Method, apparatus, electronic device, and medium for business processing

Abstract

This application discloses a method, apparatus, electronic device, and medium for service processing. In this application, a service processing request sent by a target object associated with a base station device can be obtained; the service processing request can be sent to a distributed unit (DU), and a target service processing model matching the service processing request can be selected from multiple service processing models stored in the DU. The service processing model is distributed from a centralized unit (CU) in the base station device to the DU; the service processing request can be processed using the target service processing model to generate a service processing result; and the service processing result can be returned to the target object.

Description

Technical Field

[0001] This application relates to data processing technology, and in particular to a method, apparatus, electronic device, and medium for business processing. Background Technology

[0002] The 5G access network adopts a logical architecture that separates centralized units (CU) and distributed units (DU). A single base station device (gNB) includes one CU and one or more DUs. The CU can connect to the DU via the F1 interface. The DU is responsible for handling protocol stack processing functions with high real-time requirements, such as RLC / MAC / PHY, while the CU handles protocol stack processing functions with lower real-time requirements, such as PDCP / RRC / SDAP.

[0003] To address the diverse needs of future services, intelligence needs to be embedded in the access network; however, the 5G network architecture does not support intelligent deployment. Therefore, designing a solution within the existing 5G network architecture that can support the real-time requirements of intelligent decision-making at the physical and MAC layers has become a problem that needs to be solved. Summary of the Invention

[0004] This application provides a service processing method, apparatus, electronic device, and medium. According to one aspect of this application, a service processing method is provided, applied to base station equipment, and includes:

[0005] Obtain the service processing request sent by the target object associated with the base station device;

[0006] The service processing request is sent to the distributed unit (DU), and a target service processing model matching the service processing request is selected from multiple service processing models stored in the DU. The service processing model is issued from the centralized unit (CU) in the base station equipment to the DU.

[0007] The target business processing model is used to process the business processing request and generate a business processing result.

[0008] The business processing result is returned to the target object.

[0009] Optionally, in another embodiment based on the method described above in this application, before obtaining the service processing request sent by the target object associated with the base station device, the method further includes:

[0010] Receives multiple initial business processing models and model-related data uploaded by developers; and,

[0011] The multiple initial business processing models and model-related data are converted into a preset format and stored in the CU, and corresponding model indexes are generated in the CU for the multiple initial business processing models and model-related data.

[0012] or,

[0013] Receive multiple pre-trained initial business processing models uploaded by the development user.

[0014] Optionally, in another embodiment based on the method described above in this application, after generating corresponding model indexes for the plurality of initial business processing models and model-related data in the CU, the method further includes:

[0015] Receive the model retrieval request sent by the DU, wherein the model retrieval request contains the ID parameter corresponding to the DU;

[0016] Using the model index, select the initial business processing model and model-related data corresponding to the model retrieval request;

[0017] Based on the ID parameter, the initial business processing model corresponding to the model retrieval request and the model association data are sent to the DU.

[0018] Optionally, in another embodiment based on the method described above, after sending the initial business processing model corresponding to the model retrieval request and the model association data to the DU, the method further includes:

[0019] Using the training data stored in the DU, the initial business processing model is trained to generate a business processing model to be evaluated.

[0020] The model evaluation module stored in the DU is used to evaluate the business processing model to be evaluated. If the evaluation passes, the business processing model is generated.

[0021] Optionally, in another embodiment based on the method described above in this application, before obtaining the service processing request sent by the target object associated with the base station device, the method further includes:

[0022] Receive multiple initial business processing models and model association data sent by the edge server, or receive multiple trained business processing models sent by the edge server.

[0023] Optionally, in another embodiment based on the method described above in this application, selecting the target business processing model that matches the business processing request includes:

[0024] Based on the category of the service processing request, a target service processing model matching the category is selected from multiple service processing models stored in the DU, wherein the category includes at least one of intelligent channel coding, intelligent positioning, intelligent channel estimation, intelligent beam management, intelligent dynamic radio resource allocation, and intelligent link adaptation.

