Task processing method, system, device and equipment based on intention, readable storage medium and program product

Abstract

The invention relates to an intention-based task processing method, system and device, network equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: receiving intention information corresponding to a to-be-processed task; according to the intention information, obtaining a layer capability demand of the to-be-processed task for each functional layer in the communication network; according to the resource capability parameter of each functional layer, determining whether the functional layer independently meets the corresponding layer capability requirement; if the functional layer independently meets the corresponding layer capability requirement, obtaining a first subtask corresponding to the functional layer according to the layer capability requirement and the resource capability parameter of the functional layer; if the functional layer does not meet the corresponding layer capability requirement, obtaining a second subtask corresponding to each functional layer according to the layer capability requirement and the resource capability parameter of each functional layer; and distributing each first sub-task and / or second sub-task corresponding to the to-be-processed task to each corresponding functional layer. The method can improve the utilization rate of network resources.

Description

Technical Field

[0001] This application relates to the field of intelligent communication technology, and in particular to an intent-based task processing method, system, apparatus, network device, computer-readable storage medium, and computer program product. Background Technology

[0002] With the development of communication technology, technologies such as artificial intelligence models or intelligent agents are gradually being applied to communication networks to improve their intelligence level and task processing capabilities. Specifically, by deploying intelligent agents at different layers of the communication network, various communication tasks can be better accomplished through multi-layered collaboration. However, cross-layer collaboration in communication networks in these technologies can easily lead to low utilization of network resources. Summary of the Invention

[0003] Therefore, it is necessary to provide an intent-based task processing method, system, apparatus, network device, computer-readable storage medium, and computer program product to address the aforementioned technical problems.

[0004] Firstly, this application provides an intent-based task processing method, including:

[0005] Receive the intent information corresponding to the task to be processed;

[0006] Based on the intent information, the layer capability requirements of the task to be processed for each functional layer in the communication network are obtained;

[0007] Based on the resource capability parameters of each functional layer, determine whether the functional layer independently meets the corresponding layer capability requirements;

[0008] If the functional layer independently satisfies the corresponding layer capability requirements, then the first subtask corresponding to the functional layer is obtained based on the layer capability requirements and the resource capability parameters of the functional layer.

[0009] If the functional layer does not meet the corresponding layer capability requirements, then the second sub-task corresponding to each functional layer is obtained according to the layer capability requirements and the resource capability parameters of each functional layer.

[0010] Each of the first subtasks and / or the second subtasks corresponding to the task to be processed is assigned to the corresponding functional layer.

[0011] In one embodiment, obtaining the layer capability requirements of the task to be processed for each functional layer in the communication network based on the intent information includes: obtaining the service type, service requirements, intent priority, and security priority corresponding to the task to be processed based on the intent information; obtaining the basic resource requirements of the task to be processed for each key functional indicator of the communication network based on the service type and the service requirements; obtaining the indicator capability requirements of the task to be processed for each key functional indicator based on the intent information, the intent priority, the security priority, and the basic resource requirements; and obtaining the layer capability requirements corresponding to each functional layer based on the indicator capability requirements of each key functional indicator corresponding to each functional layer in the communication network.

[0012] In one embodiment, determining whether a functional layer independently meets the corresponding layer capability requirements based on the resource capability parameters of each functional layer includes: obtaining the indicator capability parameters of each resource instance of the functional layer for each key functional indicator based on the resource capability parameters of the functional layer; determining whether the functional layer has a resource allocation scheme that meets the indicator capability requirements of each key functional indicator in the layer capability requirements based on the indicator capability parameters of each resource instance; if yes, then determining that the functional layer independently meets the corresponding layer capability requirements; if no, then determining that the functional layer does not meet the corresponding layer capability requirements.

[0013] In one embodiment, if a functional layer fails to meet its corresponding layer capability requirements, a second sub-task corresponding to each functional layer is obtained based on the layer capability requirements and the resource capability parameters of each functional layer. This includes: determining the capability gap of the task to be processed based on the resource capability parameters of each functional layer and the corresponding layer capability requirements; determining the layer capability efficiency of each functional layer based on the resource capability parameters of each functional layer and the indicator capability requirements of each key functional indicator corresponding to the task to be processed; determining the task allocation weight of each functional layer based on the layer capability efficiency of each functional layer, the business adaptation parameters of the task to be processed, and the resource efficiency parameters of the functional layer; and allocating tasks to the capability gap based on the task allocation weight of each functional layer to obtain the second sub-task corresponding to each functional layer.

[0014] In one embodiment, the intent information is sent by the edge agent; the intent information is obtained by the edge agent based on the task scenario data, user behavior data, and user preference information of the task to be processed.

[0015] Secondly, this application also provides an intent-based task processing system, including: an edge-side agent and a network-side agent coordinator;

[0016] The edge-side intelligent agent is used to acquire task scenario data, user behavior data, and user preference information of the task to be processed; obtain the intent information of the task to be processed based on the task scenario data, the user behavior data, and the user preference information; and send the intent information to the network-side intelligent agent coordinator.

[0017] The network-side intelligent agent coordinator is used to receive the intent information and, based on the intent information, obtain the layer capability requirements of the task to be processed for each functional layer in the communication network.

[0018] The network-side intelligent agent coordinator is also used to determine whether the functional layer independently meets the corresponding layer capability requirements based on the resource capability parameters of each functional layer.

[0019] The network-side intelligent agent coordinator is further configured to, if the functional layer independently meets the corresponding layer capability requirements, obtain the first subtask corresponding to the functional layer based on the layer capability requirements and the resource capability parameters of the functional layer;

[0020] The network-side intelligent agent coordinator is further configured to, if the functional layer does not meet the corresponding layer capability requirements, obtain a second subtask corresponding to each functional layer based on the layer capability requirements and the resource capability parameters of each functional layer.

[0021] The network-side intelligent agent coordinator is further configured to assign each of the first subtasks and / or the second subtasks corresponding to the task to be processed to the corresponding functional layers.

[0022] Thirdly, this application also provides an intent-based task processing apparatus, comprising:

[0023] The intent receiving module is used to receive intent information corresponding to the task to be processed;

[0024] The requirement parsing module is used to obtain the layer capability requirements of the task to be processed for each functional layer in the communication network based on the intent information.

[0025] The requirement adaptation module is used to determine whether a functional layer independently meets the corresponding layer capability requirements based on the resource capability parameters of each functional layer.

[0026] The first task generation module is used to obtain the first subtask corresponding to the functional layer based on the layer capability requirements and the resource capability parameters of the functional layer if the functional layer independently meets the corresponding layer capability requirements.

[0027] The second task generation module is used to obtain a second sub-task corresponding to each functional layer based on the layer capability requirements and the resource capability parameters of each functional layer if the functional layer does not meet the corresponding layer capability requirements.

[0028] The subtask allocation module is used to allocate each of the first subtasks and / or the second subtasks corresponding to the task to be processed to the corresponding functional layers.

