Enabling data labels sharing for transfer learning

Abstract

A method including receiving from a peer network equipment a request to provide one or more data labels associated with a machine learning, authenticating and / or authorizing the peer network equipment and, in response to a successful authentication and / or authorization, obtaining data label information or a storage identifier of the data label information, and transmitting a response to the peer network equipment containing the obtained data label information or storage identifier.

Description

ENABLING DATA LABELS SHARING FOR TRANSFER LEARNINGTECHNICAL FIELD

[0001] The present disclosure relates to wireless communications, and more specifically to enabling data labels sharing for transfer learning.BACKGROUND

[0002] A wireless communications system may include one or multiple network communication devices, which may be otherwise known as network equipment (NE), supporting wireless communications for one or multiple user communication devices, which may be otherwise known as user equipment (UE), or other suitable terminology. The wireless communications system may support wireless communications with one or multiple user communication devices by utilizing resources of the wireless communication system (e.g., time resources (e.g., symbols, slots, subframes, frames, or the like) or frequency resources (e.g., subcarriers, carriers, or the like). Additionally, the wireless communications system may support wireless communications across various radio access technologies including third generation (3G) radio access technology, fourth generation (4G) radio access technology, fifth generation (5G) radio access technology, among other suitable radio access technologies beyond 5G (e.g., sixth generation (6G)).SUMMARY

[0003] An article “a” before an element is unrestricted and understood to refer to “at least one” of those elements or “one or more” of those elements. The terms “a,” “at least one,” “one or more,” and “at least one of one or more” may be interchangeable. As used herein, including in the claims, “or” as used in a list of items (e.g., a list of items prefaced by a phrase such as “at least one of’ or “one or more of’ or “one or both of’) indicates an inclusive list such that, for example, a list of at least one of A, B, or C means A or B or C or AB or AC or BC or ABC (i.e., A and B and C). Also, as used herein, the phrase “based on” shall not beconstrued as a reference to a closed set of conditions. For example, an example step that is described as “based on condition A” may be based on both a condition A and a condition B without departing from the scope of the present disclosure. In other words, as used herein, the phrase “based on” shall be constmed in the same manner as the phrase “based at least in part on. Further, as used herein, including in the claims, a “set” may include one or more elements.

[0004] A network equipment for wireless communication is described. The network equipment may be configured to, be capable of, or be operable to perform one or more operations as described herein. For example, the network equipment may include at least one memory and at least one processor coupled with the at least one memory and configured to cause the network equipment to receive from a peer network equipment a request to provide one or more data labels associated with machine learning; authenticate and / or authorize the peer network equipment and, in response to a successful authentication and / or authorization, obtain data label information or a storage identifier of the data label information; transmit a response to the peer network equipment containing the obtained data label information or storage identifier.

[0005] In some implementations of the network equipment and method described herein, said network equipment may be a network repository function or a network analytics training entity.

[0006] In some implementations of the network equipment and method described herein, said network equipment is configured to operate in a 5G System.

[0007] In some implementations of the network equipment and method described herein, said request may be a one-time request or a service subscription request that allows the exchange of new data labels once they become available and / or at least one notification condition is satisfied.

[0008] In some implementations of the network equipment and method described herein, said request may contain at least one of the following: an identifier related to a requested data label; a network condition related to a requested data label; a data label usage condition; reporting information related to a data label;a notification address for receiving a reporting of data label information.

[0009] In some implementations of the network equipment and method described herein, authenticating and / or authorizing the peer network equipment may comprise checking an allowability of data label permissions and / or interoperability rules.

[0010] In some implementations of the network equipment and method described herein, authenticating and / or authorizing the peer network equipment may comprise authenticating and / or authorizing the peer network equipment to obtain data label information from a further peer network equipment.

[0011] In some implementations of the network equipment and method described herein, the transmitted data label information may comprise one or more data labels with an assisting piece of information that contains: an analytics identifier where the said data label is to be used; input data identifying where the said data label is going to provide context when used; an analytics model and / or analytics model component where the said data label is going to be used; a data label source identifier to enable backtracking of the said data label; a network condition where the said data label is going to be used; an instruction related to applying the said data label to another analytics task, different from the one where the said data labels were originally used; a data re-distribution permission and / or restriction related with the said data label.

[0012] In some implementations of the network equipment and method described herein, data labels may be stored according to at least one of the following: together with data set information that relating data labels with a data set; together with analytics model information that relates data labels with an analytics model; as a separate entry that relates to data label information.

[0013] In some implementations of the network equipment and method described herein, wherein the processor is configured to cause said network equipment to store data label information in a second peer network equipment, the storage position in the second peer network equipment being identified by said storage identifier.

[0014] In another example, the network equipment may include at least one memory and at least one processor coupled with the at least one memory and configured to cause the networkequipment to transmit to a peer network equipment a request to provide one or more data labels associated with a machine learning model, and receive a response containing the data label information or a storage identifier for the data label information.

[0015] In some implementations of the network equipment and method described herein, the processor may be configured to cause said network equipment, when said response contains a storage identifier, to access information to request or subscribe to a further peer network equipment for receiving data label information, said further storage position in the peer network equipment being identified by said storage identifier.

[0016] In some implementations of the network equipment and method described herein, said network equipment may be a network analytics training entity.

[0017] In some implementations of the network equipment and method described herein, said peer network equipment may be a network repository function.

[0018] In some implementations of the network equipment and method described herein, the processor may be configured to cause said network equipment to operate as an analytical data repository function and to receive data label information from a first peer network equipment, the information being associated with a machine learning process, store the received information and assign a storage identifier, receive from a second peer network equipment a request that includes the said storage identifier to provide said data label information, authenticate and / or authorize the second peer network equipment and, in response to a successful authentication and / or authorization, obtain data label information, and transmit a response to the second peer network equipment containing the requested data label information.

[0019] A method performed by a network equipment is described. The method may include receiving from a peer network equipment a request to provide one or more data labels associated with a machine learning, authenticating and / or authorizing the peer network equipment and, in response to a successful authentication and / or authorization, obtaining data label information or a storage identifier of the data label information, and transmitting a response to the peer network equipment containing the obtained data label information or storage identifier.

[0020] In some implementations of the network equipment and method described herein, said network equipment may be a network repository function or a network analytics training entity.

[0021] In some implementations of the network equipment and method described herein, said peer network equipment may perform network analytics training.

[0022] In some implementations of the network equipment and method described herein, said network equipment may operate in a 5G System.

[0023] In some implementations of the network equipment and method described herein, said storage identifier may be an identifier of a further peer network equipment at which data label information is stored.

[0024] In the context of this disclosure a data label capability information may be information that identifies a capability, of a given NE, to provide data labels associated with a given AL / ML analytics (model).BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 illustrates schematically a network comprising a number of NWDAF variants and their respective input data sources and output result consumers;

[0026] Figure 2 illustrates schematically a Transfer Learning (TL) architecture involving a knowledge transfer, i.e., the transfer of an AI / ML Model X or related parameters, among two different Analytics Tasks that use different input data sets to produce different outputs;

[0027] Figure 3 illustrates a 5G System architecture allowing the ADRF to store and retrieve collected data and analytics;

[0028] Figure 4 illustrates a procedure of requesting or subscribing to Data Labels capabilities focusing on a direct Data Label exchange between an NWDAF MTLF DLS Producer and an NWDAF MTLF DLS Consumer;

[0029] Figure 5 illustrates a process of storing and deleting Data Labels into the ADRF;

[0030] Figure 6 illustrates a process of retrieving Data Labels stored into the ADRF;

[0031] Figure 7 illustrates an example of a wireless communications system in accordance with aspects of the present disclosure;

[0032] Figure 8 illustrates an example of a Network equipment in accordance with aspects of the present disclosure; and

[0033] Figure 9 illustrate a flowchart of a method performed by a Network equipment in accordance with aspects of the present disclosure.DETAILED DESCRIPTION

[0034] Network analytics and Artificial Intelligence / Machine Learning (AI / ML) are deployed in the 5G core network via the introduction of a network data analytics function (NWDAF). Support for various analytics types is elaborated in TS 23.288 (as incorporated herein). Each deployed NWDAF may support one or more Analytics IDs and may have the role of inference called “NWDAF AnLF”, or training called “NWDAF MTLF” or both. An AnLF that supports a specific Analytics ID inference subscribes to a corresponding model training logical function (MTLF) that is responsible for training.

