WO2016192746A1

WO2016192746A1 - Method and apparatus for implementing self-operation functions within a network

Info

Publication number: WO2016192746A1
Application number: PCT/EP2015/061927
Authority: WO
Inventors: Haitao Tang
Original assignee: Nokia Solutions And Networks Oy
Priority date: 2015-05-29
Filing date: 2015-05-29
Publication date: 2016-12-08
Also published as: EP3304965A1

Abstract

A method and apparatus may include receiving a request for a recommended action from a network node. The request comprises an event information and a context information. The method may also include performing a similarity analysis to determine if the apparatus has stored a self-operation case that relates to the request. The method may also include determining a recommended action based on the similarity analysis. The method may also include transmitting the recommended action to the network node.

Description

DESCRIPTION TITLE

METHOD AND APPARATUS FOR IMPLEMENTING SELF-OPERATION

FUNCTIONS WITHIN A NETWORK

BACKGROUND: Field:

[§§§1] Embodiments of the present invention relate to implementing self-operation functions within a network.

Description of the Related Art:

[§§02] Long-term Evolution (LTE) is a standard for wireless communication that seeks to provide improved speed and capacity for wireless communications by using new modulation/signal processing techniques. The standard was proposed by the 3^rd Generation Partnership Project (3GPP), and is based upon previous network technologies. Since its inception, LTE has seen extensive deployment in a wide variety of contexts involving the communication of data. SUMMARY:

[§§§3] According to a first embodiment, a method may include receiving, by a first network node, a request for a recommended action from a second network node. The request comprises an event information and a context information. The method may also include performing a similarity analysis to determine if the first network node has stored a self- operation case that relates to the request. The method may also include determining a recommended action based on the similarity analysis. The method may also include transmitting the recommended action to the second network node.

[0004] In the method of the first embodiment, the first network node is configured to perform a self- operation function. [0005] In the method of the first embodiment, if the first network node has stored a self- operation case that relates to the request, then the determined recommended action comprises an action corresponding to the stored self-operation case. If the first network node has not stored a self-operation case that relates to the request, then the determined recommended action is recommended by a human operator.

[0006] In the method of the first embodiment, the request comprises a format including at least one of information indicating a function, information indicating an instance, information indicating a sequence number, information indicating a context, and information indicating an event.

[0007] In the method of the first embodiment, the method may also include extracting relevant information concerning the recommended action, constructing a corresponding self- operation case based on the extracted relevant information, storing the constructed self- operation case based on an analysis of a relation of the extracted relevant information, processing the constructed self-operation case, updating the self-operation case, and later applying the self-operation case.

[0008] According to a second embodiment, an apparatus may include at least one processor. The apparatus may also include at least one memory including computer program code. The at least one memory and the computer program code may be configured, with the at least one processor, to cause the apparatus at least to receive a request for a recommended action from a network node. The request comprises an event information and a context information. The apparatus may also be caused to perform a similarity analysis to determine if the apparatus has stored a self-operation case that relates to the request. The apparatus may also be caused to determine a recommended action based on the similarity analysis. The apparatus may also be caused to transmit the recommended action to the network node.

[0009] In the apparatus of the second embodiment, the apparatus may be configured to perform a self-operation function.

[0010] In the apparatus of the second embodiment, if the apparatus has stored a self- operation case that relates to the request, then the determined recommended action comprises an action corresponding to the stored self-operation case. If the apparatus has not stored a self-operation case that relates to the request, then the determined recommended action is recommended by a human operator. [0011] In the apparatus of the second embodiment, the request comprises a format including at least one of information indicating a function, information indicating an instance, information indicating a sequence number, information indicating a context, and information indicating an event. [0012] In the apparatus of the second embodiment, the apparatus is further caused to extract relevant information concerning the recommended action, construct a corresponding self- operation case based on the extracted relevant information, store the constructed self- operation case based on an analysis of a relation of the extracted relevant information, process the constructed self-operation case, update the self-operation case, and later apply the self- operation case.

[0013] According to a third embodiment, a computer program product may be embodied on a non-transitory computer readable medium. The computer program product may be configured to control a processor to perform a method according to the first embodiment.

[0014] According to a fourth embodiment, a method may include receiving, by a network node, a consultation request for an expected result of a given operation. The consultation request may be received from a human operator. The method may also include performing a similarity analysis to determine if the network node has stored a self-operation case that relates to an element of the consultation request. The method may also include transmitting a result of the similarity analysis to the human operator. [0015] In the method of the fourth embodiment, the network node is configured to perform a self-operation function.

[0016] In the method of the fourth embodiment, the consultation request comprises a format corresponding to ConsultationRequest(x).

[0017] According to a fifth embodiment, an apparatus may include at least one processor. The apparatus may also include at least one memory including computer program code. The at least one memory and the computer program code may be configured, with the at least one processor, to cause the apparatus at least to receive a consultation request for an expected result of a given operation. The consultation request is received from a human operator. The apparatus may also be caused to perform a similarity analysis to determine if the apparatus has stored a self-operation case that relates to an element of the consultation request. The apparatus may also be caused to transmit a result of the similarity analysis to the human operator.

