Data preparation in wireless communication system

Abstract

A data preparation configuration entity in a wireless communication system is provided. The data preparation configuration entity comprises a transceiver arranged to receive (910) a request for application layer data processing management, the request comprising a requirement for managing raw data from at least one data source. The data preparation configuration entity comprises a processor arranged to configure (920) at least one parameter of the data preparation configuration based on a request for application layer data processing management, the at least one parameter comprising information for preparing required data. The invention also relates to a data preparation entity.

Description

Technical Field

[0001] The subject matter disclosed herein generally relates to the field of implementing data preparation in a wireless communication system. In particular, the subject matter disclosed herein relates to implementing data preparation in a wireless communication platform (such as in an application enabling layer). The present specification defines in a wireless communication network: a data preparation configuration entity; a data preparation entity; a method in a data preparation configuration entity; and a method in a data preparation entity. Background Art

[0002] Analytics and artificial intelligence (AI) / machine learning (ML) are deployed in the 5G core network through the introduction of the network data analysis function (NWDAF). Consider supporting various analysis types, which can be distinguished using different analysis IDs (e.g. "UE mobility", "NF load"), which is further elaborated in the 3rd Generation Partnership Project (3GPP) technical specification TS23.288.

[0003] Each NWDAF can support one or more analysis IDs and can have the following roles: AI / ML reasoning, referred to as NWDAF analysis logic function (AnLF); AI / ML training, referred to as NWDAF model training logic function (MTLF); or both. NWDAF AnLF (or simply AnLF) and NWDAF MTLF (or simply MTLF) represent logic functions deployed individually or in combination. An AnLF that supports reasoning for a specific analysis ID using an AI / ML model subscribes to the corresponding MTLF, which is responsible for training the same AI / ML model used for the corresponding analysis ID.

[0004] The analysis IDs contained in the NWDAF rely on various data input sources, including data from 5G core network functions (NFs), application functions (AFs), 5G core repositories (e.g., network repository functions (NRFs), user data managers (UDMs), etc.), and operation management and maintenance (OAM) data (e.g., performance measurement (PM) / KPIs, configuration management (CM) data, alarms, etc.). The analysis IDs contained in the AnLF can provide analysis output results to the 5G core NFs, AFs, 5G core repositories (e.g., UDMs, user data repositories (UDRs), analysis data repository functions (ADRFs), or OAM management services (MnS) consumers or management functions (MFs)). The MTLF and the AnLF can exchange AI / ML models (e.g., via serialization, containerization, etc.), including relevant model information. Optionally, a data collection coordination function (DCCF) and a messaging framework adapter function (MFAF) can be involved to distribute and collect duplicate data to and from various data sources.

[0005] In addition, analytics (which may be ML-enabled) are provided at the edge / application side, at the Application Data Analytics Enabler Service (ADAES defined in 3GPP TR 23.700-36), or generally at the application side (Vertical Application Layer (VAL) server or application), where data may be collected by multiple data sources including 5GC, OAM, MEC, VAL layer, User Equipment (UE). In some deployments, the ADAE server may reuse the existing 3GPP data analytics framework for data collection coordination, delivery, and storage.

[0006] Data preparation is a necessary step in the ML model lifecycle and is the process of preparing raw data for further processing and analysis. Key steps include collecting, cleaning, and labeling raw data into a form suitable for machine learning (ML) algorithms, and then exploring and visualizing the data. According to ORAN (O-RAN.WG2.AIML v01.03), data preparation depends on the use case (i.e., analysis type) and AI / ML model architecture adopted, and may have an impact on model performance.

[0007] Data preparation may also be used if similar data from heterogeneous data sources requires some preparation before being exposed to the data consumer. This may require ensuring data quality, and if data is missing, proactively performing data recovery mechanisms to avoid data consumers (e.g., which may be analysis functions or optimization functions) having some impact from possible data quality issues. For example, a VAL server or UE may provide QoE data; SEALDD may provide QoE data; and OAM may also provide KPI monitoring data. Data preparation may format / process data received from different sources and may provide a unified set of data with the required data characteristics. Summary of the invention

[0008] When adopting ML-enabled analytics in 3GPP, some data preparation needs to be considered, especially due to the fact that various data are collected from different types of sources, including UEs, network functions, management entities, applications. Such data can be used for ML model training and / or inference, and it is necessary to ensure that the quality of the data is optimal to avoid model drift.

[0009] However, currently, in the 3GPP architecture (considering both SA2 and SA6), there is no consideration about data preparation, which is the first step of analysis and significantly affects the analysis performance. Data preparation is responsible for (i) understanding the characteristics of the data, i.e., collecting information about the data, such as data type, range, etc., (ii) determining whether the data suffers from quality issues, such as errors or missing values, and handling them, and (iii) formatting and labeling the data, and also preparing the data set for training purposes. Data preparation can pre-process the raw data from UE, network and application sources into a data format that can be provided for both AI / ML model training and inference stages. The raw data source can include the following types of data: Numbers - values ​​of real data that allow arithmetic operations; Intervals - values ​​that allow sorting and subtraction, such as time windows; Ordinal - values ​​that allow sorting but not arithmetic operations, such as Quality of Experience (QoS) as low, medium, high; Boolean - binary values, such as 0 and 1; Category - a set of finite values ​​that cannot be sorted or perform arithmetic operations, such as UE, MICO; Text - free-form text data, such as names or identifiers.

[0010] Data preparation may also require guidance to provide support on how to handle low data quality based on: i) analysis of data characteristics, ii) types of AI / ML models using such data, iii) availability of external tools or data sources. Such guidance may rely on input provided by 5G NF, AF including third parties, and other network tools.

[0011] Implementation-specific solutions may rely on pre-configured or “closed” mechanisms to handle data preparation, or may be vendor-specific. However, pre-configured, “closed” or vendor-specific solutions may not be able to handle unknown problems and may introduce overhead for preparing data that can only be used by a specific NWDAF and cannot be shared with other vendors. Data preparation may also cover two types of NWDAFs, namely MTLF for training and AnLF for inference, which may be deployed by different vendors. Therefore, the configuration of data preparation may need to be coordinated, and if no dedicated functionality exists, such logic needs to exist at both MTLF and AnLF, introducing higher overhead. In addition, implementation-specific solutions limit the interaction with other tools (e.g., digital twins or sandboxes), or with 5G NFs, AFs from third parties, and OAM (which may be provided by different management participants).

[0012] In summary, poor and inaccurate data preparation can degrade the performance of AI / ML introducing model drift, while data preparation with open controls can be customized based on the type of data, the use of the data for a given analytical event, the type of consumer, and the data source profile.

[0013] Although the concepts of formatting and / or processing in the current 3GPP architecture are introduced in DCCF / MFAF, as described in TS23.288 clause 5A.4, which can be provided by the data consumer in the request, formatting and / or processing do not involve data preparation. Formatting determines when a notification is sent to the consumer, for example, considering the time of an event trigger, and this process has nothing to do with transforming the data into a shape that is useful for AI / ML models. On the other hand, processing instructions allow notifications to be aggregated to reduce the amount of data reported to the data consumer. The result of processing is the aggregation of information from multiple notifications into a common report. Therefore, processing also focuses on data collection optimization rather than data preparation for use with AI / ML models.

[0014] Additionally, while the concept of data preparation is introduced in ITU-T Y.3172 (06 / 2019) as a preprocessor node or logical entity responsible for cleaning data, aggregating data, or performing any other preprocessing required for the data to be in an appropriate form so that the ML model can use it. ITU-T Y.3172 mainly discusses ML pipeline control, i.e., how to combine preprocessors with other ML related entities. However, the introduction of a data preparation entity including corresponding controls with standardized interfaces to control data preparation (i.e., allowing access and interaction with other NFs, AFs, OAMs, tools, and third parties) remains an open problem. Such data preparation and control can provide data sharing between various analysis functions (ADAES, NWDAF) and can enhance solution options when data preparation faces data quality issues. In addition, data preparation is a challenging task for the case when the UE is the data source for real-time data, which requires intelligent and policy-based configuration to ensure that the data collection from the UE is sufficient and provided to the network side in a timely manner to allow accurate predictions.

[0015] The present invention discloses a data preparation process in a wireless communication system. The above process can be implemented by the following items: a data preparation configuration entity in a wireless communication system; a data preparation entity in a wireless communication system; a method in a data preparation configuration entity, the data preparation configuration entity is located in the wireless communication system; and a method in a data preparation entity, the data preparation entity is located in the wireless communication system.

[0016] A data preparation configuration entity in a wireless communication system is provided, the data preparation configuration entity comprising: a transceiver arranged to receive a request for application layer data processing management, the request comprising a requirement for managing raw data from at least one data source; and a processor arranged to configure at least one parameter of the data preparation configuration based on the request for application layer data processing management, the at least one parameter comprising information for preparing required data.