[0035] Figure 1 illustrates a number of NWDAF variants and their respective input data sources and output result consumers, which may include 5G core NFs, AFs, 5G core repositories, e.g., Network Repository Function (NRF), User Data Manager (UDM), etc., and the Operations, Administration and Maintenance (0AM) (MnS Consumer or MF). The MTLF and AnLF may exchange AI / ML models, e.g., via the means of serialization or containerization. Optionally, a Data Collection Coordination Function (DCCF) and Messaging Framework Adapter Function (MFAF) may be involved to distribute and collect repeated data towards or from various data sources.

[0036] Current AI / ML mechanisms adopt an isolated training approach, where each AI / ML model is independently trained for a specific usage without considering prior training knowledge or experience. In other words, the instantiation of an AI / ML model includes training from “scratch”, assuming that the corresponding NWDAF MTLF is able to collect sufficient input data. In cases where the collected input data is not sufficient, this can be reflected in a confidence degree parameter that is provided to the analytics consumer when the requested output data is supplied to that consumer. The confidence degree indicates the “quality” of the data output (i.e., mainly for a predictive data output) that the NWDAF MTLF has produced, considering the amount of collected input data that is ideally needed.

[0037] Collecting sufficient input data can prove to be challenging, especially when dealing with a newly installed analytics service. For example it can be expensive to collect input data with constrained network and computing resources. Training an AI / ML model from scratch may take time and can impact the analytics service performance, especially when the requested time for AI / ML model training is limited.

[0038] In a network and service architecture, knowledge is an asset, and hence it is desirable to preserve and transfer knowledge when applicable. This is the objective of “Transfer Learning” (TL). TL is a technique that aims to share knowledge by reusing a pre-trained AI / ML model or parameters, related to an AI / ML model and which was prepared with respect to a certain task, for a new task, hence exploiting the knowledge gained a priori. An overview of the TL concept is illustrated in Figure 2 which shows a knowledge transfer, e.g., the transfer of an AI / ML Model X or related parameters, among two different Analytics Tasks that use different input data sets to produce different outputs.

[0039] TL can reuse a pre-trained AI / ML model: (i) as trained or partially trained, i.e., some of its parameters, (ii) as a starting point for further training with respect to a new task, e.g., using new data, or (iii) modified with respect to a new task or environment. AI / ML knowledge-based TL refers to a technique where the knowledge gained from training of one or more AI / ML models is applied or adapted to improve or develop another AI / ML model. A challenge with TL is to decide which part of the knowledge is beneficial to be transferred to assist a target task; this decision can be based on: (i) the relationship between the source and target tasks considering, e.g., the same or similar tasks, if they share the same features or not, (ii) the relationship of the environments in which the source and target tasks exist, e.g., are the domain of the source and target the same, share similar characteristics or are different, and (iii) the similarity and characteristics of data used for training in the source and target environments.

[0040] The task and environment relations among the source and target tasks can reveal whether some knowledge may be common such that knowledge sharing may improve the performance of a target domain or task, and identify which knowledge can be transferred and under which circumstances. In other words, TL aims to extract the knowledge from one or more source tasks and apply the knowledge to a target task. Knowledge transfer may be included in: (i) a context transfer, which describes how to apply the knowledge gained, (ii) ashared AI / ML model characteristic, e.g., a feature or parameter, (iii) a transformed AI / ML model characteristic, (iv) a relation mapping with respect to the applied network environment or usage.

[0041] The concept of knowledge reflects a developed “skill” or ability that can be adopted to a target task. In other words, knowledge is a quality that can be derived initially before being applied, considering commonality and the type of skills that can be re-used. Knowledge is distinct from, for example, AI / ML model parameters and model input and output data.

[0042] TL is currently used in 5G systems in several scenarios. Registering an AI / ML model in a repository for further use and employing a model profile can accelerate the adoption of TL. The AI / ML model profile may carry information related to the AI / ML model identifier, the preparation phase, i.e., considering which data sources were used, the time schedule and duration of training, the geographical area and objects used as well as some post training information including how to validate and test the AI / ML model. With respect to TL, the AI / ML model profile may carry information reflecting how a trained AI / ML model can be transformed to be re-used for another specific task.

[0043] In the network management and orchestration, a knowledge-based TL is considered in TR 28.858 (as incorporated herein), where a knowledge transfer management entity is introduced that holds knowledge supplied by different management services. In this way knowledge is shared without sharing AI / ML models to avoid sharing vendors specific valuable information.

[0044] In the application layer, TL has been considered in TR 23.700-82 (as incorporated herein), where an AI / ML model can be exchanged directly among the source and target analytics entities or stored and retrieved from a model registry. Registering an AI / ML model for TL may include the following information: (i) a task identifier, (ii) UE or group of UEs, (iii) service filter information, e.g., geographical area, time, environment, usage, and charging, (iv) model context information, e.g., set of features, training data requirements, required computing power and (v) permissions, i.e., access, exposure, and vendor.

[0045] In addition, the notion of a TL enabler, i.e., to detect the need for using TL for a certain AI / ML service or task, is already in place. A subscriber may provide the necessary model context information including the model type, features, dataset requirements, desiredconfidence level, UE(s), service profile, location, and time of interest. The TL enabler can discover, fetch a model from the repository, and determine whether such model shall be used as a pre-trained model considering the similarity in its capabilities, input data and previous usage experience.

[0046] To date, TL considers as knowledge the AI / ML model transfer, parameters or feature transfer or other model related information or capabilities transfer. Although the notion of experience contains the idea of knowledge transferred to a new task, this knowledge does not contain data labels that can be used to characterize data related to AI / ML model training.

[0047] Data labels are meta-data that can be attached to data assets to help classify data. They are tags or annotations added to raw data to help machine learning (ML) and artificial intelligence (Al) models understand and learn from it. Alternatively or additionally, data labels provide context and categorization for AI / ML models to interpret data effectively.

[0048] Data labelling is the activity of assigning context or meaning to data that may vary with respect to the analytics service, e.g., in the case of network load, different labels may be used for analytics related to service experience where the high load may mean congestion, or energy saving where the high load may mean no energy saving is applicable.

[0049] With reference to Ligure 3, the 5G System architecture allows the ADRF to store and retrieve the collected data and analytics. The following options are supported:• ADRF exposes the Nadrf service for storage and retrieval of data by other 5GC NTs (e.g. NWDAF) which access the data using Nadrf services.• Based on the NF request or configuration on the DCCF, the DCCF may determine the ADRF and interact directly or indirectly (via the Messaging Framework) with the ADRF to request or store data.• The ADRF stores data received.• The ADRF checks if the Data Consumer is authorized to access ADRF services and provides the requested data using the procedures specified in clause 7.1.4 of TS 23.501.

[0050] Currently there are no mechanisms that can enable data labels sharing or exchange between analytics functions responsible for training, e.g., NWDAF MTLF. In addition, there is no mechanism for storing and retrieving data labels from an ADRF.