[0018] In the apparatus of the fifth embodiment, the apparatus is configured to perform a self-operation function. [0019] In the apparatus of the fifth embodiment, the consultation request comprises a format corresponding to ConsuitationRequest(x).

[0020] According to a sixth embodiment, a computer program product may be embodied on a non-transitory computer readable medium. The computer program product may be configured to control a processor to perform a method according to the fourth embodiment. [0021 ] According to a seventh embodiment, a method may include receiving, by a first network node, an operation from a human operator. The method may also include forwarding the operation to a second network node. The method may also include receiving a notification indicating a result of the operation. The method may also include transmitting the notification to the human operator. [0022] In the method of the seventh embodiment, the first network node is configured to perform a self- operation function.

[0023] In the method of the seventh embodiment, the operation comprises a format including at least one of information indicating a function, information indicating an instance, information indicating a sequence number, and information indicating an action. [0024] In the method of the seventh embodiment, the method further comprises extracting relevant information concerning the recommended action, constructing a corresponding self- operation case based on the extracted relevant information, storing the constructed self- operation case based on an analysis of a relation of the extracted relevant information, processing the constructed self-operation case, updating the self-operation case, and later applying the self-operation case.

[0025] According to an eighth embodiment, an apparatus may include at least one processor. The apparatus may also include at least one memory including computer program code. The at least one memory and the computer program code may be configured, with the at least one processor, to cause the apparatus at least to receive an operation from a human operator. The apparatus may also be caused to forward the operation to a network node. The apparatus may also be caused to receive a notification indicating a result of the operation. The apparatus may also be caused to transmit the notification to the human operator.

[0026] In the apparatus of the eighth embodiment, the apparatus may be configured to perform a self- operation function. [0027] In the apparatus of the eighth embodiment, the operation comprises a format including at least one of information indicating a function, information indicating an instance, information indicating a sequence number, and information indicating an action.

[0028] In the apparatus of the eighth embodiment, the apparatus is further caused to extract relevant information concerning the recommended action, construct a corresponding self- operation case based on the extracted relevant information, store the constructed self- operation case based on an analysis of a relation of the extracted relevant information, process the constructed self-operation case, update the self-operation case, and later apply the self- operation case.

[0029] According to a ninth embodiment, a computer program product may be embodied on a non-transitory computer readable medium. The computer program product may be configured to control a processor to perform a method according to the sixth embodiment.

BRIEF DESCRIPTION OF THE DRAWINGS:

[0030] For proper understanding of the invention, reference should be made to the accompanying drawings, wherein:

[0031] Fig. 1 illustrates an architecture of self-operation based on stored self-operation cases and human knowledge.

[0032] Fig. 2 illustrates example information elements of a self-operation case.

[0033] Fig. 3 illustrates a flowchart of a method in accordance with certain embodiments of the invention.

[0034] Fig. 4 illustrates a flowchart of a method in accordance with certain embodiments of the invention.

[0035] Fig. 5 illustrates a flowchart of a method in accordance with certain embodiments of the invention. [0036] Fig. 6 illustrates an apparatus in accordance with certain embodiments of the invention.

[0037] Fig. 7 illustrates an apparatus in accordance with certain embodiments of the invention. [0038] Fig. 8 illustrates an apparatus in accordance with certain embodiments of the invention.

[0039] Fig. 9 illustrates an apparatus in accordance with certain embodiments of the invention.

DETAILED DESCRIPTION:

[0040] Certain embodiments of the present invention relate to implementing self-operation functions within a network. Specifically, certain embodiments of the present invention may relate to implementing self-operation functions within a network, where the self-operation functions are configured with potentially incomplete and/or inconsistent settings. [0041] Self-x functions (such as self-optimizing functions, self-organizing functions, self- healing functions, self-configuring functions, and/or some Traffic Steering functions, for example) may be utilized with 3G and 4G networks. Self-x functions may be used in conjunction with operations support systems (OSS) of these networks. Currently, self-x functions are generally assumed to operate in accordance with rules that have been pre- defined/pre- set prior to performing network operations, while certain other rules may be provided when actually performing the network operations.

[0042] Self-x functions have generally reduced the amount of manual operations that are required to be performed within 3G and 4G networks. 5G systems (including networks and OSS systems) are expected to utilize an even wider scope of self-x functions, as one of the objectives of implementing 5G systems is to minimize the need for human involvement while performing network operations.

[0043] However, certain technical problems may occur when implementing self-x functions that are based on rules. For example, the self-x functions and their corresponding networks/OSS systems may be configured with rules that are inconsistent with each other. [0044] Further, even if there are no inconsistencies between the rules, certain situations may not be properly addressed by the rules. For example, certain situations may not be properly addressed by the rules because they are unexpected situations. As such, the possibility exists where existing rules do not properly address certain situations, regardless of whether the rules are predefined/pre- set before the actual network operations or whether the rules are provided during the actual network operations. Further, certain technical problems may exist if the existing rules are an incomplete set of rules.

[0045] The above-described problems may be reduced by providing directions/reasoning of how to proceed for a plurality of situations, and the directions/reasoning may be provided based on a pre-defined ontology. However, systems that utilize such directions/reasoning may still encounter technical problems that are similar to the above-described technical problems (as when rules are utilized). For example, if the ontology has not been configured to address a certain situation in advance (regardless of whether the ontology is human-defined or is provided during the network operations), the situation may possibly not be properly addressed.