[0017] A data preparation entity in a wireless communication system is also provided, the data preparation entity comprising: a transceiver arranged to receive a data preparation configuration, the data preparation configuration comprising at least one parameter, the at least one parameter comprising information for preparing required data, the required data being required from at least one data source, wherein the transceiver is also arranged to receive raw data from at least one data source; a processor arranged to process the raw data based on the data preparation configuration; and wherein the processor is also arranged to control the transceiver to send a report indicating data quality issues with the raw data and / or processed data.

[0018] A method in a data preparation configuration entity is also provided, the data preparation configuration entity being located in a wireless communication system, the method comprising: receiving a request for application layer data processing management, the request comprising a requirement for managing raw data from at least one data source; and configuring at least one parameter of the data preparation configuration based on the request for application layer data processing management, the at least one parameter comprising information for preparing required data.

[0019] A method in a data preparation entity is also provided, the data preparation entity being located in a wireless communication system, the method comprising: receiving a data preparation configuration, the data preparation configuration comprising at least one parameter, the at least one parameter comprising information for preparing required data, the required data being required from at least one data source; receiving raw data from at least one data source; processing the raw data based on the data preparation configuration; and sending a report indicating data quality issues with the raw data and / or processed data.

[0020] The data preparation configuration entity may be a network node of a wireless communication system, which may include an enabling layer / application layer entity within the extended concept of a network. The data preparation configuration entity itself may also be a data preparation entity. The data preparation entity may be on the UE / device side, i.e., an application entity. In some embodiments, the data preparation configuration entity and the data preparation entity may be capabilities of the new VAL data collection management function, and in other embodiments, may be deployed as an enhanced new SEAL or SEALDD service. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to describe the manner in which the advantages and features of the present disclosure can be obtained, the present disclosure is described by reference to certain devices and methods shown in the accompanying drawings. Each of these drawings depicts only certain aspects of the present disclosure and therefore should not be considered as limiting the scope thereof. For the sake of clarity, the drawings may have been simplified and are not necessarily drawn to scale.

[0022] A method and apparatus for data preparation in a wireless communication system will now be described, by way of example only, with reference to the accompanying drawings, in which:

[0023] Figure 1 An embodiment of a wireless communication system for data preparation is illustrated;

[0024] Figure 2 An embodiment of a user equipment device for data preparation is illustrated;

[0025] Figure 3 An embodiment of a network node for data preparation is illustrated;

[0026] Figure 4 Various NWDAF embodiments including corresponding inputs and outputs are illustrated;

[0027] Figure 5 An embodiment of a general functional model of ADAE for reusing existing data analysis models is illustrated;

[0028] Figure 6 Provides an illustration of the general AI / ML process provided by ORAN;

[0029] Figure 7 An embodiment of a Service Enabler Architecture Layer (SEAL) Data Preparation Management (DPM) is illustrated;

[0030] Figure 8 Picture shows Figure 7 The DPM functions include data analysis and data processing operations;

[0031] Fig. 9 An embodiment of a method in a data preparation configuration entity is illustrated;

[0032] Fig.10 A further embodiment of a method in a data preparation configuration entity is illustrated;

[0033] Fig.11 An embodiment of a method in a data preparation entity is illustrated; and

[0034] Fig.12 Further embodiments of a method in a data preparation entity are illustrated. DETAILED DESCRIPTION

[0035] Those skilled in the art will appreciate that aspects of the present disclosure may be implemented as systems, devices, methods or program products. Therefore, the arrangements described herein may be implemented entirely in hardware, entirely in software (including firmware, resident software, microcode, etc.), or in a combination of software and hardware.

[0036] For example, the disclosed methods and apparatus may be implemented as hardware circuits including custom very large scale integration ("VLSI") circuits or gate arrays, off-the-shelf semiconductors such as logic chips, transistors, or other discrete components. The disclosed methods and apparatus may also be implemented in programmable hardware devices such as field programmable gate arrays, programmable array logic, programmable logic devices, etc. As another example, the disclosed methods and apparatus may include one or more physical or logical blocks of executable code, which may be organized, for example, as objects, procedures, or functions.

[0037] In addition, the method and apparatus may take the form of a program product that is implemented in one or more computer-readable storage devices that store machine-readable code, computer-readable code, and / or program code (hereinafter referred to as code). The storage device may be tangible, non-transient, and / or non-transmitting. The storage device may not implement a signal. In some arrangements, the storage device only employs a signal for accessing the code.

[0038] Any combination of one or more computer readable media may be utilized. The computer readable medium may be a computer readable storage medium. The computer readable storage medium may be a storage device storing code. The storage device may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, holographic, micromechanical, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing.

[0039] More specific examples of storage devices (a non-exhaustive list) would include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory ("RAM"), a read-only memory ("ROM"), an erasable programmable read-only memory ("EPROM" or flash memory), a portable compact disk read-only memory ("CD-ROM"), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the context of this specification, a computer-readable storage medium may be any tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0040] In this specification, the reference to the example of a particular method or device or similar language indicates that the specific features, structures or characteristics described in conjunction with the example are included in at least one implementation of the method and device described in this article. Therefore, unless otherwise expressly provided, the reference to the features of the example of a particular method or device or similar language may but not necessarily all refer to the same example, but to "one or more but not all examples". Unless otherwise expressly provided, the terms "include", "comprise", "have (having)" and their variants refer to "including but not limited to". Unless otherwise expressly provided, the enumerated list of items does not mean that any or all items are mutually exclusive. Unless otherwise expressly provided, the terms "one", "an" and "the" also refer to "one or more".

[0041] As used herein, a list with the conjunction "and / or" includes any single item in the list or a combination of items in the list. For example, a list of A, B, and / or C includes only A, only B, only C, a combination of A and B, a combination of B and C, a combination of A and C, or a combination of A, B, and C. As used herein, a list using the term "one or more of ..." includes any single item in the list or a combination of items in the list. For example, one or more of A, B, and C includes only A, only B, only C, a combination of A and B, a combination of B and C, a combination of A and C, or a combination of A, B, and C. As used herein, a list using the term "one of ..." includes one and only one of any single item in the list. For example, "one of A, B, and C" includes only A, only B, or only C, and excludes a combination of A, B, and C. As used herein, "a member selected from a group including A, B, and C" includes one and only one of A, B, or C, and excludes a combination of A, B, and C. As used herein, “a member selected from the group consisting of A, B, and C and combinations thereof” includes only A, only B, only C, a combination of A and B, a combination of B and C, a combination of A and C, or a combination of A, B, and C.

[0042] In addition, the features, structures or characteristics described herein may be combined in any suitable manner. In the following description, many specific details are provided, such as examples of programming, software modules, user selections, network transactions, database queries, database structures, hardware modules, hardware circuits, hardware chips, etc., to provide a comprehensive understanding of the present disclosure. However, those skilled in the relevant art will recognize that the disclosed methods and apparatus may be practiced without one or more of the specific details, or may be practiced using other methods, components, materials, etc. In other cases, well-known structures, materials or operations are not shown or described in detail to avoid obfuscating aspects of the present disclosure.

[0043] Aspects of the disclosed methods and apparatus are described below with reference to schematic flow charts and / or schematic block diagrams of methods, apparatuses, systems, and program products. It will be understood that each frame of the schematic flow charts and / or schematic block diagrams and the combination of frames in the schematic flow charts and / or schematic block diagrams can be implemented by code. The code can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine, so that instructions executed by a processor of a computer or other programmable data processing device can create components for implementing the functions / actions specified in the schematic flow charts and / or schematic block diagrams.

[0044] The code may also be stored in a storage device that can instruct a computer, other programmable data processing apparatus, or other device to work in a specific manner, so that the instructions stored in the storage device can produce an article of manufacture that includes instructions for implementing the functions / actions specified in the schematic flowchart and / or schematic block diagram.

[0045] The code may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are executed on the computer, other programmable apparatus, or other device, thereby producing a computer-implemented process, so that the code executed on the computer or other programmable apparatus can provide a process for implementing the functions / actions specified in the schematic flowchart and / or schematic block diagram.

[0046] The schematic flow charts and / or schematic block diagrams in the figures illustrate the possible implementation architectures, functions and operations of the apparatus, system, method and program product. In this regard, each box in the schematic flow charts and / or schematic block diagrams may represent a module, segment or portion of code, which includes one or more executable instructions of the code for implementing (multiple) specified logical functions.

[0047] It should also be noted that in some alternative implementations, the functions shown in the blocks may not occur in the order shown in the figures. For example, two blocks shown in succession may in fact be executed substantially simultaneously, or the blocks may sometimes be executed in the reverse order, depending on the functions involved. Other steps and methods may be conceived to be equivalent in function, logic or effect to one or more blocks or portions thereof of the illustrated figures.

