A method, apparatus and device for dynamically constructing an intent

Abstract

The application provides a dynamic construction method, device and equipment of an intention, and the method comprises the following steps: receiving relevant information generated by an intention system based on intention input information and system state data; obtaining target control information according to the relevant information; and controlling the intention system to construct at least one intention process for running according to the target control information. The scheme provided by the application can make the running of the whole intention process more automatic, support the automatic design of a communication network and the running process, and meanwhile, can solidify and enrich the experience of relevant processes in intention design and running, and improve the reusability of the intention.

Description

Technical Field

[0001] This invention relates to the field of communication technology, and in particular to a method, apparatus, and device for dynamically constructing intent. Background Technology

[0002] 5G networks introduce network slicing, supporting end-to-end slicing. Slicing divides an operator's physical network into multiple logical networks to achieve multi-purpose use of a single network. Slicing allows operators to build multiple dedicated, virtual, isolated, and customized logical networks on top of a single physical network to meet the diverse network capability requirements (such as latency, bandwidth, and number of connections) of different industry customers. A network slice instance consists of a collection of network functions and required physical / virtual resources, comprising sub-network slice instances of radio, transport, and core networks.

[0003] In existing network services, the workflow for fulfilling user needs can be designed in the form of intents. Users only need to input the corresponding intents without having to worry about the specific implementation details of the network service to fulfill the relevant business requirements.

[0004] In practical applications, intents are widely incorporated into communication networks. A user intent is taken as input, translated into necessary network configurations, and corresponding network changes are applied through network automation and / or network orchestration. Simultaneously, a closed-loop system is used to continuously monitor the network status, verifying in real time whether the intent is fulfilled, and taking appropriate corrective measures when the intended intent is not achieved.

[0005] Intents can also be decomposed according to multiple dimensions. Intents of different dimensions represent the concerns and goals of different users in the autonomous communication network. By dividing intents, intent-driven management can be introduced to manage the communication network, which is complex in structure. This allows users to manage the network without having to delve into the complex details of the underlying network infrastructure, effectively reducing the complexity of network management.

[0006] In existing network technologies, when applying intent-based technologies, corresponding intents need to be designed based on user needs. Once a user's intent is introduced into the network, the corresponding intent knowledge is obtained by parsing the user intent, which is then converted into the necessary network configuration. Appropriate network changes are then applied through network automation and / or network orchestration to meet the user's requirements.

[0007] Similarly, intents can be introduced into the implementation of requirements related to slicing services. Users do not need to concern themselves with the specific technical implementation of the slicing service process; they can achieve their slicing service requirements through the use of intents. For intents related to slicing services, the highest-level user intent can be decomposed. For example, a user's intent regarding slicing service requirements can be composed of probing sub-intents, activation sub-intents, and guarantee sub-intents. Each of these sub-intents is further composed of lower-level sub-intents. For instance, the activation sub-intent can be composed of sub-intents from the core network domain, transmission network domain, and radio network domain. The core network domain sub-intents can be further composed of slice subscription sub-intents, core network element slice selection sub-intents, slice isolation sub-intents, etc. Following this idea of ​​decomposing and combining intents, the various sub-processes related to the user's intent implementation workflow for slicing services can be automatically associated, reducing human intervention and human error, making the entire intent-supporting process more automated. Furthermore, all the decomposed sub-intents can be flexibly combined to form various composite intents, further improving the reusability of existing technologies.

[0008] However, in existing solutions, when dealing with complex intents, such as applying intents to slice-related business, there is a lack of flexible and dynamic processes for intent flow and information transmission. This results in the inability to reuse existing intent models when faced with different user inputs or system states, leading to low reusability of existing intent models and high costs for intent design and use. Summary of the Invention

[0009] The technical problem to be solved by the present invention is to provide a method, apparatus and device for dynamic construction of intent, so as to enhance the flexibility of intent design and execution and improve the reusability of intent.

[0010] To address the aforementioned technical problems, embodiments of the present invention provide a method for dynamically constructing intent, the method comprising:

[0011] The system receives relevant information based on the intent input information and system status data;

[0012] Based on the aforementioned relevant information, obtain the target control information;

[0013] Based on the target control information, the intent system is controlled to construct and execute at least one intent flow.

[0014] Optionally, based on the aforementioned relevant information, target control information is obtained, including:

[0015] Based on the aforementioned relevant information, obtain the target strategy from the strategy library and / or obtain the target decision-making experience from the experience library;

[0016] Based on the target strategy and / or the target decision-making experience, obtain target control information.

[0017] Optionally, according to the target strategy, target control information is obtained, including:

[0018] The target strategy is executed to generate target control information, which includes the execution information of the target strategy.

