CN113849594A

CN113849594A - User intention implementation method, device and storage medium in intention driven network

Info

Publication number: CN113849594A
Application number: CN202010596851.2A
Authority: CN
Inventors: 孙雪媛; 李晨
Original assignee: China Telecom Corp Ltd
Current assignee: China Telecom Corp Ltd
Priority date: 2020-06-28
Filing date: 2020-06-28
Publication date: 2021-12-28

Abstract

The disclosure provides a method, a device and a storage medium for realizing user intention in an intention-driven network, and relates to the technical field of networks. The disclosed user intention realizing method in intention driven network includes: acquiring a user intention set; classifying the user intentions in the user intention set to acquire classified user intentions; converting the classified user intent into a network policy; verifying a network policy by executing the network policy in a network environment to obtain a verification result; and confirming or modifying the network policy according to the verification result until the user intention is reached. By the method, before the intents are converted into the network policies, the intents are classified, so that the data volume of retrieval and polling processing in the policy library can be reduced, the time complexity is reduced, and the processing efficiency is improved; the probability of error conversion is reduced, and the accuracy is improved.

Description

User intention implementation method, device and storage medium in intention driven network

Technical Field

The present disclosure relates to the field of network technologies, and in particular, to a method, an apparatus, and a storage medium for implementing a user intention in an intention driven network.

Background

With the explosion of the internet and applications, the network is moving to a direction with higher intelligence. How to convert the intention of input modes such as User text, voice, GUI (Graphical User Interface), third party and the like into abstract network language to be configured and executed in the system is a necessary development trend of future intelligent networks. The network based on intention recognition can be summarized into a closed-loop network architecture which is automatically built and operated based on human business intention under the condition of mastering the global state of the network.

Disclosure of Invention

One object of the present disclosure is to improve the efficiency and accuracy of the intended implementation.

According to an aspect of some embodiments of the present disclosure, there is provided a method for user intent implementation in an intent-driven network, comprising: acquiring a user intention set; classifying the user intentions in the user intention set to acquire classified user intentions; converting the classified user intent into a network policy; verifying a network policy by executing the network policy in a network environment to obtain a verification result; and confirming or modifying the network policy according to the verification result until the user intention is reached.

In some embodiments, classifying the user intent, the obtaining the classified user intent comprising: determining a business scene, a user type and an intention type of each user intention in the user intention set, wherein the intention type comprises an intention with a life cycle and an intention without a life cycle.

In some embodiments, determining the business scenario for each user intent in the set of user intents comprises: acquiring an identification of a user providing a user intention; determining the network environment in which the user is located according to the user identification, and using the network environment as a service scene of the user intention, wherein the network environment comprises an operator network, a DC (Data Center) network or an enterprise network.

In some embodiments, determining the user type of each user intent in the set of user intentions comprises: extracting key fields of user intentions through an attribute collector; the function judger judges whether the user intention has feedback according to the key field; if the user intention does not have the feedback property, determining that the user type is a common user; and if the user intention is feedback, determining the user type as the administrator.

In some embodiments, determining the intent type of each user intent in the set of user intentions comprises: extracting key fields of user intentions through an attribute collector; the function judger judges whether the user intention has a life cycle according to the key field; if the user intention has a life cycle, determining the intention type as the intention with the life cycle; if the user intent does not have a lifecycle, then the intent type is determined to be an intent without a lifecycle.

In some embodiments, converting the categorizing user intent into a network policy comprises: determining a corresponding strategy library according to the classified user intention; the classified user intent is translated into a network policy based on the determined policy repository.

In some embodiments, verifying the network policy by executing the network policy in the network environment, obtaining the verification result comprises: enforcing a network policy in a network environment; generating an executable verification result according to whether the network strategy is successfully executed; generating an effectiveness verification result according to whether the change of the network state meets the expectation of the user intention; the verification result comprises an executable verification result and a validity verification result.

In some embodiments, validating or modifying the network policy according to the verification result until the user intent is reached comprises: screening out network strategies which fail to pass the verification based on artificial intelligence or administrator instructions according to the verification result; and determining the classified user intention corresponding to the network policy which fails to pass the verification, and re-executing the operation of converting the classified user intention into the network policy until the verification passes.

In some embodiments, the method for user intent implementation in an intent-driven network further comprises: after the user intention set is obtained, verifying the user intention in the user intention set; feeding back the user intention which is not verified to the user so as to facilitate the user to modify; and performing an operation of classifying the user intention set on the verified user intention.