[0025] Optionally, in another embodiment based on the method described above in this application, sending the service processing request to the distributed unit (DU) includes:

[0026] Depending on the type of the service processing request, it is selected to send it to the DU via the MAC layer or the physical layer.

[0027] According to another aspect of the embodiments of this application, a service processing apparatus is provided, applied to base station equipment, comprising:

[0028] The acquisition module is configured to acquire service processing requests sent by a target object associated with the base station device;

[0029] 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 sent from the centralized unit (CU) in the base station equipment to the DU.

[0030] The generation module is configured to perform business processing on the business processing request using the target business processing model and generate a business processing result.

[0031] The sending module is configured to return the business processing result to the target object.

[0032] According to another aspect of the embodiments of this application, an electronic device is provided, comprising:

[0033] Memory, used to store executable instructions; and

[0034] A display for showing, in conjunction with the memory, the operation of a method for executing the executable instructions to complete any of the aforementioned business processes.

[0035] According to another aspect of the embodiments of this application, a computer-readable storage medium is provided for storing computer-readable instructions, which, when executed, perform the operation of any of the above-described business processing methods.

[0036] In this application, a service processing request sent by a target object associated with a base station device can be obtained; the service processing request is sent to a distributed unit (DU), and a target service processing model matching the service processing request is selected from multiple service processing models stored in the DU. The service processing model is distributed from the centralized unit (CU) in the base station device to the DU; the service processing request is processed using the target service processing model to generate a service processing result; and the service processing result is returned to the target object. By applying the technical solution of this application, multiple service processing models can be deployed in the DU of the base station device. Therefore, upon receiving a service request sent by a physical layer or MAC layer object associated with the base station device, the corresponding service model can be selected to make a decision on the service request, and the processing result can be returned to the physical layer or MAC layer object. This achieves the goal of introducing intelligent decision-making functionality into the physical layer and MAC layer functions of the 5G network.

[0037] The technical solution of this application will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0038] The accompanying drawings, which form part of this specification, illustrate embodiments of this application and, together with the description, serve to explain the principles of this application.

[0039] This application can be more clearly understood with reference to the accompanying drawings and the following detailed description, wherein:

[0040] Figure 1 This is a schematic diagram of a business processing method proposed in this application;

[0041] Figure 2 This is a schematic diagram of the system architecture of the base station equipment used for service processing proposed in this application;

[0042] Figures 3-5 This is a flowchart illustrating a business process proposed in this application;

[0043] Figure 6 A schematic diagram of the electronic device for business processing proposed in this application;

[0044] Figure 7 This is a schematic diagram of the electronic device structure for the business processing proposed in this application. Detailed Implementation

[0045] Various exemplary embodiments of the present application will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of the present application.

[0046] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0047] The following description of at least one exemplary embodiment is merely illustrative and is not intended to limit the scope of this application or its application or use.

[0048] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0049] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0050] Furthermore, the technical solutions of the various embodiments of this application can be combined with each other, but only if they are based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such combination of technical solutions does not exist and is not within the scope of protection claimed by this application.

[0051] It should be noted that all directional indicators (such as up, down, left, right, front, back, etc.) in the embodiments of this application are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicator will also change accordingly.

[0052] The following is combined with Figures 1-5 This application describes a method for performing business processing according to exemplary embodiments thereof. It should be noted that the following application scenarios are shown only to facilitate understanding of the spirit and principles of this application, and the embodiments of this application are not limited in any way. Rather, the embodiments of this application can be applied to any applicable scenario.

[0053] This application also proposes a service processing method, apparatus, base station equipment, and medium.

[0054] Figure 1 A schematic flowchart illustrating a business processing method according to an embodiment of this application is shown. Figure 1 As shown, this method is applied to base station equipment and includes:

[0055] S101, Obtain the service processing request sent by the target object associated with the base station equipment.

[0056] In related technologies, 5G access networks adopt a logical architecture of CU-DU separation, where a gNB includes one CU and one or more DUs. The CU can connect to the DU via the F1 interface. The DU is responsible for handling protocol stack processing functions with high real-time requirements, such as RLC / MAC / PHY, while the CU is responsible for handling protocol stack processing functions with lower real-time requirements, such as PDCP / RRC / SDAP.

