Task processing method and apparatus, and related device
By collaborating with the first network element and the second and third network elements, and leveraging AI model management and business processing capabilities, the problem of task management being unable to deconstruct user intent in an open environment was solved, enabling the generation and understanding of task instances.
Patent Information
- Application Number
- PCT/CN2026/094749
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2025-05-08
- Filing Date
- 2026-05-06
- Publication Date
- 2026-11-12
AI Technical Summary
In an open environment, the task management function cannot break down or understand the user's intent, resulting in the inability to obtain the task instance requested by the user.
Through collaboration between the first network element, the second network element, and the third network element, task instances that cannot be generated locally are obtained. The AI model management of the second network element and the business processing capabilities of the third network element are then used to generate the task instances.
This solution addresses the issue of being unable to generate task instances locally on the first network element, effectively deconstructing user intents and obtaining task instances, thus achieving completeness and accuracy in task management.
Smart Images

Figure CN2026094749_12112026_PF_FP_ABST
Abstract
Description
Task processing methods, devices and related equipment
[0001] Cross-references to related applications
[0002] This application claims priority to Chinese Patent Application No. 202510591124.X, filed in China on May 8, 2025, the entire contents of which are incorporated herein by reference. Technical Field
[0003] This application belongs to the field of communication technology, specifically relating to a task processing method, apparatus, and related equipment. Background Technology
[0004] In related technologies, Task Management (TM) functions can translate or break down user task requests into task instances. Future communication networks will not only provide users with services integrating communication, perception, computing, and artificial intelligence (AI) in specific scenarios, but also services addressing open problems in open environments, such as environmental recognition and intent recognition. However, for open problems in open environments, Task Management functions cannot break down or understand user intent, and therefore cannot obtain the task instances requested by the user. Summary of the Invention
[0005] This application provides a task processing method, apparatus, and related equipment that can solve the problem that task management functions for open problems in open environments cannot decompose or understand user intent, and thus cannot obtain the task instances requested by the user.
[0006] Firstly, a task processing method is provided, including:
[0007] The first network element acquires a first message sent by the terminal, the first message including first task description information;
[0008] If the first network element is unable to generate a task instance corresponding to the first task description information locally, the first network element obtains the task instance corresponding to the first task description information through at least one of the second network element and the third network element.
[0009] Secondly, a task processing method is provided, including:
[0010] The second network element receives a third message from the first network element, the third message including information for indicating the first task description information;
[0011] The second network element sends relevant information about the task instance corresponding to the first task description information to the first network element. The task instance cannot be generated locally on the first network element, and the task instance is determined based on the relevant information of the task instance.
[0012] Thirdly, a task processing method is provided, including:
[0013] The third network element obtains the seventh message sent by the first network element, the seventh message including information for indicating the first task description information;
[0014] The third network element sends the task instance corresponding to the first task description information to the first network element, wherein the task instance cannot be generated locally on the first network element.
[0015] Fourthly, a task processing method is provided, including:
[0016] The terminal sends a first message to the first network element, the first message including first task description information;
[0017] The terminal obtains a second message sent by the first network element, the second message including at least one of the following: at least one task list related to the task instance, and at least one candidate task template related to the task instance.
[0018] Fifthly, a task processing apparatus is provided, comprising:
[0019] The first receiving module is used to acquire a first message sent by the terminal, the first message including first task description information;
[0020] The first processing module is used to obtain the task instance corresponding to the first task description information through at least one of the second network element and the third network element when the task instance corresponding to the first task description information cannot be generated locally on the first network element.
[0021] Sixthly, a task processing apparatus is provided, comprising:
[0022] The second processing module is configured to receive a third message from the first network element, the third message including information for indicating first task description information; and send relevant information of the task instance corresponding to the first task description information to the first network element, wherein the task instance cannot be generated locally on the first network element, and the task instance is determined based on the relevant information of the task instance.
[0023] In a seventh aspect, a task processing apparatus is provided, comprising:
[0024] The third processing module is used to obtain a seventh message sent by the first network element, the seventh message including information for indicating the first task description information; and to send a task instance corresponding to the first task description information to the first network element, wherein the task instance cannot be generated locally on the first network element.
[0025] Eighthly, a task processing apparatus is provided, comprising:
[0026] The third sending module is used to send a first message to the first network element, the first message including first task description information;
[0027] The fourth receiving module is used to obtain a second message sent by the first network element, the second message including at least one of the following: at least one task list related to the task instance, and at least one candidate task template related to the task instance.
[0028] A ninth aspect provides a task processing apparatus configured to perform the steps of the method described in the first aspect, or to implement the steps of the method described in the second, third, or fourth aspect.
[0029] In a tenth aspect, a terminal is provided, the terminal including a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the method as described in the fourth aspect.
[0030] Eleventhly, a terminal is provided, including a processor and a communication interface, wherein the communication interface is used to send a first message to a first network element, the first message including first task description information; and to obtain a second message sent by the first network element, the second message including at least one of the following: at least one task list related to the task instance, and at least one candidate task template related to the task instance.
[0031] In a twelfth aspect, a network-side device is provided, the network-side device including a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the method as described in the first, second, or third aspect.
[0032] In a thirteenth aspect, a network-side device is provided, including a processor and a communication interface, wherein the communication interface is used to acquire a first message sent by a terminal, the first message including first task description information; the processor is used to acquire a task instance corresponding to the first task description information through at least one of a second network element and a third network element when a task instance corresponding to the first task description information cannot be generated locally on the first network element.
[0033] Alternatively, the processor is configured to receive a third message from a first network element, the third message including information for indicating first task description information; and send relevant information of a task instance corresponding to the first task description information to the first network element, wherein the task instance cannot be generated locally on the first network element, and the task instance is determined based on the relevant information of the task instance.
[0034] Alternatively, the processor is configured to acquire a seventh message sent by the first network element, the seventh message including information for indicating first task description information; and send a task instance corresponding to the first task description information to the first network element, wherein the task instance cannot be generated locally on the first network element.
[0035] In a fourteenth aspect, a readable storage medium is provided, on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method as described in the first aspect, or implement the steps of the method as described in the second, third, or fourth aspect.
[0036] In a fifteenth aspect, a wireless communication system is provided, comprising: a terminal and a network-side device, wherein the terminal is configured to perform the steps of the method described in the fourth aspect, and the network-side device is configured to perform the steps of the method described in the first, second, and third aspects.
[0037] In a sixteenth aspect, a chip is provided, the chip including a processor and a communication interface coupled to the processor, the processor being used to run programs or instructions to implement the methods described in the first, second, third, and fourth aspects.
[0038] In a seventeenth aspect, a computer program / program product is provided, the computer program / program product being stored in a storage medium, the computer program / program product being executed by at least one processor to implement the steps of the methods described in the first aspect, the second aspect, the third aspect, and the fourth aspect.
[0039] In this embodiment, a first network element obtains a first message sent by a terminal, the first message including first task description information. If the first network element cannot generate a task instance corresponding to the first task description information locally, the first network element obtains the task instance corresponding to the first task description information through at least one of a second network element and a third network element. In the above solution, when the first network element cannot generate a task instance corresponding to the terminal's first task description information locally, it can obtain the corresponding task instance by using at least one of a second network element and a third network element, thereby solving the problem that a task instance cannot be obtained when the first network element cannot deconstruct or understand the user's intent to obtain a task instance. Attached Figure Description
[0040] Figure 1 shows a structural diagram of a communication system applicable to an embodiment of this application;
[0041] Figure 2 shows one of the flowcharts of the task processing method according to an embodiment of this application;
[0042] Figure 3 shows one of the interactive schematic diagrams of the task processing method according to an embodiment of this application;
[0043] Figure 4 shows a second interactive schematic diagram of the task processing method according to an embodiment of this application;
[0044] Figure 5 illustrates the third interactive schematic diagram of the task processing method according to an embodiment of this application;
[0045] Figure 6 illustrates the fourth interactive schematic diagram of the task processing method according to an embodiment of this application;
[0046] Figure 7 illustrates the fifth interactive schematic diagram of the task processing method according to an embodiment of this application;
[0047] Figure 8 illustrates the sixth interactive schematic diagram of the task processing method according to an embodiment of this application;
[0048] Figure 9 illustrates the seventh interactive schematic diagram of the task processing method according to an embodiment of this application;
[0049] Figure 10 shows an eighth interactive schematic diagram of the task processing method according to an embodiment of this application;
[0050] Figure 11 illustrates the ninth interactive schematic diagram of the task processing method according to an embodiment of this application;
[0051] Figure 12 illustrates the tenth interactive diagram of the task processing method according to an embodiment of this application;
[0052] Figure 13 shows a second schematic flowchart of the task processing method according to an embodiment of this application;
[0053] Figure 14 shows a third flowchart of the task processing method according to an embodiment of this application;
[0054] Figure 15 shows a schematic diagram of one of the modules of the task processing device according to an embodiment of this application;
[0055] Figure 16 shows a second schematic diagram of the task processing device according to an embodiment of this application;
[0056] Figure 17 shows a third schematic diagram of the task processing device according to an embodiment of this application;
[0057] Figure 18 shows a structural block diagram of a communication device according to an embodiment of this application;
[0058] Figure 19 shows a structural block diagram of the network-side device according to an embodiment of this application. Detailed Implementation
[0059] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.
