Tracking and exposing data for generating analytics

Abstract

The present invention relates to analytics generation in mobile networks. The present invention relates to tracking and exposing data information for generating analytics output in order to enable checking of the analytics output. Thus, the present invention proposes network entities and methods that support the analytics generation and its checking, respectively. For example, a first network entity for analytics generation is configured to receive a request from a second network entity for providing analytics information associated with at least one generated analytics output. Further, the first network entity is configured to provide the analytics information to the second network entity, wherein the analytics information comprises data information used for generating the at least one generated analytics output, wherein the data information comprises a reference to data or the data itself.

Description

Technical Field

[0001] This invention relates to analytics generation in mobile networks. Specifically, it relates to tracking and publishing data used to generate analytics output, enabling the examination of this output. To this end, the invention proposes network entities and corresponding methods that support analytics generation and the examination of the generated analytics. Background Technology

[0002] The next generation of mobile and wireless communications (e.g., 5G or higher) has been defined with a high degree of automation already considered in the management plane (e.g., see ETSI group specification (GS): zero-touch network and service management (ZSM); reference architecture (i.e. ETSI GSZSM002 V1.1.1 (2019-08)) and control plane (e.g., see TS 23.288)). A key component of this automation is analytics / learning / artificial intelligence (AI) services.

[0003] In this invention, the term "analysis service" is generally used to capture all of these services. Entities that provide intelligence and support system automation are defined in the mobile network management plane (e.g., management data analytics service (MDAS)) or control plane (e.g., network data analytics function (NWDAF)).

[0004] Network operators may want to track and examine why a particular analytics service produced specific analytics output—for example, why it provided specific recommendations used by certain entities, or why it gained specific insights into the network. Without the ability to understand analytics output, operators lack the capacity to identify the behavior of the analytics service and / or debug errors in its behavior.

[0005] Currently, there is no satisfactory method for operators to debug or inspect the service, nor is there a known solution to this problem. Summary of the Invention

[0006] The embodiments of the present invention are based on the insight that, for example, it is currently impossible for operators to track the relationship between the analytics output generated by the analytics service and the data used by the analytics service to generate the analytics output.

[0007] In view of the above-mentioned problems and disadvantages, the purpose of embodiments of the present invention is to improve analytics services. The aim is to enable the inspection and debugging of analytics services. Specifically, the objective is to enable a deeper understanding of the relationship between the analytics output generated by the analytics service and the data used to generate the analytics output. For example, operators should be able to obtain this relationship in order to inspect and debug the analytics service. To this end, embodiments of the present invention propose entities, as well as new interfaces and signaling between these entities.

[0008] This objective is achieved through embodiments of the invention described in the appended independent claims. Advantageous implementations of these embodiments are further defined in the dependent claims.

[0009] A first aspect of the present invention provides a first network entity for analysis generation in a mobile network, the first network entity being configured to: receive from a second network entity a request for providing analysis information associated with at least one generated analysis output; and provide the analysis information to the second network entity, wherein the analysis information includes data information for generating at least one generated analysis output, wherein the data information includes guidance on the data or the data itself.

[0010] The term "analysis generation" means that a first network entity can typically be used to provide analysis services, specifically, to generate one or more analysis outputs. Each analysis output may include recommendations and / or insights. The analysis outputs of the analysis service can be generated by one or more analysis functions (e.g., NWDAF or MDAS) implemented by the first network entity.

[0011] By providing analytical information, including data information, the analytical output can be checked and debugged, thereby enabling the checking and debugging of the analytical service. Specifically, the second network entity can obtain information about the relationship between each specific analytical output and the data used to generate that specific analytical output. For example, by being able to obtain this data, the user of the analytical output can verify the expected or unexpected functionality of the analytical service. The ability of the first network entity to associate data and analytical output and accordingly provide analytical information, including data information, is called "tracking capability."

[0012] In one implementation of the first aspect, the request for providing analysis information associated with at least one generated analysis output includes: identification information for identifying at least one generated analysis output.

[0013] Therefore, for example, if the analysis service provided by the first network entity outputs different analysis outputs, the second network entity can identify each specific analysis output. Furthermore, in response to a request from the second network entity containing identification information for one or more specific analysis outputs, the first network entity can provide the correct analysis information.

[0014] Identification information used to identify at least one generated analysis output may include a timestamp, and / or may include an identifier, and / or may include a set of filters used in service operations.

[0015] In one implementation of the first aspect, the analysis information also includes identification information for identifying the data information.

[0016] Therefore, the first network entity can be used to label data information associated with the data used to generate a specific analytical output. For example, the data information can be labeled with an identifier of the analytical output. The data information can be provided to the object that wants to use the information upon request.

[0017] In one implementation of the first aspect, the first network entity is further configured to receive an activation request for tracking data information used to generate at least one generated analytical output; and to track the data information upon receiving the activation request.

[0018] "Tracking data information" means that the first network entity uses information to determine and / or store which data has been used or will be used to generate a specific analytical output. The first network entity can then provide analytical information associated with that specific analytical output, wherein the analytical information includes data information indicating the data used or will be used to generate that specific analytical output.

[0019] In one implementation of the first aspect, the first network entity is further configured to store mapping information including one or more entries, each entry being associated with a generated analysis output, wherein each entry includes identification information associated with the corresponding generated analysis output and includes data information for generating the corresponding generated analysis output.