[0019] Optionally, the policy library stores at least one of the following policies:

[0020] The first strategy is used to construct an intent topology structure and select at least one target sub-intent to form an intent list within the intent topology structure.

[0021] The second strategy is used to construct the expected or scope information of the intent;

[0022] The third strategy is used to select the method of achieving the intention;

[0023] The fourth strategy is used for information transfer between parent and child intentions or between predecessor and successor intentions, wherein the predecessor and successor intentions are child intentions of the same level that have a predecessor-successor relationship.

[0024] Optionally, based on the target control information, the intent system is controlled to construct at least one intent flow for operation, including: during the intent operation, obtaining a list of intents for different business needs based on business requirements and the first strategy.

[0025] Optionally, based on the target control information, the intent system is controlled to construct at least one intent flow for operation, including: during the intent operation process, based on business needs, the first strategy, and the second strategy, obtaining the expected combination or scope combination of intents corresponding to different needs of the business.

[0026] Optionally, based on the target control information, the intent system is controlled to construct at least one intent process for operation, including: during the intent operation process, obtaining the intent implementation methods corresponding to different business needs based on business requirements, the first strategy, and the third strategy.

[0027] Optionally, based on the target control information, the intent system is controlled to construct at least one intent flow for operation, including: during the intent operation process, based on business needs, the first strategy and the fourth strategy, obtaining information transmission between parent intents and child intents corresponding to different needs, or information transmission between predecessor intents and successor intents.

[0028] Optionally, based on the target decision-making experience, target control information is obtained, including:

[0029] The target decision-making experience is executed to generate target control information, which includes: execution information of the target decision-making experience.

[0030] Optionally, in the dynamic construction method of intent, the target decision experience is obtained by the training module from the experience base based on the relevant information; the training module is trained based on the system information sent by the intent system; the system information includes at least one of the following: intent input information, system status information, decision experience execution information, user feedback information, and system feedback information after the decision experience is executed.

[0031] Optionally, the experience base includes at least one of the following decision-making experiences:

[0032] First decision experience is used to construct an intent topology, and in the intent topology, at least one target sub-intent is selected to form an intent list;

[0033] Secondary decision-making experience is used to construct the expected or scope information of the intent;

[0034] The third set of decision-making experience is used to select the method of achieving the intention;

[0035] The fourth decision-making experience is used for information transmission between parent intentions and child intentions, or between predecessor intentions and successor intentions, wherein the predecessor intentions and successor intentions are child intentions of the same level that have a predecessor-successor relationship.

[0036] Optionally, based on the target control information, the intent system is controlled to construct and execute at least one intent flow, including:

[0037] During the execution of the intent, based on business needs and at least one decision-making experience from the experience base, the intent system is controlled to construct and execute at least one intent process.

[0038] Optionally, the method for dynamically constructing intent further includes:

[0039] During the execution of the intent, the strategies in the strategy library and / or the decision-making experience in the experience library are updated based on the actual execution of the intent flow.

[0040] Embodiments of the present invention also provide an apparatus for dynamically constructing intent, the apparatus comprising:

[0041] The acquisition module is used to receive relevant information generated by the intent system based on intent input information and system status data;

[0042] The processing module is used to obtain target control information based on the relevant information; and to control the intent system to construct at least one intent flow for operation based on the target control information.

[0043] Embodiments of the present invention also provide a communication device, including: a processor and a memory storing a computer program, wherein the computer program, when executed by the processor, performs the method described above.

[0044] Embodiments of the present invention also provide a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the methods described above.

[0045] The above-described solution of the present invention has at least the following beneficial effects:

[0046] By receiving relevant information generated by the intent system based on intent input information and system status data; obtaining target control information based on the relevant information; and controlling the intent system to construct at least one intent flow for operation based on the target control information, the flexibility of intent design and execution flow is enhanced, while the reusability of intent is improved. Attached Figure Description

[0047] Figure 1 This is a flowchart of the dynamic construction method of intent provided in the embodiments of the present invention;

[0048] Figure 2 This is a flowchart of the dynamic construction of intents based on the policy library framework provided in this embodiment of the invention;

[0049] Figure 3 This is a flowchart of the dynamic construction of intent based on the experience base framework provided in the embodiments of the present invention;

[0050] Figure 4 This is a schematic diagram of dynamic construction of intent expectations based on a policy library framework provided in an embodiment of the present invention;

[0051] Figure 5 This is a schematic diagram illustrating the construction of a sub-intent list for sliced ​​network security intents based on a policy library framework, provided in an embodiment of the present invention.

[0052] Figure 6 This is a schematic diagram illustrating the implementation method of slice service probing intent based on the policy library framework provided in this embodiment of the invention.

