Method, apparatus and computer program

Abstract

There is provided an apparatus comprising means for receiving, at a first data analysis function, configuration information for obtaining a first set of analyses from a second analysis function, where the configuration information comprises a trigger condition for reporting the first set of analyses, where the first analysis function is configured to obtain the first set of analyses using a first set of input data, and where the first set of input data is configured to report the first set of analyses. And a second analysis function configured to obtain a second set of analyses using the second set of input data; obtaining a first set of analyses based on a first set of input data based on the configuration information; determining that the trigger condition is satisfied; and in response to determining that the trigger condition is satisfied, sending the first set of analytics to a second data analysis function.

Description

Technical Field

[0001] The present application relates to a method, apparatus, system and computer program, particularly but not exclusively to obtaining at least two sets of analyses of different scopes. Background Art

[0002] A communication system may be viewed as a facility that enables a communication session between two or more entities (such as user terminals, base stations and / or other nodes) by providing a carrier wave between the various entities involved in the communication path. A communication system may be provided, for example, by means of a communication network and one or more compatible communication devices. A communication session may include, for example, data communications for carrying communications such as voice, video, electronic mail (email), text messages, multimedia and / or content data. Non-limiting examples of the services provided include two-way or multi-way calls, data communications or multimedia services, and access to a data network system (such as the Internet).

[0003] In a wireless communication system, at least a portion of a communication session between at least two stations takes place over a wireless link. Examples of wireless systems include public land mobile networks (PLMNs), satellite-based communication systems, and different wireless local area networks, such as wireless local area networks (WLANs). Some wireless systems may be divided into cells, and are therefore often referred to as cellular systems.

[0004] A user can access the communication system through an appropriate communication device or terminal. The user's communication device may be referred to as a user equipment (UE) or user device. The communication device is equipped with appropriate signal receiving and sending means to achieve communication, for example, to achieve access to the communication network or to communicate directly with other users. The communication device can access a carrier provided by a site (e.g., a base station of a cell) and transmit and / or receive communications on the carrier.

[0005] Communication systems and associated equipment typically operate according to a given standard or specification, which specifies what the various entities associated with the system are allowed to do and how it is achieved. Communication protocols and / or parameters for the connection are also typically defined. An example of a communication system is UTRAN (3G radio). Other examples of communication systems are the Long Term Evolution (LTE) of the Universal Mobile Telecommunications System (UMTS) radio access technology and the so-called 5G or New Radio (NR) networks. NR is being standardized by the Third Generation Partnership Project (3GPP). Summary of the invention

[0006] According to one aspect, a device is provided, comprising a means for: receiving, at a first data analysis function, configuration information for obtaining a first set of analyses from a second data analysis function, wherein the configuration information includes a trigger condition for reporting the first set of analyses, wherein the first analysis function is configured to obtain the first set of analyses using a first set of input data, and the second analysis function is configured to obtain the second set of analyses using a second set of input data; based on the configuration information, obtaining the first set of analyses based on the first set of input data; determining that the trigger condition is met; and in response to determining that the trigger condition is met, sending the first set of analyses to the second data analysis function.

[0007] The apparatus may be configured to receive the second set of analyses from the second data analysis function, wherein determining that a trigger condition is satisfied comprises determining that a difference between the first set of analyses and the second set of analyses is greater than a threshold.

[0008] The difference value may include a deviation value.

[0009] The apparatus may be configured to receive one or more policies from the second data analysis function in response to sending the first set of analyses.

[0010] According to one aspect, a device is provided, comprising a means for: sending configuration information from a second analysis function to a first data analysis function so that the first data analysis function obtains a first set of analyses, wherein the configuration information includes a trigger condition for reporting the first set of analyses, wherein the second analysis function is configured to obtain the second set of analyses using a second set of input data, and the first analysis function is configured to obtain the first set of analyses using a first set of input data; in response to the trigger condition being met, receiving the first set of analyses from the first data analysis function; obtaining a second set of analyses based on the second set of input data; and determining one or more strategies based on the first set of analyses and the second set of analyses.

[0011] The apparatus may be configured to: when sending the configuration information, send the second set of analyses to the first data analysis function, wherein the trigger condition includes that a difference between the first set of analyses and the second set of analyses is greater than a threshold.

[0012] Obtaining the second set of analyses may be further based on the first set of analyses.

[0013] The apparatus may be configured to: determine that a difference between the first set of analyses and the second set of analyses is greater than a threshold; and determine the one or more policies in response to determining that the difference between the first set of analyses and the second set of analyses is greater than the threshold.

[0014] The configuration information may include information identifying at least one of: the first set of analyses; further analyses related to the first set of analyses; one or more target objects associated with the first set of analyses; an area of ​​interest associated with the first set of analyses; and timing information associated with the first set of analyses.

[0015] The first set of analyses may include predictive values.

[0016] The first data analysis function and / or the second data analysis function may include one of: a management data analysis function; a network data analysis function; an operations management function; and a radio data analysis function.

[0017] According to one aspect, a device is provided, comprising at least one processor and at least one memory comprising computer program code, wherein the at least one memory and the computer program code are configured to, together with the at least one processor, enable the device to at least: receive configuration information for obtaining a first set of analyses from a second data analysis function at a first data analysis function, wherein the configuration information includes a trigger condition for reporting the first set of analyses, wherein the first analysis function is configured to obtain the first set of analyses using a first set of input data, and the second analysis function is configured to obtain the second set of analyses using a second set of input data; based on the configuration information, obtain the first set of analyses based on the first set of input data; determine that the trigger condition is met; and in response to determining that the trigger condition is met, send the first set of analyses to the second data analysis function.

[0018] The at least one memory and the at least one processor can be configured to enable the device to: receive the second set of analysis from the second data analysis function, wherein the at least one memory and the at least one processor can be configured to enable the device to determine that a trigger condition is met by determining that a difference between the first set of analysis and the second set of analysis is greater than a threshold.

[0019] The difference value may include a deviation value.

[0020] The at least one memory and the at least one processor may be configured to cause the apparatus to: receive one or more policies from the second data analysis function in response to sending the first set of analyses.

[0021] According to one aspect, a device is provided, comprising at least one processor and at least one memory comprising computer program code, wherein the at least one memory and the computer program code are configured to, together with the at least one processor, enable the device to at least: send configuration information from a second analysis function to a first data analysis function so that the first data analysis function obtains a first set of analysis, wherein the configuration information includes a trigger condition for reporting the first set of analysis, wherein the second analysis function is configured to obtain the second set of analysis using a second set of input data, and the first analysis function is configured to obtain the first set of analysis using the first set of input data; in response to the trigger condition being met, receive the first set of analysis from the first data analysis function; obtain the second set of analysis based on the second set of input data; and determine one or more strategies based on the first set of analysis and the second set of analysis.