[0057] To address the diverse needs of future services, intelligence needs to be embedded in the access network; however, the 5G network architecture does not support intelligent deployment. The O-RAN architecture introduces the Near-RT RIC, a near real-time radio intelligent controller that connects to CU-CP, CU-UP, and DU entities via the E2 interface for centralized data collection and decision-making. Intelligence can be introduced into the Near-RT RIC to address radio resource management functions (excluding dynamic radio resource allocation). However, this intelligent controller can only handle near real-time intelligent control with a timeframe greater than 10ms.

[0058] 3GppR18 discusses the introduction of AI algorithms into physical and MAC layer functions, such as channel coding, localization, channel estimation, beam management, dynamic radio resource allocation, and link adaptation. Intelligent decision-making and control at the MAC and physical layers require high real-time performance, typically less than 10ms, and the data needed for AI algorithms resides in distributed units (DUs). Existing 5G and O-RAN network architectures cannot support the real-time requirements of intelligent decision-making at the physical and MAC layers and lack a universal AI workflow.

[0059] The target object associated with the base station equipment can be the physical layer or MAC layer of the communication network under the base station equipment.

[0060] S102, the service processing request is sent to the distributed unit DU, and the target service processing model that matches the service processing request is selected from the multiple service processing models stored in the DU. The service processing model is sent from the centralized unit CU in the base station equipment to the DU.

[0061] S103: Use the target business processing model to process the business processing request and generate the business processing result.

[0062] S104 returns the business processing result to the target object.

[0063] In one approach, a centralized intelligent model module can be deployed in the CU of the base station equipment. This intelligent model library may include a model storage, a model manager, and a model converter. The centralized intelligent model module can be deployed together with the CU or deployed on the edge server side.

[0064] The model storage unit stores the initial business processing model (e.g., an AI / ML model file) and corresponding model-related information. It's important to note that the model file includes both a model structure file and a model parameter file. Model-related information includes model functionality and the data types and format standards required for model training and inference. The model manager manages the uploading and distribution of AI / ML models. The model converter converts the formats of models developed by developers under different deep learning architectures, ensuring that AI / ML models can be deployed on the distributed intelligent control module, which will be discussed later.

[0065] Furthermore, such as Figure 2 As shown, a distributed intelligent control module can be deployed in the DU (Distributed Intelligent Control Unit) of the base station equipment. The DU can include protocol stack functions such as the RLC layer, MAC layer, and PHY layer. The distributed intelligent control module can use artificial intelligence to make intelligent decisions and predictions for the PHY and MAC layer functions.

[0066] The DU may further include a data collector for storing data needed for training and inference models (i.e., for training the initial business processing model transferred from the CU). A model training engine provides the software environment required for model training, using the training data from the data collector to train the model. After training (i.e., multiple business processing models used to process business requests), the model is deployed in the model inference engine. The model inference engine provides the software environment required for model inference; the deployed model uses the inference data from the data collector for model inference. A model evaluator evaluates the model, providing a comprehensive assessment based on factors such as the model's training convergence speed and accuracy.

[0067] Furthermore, the distributed intelligent control module acquires low-level network data, layer 1 and 2 measurement data, and user information sent by the target device through the MAC and physical layers via an interface, and stores this information in the data collector. The methods for acquiring information may include: the distributed intelligent control module actively sending data request information through the interface; the distributed intelligent control module subscribing to the MAC / physical layer; and periodically or event-triggered sending MAC and physical layer information to the intelligent controller.

[0068] Furthermore, in this application, the MAC layer and physical layer of the base station equipment can send service processing requests through an interface. The service processing requests include at least one of the following: intelligent channel coding, intelligent positioning, intelligent channel estimation, intelligent beam management, intelligent dynamic radio resource allocation, and intelligent link adaptation. The model inference engine corresponding to the requested function performs inference using inference data from the data collector and sends the intelligent decision / prediction results to the service processing requester through interface three.