[0029] Fourthly, this application also provides a network device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0030] Receive the intent information corresponding to the task to be processed;

[0031] Based on the intent information, the layer capability requirements of the task to be processed for each functional layer in the communication network are obtained;

[0032] Based on the resource capability parameters of each functional layer, determine whether the functional layer independently meets the corresponding layer capability requirements;

[0033] If the functional layer independently satisfies the corresponding layer capability requirements, then the first subtask corresponding to the functional layer is obtained based on the layer capability requirements and the resource capability parameters of the functional layer.

[0034] If the functional layer does not meet the corresponding layer capability requirements, then the second sub-task corresponding to each functional layer is obtained according to the layer capability requirements and the resource capability parameters of each functional layer.

[0035] Each of the first subtasks and / or the second subtasks corresponding to the task to be processed is assigned to the corresponding functional layer.

[0036] Fifthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0037] Receive the intent information corresponding to the task to be processed;

[0038] Based on the intent information, the layer capability requirements of the task to be processed for each functional layer in the communication network are obtained;

[0039] Based on the resource capability parameters of each functional layer, determine whether the functional layer independently meets the corresponding layer capability requirements;

[0040] If the functional layer independently satisfies the corresponding layer capability requirements, then the first subtask corresponding to the functional layer is obtained based on the layer capability requirements and the resource capability parameters of the functional layer.

[0041] If the functional layer does not meet the corresponding layer capability requirements, then the second sub-task corresponding to each functional layer is obtained according to the layer capability requirements and the resource capability parameters of each functional layer.

[0042] Each of the first subtasks and / or the second subtasks corresponding to the task to be processed is assigned to the corresponding functional layer.

[0043] Sixthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0044] Receive the intent information corresponding to the task to be processed;

[0045] Based on the intent information, the layer capability requirements of the task to be processed for each functional layer in the communication network are obtained;

[0046] Based on the resource capability parameters of each functional layer, determine whether the functional layer independently meets the corresponding layer capability requirements;

[0047] If the functional layer independently satisfies the corresponding layer capability requirements, then the first subtask corresponding to the functional layer is obtained based on the layer capability requirements and the resource capability parameters of the functional layer.

[0048] If the functional layer does not meet the corresponding layer capability requirements, then the second sub-task corresponding to each functional layer is obtained according to the layer capability requirements and the resource capability parameters of each functional layer.

[0049] Each of the first subtasks and / or the second subtasks corresponding to the task to be processed is assigned to the corresponding functional layer.

[0050] The aforementioned intent-based task processing method, system, apparatus, network device, computer-readable storage medium, and computer program product first receive intent information corresponding to the task to be processed. Then, based on the intent information, they obtain the layer capability requirements of the task to be processed for each functional layer in the communication network. Next, based on the resource capability parameters of each functional layer, they determine whether the functional layer independently meets the corresponding layer capability requirements. If the functional layer independently meets the corresponding layer capability requirements, the first subtask corresponding to the functional layer is obtained based on the layer capability requirements and the resource capability parameters of the functional layer. If the functional layer does not meet the corresponding layer capability requirements, the second subtask corresponding to each functional layer is obtained based on the layer capability requirements and the resource capability parameters of each functional layer. Finally, the first subtask and / or the second subtask corresponding to the task to be processed are assigned to the corresponding functional layers. This scheme analyzes the user's communication intent and decomposes the task to be processed into layer capability requirements for each functional layer in the communication network based on the intent information. Then, it assesses whether the resources and capabilities of each functional layer can meet its corresponding layer capability requirements. When it is determined that a functional layer can meet its corresponding layer capability requirements, it directly generates the first subtask for that layer. When it is determined that a functional layer cannot meet its corresponding layer capability requirements, it decomposes the layer capability requirements into multiple second subtasks corresponding to the functional layers. Finally, the first and second subtasks are assigned to the respective functional layers. This scheme can formulate a decomposition strategy for the task to be processed based on the user's communication intent and the resources and capabilities of each functional layer in the communication network, achieving accurate matching between network resources and user communication intent and improving the utilization rate of network resources such as intelligent agents. Attached Figure Description

[0051] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0052] Figure 1 This is an application environment diagram of an intent-based task processing method in one embodiment;

[0053] Figure 2 This is a flowchart illustrating an intent-based task processing method in one embodiment;

[0054] Figure 3 This is a flowchart illustrating the process of obtaining the layer capability requirements of each functional layer in one embodiment;

[0055] Figure 4 This is a flowchart illustrating the process of obtaining the second sub-tasks corresponding to each functional layer in one embodiment;

[0056] Figure 5 This is a schematic diagram of the structure of an intent-based task processing system in one embodiment;

[0057] Figure 6 This is a schematic diagram of the structure of an intent-based task processing system in another embodiment;

[0058] Figure 7 This is a schematic diagram illustrating the task processing flow of an intent-based task processing system in one embodiment.

[0059] Figure 8 This is a structural block diagram of an intent-based task processing device in one embodiment;

[0060] Figure 9 This is a diagram of the internal structure of a network device in one embodiment. Detailed Implementation

[0061] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0062] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various objects, but these objects are not limited by these terms. These terms are only used to distinguish the first object from the second object. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0063] The intent-based task processing method provided in this application can be applied to, for example... Figure 1 The application environment is illustrated. In this environment, the edge agent can be deployed on the user's terminal. It can extract the intent information corresponding to the task to be processed based on data provided by the user and provide it to the communication network. The communication network can be deployed with an agent coordinator, which can receive the intent information corresponding to the task to be processed provided by the edge agent, process the information to obtain the first subtask and / or the second subtask corresponding to the task to be processed, and assign them to various functional layers in the communication network. The communication network can include multiple functional layers such as the physical layer, network layer, and application layer. Each functional layer can be deployed with corresponding agents, which can be used to execute the subtasks assigned to their respective functional layers.

[0064] In one exemplary embodiment, such as Figure 2 As shown, an intent-based task processing method is provided, which can be applied to... Figure 1 Taking the agent coordinator in the example, the explanation includes the following steps:

[0065] Step S201: Receive the intent information corresponding to the task to be processed.

[0066] Specifically, the task to be processed can be a communication task that the user needs to perform. The intent information corresponding to the task to be processed may include, but is not limited to, information such as the business type, business requirements, intent priority, and security priority of the task to be processed. For example, the intent information can be structured text information, which can be generated by the edge agent and sent to the agent coordinator.

[0067] In an exemplary embodiment, the intent information is sent by the edge agent; the intent information is obtained by the edge agent based on the task scenario data of the task to be processed, user behavior data, and user preference information.

[0068] Specifically, the edge-side intelligent agent can be deployed on the terminal device of a user who needs to perform pending tasks. It can utilize various embedded sensors and hardware / software interfaces on the terminal device to collect task scenario data and user behavior data corresponding to the pending tasks, as well as obtain the user's preference information. For example, task scenario data may include, but is not limited to, location, timestamps, ambient light / noise conditions, and network signal strength; user behavior data may include, but is not limited to, user movement status, application running status, and user service type; and user preference information may include, but is not limited to, preferred interaction patterns, network connection switching strategies, communication terminal tolerance, and privacy leakage risk tolerance.