[0022] The at least one memory and the at least one processor may be configured to enable the device to: when sending the configuration information, send the second set of analyses to the first data analysis function, wherein the trigger condition includes a difference between the first set of analyses and the second set of analyses being greater than a threshold.

[0023] The at least one memory and the at least one processor may be configured to cause the apparatus to obtain the second set of analyses further based on the first set of analyses.

[0024] The at least one memory and the at least one processor can be configured to cause the device to: determine that the difference between the first group of analysis and the second group of analysis is greater than a threshold; and determine the one or more strategies in response to determining that the difference between the first group of analysis and the second group of analysis is greater than the threshold.

[0025] The configuration information may include information identifying at least one of: a first set of analyses; further analyses related to the first set of analyses; one or more target objects associated with the first set of analyses; a region of interest associated with the first set of analyses; and timing information associated with the first set of analyses.

[0026] The first set of analyses may include predictions.

[0027] The first data analysis function and / or the second data analysis function may include one of: a management data analysis function; a network data analysis function; an operations management function; and a radio data analysis function.

[0028] According to one aspect, a method is provided, comprising: at a first data analysis function, receiving configuration information for obtaining a first set of analyses from a second data analysis function, wherein the configuration information includes a trigger condition for reporting the first set of analyses, wherein the first analysis function is configured to obtain the first set of analyses using a first set of input data, and the second analysis function is configured to obtain the second set of analyses using a second set of input data; based on the configuration information, obtaining the first set of analyses based on the first set of input data; determining that the trigger condition is met; and in response to determining that the trigger condition is met, sending the first set of analyses to the second data analysis function.

[0029] The method may include receiving the second set of analyses from the second data analysis function, wherein determining that a trigger condition is satisfied includes determining that a difference between the first set of analyses and the second set of analyses is greater than a threshold.

[0030] The difference value may include a deviation value.

[0031] The method may include receiving one or more policies from the second data analysis function in response to sending the first set of analyses.

[0032] According to one aspect, a method is provided, comprising: sending configuration information from a second analysis function to a first data analysis function so that the first data analysis function obtains a first set of analysis, wherein the configuration information includes a trigger condition for reporting the first set of analysis, wherein the second analysis function is configured to obtain the second set of analysis using a second set of input data, and the first analysis function is configured to obtain the first set of analysis using the first set of input data; in response to the trigger condition being met, receiving the first set of analysis from the first data analysis function; obtaining the second set of analysis based on the second set of input data; and determining one or more strategies based on the first set of analysis and the second set of analysis.

[0033] The method may include: sending the second set of analysis to the first data analysis function when sending the configuration information, wherein the trigger condition includes a difference between the first set of analysis and the second set of analysis being greater than a threshold.

[0034] Obtaining the second set of analyses may be further based on the first set of analyses.

[0035] The method may include determining that a difference between the first set of analyses and the second set of analyses is greater than a threshold; and determining the one or more policies in response to determining that the difference between the first set of analyses and the second set of analyses is greater than the threshold.

[0036] The configuration information may include information identifying at least one of: the first set of analyses; further analyses related to the first set of analyses; one or more target objects associated with the first set of analyses; an area of ​​interest associated with the first set of analyses; and timing information associated with the first set of analyses.

[0037] The first set of analyses may include predictions.

[0038] The first data analysis function and / or the second data analysis function may include one of: a management data analysis function; a network data analysis function; an operations management function; and a radio data analysis function.

[0039] According to one aspect, a computer-readable medium comprising program instructions is provided for causing an apparatus to perform at least the following: at a first data analysis function, receiving configuration information for obtaining a first set of analyses from a second data analysis function, wherein the configuration information includes a trigger condition for reporting the first set of analyses, wherein the first analysis function is configured to obtain the first set of analyses using a first set of input data, and the second analysis function is configured to obtain the second set of analyses using a second set of input data; based on the configuration information, obtaining the first set of analyses based on the first set of input data; determining that the trigger condition is satisfied; and in response to determining that the trigger condition is satisfied, sending the first set of analyses to the second data analysis function.

[0040] The program instructions may be used to cause the apparatus to further perform: receiving the second set of analyses from the second data analysis function, wherein determining that a trigger condition is satisfied comprises determining that a difference between the first set of analyses and the second set of analyses is greater than a threshold.

[0041] The difference value may include a deviation value.

[0042] The program instructions may be configured to cause the apparatus to further perform: in response to sending the first set of analyses, receiving one or more policies from the second data analysis function.

[0043] According to one aspect, a computer-readable medium comprising program instructions is provided for causing a device to perform at least the following: sending configuration information from a second analysis function to a first data analysis function so that the first data analysis function obtains a first set of analyses, wherein the configuration information includes a trigger condition for reporting the first set of analyses, wherein the second analysis function is configured to obtain the second set of analyses using a second set of input data, and the first analysis function is configured to obtain the first set of analyses using a first set of input data; in response to the trigger condition being met, receiving the first set of analyses from the first data analysis function; obtaining the second set of analyses based on the second set of input data; and determining one or more strategies based on the first set of analyses and the second set of analyses.

[0044] The program instructions may be used to cause the apparatus to further execute: when sending the configuration information, sending the second set of analyses to the first data analysis function, wherein the trigger condition includes that a difference between the first set of analyses and the second set of analyses is greater than a threshold.

[0045] Obtaining the second set of analyses may be further based on the first set of analyses.

[0046] The program instructions may be used to cause the apparatus to further perform: determining that a difference between the first set of analyses and the second set of analyses is greater than a threshold; and determining the one or more strategies in response to determining that the difference between the first set of analyses and the second set of analyses is greater than the threshold.

[0047] The configuration information may include information identifying at least one of: the first set of analyses; further analyses related to the first set of analyses; one or more target objects associated with the first set of analyses; an area of ​​interest associated with the first set of analyses; and timing information associated with the first set of analyses.

[0048] The first set of analyses may include predictions.

[0049] The first data analysis function and / or the second data analysis function may include one of: a management data analysis function; a network data analysis function; an operations management function; and a radio data analysis function.

[0050] According to one aspect, there is provided a non-transitory computer-readable medium including program instructions for causing an apparatus to execute a method according to at least any one of the preceding aspects.

[0051] Many different embodiments have been described above. It should be understood that further embodiments can be provided by combining any two or more of the above embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Embodiments will now be described, by way of example only, with reference to the accompanying drawings, in which:

[0053] Figure 1 shows a representation of a network system according to some example embodiments;

[0054] Figure 2 shows a representation of a control device according to some example embodiments;

[0055] Figure 3 shows representations of apparatus according to some example embodiments;

[0056] Figure 4 An example management data analysis framework is shown;

[0057] Figure 5 Methods according to some examples are shown; and

[0058] Figures 6 to 8 Some example procedures are shown. DETAILED DESCRIPTION

[0059] Certain embodiments will be explained below with reference to a mobile communication device capable of communicating via a wireless cellular system and a mobile communication system serving such a mobile communication device. Figure 1 , 2 and 3 briefly explain some general principles of wireless communication systems, their access systems and mobile communication devices to help understand the technology on which the examples are based.

