业务处理,生成业务处理结果。
S104,将业务处理结果返回给目标对象。
一种方式中,基站设备的CU中可以部署有集中式智能模型模块,该智能模型库可以包括模型存储器、模型管理器、模型转换器,集中式智能模型模块可以与CU共同部署也可以部署在边缘服务器侧。
其中,模型存储器用于存储初始业务处理模型(例如可以为AI/ML模型文件)以及对应的模型相关信息。其中需要说明的是,模型文件包括模型结构文 件和模型参数文件。模型相关信息包括模型功能,以及模型训练和推理所需要输入的数据类型和格式标准。模型管理器用于管理AI/ML模型的上传和下发。模型转换器,将开发者在不同深度学习架构下开发的模型进行格式转换,确保AI/ML模型可以部署在之后介绍的分布式智能控制模块上。
进一步的,如图2所示,基站设备的DU中可以部署有分布式智能控制模块。其中DU可以包括RLC层、MAC层、PHY层等协议栈功能。以及分布式智能控制模块可以使用人工智能方式进行PHY层、MAC层功能的智能决策与预测。
其中,DU还可以包括数据收集器,用于存储训练和推理模型所需数据(即用于训练从CU传送过来的初始业务处理模型)。模型训练引擎,提供模型训练所需的软件环境,利用数据收集器中的训练数据进行模型训练,模型训练完毕之后(即用于对业务处理请求进行业务处理的多个业务处理模型)将模型部署在模型推理引擎中。模型推理引擎,提供模型推理所需的软件环境,部署的模型利用的数据收集器中的推理数据进行模型推理。模型评估器,对模型进行评估,可以综合模型训练的收敛速度以及模型的准确度等进行综合评估。
进一步的,分布式智能控制模块通过接口获取对象设备发送的通过MAC层及物理层的网络低层数据、层一层二测量数据和用户信息,并将这些信息存储在数据收集器中。其中,获取信息的方式可以包括如下方式:分布式智能控制模块通过接口主动发送数据请求信息,分布式智能控制模块向MAC/物理层订阅,周期性或者事件触发性向智能控制器发送MAC层及物理层的信息。
进一步的,本申请中基站设备的MAC层和物理层可以通过接口发送业务处理请求。所述业务处理请求包括:智能信道编码。智能定位。智能信道估计。智能智能波束管理。智能动态无线资源分配。智能链路自适应的其中至少一种等。与请求功能相对应的模型推理引擎利用数据收集器中的推理数据进行推理,并将智能决策/预测结果通过接口三发送至业务处理请求方。
本申请中,可以获取与基站设备相关联的目标对象发送的业务处理请求;将业务处理请求发送给分布式单元DU,并从DU中存储的多个业务处理模型中,选取与业务处理请求相匹配的目标业务处理模型,业务处理模型由基站设备中 的集中式单元CU下发至DU;利用目标业务处理模型对业务处理请求进行业务处理,生成业务处理结果;将业务处理结果返回给目标对象。通过应用本申请的技术方案,可以在基站设备中的DU中部署有多个业务处理模型,从而在接收到与该基站设备相关联的物理层或是MAC层对象发送的业务请求后,可以通过针对性的选取对应的业务模型对该业务请求进行决策处理,并将处理结果返还给物理层或是MAC层对象。进而实现了将智能决策功能引入到5G网络下的物理层和MAC层功能中的目的。
可选的,在本申请一种可能的实施方式中,在所述获取与所述基站设备相关联的目标对象发送的业务处理请求之前,还包括:
接收开发用户上传的多个初始业务处理模型以及模型关联数据;以及,
将所述多个初始业务处理模型以及模型关联数据转换成预设格式后存储到所述CU中,以及在所述CU中为所述多个初始业务处理模型以及模型关联数据生成对应的模型索引;
或,
接收所述开发用户上传的多个已训练完毕的初始业务处理模型。
可选的,在本申请一种可能的实施方式中,在所述在所述CU中为所述多个初始业务处理模型以及模型关联数据生成对应的模型索引之后,还包括:
接收所述DU发送的模型调取请求,所述模型调取请求中包含有所述DU对应的ID参数;