[0020] Therefore, the first network entity is used to track the data used to generate each specific analytics output and to maintain the relationship between that data and the analytics output. The user of this tracking capability can be an operator, a management plane or control plane service or function, or an external entity, such as a network entity used for analytics generation in another mobile network.

[0021] In one implementation of the first aspect, each entry further includes at least one of the following: an identifier of a network entity generated for analysis of the mobile network, the network entity being used to generate the corresponding generated analysis output; a list of network entities using the corresponding generated analysis output; and a type of data information used to generate the corresponding generated analysis output.

[0022] The identifier of the network entity generated for analysis of the mobile network (the network entity used to generate the corresponding analysis output) can be the identifier of a first network entity. The first network entity may also store mapping information that is associated with one or more other network entities used for analysis.

[0023] In one implementation of the first aspect, for each piece of data information, the mapping information further includes at least one of the following: an identifier of the data information; the source of the data information; time information associated with the data information; and manipulation techniques applied to the data information.

[0024] In one implementation of the first aspect, the first network entity is a control plane entity, specifically including a network data analytics function (NWDAF), or the first network entity is a management plane entity, specifically including a management data analytics service (MDAS).

[0025] The management surface entity can also be an implementation of the analysis service in ETSI GS ZSM002 V1.1.1 (2019-08).

[0026] A second aspect of the invention provides a second network entity for inspecting analysis generated by a mobile network, the second network entity being configured to: provide a request to a first network entity for analysis generation for analysis information associated with at least one generated analysis output; and receive analysis information from the first network entity, wherein the analysis information includes data information for generating at least one generated analysis output, wherein the data information includes guidance on the data or the data itself.

[0027] The second network entity can be a user of the analytics service provided by the first network entity. Accordingly, the second network entity can be used, for example, to receive one or more analytics outputs generated by the first network entity upon request. The second network entity is used to obtain data information associated with a specific analytics output, and therefore can examine the received analytics output and / or (typically) the analytics service. For example, the data information can enable the second network entity to debug the analytics service. It should be noted that the second network entity can receive analytics information and associated analytics outputs. However, the second network entity can also request analytics information after receiving associated analytics outputs. The second network entity can also request analytics information associated with analytics outputs received by another entity. That is, the second network entity does not necessarily have to be a user of the analytics outputs.

[0028] In one implementation of the second aspect, the second network entity is used to: provide an activation request for tracking data information used to generate at least one generated analytical output.

[0029] In this way, the second network entity can be used to activate the service at the first network entity, and the activated service can then provide analytical information, including data information, to the second network entity or another entity.

[0030] In one implementation of the second aspect, the request for providing analysis information associated with at least one generated analysis output includes: identification information for identifying at least one generated analysis output.

[0031] Identification information used to identify at least one generated analysis output may include a timestamp, and / or may include an identifier, and / or may include a set of filters used in service operations.

[0032] In one implementation of the second aspect, the analysis information also includes identification information for identifying the data information.

[0033] In one implementation of the second aspect, the data information includes guidance on the data, and the second network entity is further configured to: send analysis information including the data information to a third network entity; and receive data from the third network entity, the data being guided by the guidance on the data in the data information.

[0034] The third network entity can be a data lake entity, as described in the specific implementation.

[0035] In one implementation of the second aspect, the second network entity is a network function (NF), an application function (AF), or an operation, administration and management (OAM) function.

[0036] A third aspect of the present invention provides a method for generating analysis for a mobile network, the method comprising: receiving a request for providing analysis information associated with at least one generated analysis output; and providing the analysis information, wherein the analysis information includes data information for generating at least one generated analysis output, wherein the data information includes guidance on the data or the data itself.

[0037] In one implementation of the third aspect, the request for providing analysis information associated with at least one generated analysis output includes: identification information for identifying at least one generated analysis output.

[0038] In one implementation of the third aspect, the analysis information also includes identification information used to identify the data information.

[0039] In one implementation of the third aspect, the method further includes: receiving an activation request for tracking data information used to generate at least one generated analytical output; and tracking the data information upon receiving the activation request.

[0040] In one implementation of the third aspect, the method further includes storing mapping information comprising one or more entries, each entry being associated with a generated analysis output, wherein each entry includes identification information associated with the corresponding generated analysis output and includes data information for generating the corresponding generated analysis output.

[0041] In one implementation of the third aspect, each entry further includes at least one of the following: an identifier of a network entity generated for analysis of the mobile network, the network entity being used to generate the corresponding generated analysis output; a list of network entities using the corresponding generated analysis output; and a type of data information used to generate the corresponding generated analysis output.

[0042] In one implementation of the third aspect, for each piece of data information, the mapping information further includes at least one of the following: an identifier of the data information; the source of the data information; time information associated with the data information; and manipulation techniques applied to the data information.

[0043] In one implementation of the third aspect, the method is executed by the control plane entity, specifically by NWDAF, or by the management plane entity, specifically by MDAS.

[0044] The third approach achieves the same advantages as the first network entity in the first approach.

[0045] A fourth aspect of the present invention provides a method for examining the generation of analysis on a mobile network, the method comprising: providing a request for analysis information associated with at least one generated analysis output; and receiving the analysis information, wherein the analysis information includes data information for generating at least one generated analysis output, wherein the data information includes guidance on the data or the data itself.

[0046] In one implementation of the fourth aspect, the method includes: providing an activation request for tracking data information used to generate at least one generated analytical output.

[0047] In one implementation of the fourth aspect, the request for providing analysis information associated with at least one generated analysis output includes: identification information for identifying at least one generated analysis output.