[0053] Figure 7 This is a schematic diagram illustrating the construction of a sub-intent period for information transmission of network security isolation intent based on a policy library framework, as provided in an embodiment of the present invention.

[0054] Figure 8This is a schematic diagram of intent expectation and scope construction based on the experience base framework provided in the embodiments of the present invention;

[0055] Figure 9 This is a flowchart illustrating the intended design of slice security isolation provided in an embodiment of the present invention;

[0056] Figure 10 This is a flowchart illustrating the operation of the premium user isolation intent provided in this embodiment of the invention;

[0057] Figure 11 This is a flowchart illustrating the operation of the dedicated user isolation intent provided in this embodiment of the invention;

[0058] Figure 12 This is a schematic diagram of the module of the dynamic construction device provided in the embodiment of the present invention. Detailed Implementation

[0059] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this invention will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0060] like Figure 1 As shown, an embodiment of the present invention provides a method for dynamically constructing intent, the method comprising:

[0061] Step 11: Receive relevant information generated by the intent system based on the intent input information and system status data;

[0062] Step 12: Obtain target control information based on the aforementioned relevant information;

[0063] Step 13: Based on the target control information, control the intent system to construct at least one intent flow for operation.

[0064] In this embodiment, the relevant information is generated by the intent system based on the input intent information and the system's state data; the target control information is the execution information obtained by acquiring corresponding strategies or decision-making experience from a preset strategy module or model training module based on the relevant information and executing the corresponding strategies or decision-making experience. The target control information is used to control the intent system to construct at least one intent flow for operation, making the entire intent flow more automated and better supporting the automated design and operation of the communication network; the intent flow includes, but is not limited to: dynamically constructing intent expectation and scope information, dynamically decomposing and combining intents, dynamically selecting intent implementation methods, and dynamically transmitting intent information, etc.

[0065] like Figure 2 As shown, steps 11 to 13 above can be implemented by a strategy module. The strategy module may include a strategy system that interacts with the intent system and a strategy library that interacts with the strategy system. The strategy system is mainly used to obtain relevant information sent by the intent system. The strategy system can design corresponding strategies in the intent design stage and the intent execution stage respectively, and add them to the strategy library.

[0066] like Figure 3 As shown, steps 11 to 13 above can also be implemented by a model training module. The model training module may include a training module that interacts with the intent system and an experience base that interacts with the training module. The training module is mainly used to acquire relevant information sent by the intent system. The training module can pre-design different intent flows, design corresponding input and output information, and pre-set it as experience in the experience base. The training module can train the selected model based on these existing experiences. At the same time, during the intent execution process, dynamically generated experiences (such as system feedback information) can be saved as new experiences in the experience base. The training module can also train the model based on these new experiences to further improve the accuracy of the model training module.

[0067] By introducing strategy modules and / or model training modules, experience in the relevant processes of intent design and operation can be solidified and enriched, thereby improving the reusability of intents.

[0068] In an optional embodiment of the present invention, step 12 may include:

[0069] Step 121: Based on the relevant information, obtain the target strategy from the strategy library and / or obtain the target decision-making experience from the experience library;

[0070] Step 122: Obtain target control information based on the target strategy and / or the target decision-making experience.

[0071] In this embodiment, the strategy system of the strategy module can obtain a target strategy corresponding to the relevant information from multiple strategies in the strategy library of the strategy module, and / or the training module can obtain a target decision experience corresponding to the relevant information from multiple decision experiences in the experience library of the model training module.

[0072] The multiple strategies stored in the strategy base or the multiple decision experiences stored in the experience base include, but are not limited to: strategies or decision experiences for intentional topology design, and strategies or decision experiences for intentional component information design. In an optional embodiment of the present invention, step 122 may include:

[0073] Step 1221a: Execute the target policy to generate target control information; send the target control information to the intent system, wherein the target control information includes: policy execution information.

[0074] In this embodiment, the policy system obtains a target policy from the policy library, executes the target policy, generates target control information, the target control information contains policy execution information, and sends the target control information to the intent system so that the intent system can perform subsequent intent processes according to the policy execution information in the target control information.

[0075] In an optional embodiment of the present invention, the policy library stores at least one of the following policies:

[0076] The first strategy is used to construct an intent topology structure and select at least one target sub-intent to form an intent list within the intent topology structure.

[0077] The second strategy is used to construct the expected or scope information of the intent;

[0078] The third strategy is used to select the method of achieving the intention;

[0079] The fourth strategy is used for information transfer between parent and child intentions or between predecessor and successor intentions, wherein the predecessor and successor intentions are child intentions of the same level that have a predecessor-successor relationship.