利用所述模型索引,选取所述模型调取请求对应的初始业务处理模型以及模型关联数据;
基于所述ID参数,将所述模型调取请求对应的初始业务处理模型以及模型关联数据发送给所述DU。
可选的,在本申请一种可能的实施方式中,在所述将所述模型调取请求对应的初始业务处理模型以及模型关联数据发送给所述DU之后,还包括:
利用所述DU中存储的训练数据,对所述初始业务处理模型进行模型训练, 生成待评估业务处理模型;
利用所述DU中存储的模型评估模块,对所述待评估业务处理模型进行业务评估,若通过,确定生成所述业务处理模型。
可选的,在本申请一种可能的实施方式中,在所述获取与所述基站设备相关联的目标对象发送的业务处理请求之前,还包括:
接收所述边缘服务器发送的多个初始业务处理模型以及模型关联数据,或,接收所述边缘服务器发送的多个已训练完毕的业务处理模型。
可选的,在本申请一种可能的实施方式中,所述选取与所述业务处理请求相匹配的目标业务处理模型,包括:
基于所述业务处理请求的类别,从所述DU中存储的多个业务处理模型中,选取与所述类别相匹配的目标业务处理模型,其中所述类别包括智能信道编码。智能定位、智能信道估计、智能智能波束管理、智能动态无线资源分配以及智能链路自适应的至少一种。
可选的,在本申请一种可能的实施方式中,所述将所述业务处理请求发送给分布式单元DU,包括:
根据所述业务处理请求的类别,选择通过MAC层或物理层发送给所述DU。
进一步的,以图2进行举例说明,本申请中基站设备的CU中包含集中式智能模型模块以及DU功能实体。
其中,集中式智能控制模块包括模型转换器、模型管理器、模型存储器。如图2所示,集中式智能模型模块与所述DU功能实体通过接口二连接,DU功能实体可以通过接口二发送模型调取请求,模型调取请求中包括DU功能实体的ID号,也可以包括所调取模型对应的模型功能信息。
其中,如图3所示,存储与CU中的集中智能模型模块收到模型调取请求之后,CU中的模型管理器通过模型功能进行模型索引,并后续将对应的初始业务模型下发到相应的DU功能实体中。DU功能实体利用下发的模型进行模型训练和模型推理之后,即可得到待评估业务处理模型,再利用DU中存储的模型评估模块,对待评估业务处理模型进行业务评估通过后,确定生成业务处理模型。
更进一步的,初始业务处理模型的上传如图4所示:
步骤301,开发者通过接口一进行模型的上传至CU,其中上传的数据包括模型文件以及模型相关信息。
步骤302,CU中的模型转换器将上传的初始业务处理模型进行格式转换,统一存储格式。步骤302,模型管理器为多个初始业务处理模型分配存储空间,并且维护一张功能与地址的索引表,便于模型索引。
步骤304,模型存储器将多个初始业务处理模型存储在模型管理器分配的存储空间中。
在进一步的,如图5所示,MAC层/物理层智能功能的实施过程为:MAC层或者物理层通过接口三向DU中的分布式智能控制模块发送业务处理请求,业务处理请求包括智能信道编码、智能定位、智能信道估计、智能智能波束管理、智能动态无线资源分配、智能链路自适应的其中至少一种等。
可以理解的,本申请实施例中可以根据业务处理请求的类别,选择与该类别对应的目标业务处理模型进行对应的业务处理。
其中,DU中的分布式智能控制模块中的相应功能的业务处理模型利用数据收集器中的推理模型进行推理,并将模型推理结果通过接口三发送到业务处理请求方(即目标对象)。
可选的,在本申请的另外一种实施方式中,如图6所示,本申请还提供一种业务处理的装置。其中,应用于基站设备,包括:
获取模块201,被配置为获取与所述基站设备相关联的目标对象发送的业务处理请求;
选取模块202,被配置为将所述业务处理请求发送给分布式单元DU,并从所述DU中存储的多个业务处理模型中,选取与所述业务处理请求相匹配的目标业务处理模型,所述业务处理模型由所述基站设备中的集中式单元CU下发至所述DU;