[0060] Figure 1 A schematic diagram of a 5G system (5GS) is shown. The 5GS may include a terminal or user equipment (UE), a 5G radio access network (5GRAN) or a next generation radio access network (NG-RAN), a 5G core network (5GC), one or more application functions (AFs), and one or more data networks (DNs).

[0061] 5G-RAN may include one or more gNodeBs (gNBs), or one or more gNodeB (gNB) distributed unit functions connected to one or more gNodeB (gNB) centralized unit functions. 5GC may include the following entities: Network Slice Selection Function (NSSF); Network Open Function; Network Repository Function (NRF); Policy Control Function (PCF); Unified Data Management (UDM); Application Function (AF); Authentication Server Function (AUSF); Access and Mobility Management Function (AMF); and Session Management Function (SMF).

[0062] Figure 2 Diagram for controlling Figure 1An example of a control device 200 for the functions of a 5GRAN or 5GC shown. The control device may include at least one random access memory (RAM) 211a, at least one read-only memory (ROM) 211b, at least one processor 212, 213, and an input / output interface 214. At least one processor 212, 213 may be coupled to the RAM 211a and the ROM 211b. At least one processor 212, 213 may be configured to execute appropriate software code 215. The software code 215 may, for example, allow one or more steps to be executed to perform one or more aspects of the present invention. The software code 215 may be stored in the ROM 211b. The control device 200 may be interconnected with other control devices 200 that control other functions of the 5GRAN or 5GC. In some embodiments, each function of the 5GRAN or 5GC includes a control device 200. In an alternative embodiment, two or more functions of the 5GRAN or 5GC may share a control device.

[0063] Figure 3 An example of a terminal 300 is shown, such as Figure 1 The terminal shown. The terminal 300 can be provided by any device capable of sending and receiving radio signals. Non-limiting examples include user equipment, a mobile station (MS) or a mobile device (such as a mobile phone or a so-called "smartphone"), a computer equipped with a wireless interface card or other wireless interface facilities (e.g., a USB dongle), a personal data assistant (PDA) or tablet computer equipped with wireless communication capabilities, a machine type communication (MTC) device, an Internet of Things (IoT) type communication device, or any combination of these or the like. The terminal 300 can provide, for example, data communications for bearer communications. The communication can be one or more of voice, electronic mail (email), text messaging, multimedia, data, machine data, etc.

[0064] The terminal 300 may receive signals via the air or radio interface 307 via suitable means for receiving, and may transmit signals via suitable means for transmitting radio signals. Figure 3 In the mobile device, the transceiver arrangement is schematically designated by block 306. The transceiver arrangement 306 may be provided, for example, by means of a radio component and an associated antenna arrangement. The antenna arrangement may be arranged internally or externally to the mobile device.

[0065] The terminal 300 may be equipped with at least one processor 301, at least one memory ROM 302a, at least one RAM 302b and other possible components 303 for software and hardware assistance to perform the tasks it is designed to perform, including control of access and communication to access systems and other communication devices. At least one processor 301 is coupled to RAM 302b and ROM 302a. At least one processor 301 may be configured to execute appropriate software code 308. Software code 308 may, for example, allow one or more aspects of the present invention to be performed. Software code 308 may be stored in ROM 302a.

[0066] The processor, memory and other related control devices can be provided on an appropriate circuit board and / or in a chipset. This feature is represented by reference numeral 304. The device may optionally have a user interface, such as a keyboard 305, a touch screen or touch pad, a combination thereof, etc. Depending on the type of device, one or more of a display, a speaker and a microphone may be provided.

[0067] In some examples, artificial intelligence (AI) / machine learning (ML) techniques may be implemented in wireless networks to enhance network operations and optimize network performance.

[0068] In some embodiments, a managed data analytics (MDA) managed service (MnS) producer may perform both AI / ML inference and AI / ML training (which may help protect internal implementations of AI / ML models across vendors). The MDA MnS may consume various types of data, which may include performance measurements per 3GPP TS28.552, key performance indicators (KPIs) per 3GPP TS28.554, and trace data, including Minimization of Drive Tests (MDT), Radio Link Failures (RLF), and Radio Connectivity Establishment Failures (RCEF) per 3GPP TS 32.422 and 3GPP TS 32.423.

[0069] AI / ML model training can be requested by MDA MnS consumers. For example, an MDA MnS consumer can send a training request to an AI / ML model training coordinator to request model training.

[0070] AI / ML model training orchestrators (also known as MDA MnS consumers) can decide when such training should take place, what input data the model should use, the scope of training (e.g., in terms of numeric ranges or other relevant properties), and which MDA MnS producers should perform the training.

[0071] In a training request, an MDA MnS consumer can provide the type of AI / ML model and the type of analysis (i.e., the purpose it serves - e.g., solving a coverage problem) as well as the desired AI / ML model performance (e.g., in terms of accuracy). An MDA MnS consumer can choose to provide data sources or other data for the training performed by an MDA MnS producer. In some examples, an MDA MnS producer may decide to use other data sources.

[0072] As defined in 3GPP TS28.104, the functional framework for MDA and its relationship with the Network Data Analysis Function (NWDAF) is as follows Figure 4 shown.

[0073] exist Figure 4 In the example shown, a management function (such as a Management Data Analysis Function, MDAF) may play the roles of an MDA MnS producer, an MDA MnS consumer, an NWDAF consumer, and an LMF service consumer.

[0074] The MDA (or more generally the data analysis function) can obtain information from the NWDAF, such as analysis related to 5GC data. The analysis from the MDA can also be made available at authorized consumers (including the NWDAF).

[0075] For example, the MDA may obtain network slice load-related analysis from the NWDAF and perform network slice load analysis. The MDA may then return the output of the network slice load analysis to the NWDAF. For example, the output may include slice load level-related network data analysis and user plane performance analysis (i.e., average / maximum traffic rate, average / maximum packet delay, average packet loss rate, and related prediction results).

[0076] In another example, MDA-assisted energy saving can utilize network analysis data from NWDAF in the input (e.g., observed service experience related analysis) to provide an output including the energy saving state of the statistical cell at a given time. This information can be used to decide when to enter or exit the energy saving state based on the current state.

[0077] The use of analytics may have different operating scopes in terms of analysis type, input data scope, objects involved, time scale, specific analysis scenarios (eg, UE profile, area of ​​interest), etc.

[0078] MDA and RAN analysis can be run independently, i.e., there may be no interworking between MDA and RAN analysis during the inference and training phases. This may result in suboptimal inference or training, as not all available information is utilized.