[0046] Further, even if the rules / ontology of certain operations can be learned (by machine- learning functions, for example), there is no guarantee that the rules / ontology will be correctly learned. In view of this lack of sufficient reliability and trustworthiness, an operator may not want to allow machine-learning functions to work autonomously on critical operations/tasks.

[0047] Therefore, in view of the above technical problems, certain embodiments of the present invention provide a practical and realizable solution that enables a human operator to interactively work with the above networks and OSS systems during the network operations. The interworking between the human operator and the networks may enable and guarantee the reliability and trustworthiness of a machine learning, and the interworking may enable/guarantee the reliability of a mutual learning between the human operator and the operation resources, as described in greater detail below.

[0048] Certain embodiments of the present invention are directed to implementing a self- operation function, where an OSS/network system is using potentially incomplete and/or an inconsistent set of rules/ontology. Certain embodiments may solve the problems relating to missing rules/ontology and the problems relating to inconsistencies between rules/ontology. Certain embodiments of the present invention may resolve the above-described problems during the actual network operations of the system by learning self-operation cases. Certain embodiments may apply the learned self-operation cases to actual network operations as well as to human operator consultation. [0049] Certain embodiments of the present invention can allow a human operator's role to be gradually minimized so that the human operator merely sets operation targets. At the same time, certain embodiments may guarantee the reliability and the trustworthiness of the network operations.

[0050] Certain embodiments may define self-operation cases, define how self-operation cases are analyzed, and/or define how consultation services are provided based on stored self- operation cases. As described in more detail below, certain embodiments may be directed to a self-operation architecture that includes a human user interface (UI), a self-operation function, and/or an OSS/network function. With certain embodiments, a computer may present information to a human operator via the human UI. The UI may present information to the human operator via a display device, for example. The UI may permit the human operator to provide an input to the network. For example, the UI may permit the human operator to provide a Response ActionRccommendation. as described in more detail below. Fig. 1 illustrates an architecture of self- operation based on stored self-operation cases and human knowledge. The OSS/network function may include, for example, SON coordination functions, verification functions, analytics functions, self-x functions and instances, and/or other network / OSS resources, as illustrated by Fig. 1. With the architecture of certain embodiments of the present invention, two self-operation procedures may be defined, which may be referred to as "Procedure 1" and "Procedure 2" below, for example.

[0051] Procedure 1 may enable interactive self-operation by applying knowledge of self- operation cases or of human instructions, as described in more detail below. Procedure 2 may learn and build a self-operation knowledge by automatically constructing and storing self- operation cases from information derived from the corresponding system operations and human instructions.

[0052] With certain embodiments of the present invention, a self-operation function may learn and automatically store self- operation cases from the self-operation function's interactions with the OSS/network function and from the self- operation function's interactions with the human operator. The self-operation function may then provide a recommendation to an OSS/network function (and/or to a human operator) regarding what action to take / what consequence to expect, for example. The provided recommendations may be based on the stored self-operation cases and/or the information from the human operator. The self- operation function can also import self- operation cases from outside sources.

[0053] With certain embodiments, a self-operation case may be a tuple that includes at least one of: (1) information indicating a context, (2) information indicating an event, (3) information indicating an action, (4) information indicating a result, (5) information indicating a profile, and/or (6) information indicating a group. For example, a self-operation case may be described by a corresponding tuple, including information such as: (context, event, action, result, profile, groupID). Fig. 2 illustrates the elements of a tuple in accordance with certain embodiments of the present invention.

[0054] The self-operation case can be built gradually, which means that some of the self- operation's information elements (as reflected within the self-operation's corresponding tuple) may be initially unknown. Some of the self-operation's information elements may then be completed/filled during later relevant network operations. If all the information is available, a self-operation case can be completely built.

[0055] With respect to analyzing self-operation cases, the elements of a tuple (with the exception of "groupID") of a self-operation case, may be learned from messages exchanged between the self-operation function, other OSS/network functions, as well as a human operator. These elements may contain information (which may be "raw" information) that is extracted from the messages, and the information may provide the details of the corresponding operation. The "profile" element may be obtained from analysis of learned elements by the self-operation function. [0056] As network operations are performed, more and more self-operation cases may be generated. Many of the self-operation cases may be similar to or may be the same as other self-operation cases. Certain embodiments may group self-operation cases according to their similarity, as discussed in more detail below. In addition, such a grouping can be associated with reliability information. As such, a stored/existing self-operation case can be used to guide a new operation. For example, certain embodiments may store a percentage of self- operation cases in a group that have achieved a successful result. The groupID element may be used to associate a grouping of self-operation cases with the reliability information.

[0057] Certain embodiments may perform a similarity analysis of the self- operation cases based on pre-defined ontology or based on rules for the self-operation cases. Self-operation cases that are determined to be similar and/or the same may be assigned to a corresponding same unique groupID.

[0058] With certain embodiments, Procedure I may be directed to an interactive operation that utilizes stored self-operation cases and/or human knowledge. Procedure 1 may be invoked to perform interactive operations in accordance with the following defined events (referred to as events "a" to "γ" below).