生成模块203,被配置为利用所述目标业务处理模型对所述业务处理请求进 行业务处理,生成业务处理结果;
发送模块204,被配置为将所述业务处理结果返回给所述目标对象。
本申请中,可以获取与基站设备相关联的目标对象发送的业务处理请求;将业务处理请求发送给分布式单元DU,并从DU中存储的多个业务处理模型中,选取与业务处理请求相匹配的目标业务处理模型,业务处理模型由基站设备中的集中式单元CU下发至DU;利用目标业务处理模型对业务处理请求进行业务处理,生成业务处理结果;将业务处理结果返回给目标对象。通过应用本申请的技术方案,可以在基站设备中的DU中部署有多个业务处理模型,从而在接收到与该基站设备相关联的物理层或是MAC层对象发送的业务请求后,可以通过针对性的选取对应的业务模型对该业务请求进行决策处理,并将处理结果返还给物理层或是MAC层对象。进而实现了将智能决策功能引入到5G网络下的物理层和MAC层功能中的目的。
在本申请的另外一种实施方式中,获取模块201,还包括:
获取模块201,被配置为接收开发用户上传的多个初始业务处理模型以及模型关联数据;以及,
获取模块201,被配置为将所述多个初始业务处理模型以及模型关联数据转换成预设格式后存储到所述CU中,以及在所述CU中为所述多个初始业务处理模型以及模型关联数据生成对应的模型索引;
或,
获取模块201,被配置为接收所述开发用户上传的多个已训练完毕的初始业务处理模型。
在本申请的另外一种实施方式中,获取模块201,还包括:
获取模块201,被配置为接收所述DU发送的模型调取请求,所述模型调取请求中包含有所述DU对应的ID参数以及调取模型功能;
获取模块201,被配置为利用所述模型索引,选取所述调取模型功能对应的初始业务处理模型以及模型关联数据;
获取模块201,被配置为基于所述ID参数,将所述模型调取请求对应的初始业务处理模型以及模型关联数据发送给所述DU。
在本申请的另外一种实施方式中,获取模块201,还包括:
获取模块201,被配置为利用所述DU中存储的训练数据,对所述初始业务处理模型进行模型训练,生成待评估业务处理模型;
获取模块201,被配置为利用所述DU中存储的模型评估模块,对所述待评估业务处理模型进行业务评估,若通过,确定生成所述业务处理模型。
在本申请的另外一种实施方式中,获取模块201,还包括:
获取模块201,被配置为接收所述边缘服务器发送的多个初始业务处理模型以及模型关联数据,或,接收所述边缘服务器发送的多个已训练完毕的业务处理模型。
在本申请的另外一种实施方式中,获取模块201,还包括:
获取模块201,被配置为基于所述业务处理请求的类别,从所述DU中存储的多个业务处理模型中,选取与所述类别相匹配的目标业务处理模型,其中所述类别包括智能信道编码。智能定位、智能信道估计、智能智能波束管理、智能动态无线资源分配以及智能链路自适应的至少一种。
在本申请的另外一种实施方式中,获取模块201,还包括:
获取模块201,被配置为根据所述业务处理请求的类别,选择通过MAC层或物理层发送给所述DU。
图7是根据一示例性实施例示出的一种电子设备的逻辑结构框图。例如,电子设备300可以是移动电话,计算机,数字广播终端,消息收发设备,游戏控制台,平板设备,医疗设备,健身设备,个人数字助理等。
在示例性实施例中,还提供了一种包括指令的非临时性计算机可读存储介质,例如包括指令的存储器,上述指令可由电子设备处理器执行以完成上述业务处理的方法,该方法包括:获取与所述基站设备相关联的目标对象发送的业务处理请求;将所述业务处理请求发送给分布式单元DU,并从所述DU中存储的 多个业务处理模型中,选取与所述业务处理请求相匹配的目标业务处理模型,所述业务处理模型由所述基站设备中的集中式单元CU下发至所述DU;利用所述目标业务处理模型对所述业务处理请求进行业务处理,生成业务处理结果;将所述业务处理结果返回给所述目标对象。可选地,上述指令还可以由电子设备的处理器执行以完成上述示例性实施例中所涉及的其他步骤。例如,非临时性计算机可读存储介质可以是ROM、随机存取存储器(RAM)、CD-ROM、磁带、软盘和光数据存储设备等。