[0048] In one implementation of the fourth aspect, the analysis information also includes identification information used to identify the data information.

[0049] In one implementation of the fourth aspect, the data information includes guidance on the data, and the second network entity is also used to: send analysis information including the data information to the third network entity; and receive data from the third network entity, which is guided by the guidance on the data in the data information.

[0050] In one implementation of the fourth aspect, the method is performed by the NF, AF, or OAM function.

[0051] The method in the fourth aspect achieves the same advantages as the second network entity in the second aspect.

[0052] The fifth aspect of the invention provides a computer program comprising program code for performing, when executed on a computer, a method according to any one of the third or fourth aspects or implementations thereof.

[0053] A sixth aspect of the invention provides a non-transitory storage medium storing executable program code that, when executed by a processor, causes the execution of a method according to any one of the third or fourth aspects or their implementations.

[0054] It should be noted that all devices, elements, units, and apparatuses described in this application can be implemented by software or hardware elements or any combination thereof. All steps performed by the various entities described in this application, and the functions described as being performed by the various entities, are intended to indicate that the respective entities are suitable for or used to perform the respective steps and functions. Although in the following description of specific embodiments, the specific functions or steps performed by external entities are not reflected in the detailed description of the specific elements of the entity performing that specific step or function, it will be apparent to those skilled in the art that these methods and functions can be implemented by corresponding hardware or software elements or any combination thereof. Attached Figure Description

[0055] The above aspects and implementations will be described in detail below with reference to the accompanying drawings, in which:

[0056] Figure 1 The diagram illustrates a first network entity and a second network entity interacting with each other according to an embodiment of the present invention.

[0057] Figure 2 A first network entity according to an embodiment of the present invention is shown.

[0058] Figure 3 The diagram illustrates the mapping information stored by a first network entity according to an embodiment of the present invention.

[0059] Figure 4 An example of a second network entity according to an embodiment of the present invention is shown, wherein the second network entity requests analysis information from a first network entity according to an embodiment of the present invention.

[0060] Figure 5 The NWDAF according to an embodiment of the present invention is shown as a first exemplary use option for a first network entity.

[0061] Figure 6 The NWDAF according to an embodiment of the present invention is shown as a second exemplary use option for a first network entity.

[0062] Figure 7 An implementation of the NWDAF service extension / enhancement is shown.

[0063] Figure 8 The interaction between the first network entity and the second network entity is shown.

[0064] Figure 9 The diagram illustrates the interaction between the analysis user and the analysis output from NWDAF, as well as the OAM check of the generated analysis. Detailed Implementation

[0065] Figure 1 An interactive first network entity 100 and a second network entity 101 according to an embodiment of the present invention are illustrated. The first network entity 100 is adapted for generating analysis of a mobile network, and the second network entity 101 is adapted for inspecting the generated analysis. The second network entity 101 may or may not be a user of the analysis. The analysis may be provided by the first network entity 100 as an analysis service in the form of one or more analysis outputs.

[0066] The second network entity 101 is configured to provide the first network entity 100 with a request 102 for analysis information 103 associated with one or more generated analysis outputs. Accordingly, the first network entity 100 is configured to receive the request 102 provided by the second network entity 101.

[0067] Furthermore, the first network entity 100 provides analysis information 103 to the second network entity 101. The analysis information 103 includes information for generating one or more generated analysis outputs 201 (see...). Figure 2 Data information 200, wherein data information 200 includes data 202 (see Figure 2 The analysis information 103 may include the data 202 itself or the instructions for generating one or more analysis outputs 201.

[0068] The instructions for data 202 include information enabling access to data 202. For example, the instructions may include a pointer to data 202, a link to data 202, or a timestamp indicating the receipt of data 202. The instructions may also indicate the storage location of data 202, or may include information about the entity storing data 202. Accordingly, the second network entity 101 is used to receive analysis information 103 from the first network entity 100.

[0069] Thus, for each analysis output, the second network entity 101 can know the data 202 used to generate that analysis output 201.

[0070] The first network entity 100 and / or the second network entity 101 can uniquely identify each individual analysis output 201. The first network entity 100 can map each uniquely identified generated analysis output 201 to the data 202 used to generate the analysis output 201.

[0071] For example, for each piece of data 202 used to generate a given unique identifier for the generated analysis output 201, the first network entity 100 may maintain one or more of the following mappings:

[0072] -Identification information of the collected data 202;

[0073] -Identification information of the source of the collected data 202;

[0074] - A time description of the collected data 202 (e.g., the time interval between the collected data samples);

[0075] - One or more manipulation techniques (e.g., which filtering, aggregation, classification, or selection mechanism) are applied to the collected data 202.

[0076] The first network entity 100 can provide services, for example, upon request from the second network entity 101, such services that provide data information 200 related to data 202 for each individual analysis output 201. Mapping between multiple users uniquely identifying the generated analysis output 201 is also possible.

[0077] The first network entity 100 and / or the second network entity 101 may include a processor or processing circuitry (not shown) for performing, conducting, or initiating various operations of the first network entity 100 and / or the second network entity 101 described herein. The processing circuitry may include hardware and / or may be software-controlled. The hardware may include analog or digital circuitry, or both. The digital circuitry may include components such as application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), or multi-purpose processors.

[0078] The first network entity 100 and / or the second network entity 101 may further include memory circuitry storing one or more instructions that can be executed by a processor or processing circuitry (in particular, under software control). For example, the memory circuitry may include a non-transitory storage medium storing executable software code that, when executed by a processor or processing circuitry, causes various operations of the first network entity 100 and / or the second network entity 101 to be performed.