[0059] Event a may correspond to an event where an OSS/network function has no knowledge for properly determining what to do for a given event. With this event, Procedure 1 may be invoked to perform the following:

• a) The OSS/network function (for example, a coordination function) may send a request (with an "event" and a relevant "context") to the self-operation function. The request may include, for example, at least one of: (1) information indicating a function, (2) information indicating an instance, (3) information indicating a sequence number, (4) information indicating a context, and/or (5) information indicating an event. The request may be a request for a recommendation, and the request may be in the form of, for example: RequestActionRecommendation (functionlD, in stance 11 ), sn_f, context_f, event_f). The functionll ) and instancelD may together identify the requesting OSS/network function. The "sn_f" may be a sequence number of the request that is provided by this identified function. In general, a sequence number may be a unique number assigned to an initial request. A later reply and/or related information element may be linked to the initial request and its created/used information elements. The "context_f" and "event_f" may be the context and the event that are indicated in the request by the OSS/network function. The context and the event may correspond to context information and event information that are indicated by the initital request. For example, an initial request may be: "Can MRO configure the HO threshold between Cell A and Cell C?" With this example, the related context may be the status and configuration information of the cells, and/or the active functions or still-impacting functions on these two cells. With this example, the event may correspond to the intention to configure the threshold.

• b) After the self-operation function receives the request, the self-operation function performs a similarity analysis to determine if the self-operation function already has knowledge in its stored self-operation case(s) that relate to the request. For example, based on a corresponding similarity measure (like a group of structured and value-assigned keywords), the self-operation function may perform a search of its stored self-operation cases. Self-operation cases that match the given similarity measure may then be considered to be the knowledge that relates to the request. With certain embodiments, the similarity measure may relate to matching context and/or matching event information, for example. Accordingly, the self-operation function may then perform one of the following: o If the self-operation function already has knowledge in its stored self- operation cases of (context, event, action, result, profile, groupID) that relate to the request, the self-operation function performs the following:

^■ The self-operation function may recommend a corresponding action to the requesting OSS/network function in the form of, for example, ResponseActionRecommendation(sn_f, action)

^■ The self-operation function may partially create a current self- operation case (context_so, event_f, action, result=NULL, profile=NULL, groupID), with the information elements received from the request and a stored self-operation case. The "context_so" in this response may have been extended/elaborated upon by the self-operation function based on the "context_f" that is received in the request from the OSS/network function. The context information may be extended by adding more information elements to the original given context_f. For example, the extra information element may correspond to an intended configuration event that has similar events who have similar percentages of both failure and success results in the history. Otherwise, context_so may correspond to context_f. The self- operation function may decide if an extension of context information is needed. ^■ The self-operation function may invoke Procedure 2 (B.) (as described below) to construct a current self-operation case under the existing groupID.

^■ The self-operation may then end Procedure 1.

o If the coordination function has no knowledge in any of its stored self- operation cases that is related to the request, Procedure 1 continues to Step c.

• c) The self-operation function further sends a request (with the "event" and its relevant "context") to the human operator. As described above, the human operator may review the request via a human UI. The request may be a request for a recommendation of a course of action in the form of, for example, RequestActionRecommendation (functionID, instancelD, sn_so, context_so, event_f). The functionID and instancelD may together identify the self-operation function. The "sn_so" may be the sequence number of the request, as raised/provided by this self- operation function. The "context_s,," and "event_f" may be defined in accordance with the corresponding definitions of a self-operation case, as described above. The context_so in this request may have been extended by the self-operation function, based on the context_f received in the request from the OSS/network function. Otherwise, context_so may correspond to context_f. The self-operation function may decide if such an extension may be needed.

• d) The human operator may decide on the corresponding action for the request, and the human operator may respond to the self-operation function in the form of, for example, ResponseActionRecommendation(sn_so, action). For example, as described above, the human operator may provide an input, into the human UI, that corresponds to ResponseActionRecommendation.

• e) The self-operation function may receive the operator response and may perform the following:

o The self-operation function may recommend the corresponding action to the requesting OSS/network function in the form of, for example, ResponseActionRecommendation(sn_f, action) o The self-operation function may invoke Procedure 2 (A.) (as defined below) to learn from the human decision regarding how to respond to such an incident and to accordingly construct a new self-operation case.

• f) The OSS/network function may perform the recommended action (if any recommended action was recommended) according to the response.

• g) Procedure 1 may then end.

[0060] Event β may correspond to an event where the human operator consults the self-peration function regarding an expected result of an intended operation. With event β,rocedure 1 may be invoked to perform the following: · a) The human operator may send a consultation request to the self-operation function. The consultation request may be sent with certain given elements) "x" of an assumed self-operation case, in the form of, for example, ConsultationRequest(x). For example, the "x" can correspond to "an HO optimization operation for Cell i to Cell j" and/or "an intended operation to perform load balancing between radio access 1 and radio access 2."

• b) The self-operation function may perform a similarity analysis between the given "x" and the stored self-operation cases. This similarity analysis may be able to find one or more other matching elements) *(y) for the assumed self-operation case. Here, x and y may provide all of the elements for the assumed self-operation case. In one example, "y" may be determined from a self-operation case that has "x" elements) and "y" elements) in it. If there are a plurality of such self-operation cases, multiple "y"s may be found. Such a self-operation case may correspond to the elements of x and y, where different matching self-operation cases may have different (actual) y elements / value of the elements. · c) The self-operation function may respond to the human operator with the found elements *(y), in the form of, for example, ConsultationResponse(*(y)).