[0069] In this application, a service processing request sent by a target object associated with a base station device can be obtained; the service processing request is sent to a distributed unit (DU), and a target service processing model matching the service processing request is selected from multiple service processing models stored in the DU. The service processing model is distributed from the centralized unit (CU) in the base station device to the DU; the service processing request is processed using the target service processing model to generate a service processing result; and the service processing result is returned to the target object. By applying the technical solution of this application, multiple service processing models can be deployed in the DU of the base station device. Therefore, upon receiving a service request sent by a physical layer or MAC layer object associated with the base station device, the corresponding service model can be selected to make a decision on the service request, and the processing result can be returned to the physical layer or MAC layer object. This achieves the goal of introducing intelligent decision-making functionality into the physical layer and MAC layer functions of the 5G network.

[0070] Optionally, in one possible implementation of this application, before obtaining the service processing request sent by the target object associated with the base station device, the method further includes:

[0071] Receives multiple initial business processing models and model-related data uploaded by developers; and,

[0072] The multiple initial business processing models and model-related data are converted into a preset format and stored in the CU, and corresponding model indexes are generated in the CU for the multiple initial business processing models and model-related data.

[0073] or,

[0074] Receive multiple pre-trained initial business processing models uploaded by the development user.

[0075] Optionally, in one possible implementation of this application, after generating corresponding model indexes for the plurality of initial business processing models and model-related data in the CU, the method further includes:

[0076] Receive the model retrieval request sent by the DU, wherein the model retrieval request contains the ID parameter corresponding to the DU;

[0077] Using the model index, select the initial business processing model and model-related data corresponding to the model retrieval request;

[0078] Based on the ID parameter, the initial business processing model corresponding to the model retrieval request and the model association data are sent to the DU.

[0079] Optionally, in one possible implementation of this application, after sending the initial business processing model corresponding to the model retrieval request and the model association data to the DU, the method further includes:

[0080] Using the training data stored in the DU, the initial business processing model is trained to generate a business processing model to be evaluated.

[0081] The model evaluation module stored in the DU is used to evaluate the business processing model to be evaluated. If the evaluation passes, the business processing model is generated.

[0082] Optionally, in one possible implementation of this application, before obtaining the service processing request sent by the target object associated with the base station device, the method further includes:

[0083] Receive multiple initial business processing models and model association data sent by the edge server, or receive multiple trained business processing models sent by the edge server.

[0084] Optionally, in one possible implementation of this application, selecting a target business processing model that matches the business processing request includes:

[0085] Based on the category of the service processing request, a target service processing model matching the category is selected from multiple service processing models stored in the DU, wherein the category includes at least one of intelligent channel coding, intelligent positioning, intelligent channel estimation, intelligent beam management, intelligent dynamic radio resource allocation, and intelligent link adaptation.

[0086] Optionally, in one possible implementation of this application, sending the service processing request to the distributed unit (DU) includes:

[0087] Depending on the type of the service processing request, it is selected to send it to the DU via the MAC layer or the physical layer.

[0088] Furthermore, with Figure 2 As an example, the CU of the base station equipment in this application includes a centralized intelligent model module and a DU functional entity.

[0089] The centralized intelligent control module includes a model converter, a model manager, and a model storage. For example... Figure 2 As shown, the centralized intelligent model module is connected to the DU functional entity through interface two. The DU functional entity can send a model retrieval request through interface two. The model retrieval request includes the ID number of the DU functional entity, and may also include the model function information corresponding to the retrieved model.

[0090] Among them, such as Figure 3 As shown, after the centralized intelligent model module in the storage unit (CU) receives a model retrieval request, the model manager in the CU indexes the model using the model function and subsequently distributes the corresponding initial business model to the relevant functional unit (DU). The DU functional unit then uses the distributed model for training and inference to obtain the business processing model to be evaluated. Finally, using the model evaluation module stored in the DU, the business processing model to be evaluated undergoes a business evaluation. Once the evaluation is passed, the generated business processing model is determined.