[0069] In this context, the edge-side intelligent agent can utilize an artificial intelligence model to parse user intent based on collected task scenario data, user behavior data, and user preference information, thereby obtaining the intent information output by the model. For example, this artificial intelligence model can be a lightweight model deployed on the terminal device.

[0070] Step S202: Based on the intent information, obtain the layer capability requirements of the task to be processed for each functional layer in the communication network.

[0071] The communication network may include multiple functional layers, and each functional layer may be deployed with intelligent agents to implement the network functions corresponding to that functional layer. For example, the functional layers of the communication network may include, but are not limited to, the physical layer, the network layer, and the application layer.

[0072] In this step, the task to be processed can be mapped to the layer capability requirements of each functional layer in the communication network based on the intent information of the task. The layer capability requirements of each functional layer indicate the resource capabilities required by the task for each functional layer; that is, how many resources each functional layer needs to provide for the task to complete successfully. For example, each functional layer can have multiple preset key functional indicators, and the layer capability requirements of a certain functional layer can include the capability requirements of the task for each of those key functional indicators. For example, for the network layer, its corresponding key functional indicators may include, but are not limited to, path reliability and end-to-end latency; therefore, the layer capability requirements for that functional layer may include, but are not limited to, path reliability level and end-to-end latency threshold.

[0073] For example, the agent coordinator can use a pre-trained artificial intelligence model to process intent information to obtain the layer capability requirements of the task to be processed for each functional layer. For example, the agent coordinator can also use pre-configured business requirement mapping rules to transform intent information into layer capability requirements for each functional layer. These business requirement mapping rules can include the mapping relationship between various business types, business requirements, and other information and the indicator values ​​of various key functional indicators.

[0074] Step S203: Based on the resource capability parameters of each functional layer, determine whether the functional layer independently meets the corresponding layer capability requirements.

[0075] The agent coordinator can acquire resource capability parameters for each functional layer, indicating the resource capability that each functional layer can provide under its current or estimated state. Based on these parameters, the relationship between the resource capability each functional layer can provide and its corresponding layer capability requirement can be determined. If the resource capability a functional layer can provide is not less than its corresponding layer capability requirement, then that functional layer can independently meet that requirement; conversely, if the resource capability a functional layer can provide is less than its corresponding layer capability requirement, then that functional layer cannot independently meet that requirement.

[0076] Step S204: If the functional layer independently meets the corresponding layer capability requirements, then the first subtask corresponding to the functional layer is obtained based on the layer capability requirements and the resource capability parameters of the functional layer.

[0077] When it is determined that a certain functional layer in the communication network can meet its corresponding layer capability requirements, a first subtask that can be independently executed by that functional layer can be extracted from the task to be processed based on the layer capability requirements of the service to be processed for that functional layer and the resource capability parameters of that functional layer.

[0078] Step S205: If a functional layer does not meet the corresponding layer capability requirements, then based on the layer capability requirements and the resource capability parameters of each functional layer, the second sub-task corresponding to each functional layer is obtained.

[0079] When it is determined that a certain functional layer in the communication network cannot independently meet its corresponding layer capability requirements, the capability requirements of that layer can be broken down into multiple sub-requirements corresponding to each functional layer based on the resource capability parameters of all functional layers in the communication network. Each sub-requirement can be independently met by its corresponding functional layer. Subsequently, based on the resource capability parameters of each functional layer and its corresponding sub-requirements, the second sub-task corresponding to each functional layer can be obtained.

[0080] Step S206: Assign each first subtask and / or second subtask corresponding to the task to be processed to the corresponding functional layer.

[0081] After obtaining multiple first subtasks and / or second subtasks corresponding to the task to be processed, they can be assigned to the corresponding functional layers. Each functional layer can be assigned at most one first subtask, and can also be assigned one or more second subtasks, or it can be assigned no second subtasks or no first subtasks.

[0082] For example, taking a communication network's functional layers as including the physical layer, network layer, and application layer, when each functional layer can independently meet its corresponding layer capability requirements, each functional layer can be assigned a first sub-task. However, assuming the physical layer and network layer can independently meet their corresponding layer capability requirements, while the application layer cannot, the physical layer and network layer can each be assigned a first sub-task, and the application layer's layer capability requirements can be broken down into sub-requirements for the physical layer, network layer, and application layer, thus each of the three functional layers can be assigned a second sub-task. It is understandable that when a task to be processed does not require the capabilities of a certain functional layer, that task may not have a layer capability requirement for that functional layer, and therefore that functional layer will not be assigned a first sub-task.

[0083] For example, after assigning each first subtask and / or second subtask to the corresponding functional layer, the agents deployed in each functional layer can parse the received task and execute the corresponding task using the capability resources of that functional layer according to the parsing result. For example, after the agents in each functional layer obtain the parsing result of the subtask, they can also send the parsing result to the agent coordinator. The agent coordinator can perform a requirement matching degree detection between the parsing result of each functional layer and the user's intent information. Specifically, if the requirements are aligned, each layer is notified to execute the operation according to the parsing result, and the end-side agent is notified that the user's communication intent has been matched; otherwise, the reason for the requirement misalignment is analyzed and generated, and the reason is fed back to each functional layer, notifying the agents in each layer to perform subtask parsing again until the communication requirements of the user are aligned.

[0084] In the aforementioned intent-based task processing method, the user's communication intent is analyzed, and the task to be processed is decomposed into layer capability requirements for each functional layer in the communication network based on the intent information. Then, the resources and capabilities of each functional layer are evaluated to determine whether they can meet their corresponding layer capability requirements. When it is determined that a functional layer can meet its corresponding layer capability requirements, the first subtask corresponding to that layer is directly generated. When it is determined that a functional layer cannot meet its corresponding layer capability requirements, the layer capability requirements are decomposed into multiple second subtasks corresponding to the functional layers. Finally, the first and second subtasks are assigned to each functional layer. This method can formulate a decomposition strategy for the task to be processed based on the user's communication intent and the resources and capabilities of each functional layer in the communication network, achieving accurate matching between network resources and user communication intent, and improving the utilization rate of network resources such as intelligent agents.

[0085] In one exemplary embodiment, such as Figure 3 As shown, based on the intent information, the layer capability requirements of the task to be processed for each functional layer in the communication network are obtained, including:

[0086] Step S301: Based on the intent information, obtain the business type, business requirements, intent priority, and security priority corresponding to the task to be processed.

[0087] Specifically, intent information can be structured text information, which may include, but is not limited to, the business type, business requirements, intent priority, and security priority corresponding to the task to be processed. In this step, the agent coordinator can extract the business type, business requirements, intent priority, and security priority corresponding to the task to be processed from the intent information.

[0088] For example, an agent coordinator can convert structured intent information into a low-dimensional, dense vector representation, using intent vectors to describe the business type, business requirements, intent priority, and security priority of the task to be processed. For example, intent vectors... It can be represented as:

[0089]

[0090] in, Represents the business type encoding vector. Represents the business requirement encoding vector. Represents the priority scalar of intent. Security priority encoding. Intent information to intent vector. The transformation can be achieved through a pre-trained intent model or a fixed rule mapping table.