[0051] With reference to the aspects depicted herein, the term Artificial Intelligence (Al) may be used to define systems that are capable of learning from data to perform tasks without being explicitly programmed. Machine Learning (ML) may be considered a class of Al, although the terms Al ad ML may be used alternately and together.

[0052] The solution proposed here relates to an apparatus and method that introduces data label transfer capability among analytic services that perform AI / ML model training, e.g., among NWDAF MTLFs. Data label transfer capability is introduced is by providing service extensions to allow the data label owner, e.g., the NWDAF MTLF that owns data labels, to exchange data labels with interested analytics training entities, e.g., other NWDAF MTLFs.

[0053] In general, the task of labelling data may take time, resources, and may need an experienced human or specialized code that assures the desired outcome when input data sets are used for AI / ML model training. Labels can be shared considering specific strategies, e.g., among data samples that share common data sets and / or environmental conditions or among the same analytics service types. Transferring specific labels may prove to be useful when the problem with inaccuracy, i.e., when a trained AI / ML model is not performing as expected, is not an issue that relates to obtaining more raw data, but the outcome of not having correct data labels. Issues with data labels can be caused due to outdated data labels because of changes in the network conditions, e.g., topology or user movement habits (for instance towards a new training station), or simply because of a lack of data labels, i.e., having no data labels to characterize newly collected input data. The exchange of data labels can also be more efficient since the amount of the data related to data labels transfer can be small.

[0054] New data labels can be created or developed by a Data Label Producer that creates or supplies labels. Such a Data Label Producer can be realized as an analytics function or analytics service. When a new condition arises an analytics function or analytics service can characterize data based on so-called “ground truth data”, i.e. real- world data that represents the observed outcome of a system being modeled. When an AI / ML model is characterized as inaccurate and the cause behind is not the lack of raw data but the interpretation of data, i.e., the data labelling, then the ground truth data can assist with the creation of new data labels. The assumption is that the analytics function or analytics service is equipped with a logic / algorithm or function to create new data labels by considering the deviation of new input data from old data, and the impact of the deviation on analytics results.

[0055] Once new data labels are obtained we need to consider when to transfer them, i.e. the triggering conditions, which may include the options of: (i) once a new data label is available and / or (ii) when the deviation among old and new data label surpasses a configured limit, which can be applicable for numerical data and / or a new data label belongs to a new category (iii) when the impact of new data labels on the output results surpasses a pre-configured limit or category.

[0056] Additionally, aspects depicted herein consider where to transfer data labels to, i.e., towards a repository such as an ADRF that stores data labels together with data and AI / ML models or among authorized NFs, e.g., among NWDAF MTLFs or among data sources and a NWDAF MTLF.

[0057] Finally, aspects of the present disclosure provides for techniques to store data labels, which may include the options of: (i) stored together with a specific set data or data statistics (e.g., data range, max, min, deviation) that describe a data set, (ii) stored together with the AI / ML model, i.e., including the model ID and / or model type, where this data label is expected to be used, or (iii) stored separately as data labels that can be associated with one or more of: multiple AI / ML models, i.e., AI / ML model ID or model type, multiple analytic services including Analytics IDs, multiple data sets, which can be described by a variety of data statistics parameters including, e.g., at least a data range, a minimum or maximum value, a standards deviation and mean, a data distribution, while other data statistics parameters may also apply, and the source ID of data labels and / or the data label owner ID, which may be the same or different.

[0058] Once new data labels are created or obtained from another entity, they can be shared among interested analytics training functions or services, e.g., NWDAF MTLF. Data labels can be shared:• Among the same type of analytic functions / services under similar situations, with the same NWDAF Analytics ID, and / or among specific features with same Feature ID (in case of Vertical Federated Learning):o in a different geographical area of similar kind, e.g., the network load pattern in a city centre during shopping hours or at night. o in the same geographical area under the operation of a different mobile network operator, in case of roaming, e.g., among analytic services that belong to different operators, but same vendor or among compatible vendors.• Among interrelated analytic services and / or features under similar situations, e.g., (i) NWDAF Analytics ID related to Analytics ID = User Mobility and Analytics ID = NF load or (ii) Analytics ID = NF load and Analytics ID = Network Performance.• To assist multi-task learning or multi-model arrangement, e.g., for ensemble learning, by applying different data labels for a specific task as part of enhancing the AI / ML model training.• To assist newly installed AI / ML models in NWDAF without any available data labels, especially when such models are based on semi-supervised learning in where a few labels can help build knowledge.• To assist rapid learning by sharing knowledge, i.e., share new data labels, once developed.• To test and / or validate an AI / ML model or related parameters whenever is needed and is applicable.

[0059] Each data label may characterize one data unit, e.g., a single data value, or a set of data, e.g., specified between a minimum and maximum, a distribution or other data statistics parameters. Furthermore, each data label can optionally be associated with at least a single AI / ML model ID and / or Analytics ID. Each data label or data label set may carry metadata to characterize data labels containing at least one of the following pieces of information:• The data label identity and the version of the data label.• The data label owner identity, that holds the data label rights.• The data label source ID that produced the data label, which can be the same as the data label owner or different.• The analytics service or task, e.g., NWDAF Analytics ID.• The AI / ML model details including the AI / ML model ID or type, feature ID, AI / ML model depth level, etc.• A data set ID or description, e.g., DataSetTag, or including data statistics (e.g., range, distribution, etc.).• The use case or network context or a purpose or intent, e.g., network load, network performance, energy state, network faults, where the data label is used.• The target object(s) involved when creating data labels, e.g., UE types, NF type, application type.• The network context, i.e., geographical area, network load, energy conditions, network domain, Public Land Mobile Network (PLMN) ID.• The network slice, i.e., Single - Network Slice Selection Assistance Information (S- NSSAI), or network slice type, where the data label was and / or is suggested to be used.• The edge data network, e.g., Data Network Name (DDN), where the data label was and / or is suggested to be used.• The event or set of events associated with the adoption of a data label, e.g., upon a UE movement, or for stationary UEs.• The data label usage rating in terms of the performance accuracy that can be modelled as a score percentage including optionally deviation or as true positive / negative or false positive / negative.• The details related to data label transfer for an inter-related task, i.e., re-weighting with respect to a specified analytics service or task.• Permission related to data label sharing, i.e., allowed consumers, e.g., NF, AF, vendor information or mobile operator information.• AI / ML model interoperability indicator to show compatibility of data labels with AI / ML model types or AI / ML model IDs.

[0060] A Data Label Service (DLS) Consumer, i.e., a network entity with or without invalid data labels or partially invalid data labels, can be an analytics service or analytics function, e.g., an NWDAF MTLF. A DLS Consumer can obtain data labels when needed, i.e., upon request, or on a subscription basis. A DLS Consumer can be an analytics service or analytics function, e.g., an NWDAF MTLF. A DLS Consumer may request data labels, e.g., upon realizing that the AI / ML model performance is inaccurate with the cause not being the lack of raw data but the interpretation of data, i.e., the data labelling. Alternatively, a DLSConsumer can subscribe to receive updates related to data labelling once they become available and / or upon pre-configured conditions being met (e.g., data labels that belong to a different category or with a value great than specified threshold and / or that impact the result significantly greater than a specified threshold) to assure rapid and even proactive AI / ML model re-training, i.e., before performance degradation occurs.