在示例性实施例中,还提供了一种应用程序/计算机程序产品,包括一条或多条指令,该一条或多条指令可以由电子设备的处理器执行,以完成上述业务处理的方法,该方法包括:获取与所述基站设备相关联的目标对象发送的业务处理请求;将所述业务处理请求发送给分布式单元DU,并从所述DU中存储的多个业务处理模型中,选取与所述业务处理请求相匹配的目标业务处理模型,所述业务处理模型由所述基站设备中的集中式单元CU下发至所述DU;利用所述目标业务处理模型对所述业务处理请求进行业务处理,生成业务处理结果;将所述业务处理结果返回给所述目标对象。可选地,上述指令还可以由电子设备的处理器执行以完成上述示例性实施例中所涉及的其他步骤。
图7为计算机设备30的示例图。本领域技术人员可以理解,示意图7仅仅是计算机设备30的示例,并不构成对计算机设备30的限定,可以包括比图示更多或更少的部件,或者组合某些部件,或者不同的部件,例如计算机设备30还可以包括输入输出设备、网络接入设备、总线等。
所称处理器302可以是中央处理单元(Central Processing Unit,CPU),还可以是其他通用处理器、数字信号处理器(Digital Signal Processor,DSP)、专用集成电路(Application Specific Integrated Circuit,ASIC)、现场可编程门阵列(Field-Programmable Gate Array,FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器302也可以是任何常规的处理器等,处理器302是计算机设备30的控制中心,利用各种接口和线路连接整个计算机设备30的各个部分。
存储器301可用于存储计算机可读指令303,处理器302通过运行或执行存储在存储器301内的计算机可读指令或模块,以及调用存储在存储器301内的数据,实现计算机设备30的各种功能。存储器301可主要包括存储程序区和存储数据区,其中,存储程序区可存储操作系统、至少一个功能所需的应用程序(比如声音播放功能、图像播放功能等)等;存储数据区可存储根据计算机设备30的使用所创建的数据等。此外,存储器301可以包括硬盘、内存、插接式硬盘,智能存储卡(Smart Media Card,SMC),安全数字(Secure Digital,SD)卡,闪存卡(Flash Card)、至少一个磁盘存储器件、闪存器件、只读存储器(Read-Only Memory,ROM)、随机存取存储器(Random Access Memory,RAM)或其他非易失性/易失性存储器件。
计算机设备30集成的模块如果以软件功能模块的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储介质中。基于这样的理解,本发明实现上述实施例方法中的全部或部分流程,也可以通过计算机可读指令来指令相关的硬件来完成,的计算机可读指令可存储于一计算机可读存储介质中,该计算机可读指令在被处理器执行时,可实现上述各个方法实施例的步骤。
本领域技术人员在考虑说明书及实践这里公开的发明后,将容易想到本申请的其它实施方案。本申请旨在涵盖本申请的任何变型、用途或者适应性变化,这些变型、用途或者适应性变化遵循本申请的一般性原理并包括本申请未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施例仅被视为示例性的,本申请的真正范围和精神由下面的权利要求指出。
应当理解的是,本申请并不局限于上面已经描述并在附图中示出的精确结构,并且可以在不脱离其范围进行各种修改和改变。本申请的范围仅由所附的权利要求来限制。