[0080] In this embodiment, the first strategy may be a pre-set strategy based on the relevant information during the design phase of the intent, mainly used to construct the topology of the intent. The topology of the intent may also be formed by decomposing and combining the intent through the strategy module during the execution phase of the intent, based on the pre-set strategy.

[0081] The topology of the intent can be based on intents with different processes and technologies, decomposing the intent into combinations of sub-intents at different levels to facilitate the acquisition and combination of sub-intents;

[0082] The process of constructing the topology of an intent includes, but is not limited to: combining sub-intents, selecting the first sub-intent, and selecting subsequent intents.

[0083] It is important to note that during the construction of the topology of an intent, if the intent has sub-intents, the information of all the sub-intents contained in the intent needs to be considered. If the intent is also a sub-intent, the relationship between the intent and other sub-intents belonging to the same parent intent needs to be considered.

[0084] The first strategy, the second strategy, the third strategy, and the fourth strategy can be customized by the system during the execution of the intent based on different factors such as the intent or environment, so as to achieve flexibility in intent design and execution.

[0085] In an optional embodiment of the present invention, step 13 may include:

[0086] Step 131a: During the intent execution process, obtain a list of intents corresponding to different needs based on business requirements and the first strategy.

[0087] In this embodiment, the business requirements include, but are not limited to, business modes, and further business modes include, but are not limited to, business mode levels; according to different business requirements, an intent list corresponding to the intent is obtained from the intent topology structure constructed by the first strategy. The intent list may include all sub-intents of the intent, as well as the logical relationships between the sub-intents. The logical relationships include, but are not limited to, parent-child relationships and predecessor-successor relationships.

[0088] Specifically, such as Figure 5 As shown, taking the slice security isolation intent as an example, it has four sub-intents: network element isolation sub-intent, data isolation sub-intent, network isolation sub-intent, and fault isolation sub-intent.

[0089] During the execution of the intent, the business requirement can be a level of business model, i.e., whether it is a premium customer or a valued customer. Based on the strategy module, the first preset strategy can be run to obtain sub-intent combinations of different customer levels.

[0090] If a premium customer requires all of the above sub-intents, while a premium customer only needs the data isolation sub-intent and the network isolation sub-intent; for a premium customer, its first sub-intent is the network element isolation sub-intent, and for a premium customer, its first sub-intent is the data isolation sub-intent. At the same time, for a premium customer, its subsequent intent is the fault isolation sub-intent, and for a premium customer, it is the last intent in the sub-intent list, so its subsequent intent returns and points to its parent intent, namely the slice security isolation intent.

[0091] In an optional embodiment of the present invention, step 13 may include:

[0092] Step 132a: During the intent execution process, based on business requirements, the first strategy, and the second strategy, obtain the expected combination or scope combination of intents corresponding to different business requirements.

[0093] In this embodiment, based on different business needs, an intent list corresponding to the intent is obtained from the intent topology structure constructed by the first strategy, and a sub-intent expectation combination or scope combination of intents that meet different business needs is obtained according to the second strategy.

[0094] Specifically: such as Figure 4 As shown, taking the dynamic construction of expectations as an example, the sliced ​​data isolation intention has four sub-intention expectations: needing to destroy residual data, needing to encrypt storage, needing fine-grained authorization, and needing authentication. During the intention execution process, based on the business model level (VIP customer or premium customer), a pre-set second strategy can be run according to the strategy module to obtain the expectation combinations of different customer levels. For example, VIP customers require all four expectations to be met, while premium customers only need to meet the expectations of needing authentication and needing to encrypt storage.

[0095] In an optional embodiment of the present invention, step 13 may include:

[0096] Step 133a: During the intent execution process, based on business requirements, the first strategy, and the third strategy, obtain the intent implementation methods corresponding to different business requirements.

[0097] In this embodiment, based on different business needs, an intent list corresponding to the intent is obtained from the intent topology structure constructed by the first strategy, and the corresponding intent implementation method that meets different business needs is obtained according to the third strategy.

[0098] Specifically, such as Figure 6 As shown, taking the intent detection of slice services as an example, this intent can be implemented using digital twin technology or analysis and evaluation technology in the form of workflows or policies. Digital twin technology involves building a virtual simulation environment to deeply simulate and verify the potential impact; analysis and evaluation technology assesses the potential resource requirements and impact on the existing network after the new slice is created based on existing experience; and a pre-set third policy is run based on the policy module to obtain different intent implementation methods. For example, premium customers can use digital twin technology, while high-end customers can use analysis and evaluation technology.

[0099] In an optional embodiment of the present invention, step 13 may include:

[0100] Step 134a: During the execution of the intent, based on the business requirements, the first strategy, and the fourth strategy, obtain the information transmission between the parent intent and the child intent or the information transmission between the predecessor intent and the successor intent corresponding to different business requirements.