By the method, before the intents are converted into the network policies, the intents are classified, so that the data volume of retrieval and polling processing in the policy library can be reduced, the time complexity is reduced, and the processing efficiency is improved; the probability of error conversion is reduced, and the accuracy is improved.

According to an aspect of some embodiments of the present disclosure, there is provided an intent realization apparatus for a user in an intent-driven network, including: an intention acquisition unit configured to acquire a user intention set; the classification unit is configured to classify the user intention set and acquire a classification user intention; a conversion unit configured to convert the classified user intention into a network policy; a verification unit configured to verify a network policy by executing the network policy in a network environment, obtaining a verification result; and the decision unit is configured to confirm or modify the network policy according to the verification result until the user intention is reached.

In some embodiments, the method for user intent implementation in an intent-driven network further comprises: the intention management unit is configured to verify the user intention in the user intention set acquired by the intention acquisition unit; feeding back the user intention which is not verified to the user so as to facilitate the user to modify; the user's intention that passed the verification is sent to the classification unit.

According to an aspect of some embodiments of the present disclosure, there is provided an intent realization apparatus for a user in an intent-driven network, including: a memory; and a processor coupled to the memory, the processor configured to perform any of the above-mentioned user intent implementation methods in the intent driven network based on instructions stored in the memory.

The device can classify the intents before converting the intents into the network policies, thereby reducing the data volume of the retrieval and polling processing in the policy base, reducing the time complexity and improving the processing efficiency; the probability of error conversion is reduced, and the accuracy is improved.

According to an aspect of some embodiments of the present disclosure, a computer-readable storage medium is proposed, on which computer program instructions are stored, which instructions, when executed by a processor, implement the steps of any of the above-mentioned user intent implementation methods in an intent-driven network.

By executing the instructions on the storage medium, the intents can be classified before being converted into the network policy, so that the data volume of the processing of searching and polling in the policy library can be reduced, the time complexity can be reduced, and the processing efficiency can be improved; the probability of error conversion is reduced, and the accuracy is improved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this disclosure, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure and not to limit the disclosure. In the drawings:

fig. 1 is a flow diagram of some embodiments of a user intent implementation method in an intent driven network of the present disclosure.

Fig. 2 is a flow diagram of some embodiments of classifying and translating user intent sets in a user intent implementation method in an intent driven network of the present disclosure.

FIG. 3 is a flow diagram of further embodiments of a user intent implementation method in an intent driven network of the present disclosure.

Fig. 4A is a schematic diagram of some embodiments of a user intent realization device in an intent driven network of the present disclosure.

Fig. 4B is a schematic diagram of some embodiments of the operating logic of a user intent realization device in an intent driven network of the present disclosure.

Fig. 5 is a schematic diagram of some embodiments of a classification unit in a user intent realization device in an intent driven network of the present disclosure.

Fig. 6 is a schematic diagram of further embodiments of a user intent realization device in an intent driven network according to the present disclosure.

Fig. 7 is a schematic diagram of still other embodiments of a user intent realization device in an intent driven network according to the present disclosure.

Detailed Description

The technical solution of the present disclosure is further described in detail by the accompanying drawings and examples.

The intention driving network comprises several key steps, firstly, the network requirement, namely the intention proposed by the user can be obtained, the received intention is translated into a network strategy, the enforceability of the strategy can be verified according to the current state of the network, the verified strategy is issued to the actual network, in addition, the system also monitors the state of the network in real time, the intention of the user is ensured to be correctly realized, and the result is fed back to the user. The key technology comprises the characteristics of analysis and translation of intentions, strategy issuing and execution, network state information acquisition and feedback and the like, so that more flexible network control and strategies can be conveniently loaded on a basic network, and the key technology for correctly converting user intentions into correct network language issuing configuration in the intention network and the realization have important significance.

The inventor finds that after a user inputs an intention, the intention network extracts key information and converts the key information into an intention issuing strategy through massive data retrieval and polling of a strategy library, time complexity is high, system operation efficiency is low, due to the lack of an effective intention classification mechanism, an execution risk coefficient for correctly translating the intention into a network language issuing is high, and especially for a complicated user intention, user experience cannot be guaranteed.

A flow diagram of some embodiments of a method of user intent implementation in an intent driven network of the present disclosure is shown in fig. 1.