[0048] The description of an element in each figure may refer to the elements of the subsequent figures. The same numerals represent the same elements throughout the drawings.

[0049] Figure 1 An embodiment of a wireless communication system 100 for data preparation in a wireless communication system is depicted. In one embodiment, the wireless communication system 100 includes a remote unit 102 and a network unit 104. Although Figure 1A specific number of remote units 102 and network units 104 are depicted in FIG. 1 , but one skilled in the art will recognize that any number of remote units 102 and network units 104 may be included in the wireless communication system 100.

[0050] In one embodiment, the remote unit 102 may include a computing device such as a desktop computer, a laptop computer, a personal digital assistant (“PDA”), a tablet computer, a smart phone, a smart TV (e.g., a TV connected to the Internet), a set-top box, a game console, a security system (including a security camera), a vehicle computer, a network device (e.g., a router, a switch, a modem), an aircraft, a drone, etc. In some embodiments, the remote unit 102 includes a wearable device such as a smart watch, a fitness band, an optical head-mounted display, etc. In addition, the remote unit 102 may be referred to as a subscriber unit, a mobile station, a mobile station, a user, a terminal, a mobile terminal, a fixed terminal, a subscriber station, a UE, a user terminal, a device, or other terms used in the art. The remote unit 102 may communicate directly with one or more of the network units 104 via UL communication signals. In some embodiments, the remote unit 102 may communicate directly with other remote units 102 via sidelink communications.

[0051] The network elements 104 may be distributed over a geographical area. In some embodiments, the network elements 104 may also be referred to as access points, access terminals, base stations, base stations, node Bs, eNBs, gNBs, home node Bs, relay nodes, devices, core networks, air servers, radio access nodes, APs, NRs, network entities, access and mobility management functions (“AMFs”), unified data management functions (“UDMs”), unified data repositories (“UDRs”), UDM / UDRs, policy control functions (“PCFs”), radio access networks (“RANs”), network slice selection functions (“NSSFs”), operations, maintenance, and management (“OAMs”), Session Management Function ("SMF"), User Plane Function ("UPF"), Application Function, Authentication Server Function ("AUSF"), Security Anchor Function ("SEAF"), Trusted Non-3GPP Gateway Function ("TNGF"), Application Function, Service Enablement Architecture Layer ("SEAL") Function, Vertical Application Enablement Server, Edge Enablement Server, Edge Configuration Server, Mobile Edge Computing Platform Function, Mobile Edge Computing Application, Application Data Analytics Enabler Server, SEAL Data Delivery Server, Middleware Entity, Network Slice Capability Management Server, or any other term used in the art. The network element 104 is typically part of a radio access network that includes one or more controllers that can be communicatively coupled to one or more corresponding network elements 104. The radio access network is typically communicatively coupled to one or more core networks that can be coupled to other networks, such as networks such as the Internet and the Public Switched Telephone Network. These and other elements of the radio access network and the core network are not shown, but are generally known to those of ordinary skill in the art.

[0052] In one implementation, the wireless communication system 100 complies with the New Radio (NR) protocol standardized in 3GPP, wherein the network unit 104 transmits on the downlink (DL) using an orthogonal frequency division multiple access ("OFDM") modulation scheme, and the remote unit 102 transmits on the uplink (UL) using a single carrier frequency division multiple access ("SC-FDMA") scheme or an OFDM scheme. More generally, however, the wireless communication system 100 may implement some other open or proprietary communication protocol, such as WiMAX, an IEEE 802.11 variant, GSM, GPRS, UMTS, an LTE variant, CDMA2000, ZigBee, Sigfox, etc. The present disclosure is not intended to be limited to the implementation of any particular wireless communication system architecture or protocol.

[0053] The network unit 104 can serve multiple remote units 102 within a service area (eg, a cell or cell sector) via wireless communication links. The network unit 104 sends DL communication signals to serve the remote units 102 in the time, frequency, and / or spatial domains.

[0054] The disclosure herein provides a data preparation configuration entity and a data preparation entity that provides data preparation, particularly for AI / ML model training and / or reasoning data. Such entities and methods in the above-mentioned entities will be described herein using examples with special reference to SEAL.

[0055] SEAL itself provides a set of capabilities at the application layer to support integration with vertical industries. Such services include location management, group management, slice enablement, analysis enablement, etc. SEAL is specified in 3GPP technical specification TS23.434.

[0056] In SEAL, there are various reasons for collecting raw data from different domains. Specifically, the Network Slice Capability Enablement (NSCE) service (also specified in 3GPP TS23.435) collects PM / FM data from OAM, performance data from UE applications, and QoE data from application-specific servers. Based on this data, it provides some slice-related support services (e.g., QoS verification, active slice adaptation triggering, etc.) to vertical consumers. In addition, the Application Data Analysis Enabling Service (ADAES, specified in 3GPP TS23.436) collects data from different data sources directly or via A-DCCF to perform analysis.

[0057] In addition, for SEAL, a SEAL Data Delivery (SEALDD) service (specified in 3GPP TS23.433) is introduced for handling user plane data between UE and application server (e.g., for caching, service optimization). A possible new SEAL service (i.e., VAL data collection management function) that has not yet been specified can be used to provide data collection management services to other SEAL functions that need to collect data from VAL clients or VAL servers (e.g., NSCE, ADAE, SEALDD, etc.).

[0058] The disclosure described herein relates to the operation of data preparation, which involves preprocessing raw data into a form used by a consumer of the data, which may be an AI / ML model (in the case where the analytical function is a consumer). Data preparation processes two main types of data: continuous data (i.e., data values ​​as a function of time) and categorical data (data belonging to different categories or levels / states). It is the initial step of network analysis and may include several different tasks, such as loading data from a selected data source, data analysis, data cleaning, data processing or modification, and data enhancement. These tasks fall into the following main categories: i) data collection and analysis to identify violations; ii) data recovery and cleaning, considering (a) systematic errors involving large data records from different data sources, and / or (b) individual data errors due to random or processing errors; iii) data formatting; and iv) data labeling and separating data into sets for adapting to different training tasks. Data labeling is the process of identifying raw data and adding one or more meaningful and informative labels to provide context so that a machine learning model can learn from it. For example, the labels of certain data samples may be labeled "user data" or "QoE data".

[0059] The present application proposes a solution to these problems.

[0060] Figure 2 A user equipment device 200 is depicted that can be used to implement the methods described herein. The user equipment device 200 is used to implement one or more of the solutions described herein. The user equipment device 200 conforms to one or more of the user equipment devices described in the embodiments herein. Specifically, the user equipment device 200 conforms to Figure 1 102, and Figure 7 710 and 712, and Fig.10 1010 and Fig.12 1210, and thus reference numeral 200 is used hereinafter to indicate a user equipment device that complies with 102, 710, 1010, and / or 1210. User equipment device 200 itself may be a data preparation entity. User equipment device 200 may include a DPM client for performing data preparation at user equipment device 200. User equipment device 200 includes a processor 205, a memory 210, an input device 215, an output device 220, and a transceiver 225.

[0061] The input device 215 and the output device 220 may be combined into a single device, such as a touch screen. In some implementations, the user equipment apparatus 200 does not include any input device 215 and / or output device 220. The user equipment apparatus 200 may include one or more of the following: a processor 205, a memory 210, and a transceiver 225, and may not include an input device 215 and / or an output device 220.

[0062] As depicted, the transceiver 225 includes at least one transmitter 230 and at least one receiver 235. The transceiver 225 can communicate with one or more cells (or wireless coverage areas) supported by one or more base station units. The transceiver 225 can be operable on an unlicensed spectrum. In addition, the transceiver 225 can include multiple UE panels supporting one or more beams. Additionally, the transceiver 225 can support at least one network interface 240 and / or application interface 245. (Multiple) application interface 245 can support one or more APIs. (Multiple) network interface 240 can support 3GPP reference points such as Uu, N1, PC5, etc. As understood by a person of ordinary skill in the art, other network interfaces 240 can be supported.

[0063] The processor 205 may include any known controller capable of executing computer-readable instructions and / or capable of performing logical operations. For example, the processor 205 may be a microcontroller, a microprocessor, a central processing unit (“CPU”), a graphics processing unit (“GPU”), an auxiliary processing unit, a field programmable gate array (“FPGA”), or a similar programmable controller. The processor 205 may execute instructions stored in the memory 210 to perform the methods and routines described herein. The processor 205 is communicatively coupled to the memory 210, the input device 215, the output device 220, and the transceiver 225.

[0064] Processor 205 may control user equipment device 200 to implement the user equipment device behaviors described herein. Processor 205 may include an application processor (also referred to as a "main processor") that manages application domain and operating system ("OS") functions, and a baseband processor (also referred to as a "baseband radio processor") that manages radio functions.