[0101] In this embodiment, the intent system obtains an intent list corresponding to the intent from the intent topology structure constructed by the first strategy according to different business needs, and obtains the information transmission between parent intents and child intents or between predecessor intents and successor intents corresponding to different business needs according to the fourth strategy.

[0102] Specifically, such as Figure 7 As shown, during the intent execution phase, information can be dynamically transmitted through the policy module based on a pre-defined fourth strategy. This includes dynamic information transmission between parent and child intents, and dynamic information transmission between predecessor and successor intents. In the example above, running the pre-defined fourth strategy based on the policy module can obtain parameter information at different levels for different business modes. For premium customers, the parent intent slice security isolation intent is transmitted to its child intent, meaning the network element isolation child intent has a high isolation level and an isolation period of 30 days. For premium customers, the isolation level is low and the isolation period is 10 days.

[0103] In an optional embodiment of the present invention, step 122 may include:

[0104] Step 122b: Execute the target decision experience to generate target control information; send the target control information to the intent system, wherein the target control information includes: execution information of the decision experience.

[0105] In this embodiment, the training module obtains target decision-making experience from the experience base, executes the target decision-making experience, and generates target control information. The target control information contains execution information of the decision-making experience. The training module sends the target control information to the intent system so that the intent system can perform subsequent intent processes based on the execution information of the decision-making experience in the target control information.

[0106] In an optional embodiment of the present invention, in the dynamic construction method of intent, the target decision experience is obtained by the training module from the experience base according to the relevant information; the training module is trained according to the system information sent by the intent system; the system information includes at least one of the following: intent input information, system status information, decision experience execution information, user feedback information, and system feedback information after the decision experience is executed.

[0107] In this embodiment, the experience base contains various decision-making experiences trained based on different models. During the intent design or operation process, the intent system sends relevant system information to the training module. The training module trains the corresponding model to optimize it and saves the generated experience to the experience base. At the same time, the training module can also train the selected model based on these new experiences to improve the accuracy of the model's decision-making. The different models and corresponding experiences include, but are not limited to: models and related decision-making experiences of intent expectation and scope, models and related decision-making experiences of intent topology construction, models and related decision-making experiences of intent implementation method selection, and models and related decision-making experiences of dynamic intent information transmission.

[0108] In an optional embodiment of the present invention, the experience base includes at least one of the following decision-making experiences:

[0109] First decision experience is used to construct an intent topology, and in the intent topology, at least one target sub-intent is selected to form an intent list;

[0110] Secondary decision-making experience is used to construct the expected or scope information of the intent;

[0111] The third set of decision-making experience is used to select the method of achieving the intention;

[0112] The fourth decision-making experience is used for information transmission between parent intentions and child intentions, or between predecessor intentions and successor intentions, wherein the predecessor intentions and successor intentions are child intentions of the same level that have a predecessor-successor relationship.

[0113] In this embodiment, the definition and generation of the first decision experience, the second decision experience, the third decision experience, and the fourth decision experience correspond one-to-one with the first strategy, the second strategy, the third strategy, and the fourth strategy in the above embodiment, and are the same, so they will not be repeated here.

[0114] In an optional embodiment of the present invention, step 13 may include:

[0115] Step 131b: During the intent execution process, based on business needs and at least one decision-making experience in the experience base, control the intent system to construct at least one intent process for execution.

[0116] In this embodiment, the business requirements include, but are not limited to, business models. Furthermore, the business models include, but are not limited to, business model levels. During intent execution, a list of intents corresponding to different needs can be obtained based on the business requirements and the first decision-making experience. Expected combinations or scope combinations of intents corresponding to different needs can be obtained based on the business requirements, the first decision-making experience, and the second decision-making experience. Intent implementation methods corresponding to different needs can be obtained based on the business requirements, the first decision-making experience, and the third decision-making experience. Information transmission between parent and child intents or between predecessor and successor intents corresponding to different needs can be obtained based on the business requirements, the first decision-making experience, and the fourth decision-making experience. Specifically: Figure 8 As shown, taking the construction of intention expectation and scope information as an example, during the intention execution process, based on the model trained in various scenarios, the combination of intention expectation and scope information is constructed to achieve the flexibility of the intention process.

[0117] In an optional embodiment of the present invention, based on steps 11-13 above, the invention further includes:

[0118] Step 14: During the execution of the intent, update the strategies in the strategy library and / or update the decision-making experience in the experience library according to the actual execution of the intent flow.