In step 101, a set of user intentions is obtained. In some embodiments, one or more user intentions provided by the user are obtained through the business layer, and the user intention set comprises all intentions provided by the user.

In some embodiments, after the intentions provided by the user are obtained, the intentions can be verified and classified by the intention orchestration layer, the eligible intentions are further processed by step 102, and the ineligible intentions are fed back to the user for further modification and adjustment.

In step 102, the user intentions in the user intention set are classified, and the classified user intentions are obtained. In some embodiments, user intent classification may be performed from three aspects of business scenario, user type, and business attributes.

The service scenario may be a current network environment, such as an operator network, a DC network, or an enterprise network; the user types can be divided into managers or operation operators (collectively referred to as managers) needing to obtain the network state feedback, and common users or developers needing not to obtain the network state feedback; business attributes can be divided into non-lifecycle intent, which is intended to be completed upon successful execution of a specified operation, and lifecycle intent, which is intended to be deactivated or deleted once an intent is successfully activated and deployed, by the system to keep all related intents active until they are deactivated or deleted.

In step 103, the classified user intent is translated into a network policy. In some embodiments, each category has a corresponding policy repository, and the corresponding policy repository may be determined according to the category user intent, and the category user intent may be converted into a network policy based on the determined policy repository. In some embodiments, different classes have corresponding converters, which may be determined according to user intent to convert the class user intent into a network policy, based on a different policy library.

In step 104, a network policy is verified by executing the network policy in the network environment, and a verification result is obtained. In some embodiments, the verification result is per user policy.

In step 105, it is determined whether the network policy corresponding to the verification result passes according to the verification result. For the verified network policy, executing step 106; for a policy that fails verification, then a modification is required. In some embodiments, step 103 may be performed to reconvert the corresponding intent into a network policy.

In step 106, a network policy is determined.

In some embodiments, the verification of network policies is divided into two categories, one being performability verification of the configuration. The configuration obtained in the translation process needs to verify whether it can be executed in an actual network environment according to the real-time network state. The second is validity verification. When the configuration is actually executed, the network status changes, and it needs to be verified whether the execution of the configuration causes the network status to change as expected. In some embodiments, the process of generating the verification result may include: enforcing a network policy in a network environment; generating an executable verification result according to whether the network strategy is successfully executed; and generating a validity verification result according to whether the network state change meets the expectation of the user intention, wherein the verification result comprises an executable verification result and a validity verification result.

By the method, the generated strategy can be verified from two aspects of performability and effectiveness, so that the network strategy is reasonably evaluated, a data base is provided for subsequent decision making, the execution is ensured, the execution result is ensured to be in accordance with the user intention, and the intention realization accuracy is improved.

In some embodiments, determining the business scenario for each user intent in the set of user intents comprises: acquiring an identification of a user providing a user intention; and determining the network environment where the user is located according to the identification of the user, and taking the network environment as a service scene of the user intention, wherein the network environment comprises an operator network, a DC network or an enterprise network.

A flow diagram of some embodiments of classifying a set of user intentions and translating the user intentions in a method of user intent implementation in an intent driven network of the present disclosure is shown in fig. 2.

In step 201, a user identification user-id is obtained.

In step 202, a service scenario is determined based on the user identity. The basic information of the user can be identified according to the user-id of the user, so that the network environment from which the user comes, such as an operator network, a DC network or an enterprise network, is determined as a service scene.

In step 203, a service scene identifier (intent-service identifier) corresponding to the service scene is added to the user intention message.

In step 204, it is determined whether the user's intent is for feedback. In some embodiments, the key field of the intention can be retrieved by the attribute collector to determine whether the intention is feedbackable.

The feedback property refers to whether network information and the like need to be fed back to the intention presenter after the intention is executed. For ordinary users, application developers and the like, network details and underlying configuration information do not need to be clear, how the intentions are executed is not concerned, and only the execution effects of whether the execution results of the intentions achieve the target, the completion quality, the execution time length and the like are concerned, so that the user intentions provided by the personnel do not have feedback. However, for management personnel, such as network administrators and operation operators, they perform intentions, such as allocating network resources, selecting transmission paths, handling network failures, and the like, and a plurality of feedback indexes are required for network resource conditions, congestion conditions, failure conditions, and the like after the intentions are performed, and therefore, the user intentions provided by these personnel have feedback.