• d) The human operator may derive the expected result from x and *(y).

• e) Procedure 1 may then be Ended. [0061] Event γ may correspond to an event where the human operator sends a manual operation command to an OSS/network function (where the operation command may be sent via a self-operation function or may be monitored by the self-operation function ). The manual operation command may include at least one of: (1) information indicating a function, (2) information indicating an instance. (3) information indicating a sequence number, and/or (4) information indicating an action. For example, the manual operation command may be in the form of, for example, Operation (<functionID>, <instanceID>, ns_hm, action ). As an illustrative example, a human operator may send the manual command "Disable functionll ) and instance!D" to/via the OSS system. The instance identified by the IDs can thus be disabled. A self-operation case can be created for this manual operation, where the related network context and result of this trigger and its corresponding action can be added. With Event γ, Procedure 1 may be invoked to perform the following:

• a) The self-operation function may receive Operation(<functionID>, <in stance I D>, ns_hm, action). ns_hm may be a unique sequence number that is assigned to identify the operation taken by the human operator. Any further messages of the operation will be identified with its sequence number so that the coming result of this operation can be linked to the operation.

• b) When an OSS/network function sends the corresponding notification towards the human operator, the notification may be sent via the self-operation function. The self-operation function may receive this corresponding notification,

Notification(nshm, result)

• c) Procedure 1 may also invoke Procedure 2 (D.) to construct the corresponding self-operation case of this human manual operation.

• d) Procedure 1 may then be ended. [0062] With certain embodiments, Procedure 2 may be directed to a self-construction of a self-operation case. Procedure 2 may be invoked to construct a self-operation case by one of the specifically defined events (A.-B.) accordingly:

• A. In the event that the self-operation function receives

"RequestActionRecommendation ( functionll ). instancell ), s¾ contexts event_f)" and there is no matching self-operation case that relates to the request, Procedure 2 may be invoked to do the following: ο 1) Procedure 2 may be invoked to extract the event element from the request of the OSS/network function, RequestActionRecommendation (functionID, instancelD, sn_f, context_f, event_f)

o 2) Procedure 2 may extract the context element from the request of the self- operation function, RequestActionRecommendation (functionID, instancelD, sn_so, context_so, event_f)

o 3) Procedure 2 may extract the action element from the human operator response, ResponseActionRecommendation(sn_so, action)

o 4) When receiving the result from the notification, Notification(functionID, instancelD, sn_f result), Procedure 2 may extract the result element from this notification, where the functionID, instancelD, and sn_f together identify the corresponding function, event_f, context_so, and action of the result.

o S) Procedure 2 may analyze the relation between the elements of contextso, event_f, action, and result. In an illustrative example case, Procedure 2 may analyze the relation between the elements and summarize the relation as: "if the context appears, the event will be triggered, and the corresponding action will be taken and the certain result will be achieved." Later, when there are more stored similar cases, the analysis can even provide different possible relations that may be found from all of the similar self-operation cases, and the possibilities of the relations, between the elements. In addition, a profile of a self-operation case can be updated after the creation of the case. o 6) Procedure 2 may also assign the result/consequence of the analysis to the profile element.

o 7) Procedure 2 may also generate a new groupID.

o 8) Procedure 2 may also create and store the corresponding self-operation case (context_so, event_f, action, result, profile, groupID) with the above information.

o 9) Procedure 2 may then be ended.

• B. When the self-operation function receives "RequestActionRecommendation (functionID, instancelD, sn_f, contexts, event_f)" and there is a matching self-operation case(s) for the request (for example, there is an existing groupID indicated by Procedure 1), Procedure 2 may be invoked to perform the following: ο 1) When receiving the result from the notification, Notification(functionID, instancelD, sf_f, result), Procedure 2 may extract the result element from this notification, where the functionID, instancelD, and sn_f may together identify the corresponding function, event_f, context_so, and action of the result.

o 2) Procedure 2 may fill the result element of the current self-operation case (context_so, event_f, action, result, profile=NULL, groupID), with the result extracted from the notification.

o 3) Procedure 2 may analyze the relation between the elements of the context_so, event_f, action, and result of the current self-operation case, and Procedure 2 may fill the analytic outcome as the profile of the current self-operation case.

o 4) Procedure 2 may create and store the corresponding self-operation case (context_so, event_f, action, result, profile, groupID) with the above information.

o 5) Procedure 2 may be ended.