[0119] In this embodiment, for the strategies or experiences preset in the design phase, the corresponding strategies or decision-making experiences can be modified according to the actual situation during the operation of the intent, and dynamically updated to the strategy library or experience library, so that the corresponding intent can be run according to the new strategies or decision-making experiences in the future.

[0120] The above scheme will be explained below using the intent of slicing for security isolation as a specific example:

[0121] Slice security isolation intent design process: Assume the slice security isolation intent consists of network element isolation sub-intents, data isolation sub-intents, network isolation sub-intents, and fault isolation sub-intents. Assume this intent comprises three expected pieces of information (isolation level, isolation period, encryption method) and one scope information (isolation area). In this embodiment, assuming a policy-based flexible construction technology is adopted, the slice security isolation intent design information is as follows: Figure 9 As shown; in addition to designing expectations, scope, and sub-intent information, six strategies were also designed, namely expectation construction strategy, parent-child intent information transmission strategy, predecessor-successor information transmission strategy, sub-intent combination strategy, first sub-intent selection strategy, and successor intent selection strategy.

[0122] Slice Security Isolation Intent Execution Flow: For VIP users, in actual operation, if the input user intent is "to implement one month of security isolation for VIP customer slice services," after the aforementioned intent input and transformation, intent parsing, intent decomposition, intent orchestration and reuse, intent detection, and intent installation stages, in the actual intent execution stage, based on the user-input intent information, various pre-defined strategies are executed. The actual intent execution is as follows: Figure 10 As shown;

[0123] For dedicated users, in actual operation, if the input user intent is "to implement two weeks of security isolation for the dedicated customer's slice business," then after executing each step of the aforementioned runtime process and based on the corresponding policy, the actual execution of the intent will be as follows: Figure 11 As shown;

[0124] Because Dedicated users are at a lower level than Premium users, their isolation levels, isolation periods, and encryption methods are lower than those of Premium users after dynamic policy-based configuration. The information isolation area requirements also only apply to the core area. Furthermore, Dedicated users do not require fault isolation; their network element isolation only applies to network elements in the core area. Regardless of whether it's a Premium or Dedicated customer's intent execution process, a subsequent intent assurance mechanism will continuously monitor and guarantee security isolation expectations to ensure that user intent is consistently met. However, the assurance technologies and requirements may differ for different customer levels.

[0125] In the above embodiments of the present invention, strategies can be generated based on strategy modules or decision-making experience generated based on model training modules. By introducing strategy modules or model training systems into the process of intent flow and information acquisition, the design and operation of intent can be flexibly completed, improving the reusability of intent models and related experience. At the same time, in the actual operating environment, different choices or information transmission and construction can be made according to different environmental factors, enhancing the flexibility of intent design and execution.

[0126] like Figure 12 As shown, embodiments of the present invention also provide an intention dynamic construction apparatus 120, the apparatus 120 comprising:

[0127] The acquisition module 121 is used to receive relevant information generated by the intent system based on intent input information and system status data;

[0128] The processing module 122 is used to obtain target control information based on the relevant information; and to control the intent system to construct at least one intent flow for operation based on the target control information.

[0129] Optionally, the processing module 122 is configured to obtain target control information based on the relevant information, including:

[0130] Based on the aforementioned relevant information, obtain the target strategy from the strategy library and / or obtain the target decision-making experience from the experience library;

[0131] Based on the target strategy and / or the target decision-making experience, obtain target control information.

[0132] Optionally, the processing module 122 is configured to obtain target control information according to the target strategy, including: executing the target strategy and generating target control information; the target control information includes: execution information of the target strategy.

[0133] Optionally, the policy library stores at least one of the following policies:

[0134] The first strategy is used to construct an intent topology structure and select at least one target sub-intent to form an intent list within the intent topology structure.

[0135] The second strategy is used to construct the expected or scope information of the intent;

[0136] The third strategy is used to select the method of achieving the intention;

[0137] The fourth strategy is used for information transfer between parent and child intentions or between predecessor and successor intentions, wherein the predecessor and successor intentions are child intentions of the same level that have a predecessor-successor relationship.

[0138] Optionally, the processing module 122 is configured to control the intent system to construct and execute at least one intent flow based on the target control information, including:

[0139] During the execution of the intent, based on business requirements and the first strategy, a list of intents corresponding to different business requirements is obtained.

[0140] Optionally, the processing module 122 is configured to control the intent system to construct and execute at least one intent flow based on the target control information, including:

[0141] During the execution of the intent, based on business needs, the first strategy, and the second strategy, the expected combination or scope combination of intents corresponding to different business needs is obtained.

[0142] Optionally, the processing module 122 is configured to control the intent system to construct and execute at least one intent flow based on the target control information, including:

[0143] During the intent execution process, based on business requirements, the first strategy, and the third strategy, the intent implementation methods corresponding to different business requirements are obtained.