[0060] The terms "first," "second," etc., used in this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same class, not limited in number; for example, the first object can be one or more. Furthermore, "or" in this application indicates at least one of the connected objects. For example, the scope of protection for "A or B" covers at least three scenarios: Scenario 1: including A but not B; Scenario 2: including B but not A; Scenario 3: including both A and B. In addition, the terms "A and / or B," "at least one of A and B," and "at least one of A or B" also cover at least the above three scenarios. The character " / " generally indicates that the preceding and following objects are in an "or" relationship.
[0061] The term "instruction" in this application can be either a direct instruction (or explicit instruction) or an indirect instruction (or implicit instruction). A direct instruction can be understood as one in which the sender explicitly informs the receiver of specific information, the operation to be performed, or the requested result, etc., in the instruction sent. An indirect instruction can be understood as one in which the receiver determines the corresponding information based on the instruction sent by the sender, or makes a judgment and determines the operation to be performed or the requested result, etc., based on the judgment result.
[0062] It is worth noting that the technologies described in this application are not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA), or other systems. The terms "system" and "network" in this application are often used interchangeably, and the described technologies can be used with the systems and radio technologies mentioned above, as well as with other systems and radio technologies. The following description describes New Radio (NR) systems for illustrative purposes, and the term NR is used in most of the following description; however, these technologies can also be applied to systems other than NR systems, such as 6th generation (6G) radio systems. th Generation 6G communication system.
[0063] Figure 1 shows a block diagram of a wireless communication system applicable to an embodiment of this application. The wireless communication system includes a terminal 11 and a network-side device 12. The terminal 11 can be a mobile phone, tablet computer, laptop computer, notebook computer, personal digital assistant (PDA), handheld computer, netbook, ultra-mobile personal computer (UMPC), mobile internet device (MID), augmented reality (AR), virtual reality (VR) device, robot, wearable device, flight vehicle, vehicle user equipment (VUE), shipboard equipment, pedestrian user equipment (PUE), smart home (home devices with wireless communication capabilities, such as refrigerators, televisions, washing machines, or furniture), game console, personal computer (PC), ATM, or self-service machine, etc. Wearable devices include: smartwatches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart chains, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. Among these, in-vehicle devices can also be referred to as in-vehicle terminals, in-vehicle controllers, in-vehicle modules, in-vehicle components, in-vehicle chips, or in-vehicle units, etc. It should be noted that the specific type of terminal 11 is not limited in this application embodiment. Network-side equipment 12 may include access network equipment or core network equipment, wherein access network equipment may also be referred to as Radio Access Network (RAN) equipment, radio access network function, or radio access network unit. Access network equipment may include base stations, Wireless Local Area Network (WLAN) access points (AS), or Wireless Fidelity (WiFi) nodes, etc.The term "base station" can be referred to as Node B (NB), Evolved Node B (eNB), Next Generation Node B (gNB), New Radio Node B (NR Node B), Access Point, Relay Base Station (RBS), Serving Base Station (SBS), Base Transceiver Station (BTS), Radio Base Station, Radio Transceiver, Basic Service Set (BSS), Extended Service Set (ESS), Home Node B (HNB), Home Evolved Node B, Transmit / Receive Point (TRP), or any other suitable term in the relevant field, as long as the same technical effect is achieved. The term "base station" is not limited to any specific technical terminology. It should be noted that this application embodiment only uses a base station in an NR system as an example for description and does not limit the specific type of base station.
[0064] Core network equipment, also known as core network nodes, core network functions, or core network elements, includes, but is not limited to, at least one of the following: Mobility Management Entity (MME), Access and Mobility Management Function (AMF), Session Management Function (SMF), User Plane Function (UPF), Policy Control Function (PCF), Policy and Charging Rules Function (PCRF), Edge Application Server Discovery Function (EASDF), Unified Data Management (UDM), Unified Data Repository (UDR), Home Subscriber Server (HSS), Centralized network configuration (CNC), Network Repository Function (NRF), Network Exposure Function (NEF), Local NEF (or L-NEF), and Binding Support. The core network functions include: BSF (Block Network Function), Application Function (AF), Location Management Function (LMF), Gateway Mobile Location Centre (GMLC), and Network Data Analytics Function (NWDAF). It should be noted that this application embodiment only uses core network equipment in the NR system as an example and does not limit the specific type of core network equipment. If the name of the core network equipment mentioned in this application embodiment changes in subsequent protocol versions (e.g., 6G), it will still be within the scope of protection of this application.
[0065] Optionally, the core network equipment can be implemented by one or more functional modules in a single device, or by multiple devices working together; this application does not specifically limit this. It is understood that the aforementioned functional modules can be network elements in hardware devices, software functional modules running on dedicated hardware, or virtualized functional modules instantiated on a platform (e.g., a cloud platform).
[0066] To enable those skilled in the art to better understand the embodiments of this application, the following description will be provided first.
[0067] I. Task Management (TM) Function;
[0068] TM can be used to achieve one or more of the following functions:
[0069] 1. Task Verification: Verify whether a task is a legitimate task requested by a User Equipment (UE) or Application Function (AF). Task verification includes at least one of the following: verifying whether the AF allows requesting a task template, whether the task request comes from a legitimate UE (whether the UE has a task subscription), whether the task request comes from a legitimate AF (depending on whether there is a task agreement between the TM and the AF), and whether it exceeds the maximum number of tasks associated with the UE or AF.
[0070] Optionally, if the task request originates from AF, the task verification function can be implemented by NEF.
[0071] 2. Task Template Generation: A task template is determined through negotiation with the AF (Automatic Feedback Unit). This task template is a customized task description provided by the network to the UE. It can be understood as a questionnaire where the requester "checks" mandatory or optional parameters to express their task requirements. The task template includes at least one of the following:
[0072] Task template identifier, used to identify task templates;
[0073] Task description;
[0074] Description of the Quality of Experience (QoE);
[0075] Task policy or Quality of Service (QoS) description;
[0076] Task parameters.
[0077] 3. Task Translation or Decomposition: Translate or decompose the task request into task instances, where each task instance is an ongoing task. Each task instance includes at least one of the following:
[0078] (1) Task description;
[0079] (2) Task type, used to indicate whether the task is a single task, a combined task, or multiple tasks, wherein the single task is any one of communication, perception, computing, or artificial intelligence (AI), and the combined task is any combination of the above tasks.
[0080] (3) Task strategy or QoS;
[0081] (4) Security-related parameters, used to encrypt transmitted signaling or data;
[0082] (5) Subtask type, which indicates the type of subtask and includes at least one of the following: perception, computation, AI;
[0083] (6) Subtask policy or QoS, used to indicate the quality of service requirements of the subtask.
[0084] If the subtask type is a perception subtask, then the subtask policy or QoS is the perception subtask configuration value (including specific configuration information);
[0085] If the subtask type is a computational subtask, then the subtask policy or QoS is the configuration value of the computational subtask (including specific configuration information);
[0086] If the subtask type is AI subtask, then the subtask policy or QoS is the AI subtask configuration value (including specific configuration information);
[0087] (7) Subtask timing relationships, including at least one of the following:
[0088] a. Subtask execution order, used to indicate the temporal relationship of subtask execution, including at least one of the following implementation methods:
[0089] TM informs the subsequent subtask execution node of the information of the preceding subtask execution node;
[0090] As the central control node for task execution, the preceding subtask execution node informs the TM of the results of the preceding subtask, and the TM informs the subsequent subtask execution node of the results of the preceding subtask.
[0091] For example, if a task includes a perception subtask and a computation subtask, and the TM determines that the perception subtask is a preceding subtask, then the TM informs the computation execution function of the address of the perception execution function. After the computation execution function receives data from the perception execution function, it can start executing the computation subtask.
[0092] b. Subtask bearer establishment order, used to indicate the timing relationship of subtask bearer establishment, including at least one of the following:
[0093] Randomly generated;
[0094] Concurrent creation;
[0095] Establish according to priority.
[0096] The timing relationship of the subtasks can be part of the subtask policy or QoS.
[0097] Due to differences in scenarios and requirements, the task instances can also be classified as follows: The task instances include general parameters and specific parameters. The general parameters describe the service quality requirements of the complete task and include at least one of the following: task description, task type, task policy or QoS, and security-related parameters. The specific parameters describe the service quality requirements of the specifically decomposed subtasks and include at least one of the following: subtask type, subtask policy or QoS, and subtask execution order.
[0098] It is worth noting that TM can also determine task policies or QoS, and subtask policies or QoS, through any of the following methods:
[0099] Obtain from PCF or Policy Billing;
[0100] The task policy or QoS, and subtask policy or QoS are determined based on information obtained from PCF or policy accounting functions.