[0065] Memory 210 may be a computer-readable storage medium. Memory 210 may include volatile computer storage media. For example, memory 210 may include RAM, including dynamic RAM ("DRAM"), synchronous dynamic RAM ("SDRAM"), and / or static RAM ("SRAM"). Memory 210 may include non-volatile computer storage media. For example, memory 210 may include a hard drive, flash memory, or any other suitable non-volatile computer storage device. Memory 210 may include both volatile and non-volatile computer storage media.

[0066] The memory 210 may store data related to implementing the traffic class field as described herein. The memory 210 may also store program code and related data, such as an operating system or other controller algorithms operating on the device 200.

[0067] Input device 215 may include any known computer input device, including a touchpad, buttons, keyboard, stylus, microphone, etc. Input device 215 may be integrated with output device 220, for example, as a touch screen or similar touch-sensitive display. Input device 215 may include a touch screen so that text can be entered using a virtual keyboard displayed on the touch screen and / or by handwriting on the touch screen. Input device 215 may include two or more different devices, such as a keyboard and a touchpad.

[0068] Output device 220 may be designed to output visual, auditory, and / or tactile signals. Output device 220 may include an electronically controllable display or display device capable of outputting visual data to a user. For example, output device 220 may include, but is not limited to, a liquid crystal display ("LCD"), a light emitting diode ("LED") display, an organic LED ("OLED") display, a projector, or a similar display device capable of outputting images, text, etc. to a user. As another non-limiting example, output device 220 may include a wearable display that is separate from but communicatively coupled to the rest of user device apparatus 200, such as a smart watch, smart glasses, a head-up display, etc. In addition, output device 220 may be a component of a smart phone, a personal digital assistant, a television, a desktop computer, a notebook (laptop) computer, a personal computer, a vehicle dashboard, etc.

[0069] Output device 220 may include one or more speakers for producing sound. For example, output device 220 may produce an audible alarm or notification (e.g., a beep or buzzer). Output device 220 may include one or more tactile devices for producing vibration, motion, or other tactile feedback. All or part of output device 220 may be integrated with input device 215. For example, input device 215 and output device 220 may form a touch screen or similar touch-sensitive display. Output device 220 may be located near input device 215.

[0070] The transceiver 225 communicates with one or more network functions of the mobile communication network via one or more access networks. The transceiver 225 operates under the control of the processor 205 to send messages, data and other signals, and also receive messages, data and other signals. For example, the processor 205 can selectively activate the transceiver 225 (or part thereof) at a specific time to send and receive messages.

[0071] The transceiver 225 includes at least one transmitter 230 and at least one receiver 235. One or more transmitters 230 can be used to provide uplink communication signals to the base station unit of the wireless communication network. Similarly, one or more receivers 235 can be used to receive downlink communication signals from the base station unit. Although only one transmitter 230 and one receiver 235 are shown, the user equipment device 200 can have any suitable number of transmitters 230 and receivers 235. In addition, (multiple) transmitters 230 and (multiple) receivers 235 can be any suitable type of transmitter and receiver. The transceiver 225 may include a first transmitter / receiver pair for communicating with a mobile communication network through a licensed radio spectrum, and a second transmitter / receiver pair for communicating with a mobile communication network through an unlicensed radio spectrum.

[0072] A first transmitter / receiver pair that can be used to communicate with a mobile communication network via a licensed radio spectrum and a second transmitter / receiver pair that can be used to communicate with a mobile communication network via an unlicensed radio spectrum can be combined into a single transceiver unit, such as a single chip that performs functions for use with both licensed and unlicensed radio spectrums. The first transmitter / receiver pair and the second transmitter / receiver pair can share one or more hardware components. For example, some transceivers 225, transmitters 230, and receivers 235 can be implemented as physically separate components that access shared hardware resources and / or software resources, such as a network interface 240.

[0073] One or more transmitters 230 and / or one or more receivers 235 may be implemented and / or integrated into a single hardware component, such as a multi-transceiver chip, a system on chip, an application specific integrated circuit ("ASIC"), or other type of hardware component. One or more transmitters 230 and / or one or more receivers 235 may be implemented and / or integrated into a multi-chip module. Other components such as a network interface 240 or other hardware components / circuits may be integrated into a single chip along with any number of transmitters 230 and / or receivers 235. Transmitters 230 and receivers 235 may be logically configured as transceivers 225 using one or more common control signals, or may be configured as modular transmitters 230 and receivers 235 implemented in the same hardware chip or multi-chip module.

[0074] Figure 3 1 depicts further details of a network node 300 that can be used to implement the methods described herein. The network node 300 may be an implementation of an entity (such as a data preparation configuration entity and / or a data preparation entity) in a wireless communication network (e.g., one or more of the wireless communication networks described herein). For example, the network node 300 may be the UE 200 described above, or a network function (NF) or an application function (AF) or another entity of one or more of the wireless communication networks of the embodiments described herein, such as Figure 1 Node 104, Figure 7 Nodes 720 and 740, Fig.10 Node 1020, and / or Fig.12 The network node 300 includes a processor 305, a memory 310, an input device 315, an output device 320, and a transceiver 325.

[0075] The input device 315 and the output device 320 may be combined into a single device, such as a touch screen. In some implementations, the network node 300 does not include any input device 315 and / or output device 320. The network node 300 may include one or more of the following: a processor 305, a memory 310, and a transceiver 325, and may not include an input device 315 and / or an output device 320.

[0076] As depicted, the transceiver 325 includes at least one transmitter 330 and at least one receiver 335. Here, the transceiver 325 communicates with one or more remote units 200. Additionally, the transceiver 325 can support at least one network interface 340 and / or an application interface 345. The (multiple) application interface 345 can support one or more APIs. The (multiple) network interface 340 can support 3GPP reference points such as Uu, N1, N2, and N3. As will be appreciated by those of ordinary skill in the art, other network interfaces 340 may be supported.

[0077] The processor 305 may include any known controller capable of executing computer-readable instructions and / or capable of performing logical operations. For example, the processor 305 may be a microcontroller, a microprocessor, a CPU, a GPU, an auxiliary processing unit, an FPGA, or a similar programmable controller. The processor 305 may execute instructions stored in the memory 310 to perform the methods and routines described herein. The processor 305 is communicatively coupled to the memory 310, the input device 315, the output device 320, and the transceiver 325.

[0078] Memory 310 may be a computer-readable storage medium. Memory 310 may include volatile computer storage media. For example, memory 310 may include RAM, including dynamic RAM ("DRAM"), synchronous dynamic RAM ("SDRAM"), and / or static RAM ("SRAM"). Memory 310 may include non-volatile computer storage media. For example, memory 310 may include a hard drive, flash memory, or any other suitable non-volatile computer storage device. Memory 310 may include both volatile and non-volatile computer storage media.

[0079] The memory 310 may store data related to establishing a multipath unicast link and / or mobile operation. For example, as described herein, the memory 310 may store parameters, configurations, resource allocations, policies, etc. The memory 310 may also store program code and related data, such as an operating system or other controller algorithms operating on the network node 300.

[0080] Input device 315 may include any known computer input device, including a touch pad, buttons, keyboard, stylus, microphone, etc. Input device 315 may be integrated with output device 320, for example, as a touch screen or similar touch-sensitive display. Input device 315 may include a touch screen so that text can be entered using a virtual keyboard displayed on the touch screen and / or by handwriting on the touch screen. Input device 315 may include two or more different devices, such as a keyboard and a touch pad.

[0081] Output device 320 can be designed to output visual, auditory and / or tactile signals. Output device 320 may include an electronically controllable display or display device capable of outputting visual data to a user. For example, output device 320 may include, but is not limited to, an LCD display, an LED display, an OLED display, a projector, or a similar display device capable of outputting images, text, etc. to a user. As another non-limiting example, output device 320 may include a wearable display such as a smart watch, smart glasses, a head-up display, etc. that is separated from the rest of network node 300 but is communicatively coupled to it. In addition, output device 320 may be a component of a smart phone, a personal digital assistant, a television, a desktop computer, a notebook (laptop) computer, a personal computer, a vehicle dashboard, etc.

[0082] Output device 320 may include one or more speakers for producing sound. For example, output device 320 may produce an audible alarm or notification (e.g., a beep or buzzer). Output device 320 may include one or more tactile devices for producing vibration, motion, or other tactile feedback. All or part of output device 320 may be integrated with input device 315. For example, input device 315 and output device 320 may form a touch screen or similar touch-sensitive display. Output device 320 may be located near input device 315.