• C. When the self-operation function receives "Notification(functionID, instancelD, sn_f, context_f, event_f, action, result)," Procedure 2 may be invoked to perform the following:

o 1) Procedure 2 may extract the information of context_f, event_f, action, result from the notification.

o 2) Optionally, the self-operation function may extend context_f into context_so, based on the other context received. Otherwise, context_so may correspond to context_f. The self-operation function may decide if such an extension would be needed.

o 3) Procedure 2 may initiate the corresponding self-operation case as (contextso, eventf, action, result, profile=NULL, groupID=NULL).

o 4) Procedure 2 may analyze the relation between the elements of context_so, event_f, action, and result.

o 5) Procedure 2 may assign the consequence of the analysis to the profile element.

o 6) Procedure 2 may perform a similarity analysis to determine if the initiated self-operation case is similar to or the same as any stored self-operation case(s). If the similarity analysis indicates that the initiated self-operation case is similar to or the same as a stored self-operation case(s), Procedure 2 may assign the groupID with the corresponding ID of the store self-operation case(s). Otherwise, Procedure 2 may generate a new groupID.

o 7) Procedure 2 may create and store the corresponding self-operation case (context_so event_f, action, result, profile, groupID) with the above information.

o 8) Procedure 2 may be ended.

• D. When the self-operation function receives "Operation(<functionID>, <instanceID>, sn_m, action)," Procedure 2 may be invoked to do the following:

o 1) Procedure 2 may extract the information of an action from the operation. o 2) When receiving the result from the notification, Notification(sn_hm, result), Procedure 2 may extract the result element from this notification.

o 3) Procedure 2 may extract context_so from the information collected via the Notification (for example, any demanded context may be extracted).

o 4) Procedure 2 may assign "command" to event_f.

o S) Procedure 2 may initiate the corresponding self-operation case as (context_so, "command", action, result, profile=NULL, groupID=NULL).

o 6) Procedure 2 may analyze the relation between the elements of context_so, "command", action, and result.

o 7) Procedure 2 rnay assign the consequence/result of the analysis to the profile element.

o 8) Procedure 2 may perform a similarity analysis to check if the initiated self- operation case is similar to or the same as stored self-operation case(s). If the initiated self-operation case is similar to or the same as a stored self-operation case, Procedure 2 may assign the groupID with the corresponding ID of the stored self-operation case(s). Otherwise, Procedure 2 may generate a new groupID.

o 9) Procedure 2 may create and store the corresponding self-operation case (context_so, "command", action, result, profile, groupID) with the above information. o 1[0) Procedure 2 may be ended. [0063] Certain embodiments may be directed to providing consultation services based on the stored self-operation cases. The self-operation function (with its stored self-operation cases) may serve the network operations in two ways.

[0064] With a first way, the self-operation function may answer a human operator's questions regarding an expected result in view of an unknown element of an assumed/intended self-operation case (context, event, action, result, profile, groupID). The answer to the operator's questions may be determined through a similarity analysis based on the known/assumed elements. For example, the operator can ask the self-operation function, "What result would be achievable given a specific context and action?" The self-operation function may answer the human operator with ail the results that match the given context and action, such as * (event, result, profile, groupID).

[0065] The profile and groupID elements may possibly not participate in the similarity analysis for expected situations. However, if a match is found, certain embodiments may indicate the profile and groupID information concerning the expected situation from that matching. An example of such an answer can be "(any, KPIx improvement, likelihood 93%, 1031)".

[0066] Certain embodiments may also answer a request from an OSS/network function with steps (a) - (g) of the Procedure l(a.).

[0067] Certain embodiments may import/retrieve self-operation cases from external sources. [0068] The operations of a network can also generate other operation-related data. Other self-operation cases may be extracted from those operation-related data by an outside function. If these self-operation cases are extracted according to the definition of a self- operation case, in accordance with certain embodiments, these self- operation cases can be imported from external sources. With the imported self- operation cases, the self-operation function should have more knowledge to make its autonomous decisions, which helps to minimize the human operator's role such that the operator merely setting operation targets.

[0069] Certain embodiments of the present invention may be a part of the sell -operation of

5G networks. Certain embodiments for 5G networks may be shown in Fig. 1. Certain embodiments may work with potentially incomplete and inconsistent rules/ontology, for example. The problems of missing rules/ontology and rule/ontology inconsistency may be resolved by certain embodiments during the actual operations, through learning self- operation cases and applying the cases to the actual operations and to human operator consultation.

[0070] With certain embodiments, a self-operation function may correspond to an individual product implemented over an interface-N (itf-N). Corresponding messages and information elements that cross the itf-N may be supported by standardization or OSSii. In order to be supported by standardization, some "standardization" work may be expected to be directed to itf-N or OSSii. The self-operation function may be configured to be multi-vendor capable.

[0071] Fig. 3 illustrates a flowchart of a method in accordance with certain embodiments of the invention. The method illustrated in Fig. 3 includes, at 310, receiving, by a first network node, a request for a recommended action from a second network node. The request comprises an event information and a context information. The method may also include, at 320, performing a similarity analysis to determine if the first network node has stored a self- operation case that relates to the request. The method may also include, at 330, determining a recommended action based on the similarity analysis. The method may also include, at 340, transmitting the recommended action to the second network node.

[0072] Fig. 4 illustrates a flowchart of a method in accordance with certain embodiments of the invention. The method illustrated in Fig. 4 includes, at 410, receiving, by a network node, a consultation request for an expected result of a given operation. The consultation request is received from a human operator. The method may also include, at 420, performing a similarity analysis to determine if the network node has stored a self-operation case that relates to an element of the consultation request. The method may also include, at 430, transmitting a result of the similarity analysis to the human operator.