[0091] Step S302: Based on the service type and service requirements, obtain the basic resource requirements of the key functional indicators of the communication network for the task to be processed.

[0092] The communication network can have multiple key functional indicators, each corresponding to a functional layer, and each functional layer can have one or more corresponding key functional indicators. In this step, the basic resource requirements of the task to be processed for each key functional indicator of the communication network can be obtained based on the service type and service requirements of the task. These basic resource requirements can be quantified using a basic demand intensity value; the higher the basic demand intensity value for a certain key functional indicator, the stronger the basic resource requirement for that key functional indicator.

[0093] For example, the agent coordinator can pre-set the business type. Business requirements The mapping relationship between the basic demand intensity values ​​of each key functional indicator can be used to leverage the business type of the tasks to be processed. and business needs The basic demand intensity values ​​for each key functional indicator are obtained through table lookup or calculation. For example, the agent coordinator can also utilize a trained artificial intelligence model to classify the business types of the tasks to be processed. and business needs The mapping is to the basic demand intensity value for each key functional indicator.

[0094] Step S303: Based on the intent information, intent priority, security priority, and basic resource requirements, obtain the indicator capability requirements of the task to be processed for each key functional indicator.

[0095] After obtaining the basic resource requirements of the task to be processed for each key functional indicator, the indicator capability requirements of the task to be processed for each key functional indicator can be obtained based on the intent information, intent priority, security priority and basic resource requirements of the task to be processed.

[0096] For example, in this step, the weight vector of the task to be processed for each key functional indicator can be calculated based on the intent priority, security priority, and basic resource requirements of the task to be processed for each key functional indicator. Then, based on the weight vector of the task to be processed for each key functional indicator and the intent information of the task to be processed, the indicator capability requirements of the task to be processed for each key functional indicator can be obtained. For example, the task to be processed for the first... The capability requirements of key functional indicators can be expressed as follows: ,in It is a demand intensity calculation function used to calculate the intent vector. For the first The intensity of demand for key functional indicators It is the first The weight vector of key functional indicators. For example, It can be represented as ,in For the first The basic demand intensity value of key functional indicators It is an influencing factor on the priority of intent. It is a safety priority influencing factor. Represents the priority scalar of intent. Security priority coding.

[0097] Therefore, the intent vector can be... The represented intent information is converted into quantified capability requirements for key functional indicators of the same communication network. For example, this can be achieved through a global indicator requirement vector. Reflecting the expected strength of the tasks to be processed for various key functional indicators of the communication network:

[0098]

[0099] In the formula, M represents the number of key functional indicators of the communication network. For the pending task to the first The indicator capability requirements for each key functional indicator are defined as follows: the higher the value of the indicator capability requirement, the stronger the requirement for that key functional indicator. This includes the global indicator requirement vector. It can cover all key functional indicators related to each functional layer of a communication network (such as the application layer, network layer, physical layer, etc.).

[0100] Step S304: Based on the indicator capability requirements of each key functional indicator corresponding to each functional layer in the communication network, obtain the layer capability requirements corresponding to each functional layer.

[0101] In a communication network, each key functional indicator can correspond to a functional layer, and each functional layer can have one or more corresponding key functional indicators. Therefore, based on the correspondence between key functional indicators and functional layers, the indicator capability requirements of each key functional indicator corresponding to each functional layer of the communication network can be extracted to obtain the layer capability requirements of the task to be processed for each functional layer.

[0102] For example, suppose the communication network includes a functional layer. Functional layer Functional layer Then, it can be derived from the global indicator demand vector. Extract the indicator and capability requirements corresponding to each functional layer to form a layer-specific resource requirement vector. .

[0103] In this embodiment, the basic resource requirements of the task to be processed for each key functional indicator are obtained according to the business type and business requirements corresponding to the task to be processed. Then, the indicator capability requirements of the task to be processed for each key functional indicator are obtained according to the intent information, intent priority, security priority and basic resource requirements. Finally, the layer capability requirements corresponding to each functional layer are obtained. This can achieve accurate mapping between user communication intent and key functional indicators corresponding to each functional layer in the communication network under different task scenarios, which is conducive to improving the accuracy of task allocation between functional layers.

[0104] In an exemplary embodiment, determining whether a functional layer independently meets the corresponding layer capability requirements based on the resource capability parameters of each functional layer may include: obtaining the indicator capability parameters of each resource instance of the functional layer for each key functional indicator based on the resource capability parameters of the functional layer; determining whether the functional layer has a resource allocation scheme that meets the indicator capability requirements of each key functional indicator in the layer capability requirements based on the indicator capability parameters of each resource instance; if yes, then it is determined that the functional layer independently meets the corresponding layer capability requirements; if no, then it is determined that the functional layer does not meet the corresponding layer capability requirements.

[0105] The agent coordinator can acquire resource capability parameters for each functional layer. These parameters indicate the resource capabilities that the functional layer can provide under its current or estimated state. Based on these parameters and the corresponding key functional indicators, the capability parameters for each resource instance within a functional layer corresponding to each key functional indicator can be obtained. These parameters can be used to measure the available capability of a specific resource instance within a functional layer for a particular key functional indicator.

[0106] For example, the indicator capability parameters of each functional layer can be represented in the form of a capability matrix, with the communication network including the application layer. Network layer Physical layer For example, a capability matrix can be defined. For example, the capability matrix of each functional layer can be dynamically maintained through periodic updates or other means.

[0107] For example, the application layer The corresponding capability matrix can be represented as:

[0108]

[0109] Where I represents the application layer The number of resource instances (such as edge server instances, application-specific gateways, SaaS instances, etc.), where X represents the application layer. The number of key functional indicators (such as available encoding / decoding schemes and efficiency, application-layer caching capacity, application-layer acceleration algorithm capacity, computing resource availability, application processing latency, etc.). Represents the application layer The metric capability parameters of the I-th resource instance for the X-th key function indicator in its current or estimated state.

[0110] For example, the network layer The corresponding capability matrix can be represented as:

[0111]

[0112] Where J represents the network layer The number of resource instances (such as SDN paths, network slice instances, QoS queues, etc.), where Y represents the network layer. The number of key functional indicators (such as path available bandwidth, path latency, path jitter, path packet loss rate, queue status, slice resource availability, SDN rule processing capability, etc.). Represents network layer The indicator capability parameters of the Jth resource entity or path for the Yth key functional indicator in the current or estimated state.

[0113] For example, the physical layer The corresponding capability matrix can be represented as:

[0114]

[0115] Where K represents the physical layer The number of resource instances (such as cells, beams, spectrum blocks, etc.), where Z represents the physical layer. The number of key functional indicators (such as radio frequency spectrum resources (time / frequency / space), channel quality, reference signal received power / quality / strength, signal-to-noise ratio, number of supported MIMO layers, highest supported modulation order, etc.). Represents the physical layer The indicator capability parameters of the Kth resource entity or channel for the Zth key functional indicator in the current or estimated state.