[0083] The transceiver 325 includes at least one transmitter 330 and at least one receiver 335. One or more transmitters 330 may be used to communicate with a UE as described herein. Similarly, one or more receivers 335 may be used to communicate with a network function in a PLMN and / or RAN as described herein. Although only one transmitter 330 and one receiver 335 are illustrated, the network node 300 may have any suitable number of transmitters 330 and receivers 335. In addition, the transmitter(s) 330 and the receiver(s) 335 may be any suitable type of transmitter and receiver.

[0084] Network analysis and analysis data preparation involve support for various analysis types, various input data sources, and various output consumers of the analysis. To help understand the breadth of network analysis that the invention described herein can involve, Figure 4 and Figure 5 It is provided as an example only. Figure 4A diagram 400 of various NWDAF embodiments 410 is provided, along with examples of their corresponding inputs 420 and outputs 430. The figure shows NWDAF (AnLf / MTLF) 411, NWDAF (AnLF) 412, and NWDAF (MTLF) 413. These NWDAF types 410 receive input from a DCAF or DCCF / MFAF 421, which itself receives input from a 5G Core NF 422, UE / AF 423 (optionally via NEF 424), a 5G Core repository 425 (such as NRF, BSF, ADRF, UDM, UDR), and OAM data 426 (such as PM, KPI, CM, alarms). The figure also shows the NWDAF type 410 output to the DCAF or DCCF / MFAF 431, which itself outputs to the 5G Core NF 432, UE / AF 433 (optionally via NEF 434), 5G Core Repository 435 (such as ADRF, UDM, UDR) and OAM 436 (such as MnS consumer or MF).

[0085] More specifically, the analysis ID contained in the NWDAF 410 depends on various data input sources, including data from the 5G core NF 422, AF 423, 5G core repository 425 (e.g., NRF, UDM, etc.), and OAM data (e.g., PM / KPI, CM data, alarms, etc.). The analysis ID contained in the AnLF can provide analysis output results to the 5G core NF 432, AF, 5G core repository 435 (e.g., UDM, UDR ADRF or OAM 436MnS consumer or MF). MTLF and AnLF can exchange AI / ML models (e.g., via serialization, containerization, etc.), including relevant model information. Optionally, DCCF and MFAF421, 431 can participate in distributing duplicate data to various data sources or collecting duplicate data from various data sources.

[0086] In addition, analytics (which may be ML-enabled) may be provided at the edge / application side, at the application data analytics enabler service, or generally at the application side, where data may be collected by multiple data sources (including 5GC, OAM, MEC, VAL layer, UE). In some deployments, the ADAE server may reuse the existing 3GPP data analytics framework for data collection coordination, delivery, and storage. Figure 5An embodiment 500 of a general functional model for ADAE using an existing data analysis model is illustrated. In this functional model 500, an application layer data collection and coordination function (A-DCCF) 510 is used to retrieve data or put data (including formatted data) into an application layer entity (e.g., A-ADRF, data source) 520. Such an A-DCCF 510 coordinates the collection and distribution of data requested by an ADAE server 530 (via ADCCF-1, ADAE-X). The ADAE server 530 can also interact directly with the data source 540 via ADAE-Y. The application layer-analysis and data repository function (A-ADRF) 520 can be used to store historical data and / or analysis, i.e., data and / or analysis related to past time periods that have been acquired by the ADAE server 530 (via AADRF-1) or other NF / NWDAF. The ADAE server 530 can also retrieve historical data from the ADRF 520. Whether the ADAE server 530 contacts the ADRF 520 directly or via the A-DCCF 510 is based on configuration. The data source 540 can be a 5GS data source (5GC, OAM) or an enabling layer data source (SEAL, EEL) or an external data source on the DN side (VAL server / EAS) 550 and a VAL UE. The A-DCCF 510 and the A-ADRF 520 can only be used to interact with certain data sources 540 (e.g., 5GC, OAM) based on configuration and can be hidden from the VAL layer.

[0087] Certain procedural aspects of AI / ML applications are provided through a background example using the ORAN AI / ML prior art generic procedures (O-RAN.WG2.AIML v01.03). Figure 6 600, which includes data collection 610 that provides input to data preparation 620, which itself inputs AI / ML training data into AI / ML training 630 and AI / ML reasoning 640. AI / ML training 630 also inputs to AI / ML model management 650, which itself inputs to AI / ML reasoning 640 and AI / ML continuous operations 660. AI / ML continuous operations 660 also inputs to AI / ML reasoning 640. AI / ML reasoning provides input to AI / ML assisted solutions 670 (e.g., configuration management 671, control actions 672, and policies 673), which can be fed into AI / ML continuous operations 660. However, data preparation in ORAN is an implementation-specific component, not a service provided in response to a specific request from a consumer.

[0088] In the field of analytical data preparation as described above, the disclosed data preparation configuration entity and data preparation entity provide data preparation capabilities as a new SEAL service (e.g., SEAL Data Preparation Management (DPM)) to provide necessary data preparation configuration of raw data based on requests from consumers (SEAL services or external applications).

[0089] This SEAL DPM service may also have a client counterpart on the UE side (i.e., DPM-C), which may be configured to prepare local data from the UE side (multiple) before sending to the server (DPM-S). For example, L2 / UE application measurements (such as QoS / radio performance measurements, e.g., channel loss, latency) may be prepared at the DPM-C to ensure that the quality of the data is acceptable before sending to the DPM-S. This will save both signaling and complexity on the server side. Figure 7 Generally illustrated is an architecture 700 that implements a VAL layer 701 and a SEAL DPM layer 702. A VAL UE 710 is shown to include a VAL client 711 that connects to a VAL server 720 via a 3GPP network system 730. The architecture 700 also illustrates how a SEAL DPM client 712 in the VAL UE 710 connects to the VAL client 711 and to a DPM server 740 via the 3GPP network system 730. The DPM server 740 is also shown to connect to the VAL server 720 and the 3GPP network system 730 itself. The DPM server 740 is also shown to connect to an ADAES 750, a NSCE-S 760, and a SEALDD-S 770. The VAL UE 710 is shown in a SEAL together with an ADAE-C 712, a NSCE-C 713, and a SEALDD-C 714. In some implementations, the SEAL DPM layer 702 can control data preparation, which can be a new capability of the SEALDD layer or a capability of a new layer or module deployed with the DPM. Although illustrated as a separate layer 702, the SEAL DPM can be deployed within the SEALDD or any other existing enabling layer, and / or can also be deployed as a trusted third-party application function (e.g., DCAF). For example, the DPM can be a function, a service, a server, a client, or a combination thereof.

[0090] SEAL DPM layer 702 includes at least one of the following operations: configuring data preparation parameters; selecting data sets or records; analyzing data; data exploration; data processing; data formatting; and preparing data. Each of these operations will be further explained below.

[0091] Configuration data preparation parameters may involve pre-configuring parameters through OAM, VAL layer, ECSP / CSP, MNO, and then performing the rest of the operations based on the configuration.

[0092] Selecting a data set or record includes selecting from certain data sources or types of data sources (to allow good repair of data from different sources to ensure integrity), as indicated in the received event ID or, for example, analysis ID or analysis type, i.e., related to the analysis work for which the data was prepared. The selection of data sources or records may also be influenced by the expected latency indicated by the consumer.

[0093] Analyzing the data includes analyzing the extraction of information about: central tendency and variation, i.e., what the main expected values ​​should be and what the variation should be, such as extracting the mean, variation, minimum, maximum, and other statistical properties of the data, including the distribution of the data; relative effects between variables or features, how the value of one variable or feature varies relative to the value of another variable or feature; and / or an amount of data sufficient for the requested task (i.e., analysis ID).

[0094] Data exploration includes exploring whether the collected data faces identification of quality issues, including: anomalies due to data source errors, i.e., failures or security incidents, or data transmission errors; missing values, such as a) percentages for each feature (features are individual measurable attributes or characteristics of data fed to AI / ML algorithms, such as UE type, mobility type, etc.) or about specific value ranges or other data conditions, and b) reasoning, for example, if data preparation requires the generation of new values ​​for use with AI / ML algorithms or indicates data unavailability from the data source, there are integration errors or processing errors; irregular cardinality, where it is necessary to check for a) feature errors (e.g., different data sources can use different names or IDs to indicate the same feature), b) unrealistic features, such as values ​​of 1 (i.e., features identified by developers but have no practical meaning for AI / ML algorithms), and c) data concentrated only in a specific range; and / or outliers, whose feature values ​​are far outside the expected range, considering a) valid values, i.e., correct values, but very different from expected values, or b) invalid values, i.e., incorrect noise values ​​inserted due to errors.