[0101] 4. Assign a task identifier or task session identifier; optionally, assign a subtask identifier or subtask session identifier.
[0102] 5. Assign task slices or task network names (DNNs), and optionally, assign subtask slices or subtask DNNs.
[0103] 6. Select a subtask management function or a subtask execution function. The TM selects a subtask management function or a subtask execution function that can meet the subtask QoT. Specifically, the TM can query the NRF, UDM, or UDR to determine a suitable subtask management function or subtask execution function, or the TM can determine a suitable subtask management function or subtask execution function based on stored or maintained information (such as whether the task is supported, computing power, etc.).
[0104] II. Service request establishment process initiated by UE.
[0105] The process includes:
[0106] Step 1: The terminal sends a first request to the TM, which is used to request the allocation of network resources for the target task.
[0107] Optionally, the first request may be at least one of the following: a task channel establishment request message, a task establishment request message, or a task resource request message.
[0108] It should be noted that the first request can be forwarded to the TM by the target network element, and the target network element is at least one of the following: AMF, SMF, and control network element (the control network element has at least one of the following functions: mobility management function, connection management function, and session management function).
[0109] Step 2: TM performs the target operation, which includes at least one of the following:
[0110] Verify whether the target task is an authorized or permitted task;
[0111] Identify the task instance of the target task;
[0112] Assign at least one of the target task identifier and the target task session identifier;
[0113] Assign at least one of the target task slice and the target task DNN;
[0114] Select the target subtask management function that satisfies the subtask quality information or subtask strategy.
[0115] Step 3: TM sends a second request to the target subtask management function, the second request being used to request the creation of a subtask.
[0116] Step 4: TM obtains the response message of the second request from the target subtask management function. The response message of the second request is used to indicate the creation result of the subtask.
[0117] In this embodiment, TM interacts with the determined target subtask management function based on the second request and the response message of the second request to determine the node information for subtask execution. The target subtask management function selects a target subtask function that meets the task requirements based on the subtask strategy and subtask quality information. The target subtask function is used to execute the corresponding subtask. The aforementioned target subtask management function may include at least one of a target perception management function, a target computation management function, and a target AI management function.
[0118] Optionally, if the TM determines the order in which subtask bearers are established, the TM can interact with the corresponding task management functions according to the order of subtask bearer establishment. For example, if the task includes a sensing task and a computing task, and the TM determines that the sensing task bearer should be established first, followed by the computing task bearer, then the TM will first interact with the target sensing management function to establish the sensing task bearer, and then interact with the target computing management function to establish the computing task bearer.
[0119] Step 5: TM creates a task context based on the received subtask function information (i.e., the content contained in the response message of the second request) to record the relationship between the task requirements and the task instance.
[0120] Optionally, when receiving a similar task request, the TM can determine a task instance that can be used for the task based on the stored task context.
[0121] Optionally, the TM associates at least one of the target task identifier and the target task session identifier with at least one of the subtask identifier and the subtask session identifier.
[0122] Optionally, the TM associates the task context with the terminal. Specifically, the TM can retrieve the associated task context using the terminal identifier.
[0123] Step 6: TM sends a first response message to the UE for the first request, indicating the result of the task request.
[0124] Optionally, if the first response message is a rejection message, it may also carry at least one of the rejection reason and the rejection message, wherein the rejection reason may include, but is not limited to, at least one of the following: the number of task requests exceeds the maximum value, task requests are not allowed, or the terminal is invalid.
[0125] The tasks in this embodiment can be understood as specific business tasks, such as a 6G system providing integrated services including communication, information, sensing, and computing on demand based on external business requests. In one optional implementation, the subtask types within the target task can be classified in multiple ways. In another optional implementation, one or more subtasks obtained by decomposing the target task can be understood as subtasks associated with the target task.
[0126] For example, the subtasks may include, but are not limited to, communication subtasks, perception subtasks, computing subtasks, data subtasks, location subtasks, Internet Protocol Multimedia System (IMS) subtasks, AI subtasks, etc.
[0127] For example, the subtasks may also include, but are not limited to, computational subtasks, information processing subtasks, multimedia subtasks, immersive subtasks, and communication subtasks. Specifically, computational subtasks include AI-related computational tasks and non-AI-related computational tasks; information processing subtasks include location information processing and synesthetic information processing; and immersive subtasks include extended reality (XR) tasks and virtual reality (VR) tasks.
[0128] The term "AI unit / AI model" as used in this application can also be referred to as AI unit, AI model, ML (machine learning) model, ML unit, AI structure, AI function, AI characteristic, machine learning model, neural network, neural network function, neural network functionality, etc. Alternatively, the term "AI unit / AI model" can refer to a processing unit capable of implementing specific algorithms, formulas, processing flows, capabilities, etc., related to AI. It can also refer to a processing method, algorithm, function, module, or unit for a specific dataset. Furthermore, it can refer to a processing method, algorithm, function, module, or unit running on AI / ML related hardware such as GPUs, NPUs, TPUs, and ASICs. This invention does not impose specific limitations in these areas. Optionally, the specific dataset includes the input and / or output of the AI unit / AI model.
[0129] Optionally, the identifier of the AI unit / AI model may be an AI model identifier, an AI structure identifier, an AI algorithm identifier, or an identifier of a specific dataset associated with the AI unit / AI model, or an identifier of a specific scenario, environment, channel characteristics, or device related to the AI / ML, or an identifier of a function, characteristic, capability, or module related to the AI / ML. The present invention does not specifically limit this.
[0130] The task processing method provided in this application will be described in detail below with reference to the accompanying drawings, through some embodiments and application scenarios.
[0131] As shown in Figure 2, this application embodiment provides a task processing method, including:
[0132] Step 201: The first network element obtains the first message sent by the terminal, the first message including first task description information.
[0133] The function of the first network element in this embodiment includes task management. The first network element can be a newly added network element, such as TM. The first network element can also be co-located with existing network elements, for example, co-located with AMF, co-located with AI service management function, or co-located with computing management function, or co-located with PCF.
[0134] In some embodiments of this application, the first task description information is a description of a task customized by the terminal, or the first task description information is not a description of a task predefined by the network.
[0135] In this embodiment of the application, the task of terminal customization can be understood as the Communication Service Provider (CSP) or operator providing differentiated network connectivity services, sensing services, data services, computing power services, AI services, or integrated services of sensing, computing and intelligence to specific terminal devices or user groups based on differences in user terminal type, needs, or scenarios, through flexible network resource allocation and management technologies (such as network slicing, QoS policies, edge computing, etc.).
[0136] The aforementioned first task description information can also be described as the user's intent.
[0137] In some implementations, the first task description information is used to indicate the type of task, that is, what kind of task it is. For example, if the task is to perceive traffic congestion in a target area, the first task description information is "traffic congestion"; if the task is to park a vehicle in a suitable or designated location, the first task description information is "automatic parking". The first task description information can be a conversational, non-standardized description.
[0138] It should be noted that the first message can be forwarded from the target network element to the first network element, and the target network element includes at least one of the following: AMF, SMF, and control network element. The control network element has at least one of the following functions: mobility management function, connection management function, and session management function.
[0139] Step 202: If the first network element cannot generate a task instance corresponding to the first task description information locally, the first network element obtains the task instance corresponding to the first task description information through at least one of the second network element and the third network element.
[0140] In this embodiment of the application, the task instance is used to indicate the parameter information allocated by the network for the target task.
[0141] Optionally, in some embodiments, the task instance includes at least one of the following:
[0142] Task description information;
[0143] Task type, used to indicate whether the task is a single task, a combined task, or multiple tasks, wherein a single task is any one of communication, sensing, or computing, and a combined task is any combination of the above tasks.
[0144] Task strategy;
[0145] Task quality information;
[0146] Security-related parameters are used to encrypt transmitted signaling or data.
[0147] Subtask type, used to indicate the type of subtask, must include at least one of the following: perception, computation, AI.
[0148] In the above solution, when the first network element cannot generate a task instance corresponding to the first task description information of the terminal locally, it interacts with at least one of the second and third network elements to obtain the corresponding task instance, thereby solving the problem that the task instance cannot be obtained when the first network element cannot disassemble or understand the user's intention to obtain the task instance.
[0149] In some embodiments of this application, the function of the second network element includes at least one of the following:
[0150] AI model management, model ID allocation, model classification, model acquisition (determining suitable models based on internal needs), model storage, and model version management, etc. This second network element can be referred to as at least one of the following: AI model management function, AI model control function, AI algorithm control function, algorithm control function, or algorithm control plane;
[0151] The required sensing resources, sensing units, and data sources are determined based on the sensing service category and its internal requirements; the required data sources and data processing units are determined based on the data service category and its internal requirements; these are used for sensing service processing or data-related service processing, including data acquisition and data processing. For example, this second network element can be referred to as at least one of the following: sensing management function, data management function, sensing function, or data source node;
[0152] Used for API interface management, API registration, API format determination, API address management, API name management, and API version management, such as API interface management functions and PAI management functions.