[0116] Specifically, based on the indicator capability parameters of each resource instance in the functional layer for each key functional indicator, it can be determined whether there is a resource allocation scheme that meets the indicator capability requirements of each key functional indicator in the corresponding layer capability requirements.

[0117] For example, the layer capability requirements corresponding to a functional layer can be represented as a layer-specific resource requirement vector. Among them, for The capability requirements for each key functional indicator in the system It can be done in the corresponding functional layer. Internally, it searches for the existence of at least one resource allocation scheme (which may include one resource instance or a combination of multiple resource instances) that enables the allocation of resources to the resource allocation scheme. All indicator capability requirements All of these can be achieved. ,in For the first under this resource allocation scheme The indicator values ​​for key functional metrics. For example, Based on the resource allocation scheme and the model function of this functional layer, A decision can be expressed as:

[0118]

[0119] In the formula, The set of resource instances corresponding to the resource allocation scheme. These are the performance parameters for each resource instance in the functional layer for each key functional indicator. This is a model function, used to determine the model based on... Calculate the effect of each resource allocation scheme on the first The key functional indicators can achieve the following indicator values.

[0120] Among them, if the functional layer If at least one resource allocation scheme exists that satisfies the capability requirements of all key functional indicators corresponding to a functional layer, then the functional layer can be determined. The corresponding layer's capability requirements must be met independently; otherwise, the functional layer can be determined. The corresponding layer capability requirements have not been met.

[0121] In this embodiment, by obtaining the indicator capability parameters of each resource instance for each key functional indicator based on the resource capability parameters of the functional layer, and then constructing the layer capability matrix, the feasibility of each resource allocation scheme in the functional layer to meet the layer capability requirements can be fully evaluated, which is conducive to improving the accuracy of the allocation between functional layers of the task to be processed.

[0122] In one exemplary embodiment, such as Figure 4 As shown, if a functional layer does not meet the corresponding layer capability requirements, then based on the layer capability requirements and the resource capability parameters of each functional layer, the second subtask corresponding to each functional layer is obtained, which may include:

[0123] Step S401: Based on the resource capability parameters of each functional layer and the corresponding layer capability requirements, obtain the capability gap of the task to be processed.

[0124] Specifically, when a functional layer cannot independently meet its corresponding layer capability requirements, the resource capabilities of multiple functional layers can be utilized to meet the layer's capability requirements through cross-layer intelligent agent collaboration.

[0125] In this step, the required capability gap for the task to be processed can be calculated based on the resource capability parameters of each functional layer and its corresponding layer capability requirements. The required capability gap for the task to be processed can include the layer capability gap between the resource capabilities provided by each functional layer in the communication network and its corresponding layer capability requirements. It is understood that when a functional layer can independently meet its corresponding layer capability requirements, that functional layer has no corresponding layer capability gap. For example, the required capability gap for the task to be processed can be the sum of the layer capability gaps corresponding to all functional layers.

[0126] For example, for a functional layer that cannot independently meet the corresponding layer capability requirements, the capability gap between the resource capabilities of that functional layer and the capability requirements of each key functional indicator in the corresponding layer capability requirements can be calculated. Then, the layer capability gap corresponding to that functional layer can be obtained based on the capability gap of each key functional indicator. For example, the layer capability gap corresponding to a functional layer can be the sum of the capability gaps of each indicator corresponding to that functional layer.

[0127] For example, the capability gap of functional layer L for the nth key functional indicator corresponding to that functional layer can be expressed as:

[0128]

[0129] in, For functional layer L, key functional indicators The gap in the capacity of the layer, For the capability requirements of the nth key functional indicator, This represents the maximum value of the indicator that can be achieved by each resource allocation scheme in functional layer L for the nth key functional indicator.

[0130] Step S402: Based on the resource capability parameters of each functional layer and the indicator capability requirements of each key functional indicator corresponding to the task to be processed, obtain the layer capability efficiency of each functional layer.

[0131] Specifically, based on the capability requirements of each key functional indicator corresponding to the task to be processed, and the resource capability parameters of each functional layer, the layer capability efficiency of each functional layer for each key functional indicator can be calculated. For example, the layer capability efficiency of functional layer L for the k-th key functional indicator corresponding to the task to be processed can be expressed as:

[0132]

[0133] In the formula, Let L be the layer capability efficiency of the functional layer for the k-th key functional indicator corresponding to the task to be processed. For the capability requirements of the k-th key functional indicator, This represents the maximum value of the indicator that can be achieved by each resource allocation scheme in functional layer L for the k-th key functional indicator.

[0134] The higher the value of the layer capability effectiveness of a certain key functional indicator, the more sufficient the available capabilities that the functional layer can provide for that key functional indicator, and the easier it is to meet the indicator capability requirements of that key functional indicator.

[0135] Step S403: Based on the layer capability efficiency of each functional layer, the business adaptation parameters with the task to be processed, and the resource efficiency parameters of the functional layer, the task allocation weight of each functional layer is obtained.

[0136] In this communication network, each functional layer can have corresponding service adaptation parameters for different service types. The higher the value of the service adaptation parameter, the higher the functional adaptability of that functional layer to the communication task of that service type. For example, the agent coordinator can store the mapping relationship between each functional layer and its service adaptation parameters for different service types, so as to obtain the service adaptation parameters of each functional layer and the task to be processed according to the service type of the task to be processed.

[0137] The resource efficiency factor for each functional layer represents its current resource utilization level. A higher resource efficiency factor indicates that the functional layer's resource capacity is being used more and its available capacity is less. For example, the resource efficiency factor for a functional layer can be calculated based on the total resource supply, current resource consumption, and resource scarcity weight of each resource instance within that functional layer, as shown in the following formula:

[0138]

[0139] In the formula, This is the resource efficiency factor for functional layer L. This represents the resource scarcity weight of the j-th resource instance in functional layer L. Let be the current resource consumption of the j-th resource instance. Let be the total resource supply for the j-th resource instance. A higher resource scarcity weight indicates a higher scarcity of the resource instance.

[0140] Specifically, the task allocation weight of each functional layer can be calculated based on its layer capability effectiveness, service adaptation parameters to the tasks to be processed, and resource efficiency parameters. For example, a communication network includes functional layers. Functional layer Functional layer For example, the functional layer The task allocation weights can be expressed as:

[0141]

[0142]

[0143] In the formula, Assign weights to the tasks in functional layer L. Assign initial weights to the tasks in functional layer L. A dynamically adjustable demand-cost balance factor ( ), Let L be the layer capability efficiency of the functional layer for the k-th key functional indicator corresponding to the task to be processed. The parameters for adapting the functional layer L to the business requirements of the task to be processed. This is the resource efficiency factor for functional layer L. The business sensitivity factor is the k-th key functional indicator corresponding to the task to be processed, which can be determined according to the business type of the task to be processed.

[0144] Step S404: Based on the task allocation weight of each functional layer, the demand capacity gap is allocated to obtain the second sub-task corresponding to each functional layer.