Claims (10)

  1. 一种业务处理的方法,其特征在于,应用于基站设备,包括:
    获取与所述基站设备相关联的目标对象发送的业务处理请求;
    将所述业务处理请求发送给分布式单元DU,并从所述DU中存储的多个业务处理模型中,选取与所述业务处理请求相匹配的目标业务处理模型,所述业务处理模型由所述基站设备中的集中式单元CU下发至所述DU;
    利用所述目标业务处理模型对所述业务处理请求进行业务处理,生成业务处理结果;
    将所述业务处理结果返回给所述目标对象。
  2. 如权利要求1所述的方法,其特征在于,在所述获取与所述基站设备相关联的目标对象发送的业务处理请求之前,还包括:
    接收开发用户上传的多个初始业务处理模型以及模型关联数据;以及,
    将所述多个初始业务处理模型以及模型关联数据转换成预设格式后存储到所述CU中,以及在所述CU中为所述多个初始业务处理模型以及模型关联数据生成对应的模型索引;
    或,
    接收所述开发用户上传的多个已训练完毕的初始业务处理模型。
  3. 如权利要求2所述的方法,其特征在于,在所述在所述CU中为所述多个初始业务处理模型以及模型关联数据生成对应的模型索引之后,还包括:
    接收所述DU发送的模型调取请求,所述模型调取请求中包含有所述DU对应的ID参数以及调取模型功能;
    利用所述模型索引,选取所述调取模型功能对应的初始业务处理模型以及模型关联数据;
    基于所述ID参数,将所述模型调取请求对应的初始业务处理模型以及模型 关联数据发送给所述DU。
  4. 如权利要求3所述的方法,其特征在于,在所述将所述模型调取请求对应的初始业务处理模型以及模型关联数据发送给所述DU之后,还包括:
    利用所述DU中存储的训练数据,对所述初始业务处理模型进行模型训练,生成待评估业务处理模型;
    利用所述DU中存储的模型评估模块,对所述待评估业务处理模型进行业务评估,若通过,确定生成所述业务处理模型。
  5. 如权利要求1所述的方法,其特征在于,在所述获取与所述基站设备相关联的目标对象发送的业务处理请求之前,还包括:
    接收所述边缘服务器发送的多个初始业务处理模型以及模型关联数据,或,接收所述边缘服务器发送的多个已训练完毕的业务处理模型。
  6. 如权利要求1所述的方法,其特征在于,所述选取与所述业务处理请求相匹配的目标业务处理模型,包括:
    基于所述业务处理请求的类别,从所述DU中存储的多个业务处理模型中,选取与所述类别相匹配的目标业务处理模型,其中所述类别包括智能信道编码。智能定位、智能信道估计、智能智能波束管理、智能动态无线资源分配以及智能链路自适应的至少一种。
  7. 如权利要求1所述的方法,其特征在于,所述将所述业务处理请求发送给分布式单元DU,包括:
    根据所述业务处理请求的类别,选择通过MAC层或物理层发送给所述DU。
  8. 一种业务处理的装置,其特征在于,应用于基站设备,包括:
    获取模块,被配置为获取与所述基站设备相关联的目标对象发送的业务处 理请求;
    选取模块,被配置为将所述业务处理请求发送给分布式单元DU,并从所述DU中存储的多个业务处理模型中,选取与所述业务处理请求相匹配的目标业务处理模型,所述业务处理模型由所述基站设备中的集中式单元CU下发至所述DU;
    生成模块,被配置为利用所述目标业务处理模型对所述业务处理请求进行业务处理,生成业务处理结果;
    发送模块,被配置为将所述业务处理结果返回给所述目标对象。
  9. 一种电子设备,其特征在于,包括:
    存储器,用于存储可执行指令;以及,
    处理器,用于与所述存储器显示以执行所述可执行指令从而完成权利要求1-7中任一所述业务处理的方法的操作。
  10. 一种计算机可读存储介质,用于存储计算机可读取的指令,其特征在于,所述指令被执行时执行权利要求1-7中任一所述业务处理的方法的操作。
PCT/CN2022/119879 2021-10-29 2022-09-20 业务处理的方法、装置、电子设备及介质 WO2023071616A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111277208.4A CN114153593A (zh) 2021-10-29 2021-10-29 业务处理的方法、装置、电子设备及介质
CN202111277208.4 2021-10-29