[0061] A DLS Consumer can then request data labels from a selected DLS Producer by providing a request or subscription, which contains one or more of the following types of information:• At least one indication related to identifying data labels, which may include one of the following: o data label identity and / or version, o data label owner identity, and / or data label source identity, o analytics service or task identity, e.g., Analytics ID, o AI / ML model ID or type and / or feature ID, o data set identity and / or data tag identity, i.e., related to data statistics.• At least one indication that identifies the network conditions, which may include one of the following: o use case or a purpose or intent, o target object(s) involved, o network context, o network slice, edge data network.• At least one conditions in where the desired data labels is expected to be used: o event or set of events associated with the adoption of a data label, o data label transfer capabilities for an inter-related task, o data label rating in terms of the performance accuracy, o data label usage permissions, o data label interoperability.• Reporting information related to the selected data label or data label set including at least one of the following: o reporting time information, e.g., provide an immediate report, a periodic time schedule, reporting until a specified time instance.o filter information, i.e., trigger a report upon:■ a network measurement or condition in relation to a given threshold,■ a new data label measurement or condition with respect to a previous data label update (e.g., data labels with a deviation greater than a threshold, or with an impact on the results greater than threshold),■ a new amount of data labels for a given data set or data set description (based on data statistics) or Analytics ID, AI / ML model or Feature ID or AI / ML model or Feature type. o reporting style, e.g., reporting order and / or format of information. o reporting service information, e.g., warning message when a subscription is about to be terminated or mention the remaining number of reports.• A notification address for reporting, which can be the address of the consumer or some other address from which the consumer can obtain the data label or data label set.

[0062] A DLS Consumer can receive a data label report that contains at least one of the following pieces of information:• The data label or data label set (that matched at least one of the request or subscription details),• The analytics services or tasks, e.g., NWDAF Analytics ID, where the data labels can be used.• The description of potential data sets where the provided data labels can be used (if data labels are not associated with a specific data set); this may contain at least one of the following: o data statistics related to the adoption of data labels. o one or more events related to the adoption of data labels.• The type of potential AI / ML models where the provided data labels can be used if data labels are not associated with a specific AI / ML model.• The one or more Feature ID that data labels can be used if Federated Learning is employed.• The data label source ID to backtrack data labels sources for security and performance purposes.• The network conditions related to the adoption of data labels including: (i) target object(s), (ii) network context, (iii) network slice information, and (iv) edge data network information.• The new data labels for a given: (i) data set or data set description (based on data statistics) or (ii) Analytics ID, or (iii) AI / ML model or Feature ID or AI / ML model or Feature type or (iv) network condition.• Instructions related to data label transfer, e.g., applied weight, in case of usage for an inter-related task.• Data label re-distribution restrictions, i.e., providing permission information related to the provided data labels.• A correlation ID related to the communication transaction that applies only for the case of the subscription.• Reporting service information, e.g., warnings or number of remaining reports or reporting time, that applies only for the case of the subscription.

[0063] In case data labels are stored in a storage repository, e.g., ADRF, a data label consumer can receive the repository or storage identifier, e.g., ADRF ID, and transaction storage ID to issue a request to obtain the desired data label or data label set.

[0064] The procedures described herein provide embodiments of this disclosure, which include requesting and providing Data Labels to a DLS Consumer, i.e., an analytics function involved in model training, e.g., NWDAF MTLF. Two different variants are described:1. The transferred Data Labels are available locally at a selected NWDAF MTLF; NWDAF MTLFs register their data label capability related to data sets to the NRF including of one or more metadata characteristics.2. The transferred data labels are obtained from an ADRF via the NWDAF MTLF that owns or is responsible for the distribution or sharing of Data Labels.

[0065] The techniques of the present disclosure support a Request / Subscribe to Data Label Capabilities of NWDAF MTLF Data Label Producer. Assuming that the DLS Consumer is pre-configured with the details of the DLS Producer or has the capability to discover an appropriate DLS Producer, this embodiment relates a process of requesting or subscribing to Data Labels capabilities focusing on a direct Data Label exchange between an NWDAFMTLF DLS Producer and an NWDAF MTLF DLS Consumer. This process is illustrated in Figure 4, with the following steps:1. The DLS Consumer has determined that its Data Labels are invalid.The DLS Consumer is configured or can discover and select the appropriate DLS Producer for obtaining new Data Labels. Once the DLS Consumer selects a DLS Producer, which can be more than one, (i.e., it can get different Data Labels from different DLS Producers that better match its selection criteria and needs), it can issue either: (i) an on-demand request to get the desired Data Labels or (ii) a subscription to get updates on Data Labels from other NWDAF MTLFs that share similar tasks (Analytics IDs), AI / ML models and input data, under similar network conditions (e.g., slice, edge data network) and usage criteria (e.g., network context, use case).Option 1 : Data Labels request2. The DLS Consumer issues a request to obtain the desired Data Labels from a selected DLS Producer (and may request data labels from more than one DLS Producer).The request related service used is determined based on how data labels are stored in the DLS Producer. If the data labels are stored together with data sets, then Nnwdaf DataManagement Fetch service can be used including to request for Data Label capabilities or if Data Labels are stored together with an AI / ML model then the Nnwdaf MLModellnfo Request service can be used instead. Otherwise, if data labels are stored separately a new service shall be used to request Data Labels irrespective of a specific data set and / or AI / ML model, e.g., Nnwdaf DataLabels F etch.The Data Labels capabilities shall include at least an identifier related to the desired Data Labels, an indication of the network context, a usage condition and reporting information including the notification address.3. The DLS Producer can then reply, providing Data Labels and any combination of other associated information, e.g., with respect to an Analytics ID, AI / ML model information, data set(s) or data set description or related events, also including network conditions and / or information for adopting Data Labels for usage of an interrelated task if this is applicable. If backtracking is required, then the Source ID of the Data Labels shall be provided too.Once new Data Labels are determined, i.e., additional from the ones to replace, then their provision shall relate them to a specific data set or data set description, Analytics ID, AI / ML model information or network condition. The provision of Data Labels to a DLS Consumer shall include instructions on how to re-distribute or restrict further redistribution.The service used to response is again determined based on how the request was issued, i.e., considering the way Data Labels are stores in the DLS Producer. Data Labels stored together with data sets, may use the Nnwdaf_DataManagement_Notify service, while Data Labels stored together with an AI / ML model may use the Nnwdaf MLModellnfo Request response service. Otherwise, if Data Labels are stored separately, a new service shall be used irrespective of data and AI / ML models, e.g., Nnwdaf_DataLabels_Notify.Option 2: Data Labels subscription4. The DLS Consumer issues a subscription to constantly get updates related to the desired Data Labels from a selected DLS Producer (and may subscribe to more than one DLS Producer).The subscription related service again is determined based on how Data Labels are stored in the DLS Producer. Data Labels stored together with data sets use Nnwdaf DataManagement Subscribe service including Data Label capabilities or if Data Labels are stored together with an AI / ML model then the Nnwdaf MLModellnfo Subscribe service can be used. Otherwise, if Data Labels are stored separately then a new service shall be used to subscribe to Data Labels, e.g., Nnwdaf_DataLabels_Subscribe.The Data Labels capabilities shall include at least an identifier related to the desired Data Labels, an indication of the network context, a usage condition and reporting information including the notification address.5. The DLS Producer can then notify the DLS Consumer once the notification conditions are met, i.e., once new Data Labels are available or when new Data Labels value and / or impact is greater than a given threshold or when network conditions alternate beyond a threshold or upon a given event.Data Labels notification updates contain Data Labels with respect to an Analytics ID, AI / ML model information, data set(s) or data set description or related events, also including network conditions and / or information for adopting Data Labels for usage of an inter-related task if this is applicable. If backtracking is required, then the Source ID of the data labels shall be provided too.Once new Data Labels are determined, i.e., additional from the ones to replace, then their provision shall relate them to a specific data set or data set description, Analytics ID, AI / ML model information or network condition. The provision of data labels to a DLS Consumer shall contain instructions on how to re-distribute or restrict redistribution of data labels further.Each notification shall include a correlation ID to relate it to a specific subscription and shall also carry a warning or reporting information related to the subscription lifetime.The service used to response is again determined based on how the request was issued, i.e., considering the way Data Labels are stored in the DLS Producer. Data Labels stored together with data sets, may use the Nnwdaf_DataManagement_Notify service, while Data Labels stored together with an AI / ML model may use the Nnwdaf MLModellnfo Request response service. Otherwise, if data labels are stored separately, a new service shall be used to request Data Labels, e.g., Nnwdaf_DataLabels_N otify . A DLS Producer may characterize an AI / ML model as inaccurate as per TS 23.288 clause 6.2E. If the cause behind is not the lack of data but the interpretation of data, i.e., the data labelling, then the DLS Producer may create new Data Labels to replace the invalid ones provided that it is equipped with a data labelling logic / algorithm.The DLS Producer can create new Data Labels by considering the deviation of ground truth data and its impact to analytics results. Once new Data Labels are available and the notification conditions are met, the DLS Producer provides updates that contain Data Labels including the respective metadata as described in step 5.The service used to response is again determined based on how the request was issued, i.e., considering the way Data Labels are stored in the DLS Producer, i.e.,using Nnwdaf_DataManagement_Notify service when Data Labels are stored together with data, Nnwdaf MLModellnfo Request response service if stored together with an AI / ML model and using a new service, e.g., Nnwdaf_DataLabels_Notify, if Data Labels are stored separately.In case Data Labels are deleted the DLS Consumer is notifies and the subscription is terminated.