[0145] Specifically, based on the task allocation weights of each functional layer, the overall capability gap for the task to be processed can be allocated. By distributing the capability gaps across multiple functional layers, each functional layer can be responsible for meeting a portion of the capability gap, thus obtaining the corresponding second sub-task for each functional layer. The higher the task allocation weight of a functional layer, the higher the capability requirement corresponding to its assigned second sub-task.

[0146] In this embodiment, by calculating the task allocation weight of each functional layer based on the resource capability parameters, layer capability efficiency, business adaptation parameters, and resource efficiency parameters of each functional layer, and then allocating tasks to the demand capability gap according to the task allocation weight, the accurate allocation of cross-layer tasks can be achieved based on the actual resource situation of each functional layer and its adaptability to the business.

[0147] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0148] Based on the same inventive concept, this application also provides an intent-based task processing system. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more intent-based task processing device embodiments provided below can be found in the limitations of the intent-based task processing method above, and will not be repeated here.

[0149] In one exemplary embodiment, such as Figure 5 As shown, an intent-based task processing system is provided, including: an edge-side agent and a network-side agent coordinator.

[0150] The edge-side intelligent agent is used to acquire task scenario data, user behavior data, and user preference information of the task to be processed; obtain the intent information of the task to be processed based on the task scenario data, the user behavior data, and the user preference information; and send the intent information to the network-side intelligent agent coordinator.

[0151] The network-side intelligent agent coordinator is used to receive the intent information and, based on the intent information, obtain the layer capability requirements of the task to be processed for each functional layer in the communication network.

[0152] The network-side intelligent agent coordinator is also used to determine whether the functional layer independently meets the corresponding layer capability requirements based on the resource capability parameters of each functional layer.

[0153] The network-side intelligent agent coordinator is further configured to, if the functional layer independently meets the corresponding layer capability requirements, obtain the first subtask corresponding to the functional layer based on the layer capability requirements and the resource capability parameters of the functional layer;

[0154] The network-side intelligent agent coordinator is further configured to, if the functional layer does not meet the corresponding layer capability requirements, obtain a second subtask corresponding to each functional layer based on the layer capability requirements and the resource capability parameters of each functional layer.

[0155] The network-side intelligent agent coordinator is further configured to assign each of the first subtasks and / or the second subtasks corresponding to the task to be processed to the corresponding functional layers.

[0156] Specifically, the edge-side intelligent agent can be deployed on the user's terminal, while the network-side intelligent agent coordinator can be deployed on the communication network. The edge-side intelligent agent can be deployed on the user's terminal device that needs to perform pending tasks. It can utilize various embedded sensors and hardware / software interfaces on the terminal device to collect task scenario data and user behavior data corresponding to the pending tasks, as well as obtain the user's preference information. For example, task scenario data may include, but is not limited to, location, timestamps, ambient light / noise conditions, and network signal strength; user behavior data may include, but is not limited to, user movement status, application running status, and user service type; and user preference information may include, but is not limited to, preferred interaction patterns, network connection switching strategies, communication terminal tolerance, and privacy leakage risk tolerance.

[0157] The edge-side intelligent agent can utilize an artificial intelligence model to parse user intent based on collected task scenario data, user behavior data, and user preference information to obtain the intent information output by the model. For example, this artificial intelligence model can be a lightweight model deployed on the terminal device. Subsequently, the edge-side intelligent agent can send the intent information to the network-side intelligent agent coordinator.

[0158] The network-side agent coordinator can receive intent information corresponding to the task to be processed provided by the end-side agent, process the information to obtain the first subtask and / or the second subtask corresponding to the task to be processed, and distribute them to the functional layers in the communication network. The implementation scheme for the network-side agent coordinator to process the intent information is similar to the implementation scheme described in one or more of the above method embodiments, and will not be repeated here.

[0159] In one exemplary embodiment, such as Figure 6 As shown, a task processing system based on user intent is provided.

[0160] Specifically, such as Figure 6 As shown, the task processing system in this embodiment may include an edge-side intelligent agent, a network-side intelligent agent coordinator, a network-side intelligent agent, and a cloud-side intelligent agent. The edge-side intelligent agent can be deployed on the user's terminal and can be used to parse the user's communication intent. The network-side intelligent agent coordinator, network-side intelligent agent, and cloud-side intelligent agent can be deployed on a communication network, which may include functional layers such as the application layer, network layer, and physical layer. The network-side intelligent agent may include intelligent agents in the network layer functional modules and intelligent agents in the physical layer modules, while the cloud-side intelligent agent may include intelligent agents in the application layer functional modules. The network-side intelligent agent coordinator can quantify the user's communication intent into a resource demand vector across the application layer, network layer, and physical layer between the network-side and cloud-side intelligent agents. Based on the resource and capability status of each layer, it generates a task allocation strategy across the application layer, network layer, and physical layer between the network-side and cloud-side intelligent agents, achieving accurate mapping and on-demand invocation of multi-dimensional network / cloud resources to the user's communication intent.

[0161] In this embodiment, the system can be configured as follows: Figure 7 The process shown is for handling the task at hand:

[0162] In step S701, the edge-side intelligent agent perceives user behavior and scene characteristics, combines user personalized preferences, utilizes a local lightweight small model to parse user communication intent in real time, and generates a structured description to obtain the intent information corresponding to the task to be processed.

[0163] For example, taking the system in this embodiment as a remote robot-assisted surgery system, its core business can be that experts from a top-tier hospital remotely operate a robotic arm to remove tumors from patients. The key business requirements it needs to meet can include: motion fidelity meeting 0.1mm level tremor suppression, visual fidelity meeting 4K / 120fps / 10bit color depth, operation continuity meeting 99.999% uninterrupted, and safety fault tolerance meeting 20ms emergency braking response. The environmental challenges it faces include heterogeneous 5G networks in urban and rural areas, electromagnetic interference in operating rooms, and sudden network congestion.

[0164] Among them, the edge-side intelligent agent can collect task scenario data and user behavior data of the task to be processed through embedded sensors on the terminal device, such as the surgical stage, the current position coordinates of the robotic arm, operation instructions (such as the high-frequency electrosurgical cutting trajectory and force feedback data), environmental parameters (the need for enhanced display of blood vessels at the edge of the tumor), and user preference information such as safety constraints (medical compliance standard ISO 13482).

[0165] The edge-side agent can utilize a local lightweight model and a medical knowledge base engine to analyze user communication intent from collected multi-dimensional data and convert it into structured intent information. For example, the intent can be represented as: {"Business Type": robotic surgery, "Business Requirements": displacement error ≤ 0.08mm, visual latency ≤ 120ms, emergency response ≤ 20ms, "Intent Priority": highest, "Safety Priority": highest}. Subsequently, the edge-side agent can send the intent information of the task to be processed to the agent coordinator.

[0166] In step S702, the agent coordinator receives a structured description of the user's communication intent (i.e., intent information).

[0167] In step S703, the agent coordinator generates an intent vector based on the structured description of the user's communication intent.