[0144] Optionally, the processing module 122 is configured to control the intent system to construct and execute at least one intent flow based on the target control information, including:

[0145] During the execution of the intent, based on business requirements, the first strategy, and the fourth strategy, information transmission between parent intents and child intents or between predecessor intents and successor intents corresponding to different business requirements is obtained.

[0146] Optionally, the processing module 122 is configured to obtain target control information based on the target decision experience, including: executing the target decision experience to generate target control information; the target control information includes: execution information of the target decision experience.

[0147] Optionally, the target decision experience is obtained by the training module from the experience base based on the relevant information; the training module is trained based on the system information sent by the intent system; the system information includes at least one of the following: intent input information, system status information, decision execution information, user feedback information, and system feedback information after the decision experience is executed.

[0148] Optionally, the experience base includes at least one of the following decision-making experiences:

[0149] First decision experience is used to construct an intent topology, and in the intent topology, at least one target sub-intent is selected to form an intent list;

[0150] Secondary decision-making experience is used to construct the expected or scope information of the intent;

[0151] The third set of decision-making experience is used to select the method of achieving the intention;

[0152] The fourth decision-making experience is used for information transmission between parent intentions and child intentions, or between predecessor intentions and successor intentions, wherein the predecessor intentions and successor intentions are child intentions of the same level that have a predecessor-successor relationship.

[0153] Optionally, the processing module 122 is configured to control the intent system to construct and execute at least one intent flow based on the target control information, including:

[0154] During the execution of the intent, based on business needs and at least one decision-making experience from the experience base, the intent system is controlled to construct and execute at least one intent process.

[0155] Optionally, the processing module 122 is further configured to update the strategies in the strategy library and / or update the decision-making experience in the experience library according to the actual running status of the intent flow during the intent execution process.

[0156] It should be noted that this device is the same as the method described above. All implementations in the above method embodiments are applicable to the embodiments of this device and can achieve the same technical effect.

[0157] Embodiments of the present invention also provide a computing device, including: a processor and a memory storing a computer program, wherein the computer program, when executed by the processor, performs the method described above. All implementations in the above method embodiments are applicable to this embodiment and can achieve the same technical effects.

[0158] Embodiments of the present invention also provide a computer-readable storage medium including instructions that, when executed on a computer, cause the computer to perform the method described above. All implementations in the above method embodiments are applicable to this embodiment and can achieve the same technical effects.

[0159] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0160] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0161] In the embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0162] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0163] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0164] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0165] Furthermore, it should be noted that in the apparatus and method of the present invention, it is obvious that the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered equivalent solutions of the present invention. Moreover, the steps performing the above-described series of processes can naturally be executed in the order described, but are not necessarily required to be executed in chronological order; some steps can be executed in parallel or independently of each other. Those skilled in the art will understand that all or any step or component of the method and apparatus of the present invention can be implemented in any computing device (including processors, storage media, etc.) or network of computing devices, in hardware, firmware, software, or a combination thereof. This is something that those skilled in the art can achieve by using their basic programming skills after reading the description of the present invention.

[0166] Therefore, the object of the present invention can also be achieved by running a program or a set of programs on any computing device. The computing device can be a known general-purpose device. Therefore, the object of the present invention can also be achieved simply by providing a program product containing program code implementing the method or apparatus. That is, such a program product also constitutes the present invention, and the storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any known storage medium or any storage medium developed in the future. It should also be noted that in the apparatus and method of the present invention, it is obvious that the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered equivalent to the present invention. Furthermore, the steps performing the above series of processes can naturally be performed in the order described, but are not necessarily required to be performed in chronological order. Some steps can be performed in parallel or independently of each other.

[0167] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for dynamically constructing intent, characterized in that, The method includes: The system receives relevant information based on the intent input information and system status data; Based on the aforementioned relevant information, obtain the target control information; Based on the target control information, the intent system is controlled to construct at least one intent flow for operation; wherein, the intent flow includes at least one of the following: dynamically constructing intent expectation and scope information, dynamically decomposing and combining intents, dynamically selecting intent implementation methods, and dynamically transmitting intent information; The step of obtaining target control information based on the relevant information includes: Based on the aforementioned relevant information, target strategies are obtained from the strategy library and / or target decision-making experience is obtained from the experience library; wherein, the strategies stored in the strategy library include strategies for intention topology design and strategies for intention component information design, and the decision-making experience stored in the experience library includes decision-making experience for intention topology design and decision-making experience for intention component information design. Based on the target strategy and / or the target decision-making experience, obtain target control information; Wherein, obtaining target control information based on the target strategy and / or the target decision-making experience includes at least one of the following: Execute the target strategy to generate the target control information, wherein the target control information includes: execution information of the target strategy; The target decision-making experience is executed to generate the target control information, wherein the target control information includes: execution information of the target decision-making experience.