[0079] Certain aspects of the present application may use a combination of analyses with different operating scopes. As an example, certain aspects may combine the output of MDA and RAN analyses, or combine the output of NWDAF and RAN, or combine the output of NWDAF and OAM to enhance insight into more specific details. It should be understood that other combinations of analyses not explicitly given herein (e.g., NWDAF, RAN, etc.) may also fall within the scope of the present application.

[0080] The MDA may provide analysis based on predictions it generates or received, for example, from outside the gNB.

[0081] OAM and RAN can have different views of the network and can operate on different time scales. The same scenario can be used for the case of combined analysis between NWDAF and RAN and that between NWDAF and OAM.

[0082] For example, in RAN, the received information can be considered more "real-time", while OAM can be considered "non-real-time", but longer-lasting. Similarly, in the case of NWDAF, the received information can be related to a specific UE, as opposed to OAM, which can obtain information based on the average number of UEs in a specific cell or area of ​​interest.

[0083] These different timescales and ranges in forecasts can lead to very different results and can make interoperability more challenging.

[0084] In addition, OAM can control a large number of gNBs or network functions (NFs) and can have a wider view of the network. OAM can configure management-based procedures for RAN or 5G core to collect information through PLMN, cell lists provided within the area, routing areas (RAs), tracking areas (TAs), etc.

[0085] After receiving this information, OAM can calculate the predicted value by averaging the measurements received from RAN or 5G core. On the other hand, RAN can collect real-time information and NWDAF can collect UE information that OAM cannot collect at this rate.

[0086] When combining RAN or 5G core and OAM analysis or RAN and 5G core analysis, one question is how one domain knows the type, scope, and transport method of analysis, as described below:

[0087] Analysis types can include not only a single attribute, such as radio load, but also other related attributes, such as mobility;

[0088] Depending on the target object and its characteristics, such as UEs with high or low mobility, it may be necessary to select the operating scope, i.e., the area of ​​interest or slice, or even a specific NF (i.e., DN); and

[0089] • Depending on the need for analytical exchange between the two domains, the transport mechanism can be selected, i.e. real-time or non-real-time.

[0090] The two predictions (i.e. MDA and RAN analysis or MDA and NWDAF or RAN and NWDAF) can be very different. This can happen, for example, if the area where OAM calculates the load prediction includes gNBs or NFs that are very different in terms of their load.

[0091] To better leverage predictions from RAN, 5G core, and OAM, OAM may need to “compare” and “correlate” OAM and RAN or 5G core related analyses and enhance reporting mechanisms to capture deviations and related scenarios so that consumers can better understand.

[0092] In some examples, this can be achieved by comparing predictions from, for example, RAN and OAM or vice versa, using the collected data to learn deviation patterns, i.e., how the predicted values ​​deviate from different sources (e.g., RAN and OAM).

[0093] In some examples, the measurements can be modeled as "time series data", and analysis of the "time series data" can be used to learn patterns of time periods / seasonality or trends, etc. Time period patterns can be of various types, such as daily, weekly, monthly, quarterly, yearly, etc.

[0094] RAN nodes can collect more granular data over short durations. Finer granularity time period patterns are well captured in a timely manner, while OAM with a larger data range (more aggregated) will more accurately capture time period patterns at a higher granularity level.

[0095] Therefore, combining the analysis among RAN, 5G core, and OAM or between RAN and 5G core can improve the accuracy of the overall prediction.

[0096] On the other hand, data collected from one RAN or 5G core node may be biased towards that specific RAN node or NF, which may mean that predictions from the data with learning and inference may tend to be biased towards that specific node.

[0097] OAM, on the other hand, can collect data over a wider range and from a large number of different RAN nodes or NFs, so it may mean that the predictions can be unbiased for the overall RAN nodes or 5G core area.

[0098] Therefore, combining the results from both the RAN or 5G core and OAM, or combining the results between NWDAF and RAN, can also improve the overall prediction accuracy and alleviate some of the bias in the prediction.

[0099] Data analytics and AI / ML can be implemented in various parts of the 5G system. For example, in the 5G core, NWDAF can provide statistics and predictions, such as user mobility, communication patterns, etc., focusing on the user and control planes (as per 3GPPTS23.288). In the management plane, management data analysis (MDA) can provide statistics, predictions, and recommendations related to resource allocation, fault management, and network optimization (as per 3GPP TS28.104). At the access node, RAN analytics can provide real-time predictions to assist the scheduling process and explore AI / ML workflows (as per 3GPP TR37.817).

[0100] refer to Figure 5 , which illustrates methods according to some examples.

[0101] At 500, a method includes: receiving, at a first data analysis function, configuration information for obtaining a first set of analyses from a second data analysis function, wherein the configuration information includes a trigger condition for reporting the first set of analyses, wherein the first analysis function is configured to obtain the first set of analyses using a first set of input data, and wherein the second analysis function is configured to obtain the second set of analyses using a second set of input data.

[0102] At 502 , the method includes obtaining a first set of analytics based on a first set of input data based on configuration information.

[0103] At 504 , the method includes determining that a triggering condition is met.

[0104] At 506 , the method includes sending the first set of analyses to a second data analysis function in response to determining that the trigger condition is satisfied.

[0105] At 508, the method includes sending configuration information from the second analysis function to the first data analysis function to cause the first data analysis function to obtain the first set of analytics, wherein the configuration information includes a trigger condition for reporting the first set of analytics, wherein the second analysis function is configured to obtain the second set of analytics using the second set of input data, and the first analysis function is configured to obtain the first set of analytics using the first set of input data;

[0106] At 510 , the method includes receiving a first set of analyses from a first data analysis function in response to a trigger condition being satisfied.

[0107] At 512 , the method includes obtaining a second set of analyses based on the second set of input data.

[0108] At 514 , the method includes determining one or more strategies based on the first set of analyses and the second set of analyses.

[0109] Some aspects of the present disclosure may provide a method that allows a first data analysis function (e.g., a management data analysis function (MDAF) or a network data analysis function (NWDAF)) to compare and correlate obtained analysis with other network entities (e.g., a second data analysis function) that have a different perspective on the data analysis - for example, the other network entities may operate on a different time scale or have a different range of source data (e.g., data from the RAN or even a smaller area) compared to the first data analysis function (e.g., hourly versus daily analysis).

[0110] In some examples, a first data analysis function (e.g., MDAF or NWDAF) can compare and correlate the obtained management plane analysis with management plane analysis received from a second data analysis function (e.g., MDAF, NWDAF, or radio analysis function). As used herein, in some examples, an analysis can include a prediction, such as a prediction provided by an AI / ML model.

[0111] For example, the MDAF may obtain analysis from the radio analysis function and compare the obtained analysis with the analysis generated by the MDAF. Likewise, the radio analysis function may compare and correlate the radio analysis with the analysis received from the management data analysis function.