[0073] Fig. 5 illustrates a flowchart of a method in accordance with certain embodiments of the invention. The method illustrated in Fig. 5 includes, at 510, receiving, by a first network node, an operation from a human operator. The method may also include, at 520, forwarding the operation to a second network node. The method may also include, at 530, receiving a notification indicating a result of the operation. The method may also include, at 540, transmitting the notification to the human operator.

[0074] Fig. 6 illustrates an apparatus in accordance with certain embodiments of the invention. In one embodiment, the apparatus can be a network node configured to perform a self-operation function and/or an OSS/network function, for example. The apparatus can be a network node. Apparatus 10 can include a processor 22 for processing information and executing instructions or operations. Processor 22 can be any type of general or specific purpose processor. While a single processor 22 is shown in Fig. 6, multiple processors can be utilized according to other embodiments. Processor 22 can also include one or more of general-purpose computers, special purpose computers, microprocessors, digital signal processors (DSPs), field-programmable gate arrays (FPGAs), application- specific integrated circuits (ASICs), and processors based on a multi-core processor architecture, as examples.

[0075] Apparatus 10 can further include a memory 14, coupled to processor 22, for storing information and instructions that can be executed by processor 22. Memory 14 can be one or more memories and of any type suitable to the local application environment, and can be implemented using any suitable volatile or nonvolatile data storage technology such as a semiconductor-based memory device, a magnetic memory device and system, an optical memory device and system, fixed memory, and removable memory. For example, memory 14 include any combination of random access memory (RAM), read only memory (ROM), static storage such as a magnetic or optical disk, or any other type of non-transitory machine or computer readable media. The instructions stored in memory 14 can include program instructions or computer program code that, when executed by processor 22, enable the apparatus 10 to perform tasks as described herein.

[0076] Apparatus 10 can also include one or more antennas (not shown) for transmitting and receiving signals and/or data to and from apparatus 10. Apparatus 10 can further include a transceiver 28 that modulates information on to a carrier waveform for transmission by the antenna(s) and demodulates information received via the antenna(s) for further processing by other elements of apparatus 10. In other embodiments, transceiver 28 can be capable of transmitting and receiving signals or data directly.

[0077] Processor 22 can perform functions associated with the operation of apparatus 10 including, without limitation, precoding of antenna gain/phase parameters, encoding and decoding of individual bits forming a communication message, formatting of information, and overall control of the apparatus 10, including processes related to management of communication resources.

[0078] In an embodiment, memory 14 can store software modules that provide functionality when executed by processor 22. The modules can include an operating system 15 that provides operating system functionality for apparatus 10. The memory can also store one or more functional modules 18, such as an application or program, to provide additional functionality for apparatus 10. The components of apparatus 10 can be implemented in hardware, or as any suitable combination of hardware and software.

[0079] Fig. 7 illustrates an apparatus in accordance with certain embodiments of the invention. Apparatus 700 can be a network element/entity such as a network node that is configured to perform a self- operation function, for example. Apparatus 700 can include a receiving unit 710 that receives a request for a recommended action from a network node. The request comprises an event information and a context information. Apparatus 700 may also include a performing unit 720 that performs a similarity analysis to determine if the first network node has stored a self-operation case that relates to the request. Apparatus 700 may also include a determining unit 730 that determines a recommended action based on the similarity analysis. Apparatus 700 may also include a transmitting unit 740 that transmits the recommended action to the second network node.

[0080] Fig. 8 illustrates an apparatus in accordance with certain embodiments of the invention. Apparatus 800 can be a network element/entity such as a network node that is configured to perform a self- operation function, for example. Apparatus 800 can include a receiving unit 810 that receives a consultation request for an expected result of a given operation. The consultation request is received from a human operator. Apparatus 800 may also include a performing unit 820 that performs a simi larity analysis to determine if the network node has stored a self-operation case that relates to an element of the consultation request. Apparatus 800 may also include a transmitting unit 830 that transmits a result of the similarity analysis to the human operator.

[0081] Fig. 9 illustrates an apparatus in accordance with certain embodiments of the invention. Apparatus 900 can be a network element/entity such as a network node that is configured to perform a self- operation function, for example. Apparatus 900 can include a first receiving unit 910 that receives, by a first network node, an operation from a human operator. Apparatus 900 may also include a forwarding unit 920 that forwards the operation to a second network node. Apparatus 900 may also include a second receiving unit 930 that receives a notification indicating a result of the operation. Apparatus 900 may also include a transmitting unit 940 that transmits the notification to the human operator.

[0082] The described features, advantages, and characteristics of the invention can be combined in any suitable manner in one or more embodiments. One skilled in the relevant art will recognize that the invention can be practiced without one or more of the specific features or advantages of a particular embodiment. In other instances, additional features and advantages can be recognized i n certain embodiments that may not be present in al l embodiments of the invention. One having ordinary skill i n the art will readily understand that the invention as discussed above may be practiced with steps in a different order, and/or with hardware elements in configurations which are different than those which are disclosed. Therefore, although the invention has been described based upon these preferred embodiments, it would be apparent to those of skill in the art that certain modifications, variations, and alternative constructions would be apparent, wh ile remaining with in the spirit and scope of the invention.