2. The method for dynamically constructing intent according to claim 1, characterized in that, The policy library stores at least one of the following policies: The first strategy is used to construct an intent topology structure and select at least one target sub-intent to form an intent list within the intent topology structure. The second strategy is used to construct the expected or scope information of the intent; The third strategy is used to select the method of achieving the intention; The fourth strategy is used for information transfer between parent and child intentions or between predecessor and successor intentions, wherein the predecessor and successor intentions are child intentions of the same level that have a predecessor-successor relationship.

3. The method for dynamically constructing intent according to claim 2, characterized in that, Based on the target control information, the intent system is controlled to construct and execute at least one intent flow, including: During the execution of the intent, based on business requirements and the first strategy, a list of intents corresponding to different business requirements is obtained.

4. The method for dynamically constructing intent according to claim 3, characterized in that, Based on the target control information, the intent system is controlled to construct and execute at least one intent flow, including: During the execution of the intent, based on business needs, the first strategy, and the second strategy, the expected combination or scope combination of intents corresponding to different business needs is obtained.

5. The method for dynamically constructing intent according to claim 2, characterized in that, Based on the target control information, the intent system is controlled to construct and execute at least one intent flow, including: During the intent execution process, based on business requirements, the first strategy, and the third strategy, the intent implementation methods corresponding to different business requirements are obtained.

6. The method for dynamically constructing intent according to claim 2, characterized in that, Based on the target control information, the intent system is controlled to construct and execute at least one intent flow, including: During the execution of the intent, based on business requirements, the first strategy, and the fourth strategy, information transmission between parent intents and child intents or between predecessor intents and successor intents corresponding to different business requirements is obtained.

7. The method for dynamically constructing intent according to claim 1, characterized in that, The target decision-making experience is obtained by the training module from the experience base based on the relevant information; the training module is trained based on the system information sent by the intent system; the system information includes at least one of the following: intent input information, system status information, decision experience execution information, user feedback information, and system feedback information after the decision experience is executed.

8. The method for dynamically constructing intent according to claim 1, characterized in that, The experience base includes at least one of the following decision-making experiences: First decision experience is used to construct an intent topology, and in the intent topology, at least one target sub-intent is selected to form an intent list; Secondary decision-making experience is used to construct the expected or scope information of the intent; The third set of decision-making experience is used to select the method of achieving the intention; The fourth decision-making experience is used for information transmission between parent intentions and child intentions, or between predecessor intentions and successor intentions, wherein the predecessor intentions and successor intentions are child intentions of the same level that have a predecessor-successor relationship.

9. The method for dynamically constructing intent according to claim 8, characterized in that, Based on the target control information, the intent system is controlled to construct and execute at least one intent flow, including: During the execution of the intent, based on business needs and at least one decision-making experience from the experience base, the intent system is controlled to construct and execute at least one intent process.

10. The method for dynamically constructing intent according to claim 1, characterized in that, Also includes: During the execution of the intent, the strategies in the strategy library and / or the decision-making experience in the experience library are updated based on the actual execution of the intent flow.

11. A device for dynamically constructing intent, characterized in that, The device includes: The acquisition module is used to receive relevant information generated by the intent system based on intent input information and system status data; The processing module is used to obtain target control information based on the relevant information; and to control the intent system to construct at least one intent flow for operation based on the target control information; wherein the intent flow includes at least one of the following: dynamically constructing intent expectation and scope information, dynamically decomposing and combining intents, dynamically selecting intent implementation methods, and dynamically transmitting intent information; Specifically, the processing module is used to: obtain target strategies from a strategy library and / or target decision-making experience from an experience library based on the relevant information; the strategies stored in the strategy library include strategies for intention topology design and strategies for intention component information design, and the decision-making experience stored in the experience library includes decision-making experience for intention topology design and decision-making experience for intention component information design; and obtain target control information based on the target strategies and / or the target decision-making experience. When acquiring the target control information, the processing module is specifically used for at least one of the following: Execute the target strategy to generate the target control information, wherein the target control information includes: execution information of the target strategy; The target decision-making experience is executed to generate the target control information, wherein the target control information includes: execution information of the target decision-making experience.

12. A communication device, characterized in that, include: A processor, a memory storing a computer program, wherein the computer program, when executed by the processor, performs the method as described in any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that, Store instructions that, when executed on a computer, cause the computer to perform the method as described in any one of claims 1 to 10.

Images