[0112] Similarly, NWDAF and MDA can compare and correlate the obtained analyses with each other, since one focuses on the control plane or is user-centric, while the other handles network analysis related to, for example, resource allocation, faults, etc.

[0113] In some examples, comparing and correlating may include utilizing a deviation (eg, a standard deviation) between a predicted value calculated from the first data analysis function and a predicted value received from the second data analysis function.

[0114] Based on this correlation, in some examples, insight can be gained by identifying gNBs that are far away from the average / mean available at the first data analysis function.

[0115] In some examples, a wider perspective around a particular gNB may be obtained because the first data analysis function may compute analysis based on a wider area than the RAN analysis function which provides analysis on a per-gNB basis (or even finer granularity, e.g. gNB-CU, gNB-DU, etc.).

[0116] In some examples, comparing and correlating may include utilizing deviations, such as standard deviations, between predicted values ​​calculated from a first data analysis function (eg, MDAF) and predicted values ​​received from a second data analysis function (eg, NWDAF or RAN analysis function).

[0117] In order to be able to obtain meaningful analysis for comparison, configuration of a triggering policy may be required, ie when the results of the first data analysis function need to be provided to the second data analysis function.

[0118] The triggering strategy may include a moving threshold (ie, a threshold that varies depending on the expected distance) that determines the amount by which an analysis (eg, a predicted value) provided by a first data analysis function (eg, RAN or NWDAF) exceeds a certain value above a threshold.

[0119] The particular value may correspond to an analysis available at the second data analysis function (eg, OAM, MDA).That is, if the difference between the analysis obtained by the first data analysis function and the analysis provided by the second data analysis function exceeds a certain amount, the trigger condition may be met.

[0120] The trigger policy may trigger the second data analysis function to provide further analysis to the first data analysis function. In this way, the first data analysis function may identify several entities (e.g., gNBs) whose behavior exceeds the expected average (e.g., they exceed the predicted OAM load by a given threshold).

[0121] From a RAN perspective, similar mobility thresholds can be applied to average or wider range analysis. In addition, RAN analysis can also select areas of interest for analysis from the data analysis function based on the UE type and mobility profile of interest (e.g., IoT or mobile users with high, medium, or low mobility profiles).

[0122] The triggering condition can be part of the analysis request. This may be particularly useful for MDA, as there is currently no method at the OAM level to uniquely identify a UE.

[0123] The triggering policy may alternatively include a moving threshold that determines when a predicted value calculated by a data analysis function (MDA in OAM or NWDAF in network) exceeds a threshold by a configurable specific value corresponding to a predicted value available at a different data analysis function.

[0124] The configuration of an analysis may include an area scope (e.g., a geographic area of ​​interest), a time window of interest (start time / end time of the prediction), and a set of configured analyses. In some examples, the set of configured analyses may be indicated implicitly or explicitly. In some examples, if a certain analysis is requested, other analyses that are considered relevant may also be sent by the gNB.

[0125] The following properties can be defined to capture the configuration:

[0126] The analysis requested (analysis type, name, list of analysis values ​​or output, time interval, confidence level);

[0127] Correlation analysis, which can be in the form of correlation analysis type name, analysis value list or output, time interval, confidence level, etc.

[0128] Target objects, such as gNBs and related features;

[0129] The area of ​​interest, geographic area or TA / LA / RA or non-public network identifier, such as CAG-ID; and

[0130] Type of information, such as real-time, non-real-time, or defined expected time

[0131] The output analytics can be statistical and / or predictive values, when provided by the RAN, allowing the OAM to process them and still obtain useful results.

[0132] Once the consumer has these analysis results, the consumer can make more accurate decisions. For example, OAM can disable offloading operations for gNBs whose load exceeds the average load calculated by OAM by a threshold. In addition, OAM can configure energy saving policies for gNBs whose energy efficiency is lower than a second threshold compared to the energy efficiency prediction value calculated by MDA. In this way, MDA can configure different policies for RAN (gNB) based on the comparison between the local real-time prediction value in RAN and the OAM-related prediction value.

[0133] The following description focuses on an example of considering analysis in RAN and MDA in OAM. However, it should be understood that the same mechanism and similar sequence diagrams can also be applied to other cases, such as the case of MDA and NWDAF and the case of RAN analysis and NWDAF.

[0134] Some examples describe a method of combining MDA and RAN analysis to enhance the analysis performance in the RAN or OAM. To achieve this, some examples may include selecting:

[0135] (i) one or more gNBs from which the MDA requests analysis to enhance the MDA; and / or

[0136] (ii) One or more areas of interest from which the gNB requests a wider analysis perspective to enhance RAN analysis.

[0137] Thus, in some examples, specific trigger conditions may be utilized to specify when and where (ie, which network portion) analysis should be acquired.

[0138] In some examples, an MDAS generator (also referred to as an MDA MnS generator) can compute analytics locally. The MDAS generator can be located in a core network.

[0139] For example, the MDAS generator can calculate the predicted load on multiple cells taking into account input data from gNB performance measurements. The MDAS generator can utilize information based on a large geographical area including multiple gNBs (and cells).

[0140] The MDAS Generator may also create analytics jobs for obtaining analytics from one or more other network entities, such as one or more gNBs.

[0141] The analysis may point to the entity (eg, cell) that needs to be involved, a duration that may be explicitly specified or may start immediately until the indication ceases, and other trigger conditions, such as when the deviation exceeds a certain difference limit (threshold).

[0142] The trigger conditions may include thresholds or network states, depending on the specific analysis type. Depending on the analysis requested (e.g., prediction values), other analyses may be additionally attached to the response message. Other analyses may be other prediction values ​​related to the original analysis request, for example, if radio load is requested from the gNB, the mobility rate towards neighboring gNBs may also be required in order to gain knowledge of future load and related changes.

[0143] refer to Figure 6 , which illustrates the process according to some examples.

[0144] At 600, the MDA (first data analysis function) obtains a first set of analyses based on a first set of data available at the MDAS. The first set of analyses may include a set of predicted PRB usages.

[0145] At 602, the MDA sends configuration information to the RAN. The configuration information may be based on the first set of analyses. The configuration information may include information indicating one or more of the following:

[0146] The area scope for acquisition analysis (e.g. one or more cells / TAs / RAs);

[0147] The time period for which the analysis was obtained;

[0148] At least one trigger condition (e.g., a prediction value and a threshold from the MDA); and

[0149] Additional analytics information is enabled.

[0150] In some examples, the MDA may also send the first set of analyses to the RAN in step 602 .

[0151] An area scope (cell / TA / RA) can represent a management object or a group of management objects (MO), that is, one or more MOs. Figure 6 The RAN in the example may represent multiple RANs.

[0152] At 604 , based on the configuration information received at 602 , a radio analysis function (a second analysis function) at the RAN obtains a second set of analyses.