Claims

WE CLAIM:

1. A method, comprising: receiving, by a first network node, a request for a recommended action from a second network node, wherein the request comprises an event information and a context information; performi ng a similarity analysis to determine if the first network node has stored a self-operation case that relates to the request; determining a recommended action based on the similarity analysis; and transmitting the recommended action to the second network node.

2. The method according to claim 1, wherein the first network node is configured to perform a self- operation function.

3. The method according to claim 1 or 2, wherein, if the first network node has stored a self-operation case that relates to the request, then the determined recommended action comprises an action corresponding to the stored self-operation case; and if the first network node has not stored a self-operation case that relates to the request, then the determined recommended action is recommended by a human operator.

4. The method according to any of claims 1-3, wherein the request comprises a format including at least one of information indicating a function, information indicating an instance, information indicating a sequence number, information indicating a context, and information indicating an event.

5. The method according to any of claims I -4, wherein the method further comprises extracting relevant information concerning the recommended action, constructing a corresponding self-operation case based on the extracted relevant information, storing the constructed self-operation case based on an analysis of a relation of the extracted relevant information, processing the constructed self-operation case, updating the self-operation case, and later applying the self-operation case.

6. 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 configured, with the at least one processor, to cause the apparatus at least to receive a request for a recommended action from a network node, wherein the request comprises an event information and a context information; perform a similarity analysis to determine if the apparatus has stored a self-operation case that relates to the request; determine a recommended action based on the similarity analysis; and transmit the recommended action to the network node.

7. The apparatus according to claim 6, wherein the apparatus is configured to perform a self- operation function.

8. The apparatus according to claim 6 or 7, wherein, if the apparatus has stored a self- operation case that relates to the request, then the determined recommended action comprises an action corresponding to the stored self-operation case; and if the apparatus has not stored a self-operation case that relates to the request, then the determined recommended action is recommended by a human operator.

9. The apparatus according to any of claims 6-8, wherein the request comprises a format including at least one of information indicating a function, information indicating an instance, information indicating a sequence number, information indicating a context, and information indicating an event.

10. The apparatus according to any of claim 6-9, wherein the apparatus is further caused to extract relevant information concerning the recommended action, construct a corresponding self-operation case based on the extracted relevant information, store the constructed self-operation case based on an analysis of a relation of the extracted relevant information, process the constructed self-operation case, update the self-operation case, and later apply the self-operation case.

11. A computer program product, embodied on a non- transitory computer readable medium, the computer program product configured to control a processor to perform a method according to any of claims 1-5.

12. A method, comprising: receiving, by a network node, a consultation request for an expected result of a given operation, wherein the consultation request is received from a human operator; performing a similarity analysis to determine if the network node has stored a self- operation case that relates to an element of the consultation request; and transmitting a result of the similarity analysis to the human operator.

13. The method according to claim 12, wherein the network node is configured to perform a self- operation function.

14. The method according to claim 12 or 13, wherein the consultation request comprises a format corresponding to ConsultationRequest(x).

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 configured, with the at least one processor, to cause the apparatus at least to receive a consultation request for an expected result of a given operation, wherein the consultation request is received from a human operator; perform a similarity analysis to determine if the apparatus has stored a self-operation case that relates to an element of the consultation request; and transmit a result of the similarity analysis to the human operator.

16. The apparatus according to claim 15, wherein the apparatus is configured to perform a self- operation function.

17. The apparatus according to claim 15 or 16, wherein the consultation request comprises a format corresponding to ConsuitationRequest(x).

18. A computer program product, embodied on a non- transitory computer readable medium, the computer program product configured to control a processor to perform a method according to any of claims 12- 14.

19. A method, comprising: receiving, by a first network node, an operation from a human operator; forwarding the operation to a second network node; receiving a notification indicating a result of the operation; and transmitting the notification to the human operator.

20. The method according to claim 19, wherein the first network node is configured to perform a self-operation function.

21. The method according to claim 19 or 20, wherein the operation comprises a format including at least one of information indicating a function, information indicating an instance, information indicating a sequence number, and information indicating an action.

22. The method according to any of claims 19-21, wherein the method further comprises extracting relevant information concerning the recommended action, constructing a corresponding self-operation case based on the extracted relevant information, storing the constructed self-operation case based on an analysis of a relation of the extracted relevant information, processing the constructed self-operation case, updating the self-operation case, and later applying the self-operation case.

23. 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 configured, with the at least one processor, to cause the apparatus at least to receive an operation from a human operator; forward the operation to a network node; receive a notification indicating a result of the operation; and transmit the notification to the human operator.

24. The apparatus according to claim 23, wherein the apparatus is configured to perform a self- operation function.

25. The apparatus according to claim 23 or 24, wherein the operation comprises a format including at least one of information indicating a function, information indicating an instance, information indicating a sequence number, and information indicating an action.

26. The apparatus according to any of claims 23-25, wherein the apparatus is further caused to extract relevant information concerning the recommended action, construct a corresponding self-operation case based on the extracted relevant information, store the constructed self-operation case based on an analysis of a relation of the extracted relevant information, process the constructed self-operation case, update the self-operation case, and later apply the self-operation case.

27. A computer program product, embodied on a non- transitory computer readable medium, the computer program product configured to control a processor to perform a method according to any of claims 19-22.