[0066] The techniques of the present disclosure further support Request / Subscribe to Data Labels Capabilities from ADRF The DLS Producer may store Data Labels locally or may also instead store them in the data repository, i.e., ADRF, where data, analytics results and AI / ML models can also be stored. This embodiment sheds light into the following two steps including: (i) the process of storing and deleting Data Labels into the ADRF, and (ii) the process of requesting or subscribing to Data Labels capabilities indirectly, i.e., not from the DLS Producer, but instead from the respective ADRF where they were stored. The process of storing and deleting Data Labels into the ADRF, is illustrated in Figure 5.0. The DLS Producer determines that it needs to store Data Labels in the ADRF, (e.g., due to local storage issues), together with a specific data set or together with a specific AI / ML model or as a separate entry that can relate with multiple data sets and AI / ML models or other Data Label capabilities.In the process of storing Data Labels in the ADRF:1. The DLS Producer issues a storage request to the ADRF. The related service relies on how data labels shall be stored in ADRF. The Nadrf DataManagement StorageRequest and Nadrf_MLModelManagement_StorageRequest per TS 23.288 clause 5B and clause 10.2 are enhanced to include Data Label capabilities and are used when Data Labels stored together with data sets or AI / ML model respectively. Data Labels stored separately can use a new service irrespective of a specific data set and / or AI / ML model, e.g., Nadrf DataLabels StorageRequest. The Data Labels capabilities shall include at least an identifier (i.e., a Data Label ID, a Data Label owner identity, Data Label source ID, Analytics ID, an AI / ML model associated ID), an indication of the network context (i.e., target object, slice, edge data network, network performance / load / energy state, geographical area, PLMN ID),a usage condition (i.e., Data Label rating, use case, intent, event), Data Label modification details for inter-related usage, Data Label re-distribution policy, permissions and interoperability.2. The ADRF stores the provided Data Labels together with the related information. Storage is performed based on the data provided in the request. Otherwise, the request may provide a pointer for the ADRF to download the respective information to be stored.Storage can be arranged together with a specific data set using the DataSetTag, or with a specific AI / ML model or independently together with the related Data Label information.3. The ADRF can then return a response including the Storage Transaction Identifier. The service used to response is determined based on how the request was issued, i.e., considering the way data labels are stored. Data labels stored together with data sets, may use the Nadrf DataManagement StorageResponse associated with a DataSetTag(s), while Data Labels may use Nadrf_MLModelManagement_StorageResponse when stored together with an AI / ML model. Otherwise, if data labels are stored separately, a new service shall be used to request data labels irrespective of data and AI / ML models, e.g., Nadrf_DataLabels_storageResponse.In the process of deleting Data Labels from the ADRF:4. The DLS Producer issues a storage deletion message to the ADRF using the Transaction Reference ID. The service used is determined based on how the request was issued and Data Labels were stored. Data Labels stored together with data sets may use the Nadrf DataManagement Delete Request service, while Data Labels may use Nadrf_MLModelManagement_Delete Request service when stored together with an AI / ML model. Otherwise, if data labels are stored separately, a new service shall be used to delete Data Labels, e.g., Nadrf DataLabels Delete Request.5. The ADRF deletes the requested entries.6. The ADRF provides back an operation execution result indication, different for each respective way the Data Labels were stored.The process of retrieving Data Labels stored into the ADRF, is illustrated in Figure 6.0. The DLS Producer stores Data Labels in the ADRF, either together with a specific data set or together with a specific AI / ML model or as separate entry that can relate with multiple, data sets and AI / ML models and / or other data label metadata.1. The DLS Producer registers its Data Label capability in the NRF for other interested entities to be able to discover it. The registration may contain any of the Data Label metadata including an identifier (i.e., a Data Label ID, a Data Label owner identity, Data Label source ID, Analytics ID, an AI / ML model associated ID), a network context (i.e., target object, slice, edge data network, network performance / load / energy state, geographical area, PLMN ID), a usage condition (i.e., Data Label rating, use case, intent, event), data label modification details for interrelated usage, Data Label re-distribution policy, permissions and interoperability.2. The DLS Consumer discovers and selects one or more DLS Producer(s) by issuing a request that contains any combination of the Data Label metadata.Once the DLS Consumer selects a DLS Producer, it can issue either: (i) an on-demand request or (ii) a subscription to constantly get updates on Data Labels.Option 1 : Data Labels request3. The DLS Consumer issues a request to get the desired Data Labels from a selected DLS Producer (and may request data labels to more than one DLS Producer at the same time).The request related service used is determined based on how data labels are stored in the DLS Producer. Data Labels stored together with data sets use Nnwdaf_DataManagement_Fetch, while Data Labels stored together with an AI / ML model can use the Nnwdaf MLModellnfo Request service both including the related Data Label capabilities. If data labels are stored separately then a new service shall be used to request Data Labels irrespective of a specific data set and / or AI / ML model, e.g., Nnwdaf_DataLabels_Fetch.The Data Labels capabilities shall include at least an identifier, an indication of the network context, a usage condition and reporting information including the notification address.4. The DLS Producer as the Data Label owner or as being responsible for Data Labels re-distribution it authenticates the request that contains Data Label capabilities.If the authentication failed, the DLS Producer provides failure response indicating the reasons and the process terminates at this point.5. The DLS Producer can then notify the DLS Consumer providing the Storage Data Label Fetch ID, which is carried on the respective service, i.e., using Nnwdaf_DataManagement_Notify, Nnwdaf_MLModelInfo_Request response or Nnwdaf_DataLabels_Notify, based on how the request was issued considering the way data labels are stores in the DLS Producer.6. The DLS Consumer can then use the Storage Data Label Fetch ID carried on the respective service, i.e., using Nadrf_DataManagement_RetrievalRequest, Nadrf MLModelManagement RetrievalRequest orNadrf DataLabels RetrievalRequest, to request the ADRF the desired Data Labels.7. The ADRF can then reply providing Data Labels (and optionally new Data Label, i.e., additional from the ones to replace if available) and any combination of other related information with respect to an Analytics ID, AI / ML model information, data set(s) or data set description or related events, also including network conditions and / or information for using Data Labels if this is applicable. If backtracking is required, then the Source ID of the Data Labels shall be provided too. The provision of Data Labels to a DLS Consumer shall include instructions on how to re-distribute or restrict redistribution of Data Labels further.The ADRF can then use the respective service i.e., using Nadrf DataManagement RetrievalRequest response,Nadrf MLModelManagement RetrievalRequest response orNadrf DataLabels RetrievalRequest response to provide the Data Labels and other related information to the DLS Consumer.Option 2: Data Labels subscription8. The DLS Consumer issues a subscription request to get the desired Data Labels from a selected DLS Producer (and may request Data Labels to more than one DLS Producer at the same time).The subscription related service used is determined based on how data labels are stored in the DLS Producer, i.e., Nnwdaf DataManagement Subscribe if stored together with data, Nnwdaf MLModellnfo Subscribe if data labels are storedtogether with an AI / ML model and Nnwdaf DataLabels Subscribe if stored independently.The Data Labels capabilities shall include at least an identifier related to the desired data labels, an indication of the network context, a usage condition and reporting information including the notification address. The DLS Producer as the Data Label owner or as being responsible for Data Labels re-distribution it authenticates the subscription request that contains Data Label capabilities.If the authentication failed, the DLS Producer provides failure response indicating the reasons and the process terminates at this point. The DLS Producer can then notify the DLS Consumer providing the Storage Data Label Transaction ID, which is carried on the respective service, i.e., using Nnwdaf_DataManagement_Notify, Nnwdaf_MLModelInfo_Notify or Nnwdaf_DataLabels_Notify, based on how the request was issued considering the way Data Labels are stores in the DLS Producer. The DLS Consumer can then use the Storage Data Label Transaction ID carried on the respective service, i.e., using Nadrf_DataManagement_RetrievalRequest, Nadrf MLModelManagement RetrievalRequest orNadrf DataLabels RetrievalRequest, to subscribe to the ADRF for getting updates related to the desired Data Labels. The DLS Producer can then notify the DLS Consumer once the notification conditions are met, i.e., once new Data Labels are available or when new Data Labels value and / or impact is greater than a given threshold or when network conditions alternate beyond a threshold or upon a given event.The ADRF can then reply providing Data Label updates (and optionally new Data Labels if available) and any combination of other related information with respect to an Analytics ID, AI / ML model information, data set(s) or data set description or related events, also including network conditions and / or information for using Data Labels if this is applicable. If backtracking is required, then the Source ID of the Data Labels shall be provided too. The provision of Data Labels to a DLS Consumer shall include instructions on how to re-distribute or restrict further redistribution.Each notification shall include a correlation ID to relate it to a specific subscription and shall also carry a warning or reporting information related to the subscription lifetime.The ADRF can then use the respective service i.e., using Nadrf_DataManagement_RetrievalNotify, Nadrf_MLModelManagement_Notify or Nadrf DataLabels Notify to provide the Data Labels and other related information to the DLS Consumer.In case Data Labels are deleted the DLS Consumer is notifies and the subscription is terminated.