[0153] At 606, the RAN determines whether at least one trigger condition is satisfied based on the obtained second set of analysis. For example, the RAN may determine whether the difference between the second set of analysis (e.g., the PRB usage predicted at the RAN) and the first set of analysis (e.g., the PRB usage predicted at the MDA) exceeds a threshold amount. It should be appreciated that in some examples, other trigger conditions may be used.

[0154] At 608, in response to determining that at least one trigger condition is satisfied, the RAN sends a second set of analyses to the MDA.

[0155] In some examples, such as shown in 610, the MDA can determine one or more policies, such as one or more network configuration policies, based on the first and second sets of analyses. The MDA can then send the one or more policies to one or more other network entities (e.g., gNBs) accordingly. For example, if the MDA is provided by OAM, OAM can disable offloading operations for gNBs whose load exceeds an average load calculated by OAM by a threshold. In addition, OAM can configure energy saving policies for gNBs whose energy efficiency is lower than a second threshold compared to the energy efficiency prediction value calculated by the MDA. In this way, the MDA can configure different policies for the RAN (gNB), depending on the degree to which the local real-time prediction value in the RAN compares with the OAM-related prediction value.

[0156]

[0157]

[0158] Table 1 MDA / RAN predictions for different spacing and alignment examples

[0159] Table 1 above shows an example of target PRB usage prediction for one cell during a 2-hour duration with 24 time points.

[0160] Three forecasts are shown: OAM MDA forecast 1 is a 15 minute interval forecast, OAM MDA forecast 2 is a 1 hour interval forecast, and RAN analysis forecast is a 5 minute interval forecast.

[0161] refer to Figure 5 For example, MDA prediction 1 or prediction 2 may correspond to the first set of analysis, and the RAN prediction may correspond to the second set of analysis. The configuration information sent to the RAN may include information indicating that the RAN prediction is obtained every five minutes and / or may indicate a time period (12:00-14:00) for obtaining the second set of analysis.

[0162] The MDA forecast 1 and the RAN forecast can be aligned every 15 minutes, and all three forecasts can be aligned every 1 hour. If all analyses are statistical rather than forecasts in Table 1, the alignment process can be done in a similar way.

[0163] The threshold may be a calculated value based on the aligned statistics or predicted historical statistics at each time point in Table 1, for example, using a set of accumulated 14 days of historical data, the interquartile range (IQR) may be calculated and used as the threshold for each aligned time point.

[0164] Different thresholds can be used based on different strategies, for example, lower thresholds for warning levels of more sensitive monitoring or triggering conditions, and higher thresholds for significant deviations with higher confidence.

[0165] As shown in Table 1, for time point 6, there is a significant deviation in the predictions from MDA prediction 1 (28) and RAN prediction (38), which may trigger the RAN to send the analysis to the MDA (ie, the trigger condition at step 606 may be satisfied).

[0166] refer to Figure 7 , where an example scenario is shown where the MDA configures and requests analysis from certain gNBs and calculates deviations compared to its own analysis taking into account the analysis of the neighboring areas of these gNBs. For example, this can be calculated over a larger area corresponding to multiple gNBs (gNB groups) rather than just Figure 7 The two gNBs shown in Figure .

[0167] At 700a, the MDA sends configuration information to RAN node RAN 1, and at 700b, the MDA sends configuration information to RAN node RAN 2. The configuration information may be as described above with respect to Figure 6 That is, in some examples, the configuration information may include a trigger condition. The trigger condition may be the same for RAN 1 and RAN 2, or may be different for RAN 1 and RAN 2.

[0168] At 702a, RAN 1 obtains a first set of analyses based on the configuration information received at 700a, and at 702b, RAN 2 obtains a second set of analyses based on the configuration information received at 700b.

[0169] At 703a, RAN 1 determines that the trigger condition is met. At 703b, RAN 2 determines that the trigger condition is met.

[0170] At 704a, in response to determining that the trigger condition is met, RAN 1 sends a first set of analyses to the MDA, and at 704b, in response to determining that the trigger condition is met, RAN 2 sends a second set of analyses to the MDA.

[0171] It should be understood that steps 700a-704a and steps 700b-704b may be performed substantially in parallel, or at different times relative to each other.

[0172] At 706, the MDA determines another set of analyses based on the first and second sets of analyses received at steps 704a and 704b from RAN 1 and RAN 2. For example, the MDA may determine the predicted values ​​based on the predicted values ​​received from RAN 1 and RAN 2. For example, the MDA may receive predicted loads for RAN 1 and RAN 2 and determine an overall predicted network load based on the predicted values.

[0173] At 708 , the MDA determines the difference (eg, deviation as previously described) between the other set of analyses determined by the MDA at step 706 and each set of analyses received from the RAN at step 704 .

[0174] In some examples, the MDA can determine whether the other set of analyses and each set of analyses received from the RAN satisfy a relationship condition. That is, the MDA can determine whether the difference determined at 708 is above a threshold, indicating that the difference between the respective analysis groups is statistically significant.

[0175] Based on the determination at 708, the MDA determines one or more policies at 710 and sends an output to one or more RANs based on the determined policies.

[0176] For example, in the case where the analysis output is related to predicted RAN load, if the deviation of the predicted load between the MDA and a given gNB is very low, this may indicate that the load is “evenly” distributed. Otherwise, if the deviation is very high, this may indicate that the predicted load at the gNB is very different from the predicted load of other gNBs in the group. The MDAS generator may then assist in providing policies to the gNBs whose predictions were used in the comparison, but it may also recommend different policies to the remaining gNBs in the gNB group (e.g. RAN3, 4, etc.), even if the analysis from these gNBs was not used by the MDA. As another option, it may decide not to provide a policy to a gNB (e.g. RAN 1 in this example).

[0177] For example, if a set of cells belonging to a gNB group has a very high load (and the deviation of the load prediction value for a given gNB is very low), the OAM can configure a policy for the gNB to not activate load balancing actions because of the high load in the neighboring area. The policy (output) can also indicate to the gNB the reason for this decision, e.g. the load in the neighboring area exceeds a threshold. Different policies can be provided for the NG-RAN nodes 3, 4, ... k forming the gNB group, calculating their prediction values ​​based on this MDA. In this case, these gNBs can be instructed, e.g. to activate more cells or enable dual connectivity mode, in order to try to reduce the load at gNB1 and 2.

[0178] In some further examples, RAN analysis at the NG-RAN may request analysis from the MDAS generator. The request may specify a desired area of ​​interest. The area of ​​interest may be calculated at the NG-RAN taking into account the mobility of the considered UE (e.g., for a specific network slice).

[0179] By estimating the speed of each UE and the required frequency of receiving MDA reports, the NG-RAN can provide an area of ​​interest for receiving MDA reports for load analysis. This area of ​​interest may change as the UE moves.

[0180] Figure 8 An example signaling exchange describing this process is shown.