[0153] In some embodiments of this application, when the first object includes an AI unit, the second network element includes a network element related to AI model management. For example, the second network element is referred to as at least one of the following: AI model management function, AI model library;
[0154] In the case where the first object includes a database, the second network element includes a network element related to data management functions. For example, the second network element is referred to as at least one of the following: data management function, data control function, perception management function, and perception function.
[0155] If the first object includes an API interface, the second network element includes a network element related to API management. For example, the second network element is called an API management network element or an API interface management network element.
[0156] In some embodiments of this application, the function of the third network element includes at least one of the following:
[0157] Business processing and implementation of business strategy rules. For example, this third network element may be referred to as at least one of the following: AI resource node, computing power execution node, computing power execution function, computing power execution plane, computing node, or data source node;
[0158] Used to generate, store, and forward data, for example, the third network element is referred to as at least one of the following: data source node, data execution node, data processing node.
[0159] In this embodiment of the application, when the first object includes an AI unit, the third network element includes nodes related to the processing of AI services; for example, the third network element is referred to as at least one of the following: AI resource node or computing node, computing power node, computing power execution node;
[0160] In the case where the first object includes a database, the third network element includes a network element related to at least one of the generation, storage and forwarding of data; for example, the third network element is called a data source node; the data source node may be a PCF or an Analytics Data Repository Function (ADRF), which is mainly used to store data and models.
[0161] In this embodiment, a first network element obtains a first message sent by a terminal, the first message including first task description information. If the first network element cannot generate a task instance corresponding to the first task description information locally, the first network element obtains the task instance corresponding to the first task description information through at least one of a second network element and a third network element. In the above solution, when the first network element cannot generate a task instance corresponding to the terminal's first task description information locally, it interacts with at least one of a second network element and a third network element to obtain the corresponding task instance, thereby solving the problem that a task instance cannot be obtained when the first network element cannot deconstruct or understand the user's intent to obtain a task instance.
[0162] In some embodiments of this application, the above-described task processing method further includes:
[0163] The first network element sends a second message to the terminal, the second message including at least one of the following: at least one task list related to the task instance, and at least one candidate task template related to the task instance.
[0164] Here, by providing the terminal with at least one task list associated with the task instance and at least one candidate task template associated with the task instance, the terminal can select the task to request the first network element to process.
[0165] In this embodiment of the application, the task list refers to a list consisting of multiple tasks.
[0166] In some embodiments of this application, taking automatic parking as an example, the framework of the automatic parking task template includes general parameters, perception task parameters, and computation task parameters, wherein,
[0167] General parameters: task type, task feedback time (e.g., 10s, 20s…), accuracy (e.g., 95%, 90%…);…
[0168] Sensing task parameters: sensing measurement method (UE transmits and receives, other UEs transmit and this UE receives, base station transmits and UE receives, UE transmits and base station receives, base station transmits and base station receives), sensing purpose (surrounding environment monitoring); ...
[0169] Calculation task parameters: data processing method (denoising, privacy protection, standardization, normalization, etc.), data processing latency (10s, 20s, etc.); ...
[0170] It should be understood that the above task template is a framework description (without specific numerical descriptions). The task instance is obtained after the terminal fills it in (or sets it on the terminal) or after the first network-side device combines it with the target task strategy or target task quality information.
[0171] In the embodiments of this application, the situation in which the first network element cannot locally generate a task instance corresponding to the first task description information includes at least one of the following:
[0172] The task corresponding to the first task description information does not match the first function, and the first function is the function of the first artificial intelligence AI unit or the first algorithm.
[0173] The business category corresponding to the first task description information does not match the first business category, and the first business category is the business category corresponding to the first artificial intelligence AI unit or the first algorithm.
[0174] (1) The task corresponding to the first task description information has not been determined;
[0175] The tasks in this embodiment can be understood as specific business tasks, such as a 6G system providing integrated services including communication, information, sensing, and computing on demand based on external business requests. In one optional implementation, the subtask types within the target task can be classified in multiple ways. In another optional implementation, one or more subtasks obtained by decomposing the target task can be understood as subtasks associated with the target task.
[0176] (2) The requirement corresponding to the first task description information has not been determined;
[0177] The above requirements include at least one of the following:
[0178] Regional business capacity requirements;
[0179] Payment requirements;
[0180] Coverage area requirements;
[0181] The required level of isolation;
[0182] End-to-end latency requirements;
[0183] Mobility needs;
[0184] Overall user density requirements;
[0185] Priority requirements;
[0186] Service availability requirements;
[0187] Service reliability requirements;
[0188] User equipment (UE) speed requirements.
[0189] (3) The target corresponding to the first task description information has not been determined;
[0190] The objectives here can include communication, computing power, data, intelligence, or integrated services of sensing, computing, and intelligence provided to end users or third parties. Specifically, they can include at least one of the following:
[0191] CSPs utilize network slicing services provided by operators to provide communication services to end users;
[0192] Perform configuration operations for the network slice instance;
[0193] Perform configuration operations for the network slice subnet instance;
[0194] Report performance measurement data of network slice instances to network operators (NOPs).
[0195] (4) The constraints corresponding to the first task description information have not been determined;
[0196] The constraints of this application embodiment include at least one of the following:
[0197] The message service (MnS) consumer pause mechanism needs to be supported.
[0198] A preemption mechanism needs to be supported;
[0199] The implicit intent reporting subscription mechanism needs to be supported;
[0200] Intent execution status information needs to be provided by the Intent Report;
[0201] IntentReport needs to provide support for intent conflict detection information;
[0202] IntentReport needs to provide information to support the feasibility verification of the intent;
[0203] IntentReport needs to provide information to support intent exploration and analysis;
[0204] Negotiation functionality support is required from the Intent-driven MnS Producer.
[0205] (5) The business category corresponding to the first task description information has not been determined;
[0206] The business categories in the embodiments of this application include, but are not limited to, sports, food, and travel.
[0207] (6) The first task description information is not predefined task description information;
[0208] (7) The first task description information is the description information of the task customized by the terminal;
[0209] (8) The first task description information is unprocessed by the first network element;
[0210] Wherein, the first AI unit is the AI unit on the first network element side, and the first algorithm is the algorithm on the first network element side.
[0211] In some embodiments of this application, the first network element obtains the task instance corresponding to the first task description information through at least one of the second network element and the third network element, including:
[0212] The first network element sends a third message to the second network element, the third message including at least one of the following: first service type information, first task description information, second task description information, and first instruction information;
[0213] The first network element receives the fourth message sent by the third network element or receives the fifth message sent by the application programming interface (API);
[0214] The first network element obtains at least one task instance corresponding to the task description information based on the fourth message or the fifth message;
[0215] The first service type information includes service type information corresponding to the first task description information. The service type information is used to indicate the service classification. The first indication information is used to indicate whether the first network element can generate a task instance corresponding to the first task description information locally.
[0216] The second task description information is task feature information or task auxiliary description information extracted from the first task description information based on a database or AI unit.
[0217] The fourth message includes at least one task instance corresponding to the first task description information, and the fifth message includes at least one task instance corresponding to the first task description information.
[0218] The aforementioned database can also be described as a knowledge base.
[0219] In some embodiments of this application, the fourth message is sent after the second network element and the third network element interact with each other, or after the first network element and the third network element interact with each other; the fifth message is sent after the second network element and the API interface interact with each other, or after the first network element and the API interface interact with each other.
[0220] In some embodiments of this application, the first indication information is specifically used to indicate at least one of the following: whether the task corresponding to the first task description information matches the first function, whether the business category corresponding to the first task description information matches the first business category, whether the first task description information is predefined, whether the first task description information is customized for the terminal, whether the requirement corresponding to the first task description information is determined, whether the target corresponding to the first task description information is determined, and whether the constraint condition corresponding to the first task description information is determined.
[0221] In some embodiments of this application, the aforementioned second task description information can be obtained through the following methods:
[0222] The task description information is used as input to the model, and the key features of the task description are extracted based on the model.
[0223] Alternatively, the task description can be used as input to the database, and the most relevant descriptive information can be extracted from the database as auxiliary descriptive information.
[0224] The API interface in this embodiment includes at least one of a first API interface and a second API interface. The first API interface is an internal API interface of the communication network corresponding to the first network element; the second API interface is an external API interface of the communication network corresponding to the first network element.
[0225] In this embodiment of the application, the first network element first interacts with the second network element and sends a third message to the second network element requesting to obtain the task instance corresponding to the first task description information. Then, the second network element interacts with the third network element, or the first network element interacts with the third network element, or the second network element interacts with the API interface to obtain the task instance.
[0226] In some embodiments of this application, as one implementation, before the first network element obtains the fourth message sent by the third network element, the method further includes:
[0227] The first network element obtains a sixth message sent by the second network element. The sixth message includes at least one of a first object, address information of the first object, and identifier of the first object. The first object is used to map the first task description information to a task instance. The first object includes at least one of an artificial intelligence (AI) unit and a database.