If the user's intention is feedback, go to step 205; if not, go to step 206.

In step 205, the user type is operator or administrator.

In step 206, the user type is developer or general user.

In step 207, a user type identifier (intent-user identifier) of a corresponding type is added to the user intention message.

In step 208, it is resolved whether a lifecycle exists for each user intent. Screening out the user intentions with the life cycle, and executing the step 210; the non-lifecycle user intent is filtered out and step 209 is performed.

The lifecycle is used to indicate whether the user intent is a transient or persistent intent. A non-lifecycle intent, which is completed upon successful execution of the specified operation and which no longer affects the target object; there are lifecycle intents, and once successfully activated and deployed, the system will keep all relevant intents active until they are deactivated or deleted.

In step 209, the user intends to add the non-lifecycle service attribute identifier to the services, such as configuration, resource request, etc., belonging to the non-lifecycle.

In step 210, the user intends to have a life cycle, and services belonging to service attributes such as network optimization, connection, security, and the like need to be added with an intention type identifier of the life cycle.

In step 211, corresponding intent type identifiers (intent-type identifiers) are added for each user intent.

In some embodiments, the classification logic may be as shown in table 1 below:

in some embodiments, the relationship of the sub-modules in the taxon may be as follows:

TABLE 1 Classification relationship examples

In step 212, the intended service scene, user type and intention type are determined according to the added various identification header combinations, so that the corresponding strategy library is accurately retrieved and output to the corresponding converter module for configuration and delivery.

By the method, the generation of the control intention strategy can be refined, the corresponding classification rule management is carried out through the intention classification device according to the key information of the extracted user intention, the identification is added, so that the corresponding strategy library can be accurately retrieved, the configuration strategy is generated and issued, and the reliability of intention realization is improved.

In some embodiments, through the intent classification, in addition to being able to retrieve the intent policy base more accurately, it is also possible to provide more convenient and faster network management requests for different users in different service scenarios, as shown in table 2:

TABLE 2 Business scenario Classification and user types

Taking a cloud administrator as an example, a flowchart of another embodiment of the intent-driven network user intent implementation method of the present disclosure is shown in fig. 3.

In step 301, the cloud administrator provides user intent.

In step 302, checking the user intention in the user intention set; feeding back the user intention which fails to pass the verification to a cloud administrator for modification; step 303 is performed for the user's intent to verify passed.

In step 303, the user-id is obtained.

In step 304, the service scenario is determined to be a DC network according to the user-id.

In step 305, the intent-service identity corresponding to the DC network is added.

In step 306, it is determined whether the user's intent is for feedback. If the determination result is that feedback exists, step 307 is executed.

In step 307, the user type is determined to be administrator.

In step 308, the corresponding intent-user ID of the administrator is added.

In step 309, it is determined whether a lifecycle of the user intent exists.

For intentions that the cloud administrator wishes to perform, such as load balancing: for all traffic that requires NFV (Network Functions Virtualization) service links, it is desirable to limit the maximum load of any VNF (virtualized Network Functions) node/container to below 50% and the maximum load of any Network link to below 70%. The attribute collector retrieves the load balancing keyword, determines that the intention is a requirement of network optimization intention with a life cycle, and executes step 311.

In addition, the cloud administrator may also provide some user intentions without a lifecycle, and perform step 310.

In step 310, non-lifecycle intents, such as configuration, resource request, etc., are screened out.

In step 311, the intentions of existence of the life cycle, including network optimization, connection, security, and other services, are screened out.

In step 312, the intent-type identifier corresponding to the lifecycle is added.

In step 313, the policy library and converter corresponding to the intent translation are determined, and the user intents are translated into network policies, respectively.

By the method, the service scene, the user type and the service attribute of the user are gradually refined, the retrieval is carried out in the corresponding strategy library according to various identification heads of the intention, and the retrieval is converted into the corresponding strategy converter for configuration and issuing, so that the accuracy of intention translation is improved, and meanwhile, the interaction between intention conversion and verification is correspondingly reduced, the system efficiency is improved, and the user experience is improved.

In some embodiments, since different business scenarios and different users have different intent requirements, for a cloud administrator user, the intent types can be divided into the following modules:

1. cloud management intention: VM (Virtual Machine), database, configuration of App server, and network connectivity request, management of communication between VMs, and the like;

2. the resource management intention is as follows: according to data analysis of a cloud management system, VM resources such as calculation, storage and the like are automatically allocated or optimized;

3. the operation task intention is as follows: tasks such as addressing transmission paths, fault handling, network congestion, etc. are performed automatically except for basic configuration and resource management;

4. the strategy intention is as follows: and performing automatic execution and life cycle management on the routine operation tasks of the administrator, such as load balancing and the like.