[0168] The agent coordinator can receive intent information and generate an intent vector based on that information. For example, the intent vector... It can be represented as:

[0169]

[0170] in, Represents the business type encoding vector. Represents the business requirement encoding vector. Represents the priority scalar of intent. Security priority encoding. Intent information to intent vector. The transformation can be achieved through a pre-trained intent model or a fixed rule mapping table.

[0171] In step S704, the agent coordinator decomposes the user's communication intent into layer capability requirements for the application layer, network layer, and physical layer based on the intent vector.

[0172] The communication network can have multiple key functional indicators, each of which can correspond to a functional layer, and each functional layer can have one or more corresponding key functional indicators. For example, a remote robot-assisted surgery system may include the key functional indicators shown in Table 1.

[0173] Table 1

[0174]

[0175] The intelligent agent coordinator can calculate the basic resource requirements of the task to be processed for each key functional indicator based on the business type and business needs of the task to be processed. Then, based on the intent information, intent priority, security priority and basic resource requirements, it can obtain the indicator capability requirements of the task to be processed for each key functional indicator.

[0176] In step S705, the agent coordinator determines whether each functional layer independently meets its corresponding layer capability requirements based on the intent vector and the resource capability parameters of each functional layer. If a layer can independently meet its corresponding layer capability requirements, then based on the layer capability requirements and the resource capability parameters of that functional layer, a first subtask corresponding to that functional layer is obtained, and the first subtask is sent to the corresponding functional layer. If a layer cannot independently meet its corresponding layer capability requirements, then based on the layer capability requirements and the resource capability parameters of each functional layer, a second subtask corresponding to that functional layer is obtained, and the second subtask is sent to the corresponding functional layer.

[0177] The agent coordinator can acquire resource capability parameters for each functional layer. These parameters indicate the resource capabilities that the functional layer can provide under its current or estimated state. Based on these parameters and the corresponding key functional indicators, the capability parameters for each resource instance within a functional layer corresponding to each key functional indicator can be obtained. These parameters can be used to measure the available capability of a specific resource instance within a functional layer for a particular key functional indicator.

[0178] Specifically, the agent coordinator can determine whether a functional layer has a resource allocation scheme that satisfies the indicator capability parameters of each key functional indicator in its corresponding layer capability requirements, based on the indicator capability parameters of each resource instance in the functional layer. If such a scheme exists, it can be determined that the layer can independently meet the corresponding layer capability requirements; otherwise, it can be determined that the layer cannot independently meet the corresponding layer capability requirements.

[0179] For functional layers that can independently meet their corresponding capability requirements, the first subtask for that functional layer can be derived based on the capability requirements and resource capability parameters of that functional layer. For layer capability requirements that cannot be independently met by the corresponding functional layer, they can be decomposed into multiple second subtasks corresponding to different functional layers.

[0180] For example, when the capability requirements of one or more layers corresponding to a task to be processed cannot be independently met by the corresponding functional layer, the capability gap corresponding to the task to be processed can be calculated first, and the task allocation weight of each functional layer can be calculated separately. Then, the capability gap can be allocated to each functional layer to obtain the second sub-task corresponding to each functional layer. Specifically, when calculating the task allocation weight of each functional layer, the demand-cost balance factor can be obtained first based on the business type of the task to be processed. Business Sensitivity Factor Business adaptation parameters For example, when the business type is "robotic surgery", the demand-cost balance factor... It can be 0.85, a business adaptation parameter. It can be ,in , , These represent the application layer, network layer, and physical layer, respectively, and the service sensitivity factor. It can be This means that the key functional indicator k4 (path reliability) is the most sensitive. Furthermore, the layer capability effectiveness of each functional layer can also be calculated. and resource efficiency factor Then you can use the formula , Calculate the task allocation weights for each functional layer.

[0181] For example, after the task allocation is completed, the sub-tasks corresponding to the physical layer may include: activating millimeter-wave beamforming and reserving 100MHz of anti-interference spectrum; the sub-tasks corresponding to the network layer may include: enabling three-link redundant transmission, deploying TSN emergency channels, and real-time reliability monitoring; the sub-tasks corresponding to the application layer may include: loading real-time HDR rendering algorithms on the edge cloud and setting up anti-packet loss compression strategies.

[0182] In step S706, each layer of functional modules receives the first subtask and / or the second subtask sent by the agent coordinator, parses the subtask of its layer, and feeds back the parsing results to the agent coordinator.

[0183] In step S707, the agent coordinator receives the parsing results of the sub-tasks from each functional module and performs a requirement matching test between the parsing results and the intent information of the task to be processed. If the requirements match, the agent notifies each functional module to perform the operation according to the parsing results and notifies the end-side agent that the user's communication intent has matched; otherwise, the agent analyzes and generates the reason for the requirement mismatch and feeds back the reason to each functional module, notifying each functional module to perform sub-task parsing again. If each functional module receives a notification to perform sub-task parsing again, steps S706 and S707 are repeated until the communication requirements with the user are aligned.

[0184] Based on the same inventive concept, this application also provides an intent-based task processing apparatus for implementing the intent-based task processing method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more intent-based task processing apparatus embodiments provided below can be found in the limitations of the intent-based task processing method described above, and will not be repeated here.

[0185] In one exemplary embodiment, such as Figure 8 As shown, an intent-based task processing device is provided, comprising:

[0186] The intent receiving module 801 is used to receive intent information corresponding to the task to be processed.

[0187] The requirement parsing module 802 is used to obtain the layer capability requirements of the task to be processed for each functional layer in the communication network based on the intent information.

[0188] The requirement adaptation module 803 is used to determine whether the functional layer independently meets the corresponding layer capability requirements based on the resource capability parameters of each functional layer.

[0189] The first task generation module 804 is used to obtain the first subtask corresponding to the functional layer based on the layer capability requirements and the resource capability parameters of the functional layer if the functional layer independently meets the corresponding layer capability requirements.

[0190] The second task generation module 805 is used to obtain a second sub-task corresponding to each functional layer based on the layer capability requirements and the resource capability parameters of each functional layer if the functional layer does not meet the corresponding layer capability requirements.

[0191] The subtask allocation module 806 is used to allocate each of the first subtasks and / or the second subtasks corresponding to the task to be processed to the corresponding functional layers.

[0192] In an exemplary embodiment, the requirement parsing module 802 is configured to: obtain, based on the intent information, the service type, service requirement, intent priority, and security priority corresponding to the task to be processed; obtain, based on the service type and the service requirement, the basic resource requirements of the task to be processed for each key functional indicator of the communication network; obtain, based on the intent information, the intent priority, the security priority, and the basic resource requirements, the indicator capability requirements of the task to be processed for each of the key functional indicators; and obtain, based on the indicator capability requirements of each key functional indicator corresponding to each functional layer in the communication network, the layer capability requirements corresponding to each functional layer.