[0079] In one embodiment, the processing circuitry includes one or more processors and non-transitory memory connected to one or more processors. The non-transitory memory may carry executable program code that, when executed by one or more processors, causes the first network entity 100 and / or the second network entity 101 to perform, conduct, or initiate the operations or methods described herein.

[0080] Specifically, the first network entity 101 and the second network entity 101 can execute the methods according to embodiments of the present invention. Specifically, the first network entity 100 can execute the analysis and generation method according to the third aspect described in the summary of the invention, such as... Figure 1 As shown, and the second network entity 101 can execute the analysis generation method for inspecting mobile networks according to the fourth aspect described in the summary of the invention, such as... Figure 1 As shown.

[0081] Figure 2 A first network entity according to an embodiment of the present invention is shown, which is established on Figure 1 Based on the illustrated embodiment. Specifically, Figure 2 The first network entity 100 is shown to be used to provide analysis output 201, wherein the analysis output 201 is generated based on certain data 202.

[0082] The first network entity 100 can also provide analysis information 103 associated with the analysis output 201 (such as...). Figure 1 As shown), the provided analysis information 103 includes data information 200 associated with data 202 used to generate analysis output 201 (as described above, data information 200 may include data 202 or data 202, or may guide data 202).

[0083] Therefore, the analysis output 201 can be provided with identification information 203, so that the second network entity 101 can request data information 200 for a specific analysis output 201 identified by the identification information 203.

[0084] In fact, the two options of the first network entity 100 can be combined. Figure 2 Description. The difference between the two options lies in how the analysis output 201 is identified: in the first option, the analysis output 201 can be identified by a timestamp or by other information 203 that uniquely identifies the analysis output 201 (but not by an additional identifier).

[0085] In the second option, the analysis output 201 can be identified using an identifier 203 that is uniquely associated with it. It should be noted that these methods of identifying the analysis output 201 are merely examples, and other methods can be used.

[0086] To support the aforementioned tracking capabilities of the first network entity 100 (which enable the provision of appropriate analysis information 103, including data information 200 associated with the analysis output 201), the first network entity 100 can also be used to tag the data 202 used to obtain the analysis output 201 in a certain way. In one example, this tagging can be achieved by creating and / or saving data such as... Figure 3 The mapping information 300 shown (e.g., a mapping table) is used to implement this.

[0087] For example, in mobile networks such as 5G networks, both the control plane and management plane can store data 202 in various memories or databases. This data 202 can be fed to one or more analysis functions (e.g., analysis functions implemented by the first network entity 100 to provide analysis services), wherein the analysis functions can obtain one or more analysis outputs 201 based on the data 202, such as possible insights and / or recommendations.

[0088] The first network entity 100 may store mapping information 300. The mapping information 300 may include one or more entries 301, wherein each entry 301 may be associated with a generated analysis output 201, and wherein each entry 301 may include identification information 203 associated with the corresponding generated analysis output 201. Furthermore, each entry 301 may include data information 200 about data 202 used to generate the corresponding generated analysis output 201.

[0089] exist Figure 3 In this context, the mapping information 300 is implemented using a data structure called “KPI-Info-List for each suggestion ID” (for example, data 202 is stored in the data structure according to the analysis output 201, wherein the list of data 202 is called “KPI-Info-List” and the analysis output 201 is exemplarily called “suggestion”).

[0090] It should be noted that the suggested ID refers to the second option described above; for example, it refers to the identifier of the analysis output 201. For example, in the first option described above, the entire line associated with the analysis output 201 (in...) Figure 3 The table showing the data structure can be used to identify the analysis output 201.

[0091] In addition to identifying the analysis output 201, the KPI-Info-List can store a list of so-called "KPI-info objects" (such as multiple data 202 used to generate the analysis output 201).

[0092] Assuming that data 202 consists of the values ​​of various key performance indicators (KPIs) and their corresponding timestamps, the KPI-Info object can record only the initial and final timestamps and the identifier of each KPI, and optionally the location of the database where it is stored.

[0093] When a request 102 for analysis information 103 is received from the second network entity 101 (e.g., a request for getDataForRecommendation), the first network entity 100 can simply retrieve the KPI-Info-List from the database based on the mapping information 300, and can provide a link to data 202 (guidance to data 202) as data information 200, and a timestamp of data 202 for generating analysis output 201.

[0094] Alternatively, the first network entity 100 can acquire the entire data 202 itself and then provide the data 202 as data information 200 to the second network entity 101.

[0095] The following describes a specific implementation based on a first network entity 100 and a second network entity 101 according to an embodiment of the present invention.

[0096] Figure 4 and Figure 5 This relates to an embodiment of end-to-end (E2E) management that supports the tracking capabilities described above.

[0097] Figure 4 Table 1 is shown, which exemplarily illustrates the general analytics service in ETSI GS ZSM002 V1.1.1 (2019-08). The tracking capability can request (102) analytics information 103, which includes data information 200 about data 202 used to generate analytics output 201 (in Table 1, analytics output 201 is referred to as "Result X (M)", where "M" indicates that this is a mandatory capability of the analytics service).

[0098] Figure 5 The process in the diagram illustrates how a second network entity 101 (which is also a user of the analytics services provided by the first network entity 100) can use the tracking capabilities of the first network entity 100.