After the basic information of the intention is retrieved, a corresponding strategy library is retrieved according to the key field, the attributes of different intention types are different, the cloud administrator strategy library is retrieved through the key field, the effective identification of the intention types is carried out, and the key field comprises:

intention attributes: c1 ═ connectivity; c2 ═ safety; c3 ═ QoS; c4 ═ computational resources; c5 storage resource

Network resources: c1 ═ virtual resources; c2 ═ physical resources

Abstraction: c1 with feedback; c2 no feedback

The life cycle is as follows: c1 — full life cycle; c2-transient intention

Table 3 key field discrimination examples for cloud management cloud users

And extracting and searching key fields based on the form, thereby finely completing various service scene strategy libraries.

A schematic diagram of some embodiments of a user intent realization device in an intent driven network of the present disclosure is shown in fig. 4A.

The intention acquisition unit 401 can acquire a user intention set. In some embodiments, one or more user intentions provided by the user are obtained through the business layer, and the user intention set comprises all intentions provided by the user.

The classification unit 402 can classify the user intentions in the user intention set, and obtain the classified user intentions. In some embodiments, user intent classification may be performed from three aspects of business scenario, user type, and business attributes.

The conversion unit 403 can convert the classified user intention into a network policy. In some embodiments, each category has a corresponding policy repository, and the corresponding policy repository may be determined according to the category user intent, and the category user intent may be converted into a network policy based on the determined policy repository. In some embodiments, different classes have corresponding converters, and the corresponding converters can be determined according to the user intention to convert the classified user intention into the network policy, and the policy base based on different converters is different.

The authentication unit 404 can authenticate the network policy by executing the network policy in the network environment, and acquire an authentication result. In some embodiments, the verification result is per user policy.

The decision unit 405 can determine whether the network policy corresponding to the verification result passes according to the verification result. For the network policy passing the verification, determining to adopt the network policy; for a policy that fails verification, then a modification is required. In some embodiments, the translation unit 403 may be informed to translate the corresponding intent back into a network policy.

Before the intention is converted into the network policy, the intention is classified by the device, so that the data volume of the processing of searching and polling in the policy library can be reduced, the time complexity is reduced, and the processing efficiency is improved; the probability of error conversion is reduced, and the accuracy is improved.

In some embodiments, as shown in fig. 4A, the user intention implementing apparatus in the intention driven network may further include an intention managing unit 406 capable of checking the user intention in the user intention set acquired by the intention acquiring unit; feeding back the user intention which is not verified to the user so as to facilitate the user to modify; the user's intention that passed the verification is sent to the classification unit.

The device can check and arrange the intention of the user firstly, and ensures that the following classification and conversion work can be carried out smoothly.

In some embodiments, the operation of the user intent realization device in the intent driven network may be as shown in fig. 4B.

1. Intention management: after receiving the user intentions from the business layer, the intention arranging layer needs to verify and classify the intentions, the intentions meeting the conditions are further submitted to the classifying unit for analysis, and the intentions failing to be fed back to the user by the intention managing unit for further modification and adjustment.

2. Conversion: and distributing the analysis result to a corresponding converter in the conversion unit according to the analysis result of the classification unit, configuring and issuing the analysis result, and outputting the result to the verification unit.

3. And (3) verification: the authentication unit has two authentication functions:

one is the performability verification of the configuration. The configuration obtained in the translation process needs to verify whether the configuration can be executed in the actual network environment according to the real-time network state, and feeds back the relevant information to the decision unit.

The second is validity verification. When the configuration is actually executed, the network state changes, and at this time, it is necessary to verify whether the execution of the configuration changes the network state as expected, and to feed back the verification result to the decision module, and if the verification fails, it means that the intention layer needs to perform "intention-configuration" arrangement again.

4. And (3) decision making: the system is responsible for overall control of the network state and configuration, and is used for processing data transmitted by the verification unit and assisting the conversion unit to perform intent conversion. The decision unit supports the decision-making assisted by experience knowledge from upper-level administrators, and artificial intelligence can also be adopted to assist the decision-making. When the user intention is not realized or the network state is abnormal, the decision unit needs to make optimization or remedial measures and informs the conversion unit to respond, and the intention-to-configuration translation processing is performed again.