[0095] Data processing includes executing instructions or configurations given by the VAL layer or DPM configurator (e.g., OAM) related to: executing methods to enhance missing data, taking into account a) the indicated range, b) the percentage and amount of missing data, and iii) the method used to enhance the missing data; executing strategies to perform data cleaning to eliminate outliers and random errors by i) removing data or ii) introducing weights to reduce their impact on certain data; optionally indicating the expected performance impact on the AI / ML model in the event that input data from a specific source is still missing, i.e., even after interacting with the VAL / consumer / OAM, due to the inability to retrieve the data due to the selected method; and / or simplifying the indicated data.

[0096] Data formatting converts data into the appropriate shape required by the AI / ML model.

[0097] Preparing datasets includes preparing datasets for training, validation and testing, for example according to instructions given by a VAL consumer / OAM.

[0098] The sequence 800 of operations related to data preparation is as follows: Figure 8 8, which corresponds to the above steps. These steps are grouped into data analysis 810 and data processing 820. The data analysis 810 step includes: selecting a data source 801, analyzing data 802, and data exploration 803. Data processing 820 includes: data recovery and cleaning 804, data formatting 805, and preparing data 806. Although the figure shows a certain sequence of steps, the sequence can also be performed differently, for example, steps 804 and 805 can be reversed to allow data processing to be performed first before data recovery and cleaning.

[0099] The DPM disclosed herein can be implemented by a data preparation configuration entity in a wireless communication system, the data preparation configuration entity comprising: a transceiver arranged to receive a request for application layer data processing management, the request comprising a requirement for managing raw data from at least one data source; and a processor arranged to configure at least one parameter of the data preparation configuration based on the request for application layer data processing management, the at least one parameter comprising information for preparing required data.

[0100] DPM can be provided by a third-party trusted entity / external entity to the core network of the wireless communication system, in particular, by an enabling / application entity. In this context, the application layer includes an application enabling layer and / or an edge enabling layer. Examples of data processing management include preparation management and collection management.

[0101] Requirements for managing raw data correspond to requirements for collecting and processing data related to specific events. Such requirements may be accompanied by performance requirements related to data delivery, required data types, and data characteristics. The event itself may be an analysis event or a data collection event or a data processing event.

[0102] In some embodiments, the transceiver is further arranged to receive raw data from at least one data source; the processor is further arranged to process the raw data based on the data preparation configuration; and the processor is further arranged to control the transceiver to send a report indicating data quality issues with the raw data and / or the processed data.

[0103] Raw data may be application data, network data, and / or user data. The term "raw" means unprocessed or unanalyzed data. As an example, raw data may be radio measurements, application performance monitoring output, application QoS / QoE data, management data, core network data, edge computing data (e.g., edge load or performance data), computed load measurements, or any combination thereof.

[0104] Data quality issues can be defined based on an assessment of the raw data. For example, the problem can be due to missing data or irrelevant data or data anomalies.

[0105] In some embodiments, the processor is further arranged to perform a data recovery operation based on the data quality problem of the original data.

[0106] In some embodiments, the data recovery operation includes checking for missing data and / or low quality data, and based on the checking, controlling the transceiver to request supplemental data from at least one data source, perform additional processing using additional data sources, and / or mark the data as low quality.

[0107] In some embodiments, the processor is further arranged to control the transceiver to send a subscription request to at least one data source and / or a data collection coordination entity for performing data preparation.

[0108] In some embodiments, the processor is further arranged to control the transceiver to transmit the processed data.

[0109] In some embodiments, the transceiver is further arranged to send the data preparation configuration to the data preparation entity.

[0110] In some embodiments, the data preparation configuration entity is selected from a list of data preparation configuration entities comprising: an operations administration and maintenance function, OAM; an edge enabling server; and an application enabling server.

[0111] In some embodiments, the processor is further arranged to control the transceiver to send a positive or negative acknowledgement in response to the request for application layer data processing management.

[0112] In some embodiments, the data preparation configuration entity is used to provide data preparation for training and / or inference data for an artificial intelligence AI / machine learning ML model.

[0113] In some embodiments, at least one parameter comprising information for preparing required data includes information related to at least one of: assessment of data quality; recovery of missing data; cleaning of data; formatting of data; labeling of data; and separation of data into data sets for one or more AI / ML training and / or reasoning tasks.

[0114] In some embodiments, a request for application layer data processing management is received from a consumer selected from a list of consumers including: a third party application; a VAL server; and an enabling server.

[0115] Fig. 9 An embodiment of a method 900 in a data preparation configuration entity in a wireless communication system is illustrated.

[0116] In a first step 910, a request for application layer data processing management is received. The request includes a requirement for managing raw data from at least one data source.

[0117] In a second step 920, at least one parameter of the data preparation configuration is configured based on the request for application layer data processing management. The at least one parameter includes information for preparing the required data.

[0118] In some embodiments, the method further includes: receiving raw data from at least one data source; processing the raw data based on the data preparation configuration; and sending a report indicating data quality issues with the raw data and / or the processed data.

[0119] In some embodiments, the method further comprises performing a data recovery operation based on the data quality problem of the original data. In some embodiments, the data recovery operation comprises: checking for missing data and / or low quality data, and based on the checking, controlling the transceiver to request supplemental data from at least one data source, performing additional processing using an additional data source, and / or marking the data as low quality.

[0120] In some embodiments, the method further comprises sending a subscription request to at least one data source and / or a data collection coordination entity for performing data preparation.

[0121] In some embodiments, the method further comprises transmitting the processed data.

[0122] In some embodiments, the method further comprises sending the data preparation configuration to the data preparation entity.

[0123] In some embodiments, the data preparation configuration entity is selected from a list of data preparation configuration entities comprising: an OAM function; an edge enabling server; and an application enabling server.

[0124] In some embodiments, the method further comprises sending a positive or negative acknowledgement in response to the request for application layer data processing management.

[0125] In some embodiments, the method is used to provide data preparation for AI / ML model training and / or inference data for an AI / ML model.

[0126] In some embodiments, at least one parameter comprising information for preparing required data includes information related to at least one of: assessment of data quality; recovery of missing data; cleaning of data; formatting of data; labeling of data; and separation of data into data sets for one or more AI / ML training and / or reasoning tasks.

[0127] In some embodiments, a request for application layer data processing management is received from a consumer selected from a list of consumers including: a third party application; a VAL server; and an enabling server.

[0128] Fig.10 Another embodiment of the method 1000 in the data preparation configuration entity is illustrated. In this embodiment, the DPM server (as the data preparation configuration entity) configures and performs data preparation after subscribing to the data source based on the consumer request to obtain data and ack as intermediate quantities for user plane data delivery. The figure shows a VAL UE 1010, which includes a VAL application client 1011, a DPM client 1012 and a UE modem 1013. The figure also shows a SEAL DPM server 1020. The figure also shows a data source / SEALDD / A-DCCF / DCAF 1030. The figure also shows a consumer (ADAES, NSCE) 1040. The steps of the method 1000 will now be described.

[0129] In a first step 1001, a consumer 1040 (VAL server or ADAES / NSCE) sends a subscription request or request to the SEAL DPM 1020 to initiate data preparation in a certain area and time or for a certain application / vertical service (e.g., V2X queue). The request may include event ID, consumer ID, required data, service profile, area and / or time.

[0130] In a second step 1002, the SEAL DPM 1020 authorizes the request and determines data collection and preparation requirements based on the type of request (eg, for each analysis ID) or based on the data sources involved (eg, UE, AF, etc.).

[0131] In a third step 1003 , the SEAL DPM 1020 sends a response (ack / nack) to the consumer 1040 .

[0132] In a fourth step 1004, the SEAL DPM 1020 subscribes to the data source 1030 and optionally to the SEALDD to receive data on behalf of the consumer 1040 (VAL server or ADAES / NSCE), allowing the data to be prepared. The DPM 1020 also provides information about the data collection requirements and configuration (format, frequency, parameters to be measured, thresholds). The data source 1030 / SEALDD authorizes the subscription request and responds with a positive or negative ack. The SEAL DPM 1020 then receives data from the data source 1030 / SEALDD.

[0133] In the fifth step 1005, SEAL DPM 1020 prepares the data received from the data source 1030, and in particular, it checks for missing data, low-quality data, etc. for one or more sources, and based on this check, it can request supplementary data / perform some additional processing or mark the data as low-quality data. Depending on the data collection latency requirements, the decision of DPM 1020 can have a certain upper threshold for preparing data to ensure that the overall latency (data source 1030 - DPM1020 - consumer 1040) is not exceeded. If no decision is made, DPM 1030 sends a failure event, or does not provide data to consumer 1040.

[0134] In a sixth step 1006, the SEAL DPM 1020 sends the processed data to the consumer 1040 (VAL server, ADAES, etc.) along with possible flags in case of low quality (to allow the consumer to reduce the confidence level of possible analysis)

[0135] In a seventh step, the consumer 1040 receives the data and uses it as input for the required SEAL / VAL capabilities (e.g., analysis, slicing enablement, etc.).