[0193] In an exemplary embodiment, the requirement adaptation module 803 is configured to: obtain the indicator capability parameters of each resource instance of the functional layer for each key functional indicator based on the resource capability parameters of the functional layer; determine whether the functional layer has a resource allocation scheme that satisfies the indicator capability requirements of each key functional indicator in the layer capability requirements based on the indicator capability parameters of each resource instance; if yes, determine that the functional layer independently satisfies the corresponding layer capability requirements; if no, determine that the functional layer does not satisfy the corresponding layer capability requirements.

[0194] In an exemplary embodiment, the second task generation module 805 is configured to: obtain the required capability gap of the task to be processed based on the resource capability parameters of each functional layer and the corresponding layer capability requirements; obtain the layer capability efficiency of each functional layer based on the resource capability parameters of each functional layer and the indicator capability requirements of each key functional indicator corresponding to the task to be processed; obtain the task allocation weight of each functional layer based on the layer capability efficiency of each functional layer, the business adaptation parameters with the task to be processed, and the resource efficiency parameters of the functional layer; and allocate tasks to the required capability gap according to the task allocation weight of each functional layer to obtain the second sub-task corresponding to each functional layer.

[0195] In an exemplary embodiment, the intent information is sent by the edge agent; the intent information is obtained by the edge agent based on the task scenario data, user behavior data, and user preference information of the task to be processed.

[0196] The modules in the aforementioned intent-based task processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in hardware or independent of the processor in the network device, or stored in software in the memory of the network device, so that the processor can invoke and execute the operations corresponding to each module.

[0197] In one exemplary embodiment, a network device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 9 As shown, this network device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores intent information corresponding to the tasks to be processed, resource capability parameters of the functional layers, and other data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements an intent-based task processing method.

[0198] Those skilled in the art will understand that Figure 8The structure shown is merely a block diagram of a portion of the structure related to the solution of this application and does not constitute a limitation on the network device to which the solution of this application is applied. Specific network devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0199] In one embodiment, a network device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0200] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0201] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0202] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0203] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0204] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0205] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. An intent-based task processing method, characterized by, The method comprises: receiving intention information corresponding to a to-be-processed task; obtaining layer capability requirements of each functional layer in a communication network for the to-be-processed task according to the intention information; determining whether the functional layer independently satisfies the corresponding layer capability requirement according to the resource capability parameter of each functional layer; if the functional layer independently satisfies the corresponding layer capability requirement, obtaining a first subtask corresponding to the functional layer according to the layer capability requirement and the resource capability parameter of the functional layer; if the functional layer does not satisfy the corresponding layer capability requirement, obtaining a second subtask corresponding to each functional layer according to the layer capability requirement and the resource capability parameter of each functional layer; allocating each first subtask and / or second subtask corresponding to the to-be-processed task to each corresponding functional layer.

2. The method of claim 1, wherein, The obtaining of the layer capability requirements of each functional layer in the communication network for the to-be-processed task according to the intention information comprises: obtaining a service type, a service requirement, an intention priority and a security priority corresponding to the to-be-processed task according to the intention information; obtaining basic resource requirements of each key function indicator of the communication network for the to-be-processed task according to the service type and the service requirement; obtaining indicator capability requirements of each key function indicator for the to-be-processed task according to the intention information, the intention priority, the security priority and the basic resource requirement; obtaining layer capability requirements corresponding to each functional layer according to the indicator capability requirements of each key function indicator corresponding to each functional layer in the communication network.

3. The method of claim 1, wherein, The determination of whether the functional layer independently satisfies the corresponding layer capability requirement according to the resource capability parameter of each functional layer comprises: obtaining indicator capability parameters of each key function indicator for each resource instance of the functional layer according to the resource capability parameter of the functional layer; determining whether there is a resource allocation scheme that satisfies the indicator capability requirement of each key function indicator in the layer capability requirement for the functional layer according to each indicator capability parameter of each resource instance; if yes, determining that the functional layer independently satisfies the corresponding layer capability requirement; if no, determining that the functional layer does not satisfy the corresponding layer capability requirement.

4. The method of claim 1, wherein, The obtaining of the second subtask corresponding to each functional layer if the functional layer does not satisfy the corresponding layer capability requirement comprises: obtaining a requirement capability gap of the to-be-processed task according to the resource capability parameter of each functional layer and the corresponding layer capability requirement; obtaining a layer capability efficiency of each functional layer according to the resource capability parameter of each functional layer and the indicator capability requirement of each key function indicator corresponding to the to-be-processed task; obtaining a task allocation weight of each functional layer according to the layer capability efficiency of each functional layer, a service adaptation parameter of the to-be-processed task and a resource efficiency parameter of the functional layer; According to the task allocation weight of each function layer, the demand capability gap is allocated to obtain a second sub-task corresponding to each function layer.

5. The method according to any one of claims 1 to 4, characterized in that, The intent information is sent by an end-side agent; and the intent information is obtained by the end-side agent according to task scene data, user behavior data and user preference information of the to-be-processed task.

6. A user-intention-based task processing system, characterized by, The system comprises an end-side agent and a network-side agent coordinator. The end-side agent is configured to acquire task scene data, user behavior data and user preference information of a to-be-processed task; obtain intent information of the to-be-processed task according to the task scene data, the user behavior data and the user preference information; and send the intent information to the network-side agent coordinator. The network-side agent coordinator is configured to receive the intent information; and obtain layer capability demand of each function layer in a communication network according to the intent information. The network-side agent coordinator is further configured to determine whether the function layer independently satisfies the corresponding layer capability demand according to resource capability parameters of each function layer. The network-side agent coordinator is further configured to obtain a first sub-task corresponding to the function layer according to the layer capability demand and the resource capability parameters of the function layer if the function layer independently satisfies the corresponding layer capability demand. The network-side agent coordinator is further configured to obtain a second sub-task corresponding to each function layer according to the layer capability demand and the resource capability parameters of each function layer if the function layer does not satisfy the corresponding layer capability demand. The network-side agent coordinator is further configured to allocate each first sub-task and / or second sub-task corresponding to the to-be-processed task to each corresponding function layer. 7.A task processing apparatus based on user intention, characterized by, The apparatus comprises: An intent receiving module configured to receive intent information corresponding to a to-be-processed task; A demand analyzing module configured to obtain layer capability demand of each function layer in a communication network according to the intent information; A demand adapting module configured to determine whether the function layer independently satisfies the corresponding layer capability demand according to resource capability parameters of each function layer. A first task generating module configured to obtain a first sub-task corresponding to the function layer according to the layer capability demand and the resource capability parameters of the function layer if the function layer independently satisfies the corresponding layer capability demand. A second task generating module configured to obtain a second sub-task corresponding to each function layer according to the layer capability demand and the resource capability parameters of each function layer if the function layer does not satisfy the corresponding layer capability demand. A sub-task allocating module configured to allocate each first sub-task and / or second sub-task corresponding to the to-be-processed task to each corresponding function layer. 8.A network device, comprising a memory and a processor, wherein the memory stores a computer program, and the network device is configured to perform the method according to any one of claims 1-7. The processor executes the computer program to implement the steps of the method in any one of claims 1 to 5.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 5.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 5.

Images