[0228] The first network element sends a seventh message to the third network element, the seventh message including at least one of the following: the first task description information, the second task description information, the address information of the first object, and the identifier of the first object; the fourth message is a response message to the seventh message.
[0229] In this embodiment of the application, the AI unit in the first object includes a second AI unit, or includes a second AI unit and a third AI unit, wherein the second AI unit is used to map the task description information to a task instance, and the third AI unit is used to obtain auxiliary information, which is information used to assist in indicating the task description information.
[0230] In this implementation, the first network element first sends a third message to the second network element, then the second network element sends a sixth message to the first network element, then the first network element sends a seventh message to the third network element, and then obtains the fourth message sent by the third network element.
[0231] In addition, in some embodiments of this application, after the first network element obtains the sixth message sent by the second network element, it can also use the first task description information as input to the first object to obtain the task instance corresponding to the first task description information.
[0232] In some embodiments of this application, as another implementation, the fourth message is sent by the third network element after receiving the tenth message sent by the second network element. The tenth message includes at least one of the following: the first task description information, the second task description information, the address information of the first object, the identifier of the first object, and the address information of the first network element.
[0233] The first object is used to map the first task description information to a task instance, and the first object includes at least one of the following: an artificial intelligence (AI) unit and a database.
[0234] In this implementation, the first network element first sends a second message to the second network element, the second network element sends a tenth message to the third network element, and then the third network element sends a fourth message to the first network element.
[0235] In some embodiments of this application, as one implementation, before the first network element obtains the fifth message sent by the application programming interface (API), the method further includes:
[0236] The first network element obtains the eighth message sent by the second network element. The eighth message includes at least one of API, API address information, API format information, and API name. The API is used to map the first task description information to a task instance.
[0237] The first network element sends a ninth message to the first object. The ninth message includes at least one of the following: the first task description information, the second task description information, the API address information, the API name, and task description information that meets the API format. The fifth message is a response message to the seventh message.
[0238] In this implementation, the first network element first sends the second message to the second network element, then the second network element sends the eighth message to the first network element, the first network element sends the ninth message to the API, and obtains the fifth message sent by the API.
[0239] In some embodiments of this application, as another implementation, the fifth message is sent by the API after receiving the ninth message sent by the second network element;
[0240] The API is used to map the first task description information to a task instance.
[0241] In this implementation, the first network element first sends the second message to the second network element, then the second network element sends the ninth message to the API, and then the API sends the fifth message to the first network element.
[0242] In some embodiments of this application, when the first network element determines the service category corresponding to the first task description information, but the task corresponding to the first task description information does not match the first function, the service category corresponding to the first task description information does not match the first service category, the constraint conditions corresponding to the first task description information are not determined, the first task description information is not a predefined task description information, the first task description information is a description information of a terminal-customized task, or the first task description information has not been processed by the first network element, the third message includes the first service type information.
[0243] Alternatively, if the first network element fails to determine the task corresponding to the first task description information, fails to determine the requirement corresponding to the first task description information, fails to determine the target corresponding to the first task description information, or fails to determine the service category corresponding to the first task description information, the third message includes at least one of the following: second instruction information, first task description information, second task description information, and first instruction information;
[0244] The second indication information is used to indicate the function of the first object, and the function of the first object includes at least one of the following:
[0245] Determine the requirements corresponding to the task description information;
[0246] Determine the target corresponding to the task description information;
[0247] Determine the business category corresponding to the task description information;
[0248] Identify the task corresponding to the task description information.
[0249] In some embodiments of this application, the first network element obtains the task instance corresponding to the first task description information through at least one of the second network element and the third network element, including:
[0250] The first network element sends a seventh message to the third network element, the seventh message including at least one of the following: first task description information, second task description information, address information of a first object, and identifier of a first object, the first object being used to map the first task description information to a task instance, the first object including at least one of an artificial intelligence (AI) unit and a database; the first network element obtains a fourth message sent by the third network element, the fourth message including at least one task instance corresponding to the first task description information.
[0251] Alternatively, the first network element sends a ninth message to the API, the ninth message including at least one of the following: the first task description information, the second task description information, the API address information, the API name, and task description information that meets the API format; the first network element obtains the fifth message sent by the API, the fifth message including at least one task instance corresponding to the first task description information.
[0252] In this embodiment of the application, the first network element can also directly interact with the third network element to obtain task instances.
[0253] In the case where the second network element includes a network element related to AI model management and the third network element includes a network element related to AI service processing, the first object includes an AI unit; for example, the second network element includes AI model management functions and the third network element includes AI resource nodes or computing nodes.
[0254] In the case where the second network element includes a network element related to data management functions, and the third network element includes a network element related to at least one of data generation, storage, and forwarding, the first object includes a database; for example, the second network element includes a data management function, and the third network element includes a data source node; the data source node may be a PCF, or an Analytics Data Repository Function (ADRF), which is mainly used to store data and models.
[0255] When the second network element includes a network element related to API management, the first object includes an API interface. The functions of the network element related to API management include API interface management, API registration, API format determination, API address management, API name management, and API version management. For example, the second network element may include an API management network element or an API interface management network element.
[0256] The task processing method of this application will be described below with reference to embodiments.
[0257] Example 1: Intent understanding and / or subtask decomposition based on AI models. In this Example 1, the first network element is TM, the second network element is AI model management function, the third network element is AI resource node, and the fourth network element's function includes computing service resource management, specifically, on-demand allocation, updating and release of computing resources, and status updating and maintenance of computing resource nodes. This fourth network element can be referred to as at least one of the following: computing power control function, computing power control plane, and AI resource management function; the fifth network element is perception management function.
[0258] Example 1a: Based on an AI model, intent is mapped to task instances, thereby enabling the understanding of users' colloquial requests involving various domains and the completion of self-task decomposition.
[0259] As shown in Figure 3, the task processing method includes:
[0260] Step 1: The terminal sends a first message to the first network element. The first message is used to request the allocation of network resources for the target task. The first message includes a first task description information.
[0261] First task description information: This indicates the type of task, that is, what kind of task it is. For example, if the task is to perceive traffic congestion in a target area, then the first task description information would be "traffic congestion"; if the task is to park a vehicle in a suitable or designated location, then the first task description information would be "automatic parking". The first task description information can be colloquial and non-standardized.
[0262] It should be noted that the first message can be forwarded to the TM by the target network element, and the target network element is at least one of the following: AMF, SMF, and control network element. The control network element has at least one of the following functions: mobility management function, connection management function, and session management function.
[0263] Step 2-1: The first network element determines the service category based on the first message.
[0264] Specifically, based on the UE's first service description information, the service category is determined, which can be sports, food, or travel.
[0265] Step 2-2: Has the first network element processed the above-mentioned service classifications before?
[0266] If it has been processed, it can be processed using at least one of the following methods:
[0267] Obtain task instances based on model inference from the processed local target AI units;
[0268] Based on the above-processed business categories, determine the address of the target AI unit (skip steps 2-3 to 2-6).
[0269] If the first network element determines that the target service category has not been processed before, proceed to steps 2-3.
[0270] The aforementioned target AI unit can be used to map the first task description information in the first message into a task instance.
[0271] Steps 2-3 (optional): The first network element sends a third message to the second network element. The third message is used to request the acquisition of the target AI unit, and the third message includes first service type information. The target AI unit includes the second AI unit.
[0272] Steps 2-4 (optional): The second network element determines the target AI unit based on the first service type information. The target AI unit can be used to map the first task description information in the first message to a task instance.
[0273] Steps 2-5 (optional): The second network element sends a sixth message to the first network element. The sixth message includes the target AI unit or the address of the target AI unit. The target AI unit can perform inference on the first network element side or on the third network element side.
[0274] 1. If the target AI unit does not occupy a large amount of storage space, it can be downloaded to TM for inference;
[0275] 2. If the target AI unit occupies a large amount of storage space, it needs to be downloaded to a third network element for inference.
[0276] Steps 2-6 (optional): The first network element takes the first task description information in the first message as the model input of the target AI unit. After the first network element performs inference for the target AI unit, it obtains the task instance.
[0277] Specifically, if steps 2-5 include the target AI unit, and the first network element can be located locally in an environment that meets the operating configuration requirements of the target AI unit, and the latency also meets the requirements, then steps 2-6 are executed.
[0278] Steps 2-7 (optional): The first network element sends a seventh message to the third network element, wherein the seventh message is an inference request from the target AI unit.
[0279] The seventh message can be sent directly from the first network element to the third network element, or forwarded through the fourth network element.
[0280] The aforementioned seventh message includes at least one of the following:
[0281] The first task description information, the second task description information, and the address information of the target AI unit.
[0282] Steps 2-8 (optional): The third network element takes at least one of the first task description information and the second task description information in the seventh message as the model input of the target AI unit. After the third network element performs inference for the target AI unit, a task instance is obtained.