Publications (1)

Publication Number Publication Date
WO2023071616A1 true WO2023071616A1 (zh) 2023-05-04

Family

ID=80459134

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/119879 WO2023071616A1 (zh) 2021-10-29 2022-09-20 业务处理的方法、装置、电子设备及介质

Country Status (2)

Country Link
CN (1) CN114153593A (zh)
WO (1) WO2023071616A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114153593A (zh) * 2021-10-29 2022-03-08 北京邮电大学 业务处理的方法、装置、电子设备及介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018049626A1 (zh) * 2016-09-14 2018-03-22 海能达通信股份有限公司 一种业务处理方法、相关设备及系统
CN108934031A (zh) * 2017-05-22 2018-12-04 中兴通讯股份有限公司 数据传输方法、装置、设备及存储介质
CN109526029A (zh) * 2017-09-20 2019-03-26 中国移动通信有限公司研究院 一种业务优化方法、介质、相关装置和设备
CN113225197A (zh) * 2020-01-21 2021-08-06 株式会社Ntt都科摩 基于神经网络模型的通信系统及其配置方法
CN114153593A (zh) * 2021-10-29 2022-03-08 北京邮电大学 业务处理的方法、装置、电子设备及介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018049626A1 (zh) * 2016-09-14 2018-03-22 海能达通信股份有限公司 一种业务处理方法、相关设备及系统
CN108934031A (zh) * 2017-05-22 2018-12-04 中兴通讯股份有限公司 数据传输方法、装置、设备及存储介质
CN109526029A (zh) * 2017-09-20 2019-03-26 中国移动通信有限公司研究院 一种业务优化方法、介质、相关装置和设备
CN113225197A (zh) * 2020-01-21 2021-08-06 株式会社Ntt都科摩 基于神经网络模型的通信系统及其配置方法
CN114153593A (zh) * 2021-10-29 2022-03-08 北京邮电大学 业务处理的方法、装置、电子设备及介质

Also Published As

Publication number Publication date
CN114153593A (zh) 2022-03-08

Similar Documents

Publication Publication Date Title
CN111565418B (zh) 一种o-ran与mec的通信方法及系统
CN112153700B (zh) 一种网络切片资源管理方法及设备
US20200052969A1 (en) Network Slice Management Method and Apparatus
CN114302422B (zh) 利用学习模型进行业务处理的方法以及装置
CN108121608A (zh) 一种队列调度方法以及节点设备
CN107682397A (zh) 客户资源获取方法、装置、终端设备及存储介质
CN109964507B (zh) 网络功能的管理方法、管理单元及系统
CN110268751A (zh) 用于在接入网环境中选择接入和移动性管理功能的方法和系统
WO2021088520A1 (zh) 网络数据分析方法、功能实体及电子设备
CN114302421B (zh) 通信网络架构的生成方法、装置、电子设备及介质
WO2023071616A1 (zh) 业务处理的方法、装置、电子设备及介质
CN111694617B (zh) 网络离线模型的处理方法、人工智能处理装置及相关产品
US20230281513A1 (en) Data model training method and apparatus
CN109729519A (zh) 数据下载的方法及相关装置
CN106649600A (zh) 一种迁移文件权限的方法、装置以及系统
CN114090623A (zh) 一种缓存资源的创建方法、装置、电子设备及存储介质
CN109348434A (zh) 一种场景信息的发送方法、发送装置及终端设备
CN114640599A (zh) 意图的冲突处理方法、装置、存储介质及计算机程序产品
CN113259145B (zh) 网络切片的端到端组网方法、组网装置及网络切片设备
CN112953993B (zh) 资源调度方法、设备、网络系统及存储介质
CN114301907B (zh) 云计算网络中的业务处理方法、系统、装置及电子设备
US8549537B2 (en) Middleware bridge system and method
CN116095074A (zh) 资源分配方法、装置、相关设备及存储介质
WO2023040832A1 (zh) 一种信息传输方法、装置、设备及可读存储介质
WO2023125594A1 (zh) Ai模型传输方法、装置、设备及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22885503

Country of ref document: EP

Kind code of ref document: A1