[0067] Eigure 7 illustrates an example of a wireless communications system 100 in accordance with aspects of the present disclosure. The wireless communications system 100 may include one or more NE 102, one or more UE 104, and a core network (CN) 106. The wireless communications system 100 may support various radio access technologies. In some implementations, the wireless communications system 100 may be a 4G network, such as an LTE network or an LTE- Advanced (LTE-A) network. In some other implementations, the wireless communications system 100 may be a NR network, such as a 5G network, a 5G- Advanced (5G-A) network, or a 5G ultrawideband (5G-UWB) network. In other implementations, the wireless communications system 100 may be a combination of a 4G network and a 5G network, or other suitable radio access technology including Institute of Electrical and Electronics Engineers (IEEE) 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20. The wireless communications system 100 may support radio access technologies beyond 5G, for example, 6G. Additionally, the wireless communications system 100 may support technologies, such as time division multiple access (TDMA), frequency division multiple access (FDMA), or code division multiple access (CDMA), etc.

[0068] The one or more NE 102 may be dispersed throughout a geographic region to form the wireless communications system 100. One or more of the NE 102 described herein may be or include or may be referred to as a network node, a base station, a network element, a network function, a network equipment, a radio access network (RAN), a NodeB, an eNodeB (eNB), a next-generation NodeB (gNB), or other suitable terminology. An NE 102 and a UE 104 may communicate via a communication link, which may be a wireless or wiredconnection. For example, an NE 102 and a UE 104 may perform wireless communication (e.g., receive signaling, transmit signaling) over a Uu interface.

[0069] An NE 102 may provide a geographic coverage area for which the NE 102 may support services for one or more UEs 104 within the geographic coverage area. For example, an NE 102 and a UE 104 may support wireless communication of signals related to services (e.g., voice, video, packet data, messaging, broadcast, etc.) according to one or multiple radio access technologies. In some implementations, an NE 102 may be moveable, for example, a satellite associated with a non-terrestrial network (NTN). In some implementations, different geographic coverage areas 112 associated with the same or different radio access technologies may overlap, but the different geographic coverage areas may be associated with different NE 102.

[0070] The one or more UE 104 may be dispersed throughout a geographic region of the wireless communications system 100. A UE 104 may include or may be referred to as a remote unit, a mobile device, a wireless device, a remote device, a subscriber device, a transmitter device, a receiver device, or some other suitable terminology. In some implementations, the UE 104 may be referred to as a unit, a station, a terminal, or a client, among other examples. Additionally, or alternatively, the UE 104 may be referred to as an Internet-of- Things (loT) device, an Internet-of-Everything (loE) device, or machine-type communication (MTC) device, among other examples.

[0071] A UE 104 may be able to support wireless communication directly with other UEs 104 over a communication link. For example, a UE 104 may support wireless communication directly with another UE 104 over a device-to-device (D2D) communication link. In some implementations, such as vehicle-to-vehicle (V2V) deployments, vehicle-to- everything (V2X) deployments, or cellular-V2X deployments, the communication link 114 may be referred to as a sidelink. For example, a UE 104 may support wireless communication directly with another UE 104 over a PC5 interface.

[0072] An NE 102 may support communications with the CN 106, or with another NE 102, or both. For example, an NE 102 may interface with other NE 102 or the CN 106 through one or more backhaul links (e.g., SI, N2, N2, or network interface). In some implementations, the NE 102 may communicate with each other directly. In some other implementations, the NE 102 may communicate with each other or indirectly (e.g., via theCN 106. In some implementations, one or more NE 102 may include subcomponents, such as an access network equipment, which may be an example of an access node controller (ANC). An ANC may communicate with the one or more UEs 104 through one or more other access network transmission entities, which may be referred to as a radio heads, smart radio heads, or transmission-reception points (TRPs).

[0073] The CN 106 may support user authentication, access authorization, tracking, connectivity, and other access, routing, or mobility functions. The CN 106 may be an evolved packet core (EPC), or a 5G core (5GC), which may include a control plane entity that manages access and mobility (e.g., a mobility management entity (MME), an access and mobility management functions (AMF)) and a user plane entity that routes packets or interconnects to external networks (e.g., a serving gateway (S-GW), a Packet Data Network (PDN) gateway (P-GW), or a user plane function (UPF)). In some implementations, the control plane entity may manage non-access stratum (NAS) functions, such as mobility, authentication, and bearer management (e.g., data bearers, signal bearers, etc.) for the one or more UEs 104 served by the one or more NE 102 associated with the CN 106.

[0074] The CN 106 may communicate with a packet data network over one or more backhaul links (e.g., via an SI, N2, N2, or another network interface). The packet data network may include an application server. In some implementations, one or more UEs 104 may communicate with the application server. A UE 104 may establish a session (e.g., a protocol data unit (PDU) session, or the like) with the CN 106 via an NE 102. The CN 106 may route traffic (e.g., control information, data, and the like) between the UE 104 and the application server using the established session (e.g., the established PDU session). The PDU session may be an example of a logical connection between the UE 104 and the CN 106 (e.g., one or more network functions of the CN 106).