[0136] The DPM described herein may also be implemented by a data preparation entity in a wireless communication system that receives a data preparation configuration. The data preparation entity comprises: a transceiver arranged to receive a data preparation configuration, the data preparation configuration comprising at least one parameter, the at least one parameter comprising information for preparing required data, the required data being required from at least one data source, wherein the transceiver is further arranged to receive raw data from at least one data source; and a processor arranged to process the raw data based on the data preparation configuration; and wherein the processor is further arranged to control the transceiver to send a report indicating data quality issues with the raw data and / or the processed data.

[0137] In some embodiments, the processor is further arranged to perform a data recovery operation based on the data quality problem of the original data. In some embodiments, the data recovery operation includes: checking for missing data and / or low quality data, and based on the checking, controlling the transceiver to request supplementary data from at least one data source, using an additional data source to perform additional processing, and / or marking the data as low quality.

[0138] In some embodiments, the processor is further arranged to control the transceiver to send a subscription request to at least one data source and / or a data collection coordination entity for performing data preparation.

[0139] In some embodiments, the data preparation entity is selected from a list of data preparation entities comprising: an application-enabled server; and an application-enabled client.

[0140] In some embodiments, the data preparation entity is used to provide data preparation for AI / ML model training and / or inference data for the AI / ML model.

[0141] In some embodiments, at least one parameter comprising information for preparing required data includes information related to at least one of: assessment of data quality; recovery of missing data; cleaning of data; formatting of data; and separation of data into data sets for one or more AI / ML training and / or reasoning tasks.

[0142] Fig.11 An embodiment of a method 1100 in a data preparation entity, which is located in a wireless communication system, is illustrated.

[0143] In a first step 1110, a data preparation configuration is received, the data preparation configuration comprising at least one parameter including information for preparing required data, the required data being required from at least one data source.

[0144] In a second step 1120, raw data is received from at least one data source.

[0145] In a third step 1130 , the raw data is processed based on the data preparation configuration.

[0146] In a fourth step 1140, a report is sent indicating data quality issues of the raw data and / or the processed data.

[0147] Some embodiments further include performing a data recovery operation based on data quality issues of the original data. In some embodiments, the data recovery operation includes: checking for missing data and / or low quality data, and based on the checking, requesting supplemental data from at least one data source, performing additional processing using additional data sources, and / or marking the data as low quality.

[0148] Some embodiments further include sending a subscription request to at least one data source and / or a data collection coordination entity for performing data preparation.

[0149] In some embodiments, the data preparation entity is selected from a list of data preparation entities comprising: an application-enabled server; and an application-enabled client.

[0150] In some embodiments, the method is used to provide data preparation for AI / ML model training and / or inference data for an AI / ML model.

[0151] In some embodiments, at least one parameter comprising information for preparing required data includes information related to at least one of: assessment of data quality; recovery of missing data; cleaning of data; formatting of data; and separation of data into data sets for one or more AI / ML training and / or reasoning tasks.

[0152] Fig.12 Another embodiment of the method 1200 in the data preparation entity is illustrated, and the data preparation entity is located in the wireless communication system. In this embodiment, the DPM server configures the DPM client on the UE side for a data source associated with the UE or UE group (for example, for a fleet or V2X area), and the DPM client prepares the data to allow some processing for real-time / near real-time data and minimize anomalies. In some cases, the DPM server can support repairing the data quality on the network / server side (using app / network data) by providing additional processing. The figure shows a VAL UE or UE group 1210, which includes a local data source 1211 (app, SEALDD-C, AS / NAS) and a DPM client 1212. The figure also shows a SEAL DPM server 1220. The figure also shows a data source / SEALDD / A-DCCF / DCAF 1230. The figure also shows a consumer 1240 (ADAES, NSCE).

[0153] In a first step 1201, a consumer 1240 (VAL server or ADAES / NSCE) sends a subscription request or request to the SEAL DPM server 1220 to initiate data preparation in a certain area and time or for a certain application / vertical service (e.g., V2X queue). The request may include event ID, consumer ID, data requirements, service profile, area and / or time.

[0154] In a second step 1202, the SEAL DPM server 1220 authorizes the request and determines data collection and preparation requirements based on the type of request (eg, for each analysis ID) or based on the data sources involved (eg, UE, AF, etc.).

[0155] In a third step 1203 , the SEAL DPM server 1220 sends a response (ack / nack) to the consumer 1240 .

[0156] In a fourth step 1204, the SEAL DPM server 1220 configures the required SEAL DPM client 1212 for UE related data, including how to prepare and what policies to formulate if missing / low quality data is found.

[0157] In a fifth step 1205, SEAL DPM client 1212 subscribes to UE data source 1211 (eg, application, SEAL or SEALDD client, EEC, UE AS / NAS layer function). DPM client 1212 also provides information about data collection requirements and configuration (format, frequency, parameters to be measured, thresholds).

[0158] In a sixth step 1206 , the SEAL DPM client 1212 prepares to receive stolen data from the sources 1211 , and in particular, checks one or more sources 1211 for missing data, low quality data, and the like.

[0159] In a seventh step 1207, the SEAL DPM client 1212 sends the processed data to the consumer 1240 (VAL server, ADAES, other application or edge-enabled server) along with possible flags in case of low quality (to allow the consumer 1240 to reduce the confidence level of possible analysis).

[0160] In an eighth step 1208 , based on the DPM client 1212 inspection, the SEAL DPM server 1220 may request supplemental data from additional sources 1230 / perform some additional processing, or tag the data and trigger an event to the consumer 1240 .

[0161] In a ninth step 1209, the consumer 1240 receives the data and uses it as input for the required SEAL / VAL capabilities (e.g., analytics enablement, slice enablement, vertical application specific capabilities, etc.).

[0162] Data collection at the application layer creates some issues regarding the quality of the data, possible data anomalies during data collection, and how to fix these anomalies to ensure that the requirements of the data consumers (which can be ECSPs / CSPs that use this data for analytics, ML training, etc.) are met without being noticed. This issue is due to the fact that at the application layer, the data can be of different formats, granularity, from different systems / platforms, so it is not straightforward how and where the data will be processed before becoming the input to the analytics engine or SEAL algorithm.

[0163] The problem to be solved is how to handle the situation of data preparation and configuration of the preparation in an optimal way based on the needs of the consumer.

[0164] The present invention introduces a new SEAL service that is used to configure and support data preparation (analysis and recovery) for application raw data to derive processed data that is used as input for other SEAL services. This preparation and configuration can be based on the type of consumer and the type of application service / event.

[0165] Other alternatives are implementation specific, so consumers of analytics cannot influence data preparation, an important step for analytics performance, and the data preparation process cannot handle new or customized problems. Especially for third parties who have better understanding of their own data, open interfaces allow them to control data preparation rather than rely on preconfigured solutions, thereby obtaining better analytical results.

[0166] An exemplary embodiment provides data preparation and configuration provided by a new SEAL server (also referred to as SEAL DPM); and data preparation configuration is provided by a new SEAL server (also referred to as SEAL DPM), while data preparation is processed locally on the UE side. Such an embodiment is suitable for scenarios where a data source provides real-time data on the UE side, and preparation can help provide processed data to the network side instead of raw data. The following clauses provide additional aspects.

[0167] 1. A method for configuring data preparation (at a data preparation configuration entity, such as a DPM server or OAM), the method comprising: receiving a request for data collection management from an application entity, the request indicating a requirement for data from at least one data source; and based on the request for data collection management, configuring at least one parameter for preparing data collection, the at least one parameter including information for evaluating data quality for required data (some embodiments include sending at least one configured parameter to the data preparation entity).

[0168] 2. A method for performing data preparation (at a data preparation entity, such as a DPM server or a DPM client), the method comprising: obtaining at least one configured parameter (from an application enabling entity); receiving raw data from at least one data source (wherein the data source may also be a data collection coordination entity); and processing the raw data based on the configured parameters, the processing comprising evaluating data quality (some embodiments comprise performing data recovery based on an evaluation of the raw data (wherein data recovery comprises adding missing data)); and sending a report indicating data quality of the raw data and / or processed data.

[0169] 3. A method according to any one of clauses 1 to 2, wherein data is prepared for analysis (and in particular, the data is to be used as AI / ML model training and / or inference data for an ML model).

[0170] 4. A method according to any of clauses 1 to 2, wherein the entity for configuring and executing the data is the same entity.

[0171] 5. A method according to clause 1, wherein the data preparation configuration entity is an OAM function and / or an application enabling entity

[0172] 6. The method of clause 2, wherein the data preparation entity is an application-enabled client and / or server.

[0173] 7. The method according to clause 2, further comprising subscribing to at least one data source and / or data collection coordination entity for performing data preparation.