[0099] Figure 5 Specifically shown Figure 4 The exemplary analytics service is shown in Table 1. The integrated structure 500 can be arranged between the first network entity 100 and the second network entity 101. The integrated structure 500 can be an optional communication medium used to transmit messages between the first network entity 100 (providing the analytics service) and the second network entity 101 (using the analytics service). Users of the analytics service can also be any other software / hardware entity, managed entity, or individual.

[0100] The following steps present an example of the use of the tracking capabilities that the second network entity 101 can use.

[0101] 1. The analytics function / service of the first network entity 100 is in normal processing, for example, generating one or more analytics outputs 201 with tracing capabilities enabled. This means that any generated analytics output 201 provided by the first network entity will enable the tracing option. Alternatively, the second network entity 101 may selectively enable tracing only for some of the generated analytics outputs 201.

[0102] 2 / 3. Generate analysis output 201 and publish it to subscribed users (including the second network entity 101), or publish it to the integration structure 500, which can relay the analysis output 201 to users. Alternatively, the second network entity 101 can request a specific analysis output 201.

[0103] 4. In step 4, at least one of the analysis users (here, the second network entity 101) wishes to examine the data 202 used to generate a specific analysis output 201, which is identified by “XXX” as identification information 203. “XXX” can represent any mechanism that can be used to identify the analysis output 201, such as a universally unique identifier (UUID) or a timestamp. Therefore, the second network entity 101 sends a request 102 to the first network entity 101 indicating the identification information 203. It should be noted that the request 102 for analysis information 103 (i.e., actually for data 202) can be for a set of analysis outputs 201, not just a single analysis output 201.

[0104] 5 / 6. The tracking capability of the first network entity 101 can collect corresponding data 202 (or a pointer to data 202), that is, it can obtain data information 200 and can provide a response to the second network entity 101 including analysis information 103 (analysis information 103 includes data information 200).

[0105] For the third-generation partner project (3 rd Implementations in the Generation Partnership Project (3GPP) SA5 can achieve similar tracking capabilities, enabling a management system (represented by a first network entity 100) to provide data 202, for example, used by MDAS to generate one or more analytics outputs 201, to one or more users (including, for example, a second network entity 101).

[0106] Figures 6 to 9 Specifically, this involves the implementation of the control plane analysis service, which can expose the relationship between the generated analysis output 201 (associated with the analysis ID) and the data (samples) used to generate the analysis output 201 (e.g., based on 3GPP SA2).

[0107] In this implementation, the analytics service is mapped to a service provided by the NWDAF (as defined in 3GPP TS 23.501 and described in detail in 3GPP TS 23.288). The first network entity 100 may include the NWDAF. In this case, there are two alternative implementations:

[0108] Option 1: Two changes have been introduced in the NWDAF service.

[0109] First, the output parameters of the NWDAF service that provides analysis output 201 are expanded with new parameters (for analysis ID), such as Nnwdaf_AnalyticsSubscription_Notify and Nnwdaf_AnalyticsInfo_response. These new parameters uniquely identify the mapping between analysis output 201 and data 202 used by NWDAF 100 (e.g., machine learning (ML) engines, analytics models, big data inference engines, etc.).

[0110] Secondly, the new service is dedicated to providing analysis information 103 upon receiving request 102. This analysis information 103 includes data information 200 about data 202 (i.e., guidance on data 202 or data 202 itself), which is used by NWDAF 100 to generate a given analysis output 201. Request 102 may contain a unique identifier that maps the analysis output 201 to the data 202 used to generate that analysis output.

[0111] Option 2: There is only one change in the NWDAF service.

[0112] A new service is introduced in NWDAF 100 that provides analytics information 103 upon receiving request 102. This analytics information 103 includes data information 200 about data 202 used by NWDAF 100 to generate a given analytics output 201. Request 102 may include a set of fields and / or an analytics ID providing the analytics output 201 and / or a specific analytics output instance, these fields uniquely identifying the analytics output 201. For example, if multiple analytics outputs 201 are generated for the same analytics ID, each of these analytics outputs 201 is an analytics output instance. Furthermore, request 102 may include identification information of the user of the analytics output 201 (e.g., the ID of a second network entity 101).

[0113] Figure 6 Table 2 shows the dataset, which represents the implementation of the mapping information 300 between the generated analysis output 201 and the data 202 used to generate the analysis output 201.

[0114] Figure 7 Table 3 illustrates the implementation of the described NWDAF service extensions / enhancements. Although not shown in Table 3, the same extensions to the parameters apply to NWDAF services associated with the request / response model.

[0115] The need for data tracking can be defined statically, for example, hard-coded at NWDAF 100, or it can be indicated dynamically, for example, by the analytics subscription parameters as shown in Table 3.

[0116] Figure 8 and Figure 9 The processes shown are examples of how the services defined in Tables 2 and 3 can be used, as well as examples of entities that interact with these services.

[0117] Figure 8 The interaction between the first network entity 100 (NWDAF) and the second network entity 101 (analysis user) shown is considered to be implemented such that the analysis user explicitly instructs the NWDAF 100 via subscription / request 800 to track data 202 for one or more analysis outputs 201 (for one or more analysis IDs), and the data 202 is used for analysis output generation.