[0075] In the wireless communications system 100, the NEs 102 and the UEs 104 may use resources of the wireless communications system 100 (e.g., time resources (e.g., symbols, slots, subframes, frames, or the like) or frequency resources (e.g., subcarriers, carriers)) to perform various operations (e.g., wireless communications). In some implementations, the NEs 102 and the UEs 104 may support different resource structures. For example, the NEs 102 and the UEs 104 may support different frame structures. In some implementations, such as in 4G, the NEs 102 and the UEs 104 may support a single frame structure. In some otherimplementations, such as in 5G and among other suitable radio access technologies, the NEs 102 and the UEs 104 may support various frame structures (i.e., multiple frame structures). The NEs 102 and the UEs 104 may support various frame structures based on one or more numerologies.

[0076] One or more numerologies may be supported in the wireless communications system 100, and a numerology may include a subcarrier spacing and a cyclic prefix. A first numerology (e.g., / r=0) may be associated with a first subcarrier spacing (e.g., 15 kHz) and a normal cyclic prefix. In some implementations, the first numerology (e.g., / r=0) associated with the first subcarrier spacing (e.g., 15 kHz) may utilize one slot per subframe. A second numerology (e.g., / r=l) may be associated with a second subcarrier spacing (e.g., 30 kHz) and a normal cyclic prefix. A third numerology (e.g., / r=2) may be associated with a third subcarrier spacing (e.g., 60 kHz) and a normal cyclic prefix or an extended cyclic prefix. A fourth numerology (e.g., / r=3) may be associated with a fourth subcarrier spacing (e.g., 120 kHz) and a normal cyclic prefix. A fifth numerology (e.g., / r=4) may be associated with a fifth subcarrier spacing (e.g., 240 kHz) and a normal cyclic prefix.

[0077] A time interval of a resource (e.g., a communication resource) may be organized according to frames (also referred to as radio frames). Each frame may have a duration, for example, a 10 millisecond (ms) duration. In some implementations, each frame may include multiple subframes. For example, each frame may include 10 subframes, and each subframe may have a duration, for example, a lms duration. In some implementations, each frame may have the same duration. In some implementations, each subframe of a frame may have the same duration.

[0078] Additionally or alternatively, a time interval of a resource (e.g., a communication resource) may be organized according to slots. For example, a subframe may include a number (e.g., quantity) of slots. The number of slots in each subframe may also depend on the one or more numerologies supported in the wireless communications system 100. For instance, the first, second, third, fourth, and fifth numerologies (i.e., / r=0, jU=l, / r=2, jU=3, / r=4) associated with respective subcarrier spacings of 15 kHz, 30 kHz, 60 kHz, 120 kHz, and 240 kHz may utilize a single slot per subframe, two slots per subframe, four slots per subframe, eight slots per subframe, and 16 slots per subframe, respectively. Each slot may include a number (e.g., quantity) of symbols (e.g., OFDM symbols). In someimplementations, the number (e.g., quantity) of slots for a subframe may depend on a numerology. For a normal cyclic prefix, a slot may include 14 symbols. For an extended cyclic prefix (e.g., applicable for 60 kHz subcarrier spacing), a slot may include 12 symbols. The relationship between the number of symbols per slot, the number of slots per subframe, and the number of slots per frame for a normal cyclic prefix and an extended cyclic prefix may depend on a numerology. It should be understood that reference to a first numerology (e.g., / i =0) associated with a first subcarrier spacing (e.g., 15 kHz) may be used interchangeably between subframes and slots.

[0079] In the wireless communications system 100, an electromagnetic (EM) spectrum may be split, based on frequency or wavelength, into various classes, frequency bands, frequency channels, etc. By way of example, the wireless communications system 100 may support one or multiple operating frequency bands, such as frequency range designations FR1 (410 MHz - 7.125 GHz), FR2 (24.25 GHz - 52.6 GHz), FR3 (7.125 GHz - 24.25 GHz), FR4 (52.6 GHz - 114.25 GHz), FR4a or FR4-1 (52.6 GHz - 71 GHz), and FR5 (114.25 GHz - 300 GHz). In some implementations, the NEs 102 and the UEs 104 may perform wireless communications over one or more of the operating frequency bands. In some implementations, FR1 may be used by the NEs 102 and the UEs 104, among other equipment or devices for cellular communications traffic (e.g., control information, data). In some implementations, FR2 may be used by the NEs 102 and the UEs 104, among other equipment or devices for short-range, high data rate capabilities.

[0080] FR1 may be associated with one or multiple numerologies (e.g., at least three numerologies). For example, FR1 may be associated with a first numerology (e.g., / r=0), which includes 15 kHz subcarrier spacing; a second numerology (e.g., / r=l), which includes 30 kHz subcarrier spacing; and a third numerology (e.g., / r=2), which includes 60 kHz subcarrier spacing. FR2 may be associated with one or multiple numerologies (e.g., at least 2 numerologies). For example, FR2 may be associated with a third numerology (e.g., / r=2), which includes 60 kHz subcarrier spacing; and a fourth numerology (e.g., / r=3), which includes 120 kHz subcarrier spacing.

[0081] Figure 8 illustrates an example of a NE 200 in accordance with aspects of the present disclosure. The NE 200 may include a processor 202, a memory 204, a controller 206, and a transceiver 208. The processor 202, the memory 204, the controller 206, or thetransceiver 208, or various combinations thereof or various components thereof may be examples of means for performing various aspects of the present disclosure as described herein. These components may be coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces.

[0082] The processor 202, the memory 204, the controller 206, or the transceiver 208, or various combinations or components thereof may be implemented in hardware (e.g., circuitry). The hardware may include a processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), or other programmable logic device, or any combination thereof configured as or otherwise supporting a means for performing the functions described in the present disclosure.

[0083] The processor 202 may include an intelligent hardware device (e.g., a general- purpose processor, a DSP, a CPU, an ASIC, an FPGA, or any combination thereof). In some implementations, the processor 202 may be configured to operate the memory 204. In some other implementations, the memory 204 may be integrated into the processor 202. The processor 202 may be configured to execute computer-readable instructions stored in the memory 204 to cause the NE 200 to perform various functions of the present disclosure.

[0084] The memory 204 may include volatile or non-volatile memory. The memory 204 may store computer-readable, computer-executable code including instructions when executed by the processor 202 cause the NE 200 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such the memory 204 or another type of memory. Computer-readable media includes both non- transitory computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A non-transitory storage medium may be any available medium that may be accessed by a general-purpose or specialpurpose computer.

[0085] In some implementations, the processor 202 and the memory 204 coupled with the processor 202 may be configured to cause the NE 200 to perform one or more of the functions described herein (e.g., executing, by the processor 202, instructions stored in the memory 204). For example, the processor 202 may support wireless communication at the NE 200 in accordance with examples as disclosed herein. The NE 200 may be configured to support a means for receiving from a peer network equipment a request to provide one ormore data labels associated with machine learning, authenticating and / or authorizing the peer network equipment and, in response to a successful authentication and / or authorization, obtain data label information or a storage identifier of the data label information, and transmitting a response to the peer network equipment containing the obtained data label information or storage identifier.

[0086] Alternatively, the network element may be configured to support a means for transmitting to a peer network equipment a request to provide one or more data labels associated with a machine learning model, and receiving a response containing the data label information or a storage identifier for the data label information.