[0091] Furthermore, the upload of the initial business processing model, such as... Figure 4 As shown:

[0092] Step 301: The developer uploads the model to CU through Interface 1. The uploaded data includes the model file and related model information.

[0093] Step 302: The model converter in the CU converts the uploaded initial business processing models to a uniform storage format. Step 302: The model manager allocates storage space for multiple initial business processing models and maintains an index table of functions and addresses for easy model indexing.

[0094] Step 304: The model storage stores multiple initial business processing models in the storage space allocated by the model manager.

[0095] Furthermore, such as Figure 5 As shown, the implementation process of the MAC layer / physical layer intelligent functions is as follows: the MAC layer or physical layer sends a service processing request through the distributed intelligent control module in the three-way DU interface. The service processing request includes at least one of the following: intelligent channel coding, intelligent positioning, intelligent channel estimation, intelligent beam management, intelligent dynamic radio resource allocation, and intelligent link adaptation.

[0096] It is understood that in this embodiment of the application, the target business processing model corresponding to the category of the business processing request can be selected to perform the corresponding business processing.

[0097] In DU, the business processing model of the corresponding function in the distributed intelligent control module uses the inference model in the data collector to perform inference, and sends the model inference result to the business processing requester (i.e., the target object) through interface three.

[0098] Optionally, in another embodiment of this application, such as Figure 6 As shown, this application also provides a service processing apparatus. This apparatus, applied to base station equipment, includes:

[0099] The acquisition module 201 is configured to acquire service processing requests sent by a target object associated with the base station device;

[0100] The selection module 202 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 sent from the centralized unit CU in the base station equipment to the DU.

[0101] The generation module 203 is configured to perform business processing on the business processing request using the target business processing model and generate a business processing result;

[0102] The sending module 204 is configured to return the business processing result to the target object.

[0103] In this application, a service processing request sent by a target object associated with a base station device can be obtained; the service processing request is sent to a distributed unit (DU), and a target service processing model matching the service processing request is selected from multiple service processing models stored in the DU. The service processing model is distributed from the centralized unit (CU) in the base station device to the DU; the service processing request is processed using the target service processing model to generate a service processing result; and the service processing result is returned to the target object. By applying the technical solution of this application, multiple service processing models can be deployed in the DU of the base station device. Therefore, upon receiving a service request sent by a physical layer or MAC layer object associated with the base station device, the corresponding service model can be selected to make a decision on the service request, and the processing result can be returned to the physical layer or MAC layer object. This achieves the goal of introducing intelligent decision-making functionality into the physical layer and MAC layer functions of the 5G network.

[0104] In another embodiment of this application, the acquisition module 201 further includes:

[0105] Module 201 is configured to receive multiple initial business processing models and model-related data uploaded by the developer user; and,

[0106] The acquisition module 201 is configured to convert the plurality of initial business processing models and model-related data into a preset format and store them in the CU, and to generate corresponding model indexes for the plurality of initial business processing models and model-related data in the CU.

[0107] or,

[0108] The acquisition module 201 is configured to receive multiple trained initial business processing models uploaded by the development user.

[0109] In another embodiment of this application, the acquisition module 201 further includes:

[0110] The acquisition module 201 is configured to receive a model retrieval request sent by the DU, wherein the model retrieval request includes the ID parameter corresponding to the DU and the function to retrieve the model;

[0111] The acquisition module 201 is configured to use the model index to select the initial business processing model and model-related data corresponding to the model retrieval function;

[0112] The acquisition module 201 is configured to send the initial business processing model corresponding to the model retrieval request and the model association data to the DU based on the ID parameter.

[0113] In another embodiment of this application, the acquisition module 201 further includes:

[0114] The acquisition module 201 is configured to use the training data stored in the DU to train the initial business processing model and generate a business processing model to be evaluated.

[0115] The acquisition module 201 is configured to use the model evaluation module stored in the DU to perform a business evaluation on the business processing model to be evaluated, and if it passes, determine that the business processing model is generated.

[0116] In another embodiment of this application, the acquisition module 201 further includes:

[0117] The acquisition module 201 is configured to receive multiple initial business processing models and model association data sent by the edge server, or to receive multiple trained business processing models sent by the edge server.