[0118] 1. Specifically, user 101 can invoke the NWDAF service Nnwdaf_AnalyticsInfo_Request_request (including existing parameters defined in TS 23.288). Furthermore, this request 800 can also include a parameter called "Activate Tracking" set to "True". The advantage of using this parameter is that NWDAF 100 can obtain an indication from user 101 that data 202 needs to be tracked for the generated analytics output 201. Therefore, user 101 can use request 800 as an activation request for tracking data 202. Alternatively, if this parameter is not sent, NWDAF 100's internal logic can determine when and which generated analytics outputs 201 should be generated, or NWDAF 100 can be used to track all generated analytics outputs 201. Furthermore, the parameter in request 800 can support better resource utilization of NWDAF resources. However, this parameter can also introduce trade-offs, as it also stipulates that user 101 decides which analytics output and which data 202 will actually be tracked.

[0119] 2. Based on the received request 800 with the "Activate Tracking" parameter set to true, NWDAF 100 can create a new dataset called "Analysis Data Tracking" and can define a unique identifier "Analysis Data Tracking ID". This unique identifier can be a UUID or an Analysis Data Tracking Association Identifier, which associates the Analysis Output 201 request 800 with the "Analysis Data Tracking ID". For example, the Analysis Tracking Association Identifier can be a function of the subscriber identifier and the Analysis ID.

[0120] 3. NWDAF 100 performs analysis output generation (e.g., NWDAF 100 can calculate analysis output 201 based on the requested “analysis target” and / or “analysis report” and / or “analysis filter” included in request 800).

[0121] 4. For a specific generated analytics output 201, NWDAF 100 creates a dataset called "Data Trace Information" and defines a unique identifier "Data Trace ID" for "Data Trace Information". "Data Trace Information" can be mapped and included as part of the "Analysis Data Trace" dataset associated with the generated analytics output 201's "Analysis Data Trace ID". When creating "Data Trace Information", NWDAF 100 includes all fields defined in Table 2 within this information.

[0122] 5. NWDAF 100 sends a response 801 to user 101 using Nnwdaf_AnalyticsInfo_Request_response. Nnwdaf_AnalyticsInfo_Request_response includes parameters defined in TS 23.288, as well as the parameters "Analysis Data Trace ID" and "Data Trace ID". The first parameter is important for user 101 to be able to query NWDAF 100 to retrieve actual information about the "Analysis Data Trace" of the analysis output 201 that it uses (or will use in the future). The second parameter is important when multiple analysis outputs 201 are generated for the same analysis ID. In this case, user 101 can also specifically request only the "Data Trace Information" for a particular analysis output 201 it has received, without needing to retrieve all the "Data Trace Information" for all received analysis outputs 201.

[0123] 6. NWDAF 100 exposes the service Nnwdaf_AnalyticsDataTrace, which can be invoked by user 101 to retrieve records of the "Analysis Data Trace" for a given or all generated analysis outputs 201 (for one or more analysis IDs), and / or all or part of the records of the "Data Trace Information" for a given generated analysis output 201, as a corresponding implementation of the data information 200 included in the analysis information 103. This service exposes the operation of the query request (see step 6a), which generates a query response (see step 6b).

[0124] 6a. User 101 may invoke the Nnwdaf_AnalyticsDataTrace_Query_request service operation to provide a request 102 with parameters that specify the target “analytical data trace” dataset that user 101 wants to retrieve. Figure 8 An example of the query operation for Option 1 (as described in Table 3) is shown. In this case, user 101 indicates a specific identifier, "Analysis Data Tracking ID," for the "Analysis Data Tracking" dataset it wants to retrieve, and optionally, it also indicates one or more "Data Tracking IDs" associated with the "Data Tracking Information" that should be returned. These two parameters are used as filters by NWDAF 100 to select the data information 200 ("Analysis Data Tracking" and / or "Data Tracking Information") from the Analysis Information 103 to be retrieved and provided to user 101. In this example, all "Data Tracking Information" associated with the "Analysis Data Tracking" based on the "Analysis Tracking ID" can be returned.

[0125] 6b. This implementation shows an option in which NWDAF 100 sends a response 802 to request 102 and thus returns the actual “Analysis Data Trace” dataset as analysis information 103 including data information 200 associated with the requested “Analysis Data Trace ID” (according to the example, but if the query request indicates more “Analysis Data Trace”, the return will be a list of “Analysis Data Trace” datasets).

[0126] Figure 9 The interactions described consider possible implementations for enabling the following actions. Figure 9 In this process, the analysis user 900 uses the analysis output 201 from NWDAF (first network entity 100). However, OAM (second network entity 101) can be used to examine the generated analysis.

[0127] NWDAF 100 is used to trigger tracing of any generated analytics output 201. In this case, the parameter "Activate Tracing" does not need to be included (and set to "True") in the request 800 and / or subscription to the NWDAF service used for generating the analytics output. Ultimately, if the analytics user 101 of NWDAF 100 explicitly decides that data tracing for the requested analytics output 201 should not be performed by NWDAF 100, this "Activate Tracing" parameter can be set to "False". If this is the case, NWDAF 100 may not perform the steps related to the creation and association of the "Analysis Data Tracing" dataset and the "Data Tracing Information" dataset.

[0128] In this implementation, consider the interaction mode of Option 2 described in Table 3. In this case, the parameters of the NWDAF service used for notification and / or response on the generated analysis output 201 remain unchanged. The difference for this operation mode is the type of parameter used to query the analysis information 103 including data information 200 via the Nnwdaf_AnalyticsDataTrace_Query_request operation (request 102). OAM 101, as the user of the NWDAF query service, does not know either the "Analysis Data Trace ID" or the "Data Trace ID". Therefore, for OAM 101 to retrieve the "Analysis Data Trace" and "Data Trace Information" datasets (i.e., data information 200 in the analysis information 103 of the analysis output 201), there are two possibilities:

[0129] Alternative Option 1 (with Operation Option 2): OAM 101 uses only the Nnwdaf_AnalyticsDataTrace_Query_request operation from NWDAF 100 and uses the information indicated in Table 3 for Option 2 as a filter to request analysis information 103 including data information 200. For example, request 102 may include an analysis ID (e.g., to support the identification of the "Analysis Data Trace ID") and / or association information (e.g., to support the identification of the "Data Trace ID").