[0283] Steps 2-9 (optional): The third network element sends a fourth message to the first network element. The fourth message includes a task instance.
[0284] Step 3, the first network element sends a second message to the terminal, the second message including at least one of the following:
[0285] A list of at least one task associated with the task instance;
[0286] At least one candidate task template associated with the task instance.
[0287] Step 4: The terminal sends a first request to the TM, which is used to request the allocation of network resources for the target task.
[0288] The target task is the task selected by the terminal based on the second message.
[0289] Optionally, the first request may be at least one of the following: a task channel establishment request message, a task establishment request message, or a task resource request message.
[0290] It should be noted that the first request can be forwarded to the TM by the target network element, and the target network element is at least one of the following: AMF, SMF, and control network element (the control network element has at least one of the following functions: mobility management function, connection management function, and session management function).
[0291] Step 5, TM performs the target operation, which includes at least one of the following:
[0292] Verify whether the target task is an authorized or permitted task;
[0293] Identify the task instance of the target task;
[0294] Assign at least one of the target task identifier and the target task session identifier;
[0295] Assign at least one of the target task slice and the target task DNN;
[0296] Select the target subtask management function that satisfies the subtask quality information or subtask strategy.
[0297] Step 6: The first network element sends a second request to the target subtask management function. The second request is used to request the establishment of a subtask. The target subtask management function is a subtask management function used to perform the subtask management.
[0298] Step 7: The first network element obtains the response message of the second request from the target subtask management function. The response message of the second request is used to indicate the establishment result of the subtask.
[0299] In this embodiment, TM interacts with the determined target subtask management function based on the second request and the response message of the second request to determine the node information for subtask execution. The target subtask management function selects a target subtask function that meets the task requirements based on the subtask strategy and subtask quality information. The target subtask function is used to execute the corresponding subtask. The aforementioned target subtask management function may include at least one of a target perception management function, a target computation management function, and a target AI management function.
[0300] Optionally, if the TM determines the order in which subtask bearers are established, the TM can interact with the corresponding task management functions according to the order of subtask bearer establishment. For example, if the task includes a sensing task and a computing task, and the TM determines that the sensing task bearer should be established first, followed by the computing task bearer, then the TM will first interact with the target sensing management function to establish the sensing task bearer, and then interact with the target computing management function to establish the computing task bearer.
[0301] Step 8: TM creates a task context based on the received subtask function information to record the relationship between the task requirements and the task instance.
[0302] The subtask function information is contained in the response message of the second request.
[0303] Optionally, when receiving a similar task request, the TM can determine a task instance that can be used for the task based on the stored task context.
[0304] Optionally, the TM associates at least one of the target task identifier and the target task session identifier with at least one of the subtask identifier and the subtask session identifier.
[0305] Optionally, the TM associates the task context with the terminal. Specifically, the TM can retrieve the associated task context using the terminal identifier.
[0306] Step 9: The first network element sends a first response message for the first request to the UE, which indicates the result of the task request.
[0307] Optionally, if the first response message is a rejection message, it may also carry at least one of the rejection reason and the rejection message, wherein the rejection reason may include, but is not limited to, at least one of the following: the number of task requests exceeds the maximum value, task requests are not allowed, or the terminal is invalid.
[0308] Example 1b: Example 1a is based on an AI model that maps intent to task instances, specifically sending the user's task description information from the first network element to the third network element. Example 1b, however, involves the second network element sending the user's task description information to the third network element.
[0309] As shown in Figure 4, the task processing method includes:
[0310] Step 1 is the same as step 1 in Example 1a;
[0311] Step 2-1 is the same as step 2-1 in Example 1a;
[0312] Step 2-2 is the same as step 2-2 in Example 1a;
[0313] Steps 2-3 (optional): The first network element sends a third message to the second network element. The third message is used to request the acquisition of the target AI unit, and includes first service type information and first task description information. The third message may also include second task description information.
[0314] Steps 2-4 (optional) are the same as steps 2-4 in Example 1;
[0315] Steps 2-5 (optional): The second network element sends a tenth message to the third network element. The tenth message includes the first task description information and the address of the first network element. The tenth message may also include at least one of the following:
[0316] Target AI unit;
[0317] Identification of the target AI unit;
[0318] The address of the target AI unit;
[0319] The tenth message is forwarded through the fourth network element or sent directly to the third network element.
[0320] The aforementioned target AI unit includes a second AI unit.
[0321] Optionally, the tenth message can be forwarded via a fourth network element.
[0322] Steps 2-6 (optional) are the same as steps 2-8 in Example 1.
[0323] Steps 2-7 (optional): The third network element sends a fourth message to the first network element. The fourth message includes a task instance. The fourth message can be forwarded by the fourth network element, or it can be directly sent from the third network element to the first network element.
[0324] Steps 3 to 9 are the same as steps 3 to 9 in Example 1a.
[0325] Example 2: Intent understanding and / or subtask decomposition based on a database. In this Example 2, the first network element is TM, the second network element is the data management function, the third network element is the data source node; the data source node can be PCF or Analytics Data Repository Function (ADRF). ADRF is mainly a network element used to store data and models. The fourth network element is the computation management function, and the fifth network element is the AI model management function.
[0326] Example 2a: Example 1 is based on an AI model that maps intents to task instances. This Example 2a is based on a knowledge base that maps intents to task instances, thereby enabling the understanding of users' colloquial requests involving various domains and the completion of self-task decomposition.
[0327] As shown in Figure 5, the task processing method includes:
[0328] Step 1 is the same as step 1 in Example 1a;
[0329] Step 2-1 is the same as step 2-1 in Example 1a;
[0330] Step 2-2: Has the first network element processed the above-mentioned service classifications before?
[0331] If it has been processed, it can be processed using at least one of the following methods:
[0332] Obtain task instances from the processed local target database or target knowledge base;
[0333] Based on the above-processed business categories, determine the address of the target database or target knowledge base (skip steps 2-3 to 2-6).
[0334] If the first network element determines that the target service category has not been processed before, proceed to steps 2-3.
[0335] The aforementioned target database or target knowledge base can be used to map the first task description information in the first message to a task instance.
[0336] Steps 2-3 (optional): The first network element sends a third message to the second network element. The third message is used to request the target database and includes the first service type information.
[0337] The second network element can be a data management function.
[0338] Steps 2-4 (optional): The second network element determines the target knowledge base based on the first service type information. The target knowledge base can be used to map the first task description information in the first message to task instances.
[0339] Steps 2-5 (optional): The second network element sends a sixth message to the first network element. The sixth message includes the target knowledge base, or the address of the target knowledge base.
[0340] The retrieval of the target knowledge base includes:
[0341] 1. If the target knowledge base does not occupy a large amount of storage space, it can be downloaded to TM for processing;
[0342] 2. If the target knowledge base occupies a large amount of storage space, it needs to be downloaded to a third network element for data retrieval.
[0343] Steps 2-6 (optional): The first network element takes the first task description information in the first message as input to the target knowledge base, and obtains the task instance after the first network element performs a search of the target knowledge base.
[0344] Specifically, if steps 2-5 include the target knowledge base, and the first network element can be configured locally to meet the requirements for running the target knowledge base, and the latency also meets the requirements, then steps 2-6 are executed.
[0345] Steps 2-7 (optional): The first network element sends a seventh message to the third network element, wherein the seventh message is a retrieval request for the target knowledge base.
[0346] If steps 2-5 include the target knowledge base, but the local configuration environment of the first network element does not meet the requirements for the operation of the target knowledge base, or the latency does not meet the requirements, or if steps 2-5 include the address of the target knowledge base, then the target knowledge base will be retrieved in the third network element.
[0347] The seventh message includes at least one of the following:
[0348] First task description information;
[0349] Second task description information;
[0350] Address information of the target knowledge base.
[0351] Steps 2-8 (optional): The third network element takes at least one of the first task description information and the second task description information in the seventh message as input to the target knowledge base. After the third network element performs a search of the target knowledge base, it obtains the task instance.
[0352] Steps 2-9 (optional): The third network element sends a fourth message to the first network element. The fourth message includes a task instance.
[0353] Steps 3 to 8 are the same as steps 3 to 8 in Example 1a.
[0354] Example 2b: Example 2a is based on a knowledge base, mapping intents to task instances. Specifically, the user's task description information is directly sent from the first network element to the third network element. Example 2b is based on a knowledge base, mapping intents to task instances. The difference is that the second network element sends the user's task description information to the third network element.
[0355] As shown in Figure 6, the task processing method includes:
[0356] Step 1 is the same as step 1 in Example 2a;
[0357] Step 2-1 is the same as step 2-1 in Example 2a;
[0358] Step 2-2 is the same as step 2-1 in Example 2a;
[0359] Steps 2-3 (optional): The first network element sends a third message to the second network element. The third message is used to request the target knowledge base. The third message includes first service type information and first task description information, and may also include second task description information.