The intention execution layer mainly comprises intention configuration execution and network state sensing and feedback, a sensing information acquisition function supports information acquisition of network topology information, network flow information, a service path and the like, and when configuration is actually executed, feedback information is output to the verification unit.

The device can finely manage and control the generation of the intention strategy, and performs corresponding classification rule management and identification addition through intention classification according to key information of extracted user intentions, so that a corresponding strategy library can be more accurately retrieved, a configuration strategy is generated and issued, and the system reliability is improved; the system efficiency can be effectively improved, the defects that time complexity is high and user experience feeling cannot be guaranteed due to the fact that a strategy library is used for carrying out retrieval and extraction of key intention information such as massive data polling or enumeration method and the like are overcome, intention requests of different service scenes, user types and service attributes are effectively identified, accurate intention conversion is carried out through corresponding intention converters, interaction frequency between intention verification and intention conversion is reduced, and the system efficiency is effectively improved.

A schematic diagram of some embodiments of a classification unit in an intent-driven network of the present disclosure is shown in fig. 5.

The function constrainer 503 is capable of deciding the intended user type and service attributes, including both feedback and lifecycle constraint decision modules.

The classification rule device 501 can identify corresponding service scenarios, such as an operator network, a DC network, an enterprise network, and the like, according to the user-id of the user input intention; and identifying the corresponding user type and service attribute according to the judgment of the function constrainer. The user types comprise network managers, operation operators, APP developers, end users and the like; service attributes include, for example, network optimization, connectivity requests, QoS (Quality of Service), security requests, resource requests, device configuration, etc. Different user types have different requirements on the feedback of the intention, and different service attributes have different requirements on the life cycle of the intention. There are two types of intent that can be classified according to whether or not there is a lifecycle: there is a lifecycle intent and an inanimate intent.

The attribute collector 502 can extract the key fields of the input intentions, and the input can be input into the classification rulers to retrieve corresponding information.

The classification identifier 504 can perform identification authentication in the classification rule, and output the identification authentication to a corresponding converter module for configuration and delivery according to the added various identification header combinations.

The device effectively identifies the intention requests of the sub-service scenes, the user types and the service attributes, and converts the intention requests into corresponding intention converters for accurate intention execution, so that the interaction frequency between intention verification and intention conversion is reduced, and the system efficiency is effectively improved.

The schematic structural diagram of one embodiment of a user intention realizing device in an intention driven network of the present disclosure is shown in fig. 6. A user intent realization device in an intent driven network includes a memory 601 and a processor 602. Wherein: the memory 601 may be a magnetic disk, flash memory, or any other non-volatile storage medium. The memory is for storing instructions in the above corresponding embodiments of the method of user intent implementation in an intent driven network. Processor 602 is coupled to memory 601 and may be implemented as one or more integrated circuits, such as a microprocessor or microcontroller. The processor 602 is used for executing instructions stored in the memory, so that time complexity can be reduced, and processing efficiency can be improved; the probability of error conversion is reduced, and the accuracy is improved.

In one embodiment, as also shown in fig. 7, a user intent realization apparatus 700 in an intent driven network includes a memory 701 and a processor 702. Processor 702 is coupled to memory 701 by a BUS BUS 703. The user intent realization device 700 in the intent driven network may also be connected to an external storage device 705 via a storage interface 704 for invoking external data, and may also be connected to a network or another computer system (not shown) via a network interface 706. And will not be described in detail herein.

In the embodiment, the data instruction is stored in the memory, and the instruction is processed by the processor, so that the time complexity can be reduced, and the processing efficiency can be improved; the probability of error conversion is reduced, and the accuracy is improved.

In another embodiment, a computer-readable storage medium has stored thereon computer program instructions which, when executed by a processor, implement the steps of a method in a corresponding embodiment of an intent-driven network user intent implementation method. As will be appreciated by one skilled in the art, embodiments of the present disclosure may be provided as a method, apparatus, or computer program product. Accordingly, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable non-transitory storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present disclosure is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

Thus far, the present disclosure has been described in detail. Some details that are well known in the art have not been described in order to avoid obscuring the concepts of the present disclosure. It will be fully apparent to those skilled in the art from the foregoing description how to practice the presently disclosed embodiments.