[0118] In another embodiment of this application, the acquisition module 201 further includes:

[0119] The acquisition module 201 is configured to select a target service processing model that matches the category of the service processing request from multiple service processing models stored in the DU, wherein the category includes at least one of intelligent channel coding, intelligent positioning, intelligent channel estimation, intelligent beam management, intelligent dynamic radio resource allocation, and intelligent link adaptation.

[0120] In another embodiment of this application, the acquisition module 201 further includes:

[0121] The acquisition module 201 is configured to select whether to send the service processing request to the DU via the MAC layer or the physical layer, depending on the type of the service processing request.

[0122] Figure 7 This is a logical structure block diagram of an electronic device according to an exemplary embodiment. For example, the electronic device 300 may be a mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, medical device, fitness equipment, personal digital assistant, etc.

[0123] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory including instructions, wherein the instructions can be executed by an electronic device processor to complete the above-described service processing method. The method includes: acquiring a service processing request sent by a target object associated with the base station device; sending the service processing request to a distributed unit (DU), and selecting a target service processing model matching the service processing request from a plurality of service processing models stored in the DU, wherein the service processing model is issued to the DU by a centralized unit (CU) in the base station device; performing service processing on the service processing request using the target service processing model to generate a service processing result; and returning the service processing result to the target object. Optionally, the instructions can also be executed by an electronic device processor to complete other steps involved in the above exemplary embodiment. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0124] In an exemplary embodiment, an application / computer program product is also provided, including one or more instructions that can be executed by a processor of an electronic device to complete the above-described service processing method. The method includes: acquiring a service processing request sent by a target object associated with the base station device; sending the service processing request to a distributed unit (DU), and selecting a target service processing model matching the service processing request from a plurality of service processing models stored in the DU, wherein the service processing model is issued to the DU by a centralized unit (CU) in the base station device; performing service processing on the service processing request using the target service processing model to generate a service processing result; and returning the service processing result to the target object. Optionally, the above instructions can also be executed by a processor of an electronic device to complete other steps involved in the above exemplary embodiment.

[0125] Figure 7 This is an example diagram of computer device 30. Those skilled in the art will understand that it is illustrative. Figure 7This is merely an example of computer device 30 and does not constitute a limitation on computer device 30. It may include more or fewer components than shown, or combine certain components, or different components. For example, computer device 30 may also include input / output devices, network access devices, buses, etc.

[0126] The processor 302 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor, or processor 302 may be any conventional processor. Processor 302 is the control center of the computer device 30, connecting all parts of the computer device 30 via various interfaces and lines.

[0127] The memory 301 can be used to store computer-readable instructions 303. The processor 302 implements various functions of the computer device 30 by running or executing the computer-readable instructions or modules stored in the memory 301 and calling the data stored in the memory 301. The memory 301 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the computer device 30, etc. In addition, the memory 301 may include a hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, read-only memory (ROM), random access memory (RAM), or other non-volatile / volatile storage devices.

[0128] If the modules integrated in the computer device 30 are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by instructing related hardware through computer-readable instructions. The computer-readable instructions can be stored in a computer-readable storage medium, and when executed by a processor, the computer-readable instructions can implement the steps of the various method embodiments described above.

[0129] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0130] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for business processing, characterized in that, Base station equipment used in 5G networks includes: Obtain the service processing request sent by the target object associated with the base station device; The service processing request is sent to the distributed unit (DU), and a target service processing model matching the service processing request is selected from multiple service processing models stored in the DU. The service processing model is issued from the centralized unit (CU) in the base station equipment to the DU. The target business processing model is used to process the business processing request and generate a business processing result. The business processing result is returned to the target object; The CU is equipped with a model memory for storing the initial business processing model and the corresponding model-related information. The DU also includes a model training engine and a model inference engine. The model training engine is used to train the model using training data, and the model inference engine is used to perform model inference using inference data. The target object is the physical layer or MAC layer in the communication network under the base station equipment; the DU is equipped with a distributed intelligent control module, and the DU includes the MAC layer and the physical layer protocol stack functions. The distributed intelligent control module uses artificial intelligence to make intelligent decisions and predictions for the physical layer and MAC layer functions; the distributed intelligent control module subscribes to the physical layer or MAC layer, and periodically or event-triggeredly sends information of the MAC layer and physical layer to the distributed intelligent control module; the model inference engine of the corresponding function in the distributed intelligent control module uses inference data in the data collector to perform inference, and sends the service processing results to the target object.