[0360] Steps 2-4 (optional) are the same as steps 2-4 in Example 2a;
[0361] Steps 2-5 (optional): The second network element sends a tenth message to the third network element. The tenth message includes: first task description information and the address of the first network element. The tenth message may also include at least one of the following:
[0362] The name of the target knowledge base;
[0363] The address of the target knowledge base;
[0364] Second task description information.
[0365] Steps 2-6 (optional) are the same as steps 2-8 in Example 2a.
[0366] Steps 2-7 (optional): The third network element sends a fourth message to the first network element. The fourth message includes a task instance. The fourth message can be forwarded by the second network element, or it can be directly sent by the third network element to the first network element.
[0367] Steps 3 to 9 are the same as steps 3 to 9 in Example 2a.
[0368] Example 3: Intent understanding and / or subtask decomposition based on internal API. In this Example 3, the first network element is TM, the second network element is API management network element, the third network element is perception management function or data management function, the fourth network element is computing management function, the fifth network element is AI resource management function or computing management function, and the sixth network element is Network Exposure Function (NEF).
[0369] Example 3a:
[0370] As shown in Figure 7, the task processing method includes:
[0371] Step 1 is the same as step 1 in Example 1a;
[0372] Step 2-1 is the same as step 2-1 in Example 1a;
[0373] Step 2-2: The first network element determines whether the service classification has been processed before.
[0374] If it has been processed, the target API address can be obtained using the following method;
[0375] Based on the processed target business categories, determine the address of the target API (skip steps 2-3 to 2-6);
[0376] If the first network element determines that the target service category has not been processed before, proceed to steps 2-3.
[0377] The aforementioned target API is an internal API that can be used to map the first task description information in the first message to a task instance.
[0378] Steps 2-3 (optional): The first network element sends a third message to the second network element. The third message is used to request the target API, and the third message includes first service type information.
[0379] The API management function can be combined with the data management function.
[0380] Steps 2-4 (optional): The second network element determines the target API based on the classification of the target service. The target API can be used to map the task description in the first message to a task instance.
[0381] Steps 2-5 (optional): The second network element sends an eighth message to the first network element. The eighth message includes at least one of the following:
[0382] The address of the target API;
[0383] The name of the target API;
[0384] Input format for the target API.
[0385] Step 2-5b (optional): The second network element sends an eleventh message to the target API. The eleventh message includes at least one of the following:
[0386] The address of the target API;
[0387] The name of the target API;
[0388] Input format for the target API.
[0389] Steps 2-6 (optional): The first network element maps the first task description information to a first input that satisfies the target API input format based on the first task description information and the input format of the target API.
[0390] Steps 2-7 (optional): The first network element sends a ninth message to the target API. The ninth message includes at least one of the following: the first task description information, the second task description information, the address of the target API, and the first input.
[0391] Steps 2-8 (optional): The target API takes at least one of the first task description information, the second task description information, and the first input from the ninth message as input to obtain a task instance.
[0392] Steps 2-9 (optional): The target API sends a fifth message to the first network element. The fifth message includes the task instance.
[0393] Steps 3 to 9 are the same as steps 3 to 9 in Example 1a.
[0394] In addition, the API format management methods in this application embodiment include the following:
[0395] Method 1: When registering, the API sends its interface format to the API management function, which then sends the API's interface format to the first network element.
[0396] Method 2: The API management function determines the API interface format and notifies the API and the first network element of the determined interface format.
[0397] Example 3b: Example 3a maps intents to task instances based on an internal API. Specifically, the user's task description information is sent to the API by the first network element. This Example 3b maps intents to task instances based on an internal API interface. The difference from Example 3a is that the second network element sends the user's task description information to the internal API.
[0398] As shown in Figure 8, the task processing method includes:
[0399] Step 1 is the same as step 1 in Example 3a;
[0400] Step 2-1 is the same as step 2-1 in Example 3a;
[0401] Step 2-2 is the same as step 2-2 in Example 3a;
[0402] Steps 2-3 (optional): The first network element sends a third message to the second network element. The third message is used to request a task instance and includes first service type information and first task description information. The third message may also include second task description information.
[0403] The API management function can be combined with the data management function.
[0404] Steps 2-4 (optional): The second network element determines the target API based on the classification of the target service. The target API can be used to map the first task description in the first message to a task instance. The second network element maps user requests to inputs that satisfy the API interface format.
[0405] Step 2-5b (optional): The second network element sends the eleventh message to the target API. The eleventh message includes input conforming to the API interface format, and also includes at least one of the following:
[0406] The address of the target API;
[0407] The name of the target API;
[0408] The address of the first network element;
[0409] First task description information;
[0410] Second task description information.
[0411] Steps 2-6 (optional) are the same as steps 2-8 in Example 3a.
[0412] Steps 2-7 (optional): The target API sends a fifth message to the first network element. The fifth message includes a task instance. The fifth message can be forwarded by the second network element, or it can be sent directly to the first network element by the target API.
[0413] Steps 3 to 9 are the same as steps 3 to 9 in Example 1a.
[0414] Example 4: Intent understanding and / or subtask decomposition based on Retrieval-augmented Generation (RAG) technology. This Example 4 uses RAG technology to map intents to task instances. This allows for understanding user requests, particularly those involving colloquial language across various domains, and for decomposing them into subtasks. The difference between Example 4 and Example 1 is the addition of a third AI unit.
[0415] As shown in Figure 9, the task processing method includes:
[0416] Step 1 is the same as step 1 in Example 1a.
[0417] Step 2-1 is the same as step 2-1 in Example 1a.
[0418] Step 2-2: The first network element determines whether the target service category has been processed before.
[0419] If it has been processed, it can be processed using at least one of the following methods:
[0420] Obtain task instances based on model inference from the processed local second AI unit.
[0421] Auxiliary information is obtained based on model inference from the processed local third AI unit.
[0422] Based on the processed target business categories, determine the address of the second AI unit (skip steps 2-3 to 2-6);
[0423] Based on the processed target business categories, determine the address of the third AI unit (skip steps 2-3 to 2-6).
[0424] If the first network element determines that the target service category has not been processed before, proceed to steps 2-3.
[0425] The third AI unit can be used to map the task description in the first message into auxiliary information to assist in obtaining task instances during reasoning by the target AI unit.
[0426] The second AI unit can be used to map the task description in the first message to a task instance.
[0427] Steps 2-3 (optional): The first network element sends a third message to the second network element. The third message is used to request the target AI unit, and the third message includes first service type information. The target AI unit includes the second AI unit and the third AI unit.
[0428] Steps 2-4 (optional): The second network element determines the target AI unit based on the first service type information.
[0429] Steps 2-5 (optional): The second network element sends a sixth message to the first network element. The sixth message includes the target AI unit or the address of the target AI unit.
[0430] The target AI unit can perform inference on either the first network element side or the third network element side.
[0431] 1. If the target AI unit does not occupy a large amount of storage space, it can be downloaded to TM for inference;
[0432] 2. If the target AI unit occupies a large amount of storage space, it needs to be downloaded to a third network element for inference.
[0433] Steps 2-6 (optional): The first network element takes the first task description information and the second task description information in the first message as the model input of the target AI unit. After the first network element performs inference for the target AI unit, it obtains the task instance.
[0434] Specifically, the first network element takes the second task description in the first message as the model input of the third AI unit. After the first network element performs inference for the third AI unit, it obtains auxiliary information of the task description, namely the second task description information.
[0435] The first network element takes the first task description information and auxiliary information in the first message as the model input of the second AI unit. After the first network element performs inference for the second AI unit, it obtains the task instance.
[0436] Steps 2-7 (optional): The first network element sends a seventh message to the third network element, wherein the seventh message is an inference request from the target AI unit. This seventh message can be sent directly from the first network element to the third network element, or it can be forwarded through the fourth network element.
[0437] The aforementioned seventh message includes at least one of the following:
[0438] The first task description information, the second task description information, the address information of the second AI unit, and the address information of the third AI unit.
[0439] Steps 2-8 (optional): The third network element takes at least one of the first task description information and the second task description information in the seventh message as the model input of the target AI unit. After the third network element performs inference for the target AI unit, a task instance is obtained.
[0440] Steps 2-9 (optional): The third network element sends a fourth message to the first network element. The fourth message includes a task instance.
[0441] Steps 3 to 9 are the same as steps 3 to 9 in Example 1a.
[0442] Example 5: Intent understanding and / or subtask decomposition based on external APIs.
[0443] Example 3 maps intents to task instances based on an internal API. Example 5 maps intents to task instances based on an external API, thereby enabling the understanding of user requests that are verbally expressed and involve various domains, and the breakdown of subtasks.