[0130] Alternative Option 2 (with Operation Option 2): OAM 101 invokes the Nnwdaf_AnalyticsDataTrace_List_request operation from NWDAF 100 and, in response, obtains a list of one or more "Analysis Trace IDs" and / or a list of one or more "Data Trace IDs". OAM 101 can use the fields listed in Table 3 as filters for this service operation, such as, for each type of analysis ID, or each NWDAF 100 that generates the analysis ID, or each specific analysis output 201, or each specific user of the analysis ID. This type of operation is useful when the user of the "Analysis Data Trace" (i.e., data information 200 in analysis information 103) is not the same entity (analysis user 900) that is using the analysis. This is Figure 9The implementation example described herein uses the entity OAM101 as the "analysis data trace". The response 901 of the Nnwdaf_AnalyticsDataTrace_List service operation may include a list of one or more "analysis data trace IDs" and / or a list of one or more "data trace IDs" that match the filter provided at request 102. Optionally, the response 901 may include the actual dataset of the "analysis data trace" and / or the "data trace information" associated with the "analysis data trace ID", and / or a storage reference for retrieving these datasets (i.e., the data information 200 represented by the "analysis data trace" and / or the "data trace information" may be a guide to data 202 or data 202 itself). In this implementation, the latter case is described. When the dataset and / or the storage reference of the dataset are not included in the response of the Nnwdaf_AnalyticsDataTrace_List service operation, OAM 101 will still use the NWDAF 100 to call the Nnwdaf_AnalyticsDataTrace_Query_request based on the list of “Analysis Data Trace IDs” and / or the list of “Data Trace IDs” retrieved from the response of the Nnwdaf_AnalyticsDataTrace_List service operation call to actually retrieve the expected data information 200.

[0131] In this implementation, the "store reference" included in the response 901 of the Nnwdaf_AnalyticsDataTrace_List service operation call can be a reference to the system's data lake entity 902.

[0132] Combination Figure 9 The detailed steps of this implementation are described below:

[0133] 1. The analysis user 900 from the analysis output 201 of NWDAF 100 calls the NWDAF service Nnwdaf_AnalyticsSubscription_Subscribe, which includes existing parameters defined in TS 23.288.

[0134] 2. NWDAF 100 creates a new dataset “Analysis Data Tracking” and defines a unique identifier “Analysis Data Tracking ID”. This identifier can be a UUID or an Analysis Tracking Association Identifier, which associates the Analysis ID request 800 with such an “Analysis Data Tracking ID”. For example, this association could be a function of subscriber ID and Analysis ID.

[0135] Steps 3 through 5 can be repeated until the condition for the subscription of the analytics ID that received the request in step 1 is met.

[0136] 3. NWDAF 100 performs analysis output generation (e.g., NWDAF 100 calculates analysis output 201 based on the requested “analysis target” and / or “analysis report” and / or “analysis filter” included in request 800).

[0137] 4. For a specific generated analytics output 201, NWDAF 100 creates a "Data Trace Information" and defines a unique identifier "Data Trace ID" for the "Data Trace Information". The "Data Trace Information" is mapped and included as part of the "Analysis Data Trace" dataset associated with the generated analytics ID. When creating the "Data Trace Information", NWDAF 100 includes all fields defined in Table 2 in this information.

[0138] 5. NWDAF 100 sends a response to user 900 using Nnwdaf_AnalyticsInfo_Request_response, which includes the parameters defined in TS 23.288.

[0139] 6. OAM 101 (e.g., when evaluating the performance of an algorithm used by NWDAF 100 for an analytics ID service experience used for user plane (UP) optimization service management function (SMF)) requires "analytical data trace" information for a specific analytics ID for a specific analytics user 900. OAM 101 invokes the Nnwdaf_AnalyticsDataTrace_List_request operation from NWDAF 100 to provide a request 102 using the NF ID and analytics ID as filters. In this case, OAM 101 wants to retrieve all "data trace information" generated for the analytics ID for this NFID user. NWDAF 100 uses this filter information to filter the "analytical data trace" dataset, with fields (as described in Table 3) matching the filter information received in the service operation request. Then, the operation Nnwdaf_AnalyticsDataTrace_List_response from NWDAF 100 (e.g., the output parameters shown in Table 3) provides response 901, which will include: the requested analysis ID and the dataset of the NF user including the "analysis data trace ID" of the "data trace information", as analysis information 103 including data information 200; and a reference to the entity storing such dataset (e.g., data lake 902).

[0140] 7. Based on the information retrieved from NWDAF 100, OAM 101 also interacts with Data Lake 902 to retrieve information associated with the “Analysis Data Tracking ID”.

[0141] The invention has been described in conjunction with various embodiments and implementations as examples. However, based on a study of the drawings, the invention, and the independent claims, those skilled in the art will be able to understand and implement other variations in practicing the claimed invention. In the claims and the description, the word "comprising" does not exclude other elements or steps, and "an" does not exclude a plurality. A single element or other unit can perform the function of several entities or items recited in the claims. The fact that some measures are recited in different dependent claims does not mean that a combination of these measures cannot be used for beneficial implementation.