The methods and apparatus of the present disclosure may be implemented in a number of ways. For example, the methods and apparatus of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order for the steps of the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above unless specifically stated otherwise. Further, in some embodiments, the present disclosure may also be embodied as programs recorded in a recording medium, the programs including machine-readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.

Finally, it should be noted that: the above examples are intended only to illustrate the technical solutions of the present disclosure and not to limit them; although the present disclosure has been described in detail with reference to preferred embodiments, those of ordinary skill in the art will understand that: modifications to the specific embodiments of the disclosure or equivalent substitutions for parts of the technical features may still be made; all such modifications are intended to be included within the scope of the claims of this disclosure without departing from the spirit thereof.

Claims

1. A method of user intent implementation in an intent-driven network, comprising:

acquiring a user intention set;

classifying the user intentions in the user intention set to acquire classified user intentions;

converting the classified user intent into a network policy;

verifying the network policy by executing the network policy in a network environment to obtain a verification result;

and confirming or modifying the network policy according to the verification result until the user intention is reached.

2. The method of claim 1, wherein the classifying the user intent, the obtaining a classified user intent comprises:

determining a business scene, a user type and an intention type of each user intention in the user intention set, wherein the intention type comprises an intention with a life cycle and an intention without a life cycle.

3. The method of claim 1, wherein determining a business scenario for each user intent of the set of user intents comprises:

obtaining an identification of a user providing the user intent;

determining the network environment where the user is located according to the identification of the user, and taking the network environment as a service scene of the user intention, wherein the network environment comprises an operator network, a data center DC network or an enterprise network.

4. The method of claim 1, wherein determining a user type for each user intent in the set of user intentions comprises:

extracting key fields of user intentions through an attribute collector;

the function judger judges whether the user intention has feedback according to the key field;

if the user intention does not have the feedback property, determining that the user type is a common user;

and if the user intention is feedback, determining the user type as the administrator.

5. The method of claim 1, wherein determining an intent type for each user intent in the set of user intentions comprises:

extracting key fields of user intentions through an attribute collector;

the function judger judges whether the user intention has a life cycle according to the key field;

if the user intention has a life cycle, determining the intention type as the intention with the life cycle;

if the user intent does not have a lifecycle, then the intent type is determined to be an intent without a lifecycle.

6. The method of claim 1, wherein the translating the classification user intent into a network policy comprises:

determining a corresponding strategy library according to the classified user intention;

converting the classified user intent into a network policy based on the determined policy repository.

7. The method of claim 1, wherein the verifying the network policy by executing the network policy in a network environment, and obtaining a verification result comprises:

executing the network policy in a network environment;

generating an executable verification result according to whether the network strategy is successfully executed;

generating a validity verification result according to whether the network state change meets the expectation of the user intention;

wherein the verification result comprises the performability verification result and the validity verification result.

8. The method of claim 1, wherein the validating or modifying the network policy according to the verification result until a user intent is reached comprises:

screening out network strategies which fail to pass the verification based on artificial intelligence or administrator instructions according to the verification result;

and determining the classified user intention corresponding to the network policy which fails to pass the verification, and re-executing the operation of converting the classified user intention into the network policy until the verification passes.

9. The method of claim 1, further comprising:

after a user intention set is obtained, verifying the user intention in the user intention set;

feeding back the user intention which is not verified to the user so as to facilitate the user to modify;

and performing an operation of classifying the user intention set on the verified user intention.

10. An apparatus for user intent realization in an intent-driven network, comprising:

an intention acquisition unit configured to acquire a user intention set;

the classification unit is configured to classify the user intention set and acquire a classification user intention;

a conversion unit configured to convert the classified user intent into a network policy;

a verification unit configured to verify the network policy by executing the network policy in a network environment, and obtain a verification result;

a decision unit configured to confirm or modify the network policy according to the verification result until a user intention is reached.

11. The apparatus of claim 10, further comprising:

an intention management unit configured to verify the user intention in the user intention set acquired by the intention acquisition unit; feeding back the user intention which is not verified to the user so as to facilitate the user to modify; transmitting the user's intention passing the verification to the classification unit.

12. An apparatus for user intent realization in an intent-driven network, comprising:

a memory; and

a processor coupled to the memory, the processor configured to perform the method of any of claims 1-9 based on instructions stored in the memory.

13. A computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the steps of the method of any one of claims 1 to 9.