[0174] It should be noted that the above methods and apparatus illustrate rather than limit the present invention, and that those skilled in the art will be able to design many alternative arrangements without departing from the scope of the appended claims. The word "comprising" does not exclude the presence of other elements or steps than those listed in the claims, "a" or "an" does not exclude a plurality, and a single processor or other unit may perform the functions of several units described in the claims. Any reference signs in the claims should not be construed as limiting their scope.

[0175] Furthermore, although examples have been given in the context of specific communication standards, these examples are not intended to limit the communication standards to which the disclosed methods and apparatus may be applied. For example, although specific examples have been given in the context of 3GPP, the principles disclosed herein may also be applied to another wireless communication system, and indeed any communication system that uses routing rules.

[0176] The method may also be implemented in a set of instructions stored on a computer-readable medium, which when loaded into a computer processor, digital signal processor (DSP), etc., causes the processor to perform the above-described method.

[0177] The described methods and apparatus may be practiced in other specific forms. The described methods and apparatus are considered in all respects to be illustrative only and not restrictive. Therefore, the scope of the present invention is indicated by the appended claims rather than by the foregoing description. All changes within the meaning and equivalent range of the claims should be included within their scope.

[0178] The following abbreviations are relevant to the fields covered by this specification:

[0179] 3GPP Third Generation Partnership Project

[0180] 5G fifth generation mobile communications

[0181] AI / ML Artificial Intelligence / Machine Learning

[0182] ADRF Analytics Data Repository Capabilities

[0183] AF Application Function

[0184] AnLF Analysis Logic Function

[0185] CM Configuration Management

[0186] DCAF Data Collection Application Features

[0187] DCCF Data Collection Coordination Function

[0188] DP Data Preparation

[0189] KPI Key Performance Indicator

[0190] MF Management Function

[0191] MFAF Message Framework Adapter Functionality

[0192] MICO only initiates the connection on the mobile terminal

[0193] MnS Management Services

[0194] MTLF model training logic function

[0195] NEF Network Exposure Function

[0196] NF Network Function

[0197] NRF Network Repository Features

[0198] NWDAF network data analysis function

[0199] OAM Operations, Administration and Maintenance

[0200] ORAN Open RAN

[0201] PM performance measurement

[0202] QoE Quality of Experience

[0203] RAN Radio Access Network

[0204] SBA Service-Based Architecture

[0205] UDM User Data Manager

[0206] UDR User Data Repository

[0207] UE User Equipment

[0208] DPM Data Preparation Management

Claims

1. A data preparation configuration entity in a wireless communication system, comprising: a transceiver arranged to receive a request for application layer data processing management, the request comprising a requirement for management of raw data from at least one data source; as well as A processor is arranged to configure at least one parameter of a data preparation configuration based on said request for application layer data processing management, said at least one parameter comprising information for preparing said required data.

2. The data preparation configuration entity according to claim 1, wherein: The transceiver is further arranged to receive raw data from the at least one data source; The processor is further arranged to process the raw data based on the data preparation configuration; and The processor is further arranged to control the transceiver to send a report indicating a data quality problem of the raw data and / or the processed data.

3. The data preparation configuration entity according to claim 2, wherein the processor is further arranged to: perform a data recovery operation based on a data quality problem of the original data.

4. The data preparation configuration entity according to claim 3, wherein the data recovery operation comprises: Checking for missing data and / or low quality data and based on the checking, controlling the transceiver to request supplemental data from the at least one data source, performing additional processing using an additional data source, and / or marking the data as low quality.

5. The data preparation configuration entity according to any one of claims 2 to 4, wherein the processor is further arranged to: control the transceiver to send a subscription request for performing the data preparation to the at least one data source and / or data collection coordination entity.

6. The data preparation configuration entity according to any one of claims 2 to 5, wherein the processor is further arranged to: control the transceiver to send the processed data.

7. The data preparation configuration entity according to claim 1, wherein the transceiver is further arranged to send the data preparation configuration to a data preparation entity.

8. The data preparation configuration entity according to any one of the preceding claims, wherein the data preparation configuration entity is selected from a list of data preparation configuration entities comprising: Operation management and maintenance function OAM; edge enabling servers; and Application Enablement Server.

9. The data preparation configuration entity according to any of the preceding claims, wherein the processor is further arranged to control the transceiver to send a positive or negative acknowledgement in response to the request for application layer data processing management.

10. A data preparation configuration entity according to any one of the preceding claims, used to provide data preparation for AI / ML model training and / or inference data for an artificial intelligence AI / machine learning ML model.

11. The data preparation configuration entity according to any one of the preceding claims, wherein the at least one parameter including information for preparing the required data includes information related to at least one of the following items: Assessment of data quality; Recovery of missing data; Data cleaning; Formatting of data; labeling of data; and Separate data into datasets for one or more AI / ML training and / or inference tasks.

12. The data preparation configuration entity according to any of the preceding claims, wherein the request for application layer data processing management is received from a consumer, the consumer being selected from a list of consumers comprising: Third-party applications; VAL server; and Enable the server.

13. A data preparation entity in a wireless communication system, comprising: a transceiver arranged to receive a data preparation configuration, the data preparation configuration comprising at least one parameter, the at least one parameter comprising information for preparing required data, the required data being required from at least one data source, wherein the transceiver is further arranged to receive raw data from the at least one data source; a processor arranged to process the raw data based on the data preparation configuration; and wherein The processor is further arranged to control the transceiver to send a report indicating a data quality problem of the raw data and / or the processed data.

14. The data preparation entity of claim 13, wherein the processor is further arranged to: perform a data recovery operation based on a data quality problem of the original data.

15. The data preparation entity according to claim 14, wherein the data recovery operation comprises: Checking for missing data and / or low quality data and based on the checking, controlling the transceiver to request supplemental data from the at least one data source, performing additional processing using an additional data source, and / or marking the data as low quality.

16. The data preparation entity according to any one of claims 13 to 15, wherein the processor is further arranged to: control the transceiver to send a subscription request for performing the data preparation to the at least one data source and / or a data collection coordination entity.

17. The data preparation entity according to any one of claims 13 to 16, wherein the data preparation entity is selected from a list of data preparation entities comprising: Application enablement server; and Application-enabled client.

18. A data preparation entity according to any one of claims 13 to 17, used to provide data preparation for AI / ML model training and / or inference data for an AI / ML model.

19. The data preparation entity according to any one of claims 13 to 18, wherein the at least one parameter including information for preparing the required data includes information related to at least one of the following: Assessment of data quality; Recovery of missing data; Data cleaning; the formatting of the data; and Separate data into datasets for one or more AI / ML training and / or inference tasks.

20. A method in a data preparation configuration entity, the data preparation configuration entity being located in a wireless communication system, the method comprising: receiving a request for application layer data processing management, the request comprising a requirement for managing raw data from at least one data source; as well as At least one parameter of data preparation configuration is configured based on the request for application layer data processing management, the at least one parameter including information for preparing the required data.

21. The method according to claim 20, further comprising: receiving raw data from the at least one data source; processing the raw data based on the data preparation configuration; as well as A report is sent indicating data quality issues with the raw data and / or the processed data.

22. The method according to claim 21, further comprising: A data recovery operation is performed based on the data quality problem of the original data.

23. The method of claim 22, wherein the data recovery operation comprises: Checking for missing data and / or low quality data and based on the checking, controlling the transceiver to request supplemental data from the at least one data source, performing additional processing using an additional data source, and / or marking the data as low quality.

24. The method according to any one of claims 20 to 23, further comprising: A subscription request for performing the data preparation is sent to the at least one data source and / or a data collection coordination entity.

25. The method according to any one of claims 20 to 24, further comprising: The processed data is transmitted.

26. The method of claim 20, further comprising: The data preparation configuration is sent to a data preparation entity.

27. The method according to any one of claims 20 to 26, wherein the data preparation configuration entity is selected from a list of data preparation configuration entities comprising: OAM functions; edge enabling servers; and Application Enablement Server.

28. The method according to any one of claims 20 to 27, further comprising: A positive or negative acknowledgement is sent in response to the request for application layer data processing management.

29. A method according to any one of claims 20 to 28, used to provide data preparation for AI / ML model training and / or inference data for an AI / ML model.

30. The method according to any one of claims 20 to 29, wherein the at least one parameter comprising information for preparing the required data comprises information related to at least one of: Assessment of data quality; Recovery of missing data; Data cleaning; Formatting of data; labeling of data; and Separate data into datasets for one or more AI / ML training and / or inference tasks.

31. The method of any one of claims 20 to 30, wherein the request for application layer data processing management is received from a consumer, the consumer being selected from a list of consumers comprising: Third-party applications; VAL server; and Enable the server.

Images