Claims

1. A first network entity (100) generated from the analysis of a mobile network, characterized in that, The first network entity (100) is used for: Receive a request (102) from a second network entity (101) for providing analysis information (103) associated with at least one generated analysis output (201), wherein the request (102) includes identification information (203) identifying the at least one analysis output (201); and The analysis information (103) is provided to the second network entity (101), wherein the analysis information (103) includes data information (200) for generating the at least one generated analysis output (201), wherein the data information (200) includes guidance on data (202) for generating the at least one analysis output (201) or the data (202) itself for generating the at least one analysis output (201). The first network entity (100) is also used for: The mapping information (300) includes one or more entries (301), each entry (301) being associated with the generated analysis output (201), wherein each entry (301) includes the identification information (203) associated with the corresponding generated analysis output (201), and includes the data information (200) for generating the corresponding generated analysis output (201). The second network entity (101) is a network function (NF).

2. The first network entity (100) according to claim 1, characterized in that: The analysis information (103) also includes identification information for identifying the data information (200).

3. The first network entity (100) according to any one of claims 1 or 2, characterized in that, Used for: Receive an activation request (800) for tracking the data information (200) used to generate the at least one generated analysis output (201); and The data information (200) is tracked upon receiving the activation request (800).

4. The first network entity (100) according to claim 1, characterized in that, Each entry (301) also includes at least one of the following: - Identifiers of network entities generated for analysis of mobile networks, the network entities being used to generate the corresponding generated analysis output (201). -A list of network entities using the corresponding generated analysis output (201); - The type of data information (200) used to generate the corresponding generated analysis output (201).

5. The first network entity (100) according to claim 1 or 4, characterized in that: For each data information (200), the mapping information (300) further includes at least one of the following: - The identifier of the data information (200); - The source of the data information (200); - Time information associated with the data information (200); - Manipulation techniques applied to the data information (200).

6. The first network entity (100) according to claim 1, characterized in that: The first network entity (100) is a control plane entity, specifically including the Network Data Analysis Function (NWDAF); or The first network entity (100) is a management plane entity, specifically including the Management Data Analysis Service (MDAS).

7. A second network entity (101) generated from the analysis of a mobile network for inspection, characterized in that, The second network entity (101) is used for: A request (102) is provided to a first network entity (100) for analysis of analysis information (103) associated with at least one generated analysis output, wherein the request (102) includes identification information (203) identifying the at least one generated analysis output (201); and The analysis information (103) is received from the first network entity (100), wherein the analysis information (103) includes data information (200) for generating the at least one generated analysis output (201), wherein the data information (200) includes guidance on data (202) for generating the at least one analysis output (201) or the data (202) itself for generating the at least one analysis output (201). The first network entity (100) stores mapping information (300) including one or more entries (301), each entry (301) being associated with the generated analysis output (201), wherein each entry (301) includes the identification information (203) associated with the corresponding generated analysis output (201), and includes the data information (200) for generating the corresponding generated analysis output (201). The second network entity (101) is a network function (NF).

8. The second network entity (101) according to claim 7, characterized in that, Used for: An activation request (800) is provided for tracking the data information (200) used to generate the at least one generated analysis output (201).

9. The second network entity (101) according to claim 7 or 8, characterized in that: The analysis information (103) also includes identification information for identifying the data information (200).

10. The second network entity (101) according to claim 7, characterized in that, The data information (200) includes guidance on the data (202), and the second network entity (101) is further used for: Send the analysis information (103) including the data information (200) to the third network entity (902); and The data (202) is received from the third network entity (902), and the data (202) is directed by the data information (200) for the data (202).

11. A method for analyzing and generating mobile networks, characterized in that, The method includes: Receive a request (102) from a network function (NF) for providing analysis information (103) associated with at least one generated analysis output (201), wherein the request (102) includes identification information (203) identifying the at least one analysis output (201); and The analysis information (103) is provided to the NF, wherein the analysis information (103) includes data information (200) for generating the at least one generated analysis output (201), wherein the data information (200) includes guidance on data (202) for generating the at least one analysis output (201) or the data (202) itself for generating the at least one analysis output (201). The method further includes: The mapping information (300) includes one or more entries (301), each entry (301) being associated with the generated analysis output (201), wherein each entry (301) includes the identification information (203) associated with the corresponding generated analysis output (201), and includes the data information (200) for generating the corresponding generated analysis output (201).

12. A method for generating analysis for inspecting mobile networks, characterized in that, The method includes: The network function (NF) provides a request (102) for analysis information (103) associated with at least one generated analysis output (201), wherein the request (102) includes identification information (203) identifying the at least one analysis output (201); and The network function (NF) receives the analysis information (103), wherein the analysis information (103) includes data information (200) for generating the at least one generated analysis output (201), wherein the data information (200) includes guidance on data (202) for generating the at least one analysis output (201) or the data (202) itself for generating the at least one analysis output (201). The analysis information (103) is provided based on mapping information (300) including one or more entries (301), each entry (301) being associated with the generated analysis output (201), wherein each entry (301) includes the identification information (203) associated with the corresponding generated analysis output (201), and includes the data information (200) for generating the corresponding generated analysis output (201).

13. A non-transitory storage medium, characterized in that, Includes program code that, when executed on a computer, performs the method according to claim 11 or 12.

Images