2. The method as described in claim 1, characterized in that, Before obtaining the service processing request sent by the target object associated with the base station device, the method further includes: Receives multiple initial business processing models and model-related data uploaded by developers; and, The multiple initial business processing models and model-related data are converted into a preset format and stored in the CU, and corresponding model indexes are generated in the CU for the multiple initial business processing models and model-related data. or, Receive multiple pre-trained initial business processing models uploaded by the development user.

3. The method as described in claim 2, characterized in that, After generating corresponding model indexes for the multiple initial business processing models and model-related data in the CU, the method further includes: Receive the model retrieval request sent by the DU, the model retrieval request containing the ID parameter corresponding to the DU and the function to retrieve the model; Using the model index, select the initial business processing model and model-related data corresponding to the model retrieval function; Based on the ID parameter, the initial business processing model corresponding to the model retrieval request and the model association data are sent to the DU.

4. The method as described in claim 3, characterized in that, After sending the initial business processing model corresponding to the model retrieval request and the model association data to the DU, the method further includes: Using the training data stored in the DU, the initial business processing model is trained to generate a business processing model to be evaluated. The model evaluation module stored in the DU is used to evaluate the business processing model to be evaluated. If the evaluation passes, the business processing model is generated.

5. The method as described in claim 1, characterized in that, Before obtaining the service processing request sent by the target object associated with the base station device, the method further includes: Receive multiple initial business processing models and model association data sent by the edge server, or receive multiple trained business processing models sent by the edge server.

6. The method as described in claim 1, characterized in that, The selection of the target business processing model that matches the business processing request includes: Based on the category of the service processing request, a target service processing model matching the category is selected from multiple service processing models stored in the DU, wherein the category includes at least one of intelligent channel coding, intelligent positioning, intelligent channel estimation, intelligent beam management, intelligent dynamic radio resource allocation, and intelligent link adaptation.

7. The method as described in claim 1, characterized in that, Sending the service processing request to the distributed unit (DU) includes: Depending on the type of the service processing request, it is selected to send it to the DU via the MAC layer or the physical layer.

8. A business processing apparatus, characterized in that, Base station equipment used in 5G networks includes: The acquisition module is configured to acquire service processing requests 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 sent from the centralized unit (CU) in the base station equipment to the DU. The generation module is configured to perform business processing on the business processing request using the target business processing model and generate a business processing result. The sending module is configured to return the business processing result to the target object; The CU is equipped with a model memory for storing the initial business processing model and the corresponding model-related information. The DU also includes a model training engine and a model inference engine. The model training engine is used to train the model using training data, and the model inference engine is used to perform model inference using inference data. The target object is the physical layer or MAC layer in the communication network under the base station equipment; the DU is equipped with a distributed intelligent control module, and the DU includes the MAC layer and the physical layer protocol stack functions. The distributed intelligent control module uses artificial intelligence to make intelligent decisions and predictions for the physical layer and MAC layer functions; the distributed intelligent control module subscribes to the physical layer or MAC layer, and periodically or event-triggeredly sends information of the MAC layer and physical layer to the distributed intelligent control module; the model inference engine of the corresponding function in the distributed intelligent control module uses inference data in the data collector to perform inference, and sends the service processing results to the target object.

9. An electronic device, characterized in that, include: Memory, used to store executable instructions; as well as, A processor configured to interact with the memory to execute the executable instructions to perform the operation of the method of any of claims 1-7.

10. A computer-readable storage medium for storing computer-readable instructions, characterized in that, When the instruction is executed, it performs the operation of the business processing method described in any one of claims 1-7.

Images