[0181] At 800, the RAN determines one or more UE types of interest. For example, the UE type may be determined based on a mobility profile of the UE.

[0182] At 802, the RAN sends an analysis request to the MDA. The request may include the area scope, forecast period, trigger conditions, and other forecasts enabled as previously described.

[0183] At 804 , based on the request received at 802 , the MDA obtains the requested analysis.

[0184] At 805, the MDA determines that a trigger condition is met. The trigger condition may be as described above.

[0185] At 806, in response to determining that the trigger condition is satisfied, the MDA sends an analysis response including the requested analysis.

[0186] As mentioned earlier, Figures 6 to 8 The mechanisms and sequence diagrams shown in may also be applied to other cases, such as the case of MDA and NWDAF and the case of RAN analysis and NWDAF in some examples.

[0187] For each use case, the following MDAS requirements can be provided:

[0188]

[0189]

[0190] Thus, some examples may allow a first data analysis function (such as MDA, OAM, NWDAF) to obtain a set of analytics from a second data analysis function and use the obtained set of analytics in conjunction with another set of analytics available at the first data analysis function to perform one or more operations to improve network performance. In some examples, the set of analytics may be provided when the deviation between the set of analytics and the other set of analytics is above a threshold amount, or alternatively, the set of analytics may be provided in response to a request from the first data analysis function. Because the first data analysis function is able to receive different ranges of analytics at different time scales or from different sources of analytics data, decisions on which operations to perform may be enhanced.

[0191] In some examples, a device may include: a device for receiving configuration information for obtaining a first set of analyses from a second data analysis function at a first data analysis function, wherein the configuration information includes a trigger condition for reporting the first set of analyses, wherein the first analysis function is configured to obtain the first set of analyses using a first set of input data, and the second analysis function is configured to obtain the second set of analyses using a second set of input data; based on the configuration information, obtaining the first set of analyses based on the first set of input data; determining that the trigger condition is met; and in response to determining that the trigger condition is met, sending the first set of analyses to the second data analysis function.

[0192] In some examples, a device may include at least one processor and at least one memory including computer program code, the at least one memory and the computer program code configured to, together with the at least one processor, cause the device to at least: receive configuration information for obtaining a first set of analyses from a second data analysis function at a first data analysis function, wherein the configuration information includes a trigger condition for reporting the first set of analyses, wherein the first analysis function is configured to obtain the first set of analyses using a first set of input data, and the second analysis function is configured to obtain the second set of analyses using a second set of input data; based on the configuration information, obtain the first set of analyses based on the first set of input data; determine that the trigger condition is satisfied; and in response to determining that the trigger condition is satisfied, send the first set of analyses to the second data analysis function.

[0193] In some examples, a device may include means for: sending configuration information from a second analysis function to a first data analysis function, which is used to enable the first data analysis function to obtain a first set of analyses, wherein the configuration information includes a trigger condition for reporting the first set of analyses, wherein the second analysis function is configured to obtain the second set of analyses using a second set of input data, and the first analysis function is configured to obtain the first set of analyses using the first set of input data; in response to the trigger condition being met, receiving the first set of analyses from the first data analysis function; obtaining the second set of analyses based on the second set of input data; and determining one or more policies based on the first set of analyses and the second set of analyses.

[0194] In some examples, the device may include at least one processor and at least one memory including computer program code, the at least one memory and the computer program code being configured to, together with the at least one processor, cause the device to at least: send configuration information from a second analysis function to a first data analysis function, which is used to cause the first data analysis function to obtain a first set of analyses, wherein the configuration information includes a trigger condition for reporting the first set of analyses, wherein the second analysis function is configured to obtain the second set of analyses using a second set of input data, and the first analysis function is configured to obtain the first set of analyses using the first set of input data; in response to the trigger condition being met, receive the first set of analyses from the first data analysis function; obtain the second set of analyses based on the second set of input data; and determine one or more policies based on the first set of analyses and the second set of analyses.

[0195] It should be understood that these devices may include or be coupled to other units or modules for transmitting and / or receiving, such as radio components or radio heads. Although the device has been described as one entity, different modules and memories may be implemented in one or more physical or logical entities.

[0196] It is worth noting that although some embodiments have been described in relation to 5G networks, similar principles may be applied to other networks and communication systems. Therefore, although certain embodiments are described above by way of example with reference to certain example architectures of wireless networks, technologies and standards, the embodiments may be applied to any other suitable form of communication system in addition to the communication system shown and described herein.

[0197] It is also noted herein that while the above describes example embodiments, there are numerous variations and modifications which may be made to the disclosed solution without departing from the scope of the present invention.

[0198] In general, various embodiments may be implemented in hardware or dedicated circuits, software, logic, or any combination thereof. Some aspects of the present application may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device, but the present application is not limited thereto. Although various aspects of the present application may be illustrated and described by block diagrams, flow charts, or using some other graphical representations, it is fully understood that the blocks, devices, systems, techniques, or methods described herein may be implemented in hardware, software, firmware, dedicated circuits or logic, general hardware or controllers or other computing devices, or some combination thereof, as non-limiting examples.

[0199] As used in this application, the term "circuitry" may refer to one or more or all of the following:

[0200] (a) hardware-only circuit implementations (such as implementations in analog and / or digital circuits only); and

[0201] (b) a combination of hardware circuitry and software such as (where applicable):

[0202] (i) a combination of analog and / or digital hardware circuitry and software / firmware, and

[0203] (ii) any portion of a hardware processor and software (including a digital signal processor), software and memory that work together to enable a device such as a mobile phone or server to perform various functions;

[0204] (c) A hardware circuit and / or processor, such as a microprocessor or portion of a microprocessor, that requires software (e.g., firmware) to operate, but the software may not be present when not required to operate.

[0205] This definition of circuitry applies to one or all uses of the term in this application, including in any claims. As a further example, as used in this application, the term "circuitry" also covers an implementation of only a hardware circuit or processor (or multiple processors) or a portion of a hardware circuit or processor and its (or their) accompanying software and / or firmware. For example, if applicable to a particular claim, the term "circuitry" also covers a baseband integrated circuit or processor integrated circuit for a mobile device, or a similar integrated circuit in a server, cellular network device, or other computing or network device.

[0206] Embodiments of the present application may be implemented (such as in a processor entity) by computer software executable by a data processor of a mobile device, or by hardware, or by a combination of software and hardware. Computer software or programs, also referred to as program products, include software routines, applets and / or macros, which may be stored in a data storage medium readable by any device, and they include program instructions for performing specific tasks. A computer program product may include one or more computer executable components that are configured to perform an embodiment when the program is running. One or more computer executable components may be at least one software code or a portion thereof.