[0087] Alternatively, the network element may be configured to support a means for receiving data label information from a first peer network equipment, the information being associated with a machine learning process, storing the received information and assign a storage identifier, receiving from a second peer network equipment a request that includes the said storage identifier to provide said data label information, authenticating and / or authorizing the second peer network equipment and, in response to a successful authentication and / or authorization, obtain data label information, and transmitting a response to the second peer network equipment containing the requested data label information.

[0088] The controller 206 may manage input and output signals for the NE 200. The controller 206 may also manage peripherals not integrated into the NE 200. In some implementations, the controller 206 may utilize an operating system such as iOS®, ANDROID®, WINDOWS®, or other operating systems. In some implementations, the controller 206 may be implemented as part of the processor 202.

[0089] In some implementations, the NE 200 may include at least one transceiver 208. In some other implementations, the NE 200 may have more than one transceiver 208. The transceiver 208 may represent a wireless transceiver. The transceiver 208 may include one or more receiver chains 210, one or more transmitter chains 212, or a combination thereof.

[0090] A receiver chain 210 may be configured to receive signals (e.g., control information, data, packets) over a wireless medium. For example, the receiver chain 210 may include one or more antennas for receive the signal over the air or wireless medium. The receiver chain 210 may include at least one amplifier (e.g., a low-noise amplifier (LNA))configured to amplify the received signal. The receiver chain 210 may include at least one demodulator configured to demodulate the receive signal and obtain the transmitted data by reversing the modulation technique applied during transmission of the signal. The receiver chain 210 may include at least one decoder for decoding the processing the demodulated signal to receive the transmitted data.

[0091] A transmitter chain 212 may be configured to generate and transmit signals (e.g., control information, data, packets). The transmitter chain 212 may include at least one modulator for modulating data onto a carrier signal, preparing the signal for transmission over a wireless medium. The at least one modulator may be configured to support one or more techniques such as amplitude modulation (AM), frequency modulation (FM), or digital modulation schemes like phase-shift keying (PSK) or quadrature amplitude modulation (QAM). The transmitter chain 212 may also include at least one power amplifier configured to amplify the modulated signal to an appropriate power level suitable for transmission over the wireless medium. The transmitter chain 212 may also include one or more antennas for transmitting the amplified signal into the air or wireless medium.

[0092] Figure 9 illustrates a flowchart of a method in accordance with aspects of the present disclosure. The operations of the method may be implemented by a NE as described herein. In some implementations, the NE may execute a set of instructions to control the function elements of the NE to perform the described functions.

[0093] At 300, the method may include receiving from a peer network equipment a request to provide one or more data labels associated with a machine learning. The operations of 300 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 300 may be performed by a NE as described with reference to Figure 8.

[0094] At 302, the method may include authenticating and / or authorizing the peer network equipment and, in response to a successful authentication and / or authorization, obtaining data label information or a storage identifier of the data label information. The operations of 302 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 302 may be performed by a NE as described with reference to Figure 8.

[0095] At 304, the method may include transmitting a response to the peer network equipment containing the obtained data label information or storage identifier. The operations of 304 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 304 may be performed by a NE as described with reference to Figure 8.

[0096] It should be noted that the method described herein describes a possible implementation, and that the operations and the steps may be rearranged or otherwise modified and that other implementations are possible.

[0097] The description herein is provided to enable a person having ordinary skill in the art to make or use the disclosure. Various modifications to the disclosure will be apparent to a person having ordinary skill in the art, and the generic principles defined herein may be applied to other variations without departing from the scope of the disclosure. Thus, the disclosure is not limited to the examples and designs described herein but is to be accorded the broadest scope consistent with the principles and novel features disclosed herein.

Claims

What is claimed is:

1. A network equipment for wireless communication, comprising: at least one memory; and at least one processor coupled with the at least one memory and configured to cause the network equipment to: receive from a peer network equipment a request to provide one or more data labels associated with machine learning; authenticate and / or authorize the peer network equipment and, in response to a successful authentication and / or authorization, obtain data label information or a storage identifier of the data label information; transmit a response to the peer network equipment containing the obtained data label information or storage identifier.

2. A network equipment according to claim 1, said network equipment being a network repository function or a network analytics training entity.

3. A network equipment according to any of the preceding claims, said network equipment being configured to operate in a 5G System.

4. A network equipment according to any one of claims 1 to 3, wherein said request is a one-time request or a service subscription request that allows the exchange of new data labels once they become available and / or at least one notification condition is satisfied.

5. A network equipment according to any one of the preceding claims, wherein said request contains at least one of the following: an identifier related to a requested data label; a network condition related to a requested data label; a data label usage condition; reporting information related to a data label; a notification address for receiving a reporting of data label information.

6. A network equipment according to any preceding claim, wherein authenticating and / or authorizing the peer network equipment comprises checking an allowability of data label permissions and / or interoperability rules.

7. A network equipment according to claim 6, wherein authenticating and / or authorizing the peer network equipment comprises authenticating and / or authorizing the peer network equipment to obtain data label information from a further peer network equipment.

8. A network equipment according to any preceding claim, wherein the transmitted data label information comprises one or more data labels with an assisting piece of information that contains: an analytics identifier where the said data label is to be used; input data identifying where the said data label is going to provide context when used; an analytics model and / or analytics model component where the said data label is going to be used; a data label source identifier to enable backtracking of the said data label; a network condition where the said data label is going to be used; an instruction related to applying the said data label to another analytics task, different from the one where the said data labels were originally used; a data re-distribution permission and / or restriction related with the said data label.

9. A network equipment according to any preceding claim, wherein data labels are stored according to at least one of the following: together with data set information that relating data labels with a data set; together with analytics model information that relates data labels with an analytics model; as a separate entry that relates to data label information.

10. A network equipment according to any preceding claim, wherein the processor is configured to cause said network equipment to store data label information in a second peernetwork equipment, the storage position in the second peer network equipment being identified by said storage identifier.

11. A network equipment for wireless communication, comprising: at least one memory; and at least one processor coupled with the at least one memory and configured to cause the network equipment to: transmit to a peer network equipment a request to provide one or more data labels associated with a machine learning model; receive a response containing the data label information or a storage identifier for the data label information.

12. A network equipment according to claim 11, wherein the processor is configured to cause the network equipment, when the response contains a storage identifier, to access information to request or subscribe to a further peer network equipment for receiving data label information, the further storage position in the peer network equipment being identified by the storage identifier.

13. A network equipment according to claim 11 or 12, wherein the network equipment is a network analytics training entity.

14. A network equipment according to any one of claims 11 to 13, wherein the peer network equipment is a network repository function.

15. A network equipment for wireless communication, comprising: at least one memory; and at least one processor coupled with the at least one memory and configured to cause the network equipment to operate as an analytical data repository function and to: receive data label information from a first peer network equipment, the information being associated with a machine learning process; store the received information and assign a storage identifier;receive from a second peer network equipment a request that includes the the storage identifier to provide the data label information; authenticate and / or authorize the second peer network equipment and, in response to a successful authentication and / or authorization, obtain data label information; and transmit a response to the second peer network equipment containing the requested data label information.

16. A method performed by a network equipment for wireless communication, comprising: receiving from a peer network equipment a request to provide one or more data labels associated with a machine learning; authenticating and / or authorizing the peer network equipment and, in response to a successful authentication and / or authorization, obtaining data label information or a storage identifier of the data label information; and transmitting a response to the peer network equipment containing the obtained data label information or storage identifier.

17. A method according to claim 16, the network equipment being network repository function.

18. A method according to claim 17, the peer network equipment performing network analytics training.

19. A method according to any of claims 16 to 18, the network equipment operating in a 5G System.

20. A method according to any of claims 16 to 19, the storage identifier being an identifier of a further peer network equipment at which data label information is stored.

Images