[0207] Also in this regard, it should be noted that any block in the logic flow of the Figures may represent program steps, or interconnected logic circuits, blocks and functions, or a combination of program steps and logic circuits, blocks and functions. The software may be stored on such physical media as memory chips, or memory blocks implemented within a processor, magnetic media such as hard disks or floppy disks, and optical media such as DVDs and their data variants, CDs. Physical media are non-transitory media.

[0208] The memory may be of any type suitable for the local technical environment and may be implemented using any suitable data storage technology, such as semiconductor-based storage devices, magnetic storage devices and systems, optical storage devices and systems, fixed memory, and removable memory. The data processor may be of any type suitable for the local technical environment and may include one or more of a general-purpose computer, a special-purpose computer, a microprocessor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an FPGA, a gate-level circuit based on a multi-core processor architecture, and a processor, as non-limiting examples.

[0209] Embodiments of the present application may be practiced in various components such as integrated circuit modules. The design of integrated circuits is a highly automated process. Complex and powerful software tools are available to convert logic-level designs into semiconductor circuit designs that can be etched and formed on semiconductor substrates.

[0210] The scope of protection sought by various embodiments of the present application is set forth by the independent claims. Embodiments and features described in this specification that do not fall within the scope of the independent claims (if any) should be interpreted as examples of various embodiments that help understand the content of the present application.

[0211] The foregoing description has provided by way of non-limiting examples a complete and informative description of exemplary embodiments of the present application. However, various modifications and adaptations will be apparent to those skilled in the relevant art when read in conjunction with the accompanying drawings and the appended claims. However, all such and similar modifications to the teachings of the present application will still fall within the scope of the present invention as defined by the appended claims. In fact, there are further embodiments that include a combination of one or more embodiments with any other embodiments previously discussed.

Claims

1. An apparatus comprising means for: At the first data analysis function, configuration information for obtaining a first set of analyses is received from the second data analysis function, wherein: The configuration information includes a trigger condition for reporting the first set of analyses, wherein the first analysis function is configured to utilize a first set of input data to obtain the first set of analyses, and the second analysis function is configured to utilize a second set of input data to obtain the second set of analyses; Based on the configuration information, obtaining the first set of analyses based on the first set of input data; determining that the trigger condition is satisfied; and In response to determining that the trigger condition is met, the first set of analyses is sent to the second data analysis function.

2. The device according to claim 1, wherein: The device is used for: receiving the second set of analyses from the second data analysis function, Wherein, determining whether the trigger condition is satisfied includes determining that a difference between the first group of analyses and the second group of analyses is greater than a threshold.

3. The device of claim 2, wherein: The difference value includes a deviation value.

4. A device as claimed in any one of the preceding claims, wherein: The device is used for: In response to sending the first set of analyses, one or more policies are received from the second data analysis function.

5. An apparatus comprising means for: Sending configuration information from the second analysis function to the first data analysis function so that the first data analysis function obtains a first set of analyses, wherein: The configuration information includes a trigger condition for reporting the first set of analyses, wherein the second analysis function is configured to utilize a second set of input data to obtain a second set of analyses, and the first analysis function is configured to utilize a first set of input data to obtain the first set of analyses; In response to the trigger condition being satisfied, receiving the first set of analyses from the first data analysis function; obtaining a second set of analyses based on the second set of input data; and One or more strategies are determined based on the first set of analyses and the second set of analyses.

6. The device of claim 5, wherein: The device is used for: When sending the configuration information, sending the second set of analysis to the first data analysis function, The trigger condition includes that a difference between the first group of analyses and the second group of analyses is greater than a threshold.

7. The device of claim 5, wherein: Obtaining the second set of analyses is further based on the first set of analyses.

8. The device of claim 7, wherein: The device is used for: determining that a difference between the first set of analyses and the second set of analyses is greater than a threshold; and The one or more policies are determined in response to determining that a difference between the first set of analyses and the second set of analyses is greater than the threshold.

9. The apparatus as claimed in any one of the preceding claims, wherein: The configuration information includes information identifying at least one of: The first set of analyses; further analyses related to the first set of analyses; one or more target objects associated with the first set of analyses; a region of interest associated with said first set of analyses; and Timing information associated with the first set of analyses.

10. Apparatus as claimed in any preceding claim, wherein the first set of analyses comprises predicted values.

11. The apparatus as claimed in any one of the preceding claims, wherein: The first data analysis function and / or the second data analysis function comprises one of the following: Manage data analysis functions; Network data analysis function; Operational management functions; and Radio data analysis capabilities.

12. A method comprising: receiving, at a first data analysis function, configuration information for obtaining a first set of analytics from a second data analysis function, wherein the configuration information includes trigger conditions for reporting the first set of analytics, wherein the first analysis function is configured to obtain the first set of analytics using a first set of input data, and wherein the second analysis function is configured to obtain the second set of analytics using a second set of input data; Based on the configuration information, obtaining the first set of analyses based on the first set of input data; determining that the trigger condition is satisfied; and In response to determining that the trigger condition is met, the first set of analyses is sent to the second data analysis function.

13. A method comprising: sending configuration information from a second analysis function to a first data analysis function to cause the first data analysis function to obtain a first set of analyses, wherein the configuration information includes a trigger condition for reporting the first set of analyses, wherein the second analysis function is configured to obtain the second set of analyses using a second set of input data, and the first analysis function is configured to obtain the first set of analyses using the first set of input data; In response to the trigger condition being satisfied, receiving a first set of analyses from the first data analysis function; obtaining a second set of analyses based on the second set of input data; and One or more strategies are determined based on the first set of analyses and the second set of analyses.

14. An apparatus comprising at least one processor and at least one memory including computer program code, the at least one memory and the computer program code being configured, with the at least one processor, to cause the apparatus to at least: At the first data analysis function, configuration information for obtaining a first set of analyses is received from the second data analysis function, wherein: The configuration information includes a trigger condition for reporting the first set of analyses, wherein the first analysis function is configured to utilize a first set of input data to obtain the first set of analyses, and the second analysis function is configured to utilize a second set of input data to obtain the second set of analyses; Based on the configuration information, obtaining a first set of analyses based on a first set of input data; determining that the trigger condition is satisfied; and In response to determining that the trigger condition is met, the first set of analyses is sent to the second data analysis function.

15. An apparatus comprising at least one processor and at least one memory including computer program code, the at least one memory and the computer program code being configured, with the at least one processor, to cause the apparatus to at least: Sending configuration information from the second analysis function to the first data analysis function so that the first data analysis function obtains a first set of analyses, wherein: The configuration information includes a trigger condition for reporting the first set of analyses, wherein the second analysis function is configured to utilize a second set of input data to obtain a second set of analyses, and the first analysis function is configured to utilize a first set of input data to obtain the first set of analyses; In response to the trigger condition being satisfied, receiving the first set of analyses from the first data analysis function; obtaining a second set of analyses based on the second set of input data; and One or more strategies are determined based on the first set of analyses and the second set of analyses.

Images