[0444] As shown in Figure 10, the difference from Embodiment 3 lies in that the messages in steps 2-5b, 2-7, and 2-9 involve interaction with an external API and require forwarding through the sixth network element. In this embodiment, the sixth network element is a network open function, located between the 5G core network and external third-party application functions (and possibly some internal AFs). It is responsible for managing externally open network data, all external applications, and internal data of the 5G core network. The sixth network element provides corresponding security guarantees to ensure the security of external applications accessing the 3GPP network, providing functions such as opening up external application QoS customization capabilities, mobility state event subscription, and AF request distribution. The sixth network element may be, for example, NEF or other external interface functions.
[0445] Example 6: Intent Classification.
[0446] In this embodiment of the application, as shown in Table 1, the task descriptions can be classified according to the following dimensions:
[0447] Standardized;
[0448] Non-standardized, for example, colloquial descriptions;
[0449] An open environment, for example, data collected when designing algorithms or training AI models does not include data from the environment in which the AI model infers or the algorithm is executed;
[0450] In specific environments, such as when designing algorithms or training AI models, the data collected includes data from the environment in which the AI model infers or the algorithm executes.
[0451] Open questions, for example, those where the service functions for designing algorithms or training AI models do not include AI model inference or algorithm execution; or those where the question is not explicitly given in the request, but rather it is necessary to identify what the problem to be solved is.
[0452] Specific open questions, such as those related to designing algorithms or training AI models, including the service functions during AI model inference or algorithm execution.
[0453] Table 1
[0454] Example 7: The TM cannot identify the target task based on the task description. In this Example 7, the first network element is the TM, the second network element is the AI model management function, the third network element is the AI resource node or computing node, the fourth network element is the AI resource management function, and the fifth network element is the perception management function.
[0455] Examples 1-5 assume that the TM can identify the corresponding specific problem based on the task description information. This example 7 assumes that the TM cannot identify the specific problem based on the task description and needs to rely on the target AI unit to determine the target task, thereby handling the case where the task description provided by the user is an open question.
[0456] The main difference from Example 1 is that the target task and the target task instance need to be determined based on the target AI unit obtained from the second network element.
[0457] As shown in Figure 11, the task processing method includes:
[0458] Step 1 is the same as Step 1 in Example 1.
[0459] Step 2-1a: The first network element determines whether the classification of the target service can be determined.
[0460] If the determination cannot be made, proceed to step 2-1b. If the determination can be made, the subsequent process is the same as in Example 1.
[0461] Step 2-1b (optional): The first network element sends a third message to the second network element. The third message is used to request the acquisition of the target AI unit. The third message includes second indication information, which is used to indicate the function of the first object. The function of the first object includes: determining the task corresponding to the task description information.
[0462] Steps 2-4 (optional): The second network element determines the target AI unit based on the third message. The target AI unit is used to identify the target task.
[0463] Steps 2-5 (optional): The second network element sends a sixth message to the first network element. The sixth message includes the target AI unit or the address of the target AI unit.
[0464] Steps 2-6 to 9: Same as steps 2-6 to 9 in Example 1a.
[0465] Example 8: TM cannot identify the target task based on the task description information, where the task description information is a video stream.
[0466] Example 7 assumes that the TM (Transmission Technique) cannot identify the specific question corresponding to the user's colloquially described task requirements based on the task description, and requires the assistance of the target AI unit to determine the target task. Example 8 assumes that the user is unaware of the target task and only provides, for example, a video stream. The network determines the target task and the corresponding task instance based on the video stream. This allows for handling cases where the user's task description is an open question provided in the form of a video stream.
[0467] As shown in Figure 12, the task processing method includes:
[0468] Step 1: The terminal sends a first message to the TM, which requests the allocation of network resources for the target task. The first message includes first task description information, which includes the format, size, and period of the first data.
[0469] Step 2-1 is the same as step 2-1 in Example 7.
[0470] Step 2-1b (optional) is the same as step 2-1b in Example 7.
[0471] Steps 2-4 (optional) are the same as steps 2-4 in Example 7.
[0472] Steps 2-5 (optional) are the same as steps 2-5 in Example 7.
[0473] Steps 2-7 (optional): The first network element sends a seventh message to the third network element, wherein the seventh message is an inference request from the target AI unit.
[0474] The seventh message is forwarded through the fourth network element or sent directly to the third network element.
[0475] The seventh message includes at least one of the following:
[0476] First, the task description information; the address information of the target AI unit.
[0477] Steps 2-8 (optional): The third network element deploys the target AI unit in the seventh message on the third network element.
[0478] Steps 2-9 (optional): The third network element sends a twelfth message to the first network element. The twelfth message includes a response to the deployment of the target AI unit.
[0479] Step 2-10: The first network element sends a response to the first message to the terminal. The response to the first message includes at least one of the following: the task ID and the address of the AI resource associated with the task.
[0480] Step 2-11: The terminal sends the first data to the third network element.
[0481] Steps 2-12: The third network element takes the first data as the model input of the target AI unit. After the third network element performs inference for the target AI unit, the target task and / or task instance are obtained.
[0482] Step 2-13 (optional): The third network element sends a response to the seventh message to the first network element. The response to the seventh message includes the target task and / or, the task instance.
[0483] Steps 3 to 9: Same as steps 3 to 9 in Example 1a.
[0484] In this embodiment, a first network element obtains a first message sent by a terminal, the first message including first task description information. If the first network element cannot generate a task instance corresponding to the first task description information locally, the first network element obtains the task instance corresponding to the first task description information through at least one of a second network element and a third network element. In the above solution, when the first network element cannot generate a task instance corresponding to the terminal's first task description information locally, it interacts with at least one of a second network element and a third network element to obtain the corresponding task instance, thereby solving the problem of not being able to obtain a task instance when the first network element cannot deconstruct or understand the user's intent to obtain a task instance.
[0485] As shown in Figure 13, this application embodiment also provides a task processing method, including:
[0486] Step 1301: The second network element receives a third message from the first network element, the third message including information for indicating the first task description information.
[0487] Step 1302: The second network element sends relevant information about the task instance corresponding to the first task description information to the first network element, wherein the task instance cannot be generated locally on the first network element, and the task instance is determined based on the relevant information of the task instance.
[0488] The function of the first network element in this embodiment includes task management. The first network element can be a TM, or it can be co-located with existing network elements, such as co-located with AMF, co-located with AI service management function, or co-located with computing management function.
[0489] In this embodiment of the application, the second network element includes network elements related to AI model management; or, network elements related to data management functions; or, network elements related to API management.
[0490] In some embodiments of this application, the functions of the second network element include AI model management, model ID allocation, model classification, model acquisition (determining a suitable model based on internal needs), model storage, model version management, etc. The second network element includes at least one of AI model management function, AI model control function, AI algorithm control function, algorithm control function, and algorithm control plane.
[0491] In some embodiments of this application, the third message includes at least one of the following: first service type information, first task description information, second task description information, and first indication information; the second network element sends relevant information about the task instance corresponding to the first task description information to the first network element, including:
[0492] The second network element sends a sixth message or an eighth message to the first network element;
[0493] The sixth message includes at least one of a first object, address information of the first object, and identifier of the first object, wherein the first object is used to map the first task description information to a task instance;
[0494] The eighth message includes at least one of the following: API, API address, API format information, and API name;
[0495] The first object includes an artificial intelligence (AI) unit and at least one item in a database;
[0496] The API is used to map the first task description information to a task instance.
[0497] In some embodiments of this application, it also includes:
[0498] The second network element sends the tenth message to the third network element or sends the eleventh message to the API;
[0499] The tenth message includes at least one of the following: the first task description information, the second task description information, the address information of the first object, the identifier of the first object, and the address information of the first network element;
[0500] The eleventh message includes at least one of the following: the first task description information, the second task description information, the API address information, the API name, and task description information that meets the API format;
[0501] The first object includes an artificial intelligence (AI) unit and at least one item in a database;
[0502] The API is used to map the first task description information to a task instance.
[0503] It should be noted that the interaction between the first network element and the second network element has been described in detail in the method embodiment on the first network element side, and will not be repeated here.
[0504] As shown in Figure 14, this application embodiment also provides a task processing method, including:
[0505] Step 1401: The third network element obtains the seventh message sent by the first network element, the seventh message including information for indicating the first task description information;
[0506] Step 1402: The third network element sends the task instance corresponding to the first task description information to the first network element, wherein the task instance cannot be generated locally on the first network element.
[0507] The function of the first network element in this embodiment includes task management. The first network element can be a TM, or it can be co-located with existing network elements, such as co-located with AMF, co-located with AI service management function, or co-located with computing management function.
[0508] In some embodiments of this application, the third network element includes network elements related to AI service processing; or, it includes network elements related to at least one of data generation, storage, and forwarding. The functions of the third network element include service processing and implementation of service policy rules. This third network element includes at least one of AI resource nodes, computing power execution nodes, computing power execution functions, and computing power execution planes.
[0509] In some embodiments of this application, the seventh message includes at least one of the following: the first task description information, the second task description information, the address information of the first object, and the identifier of the first object;
[0510] The third network element sends the task instance corresponding to the first task description information to the first network element, including:
[0511] The first network element sends a fourth message to the first network element, the fourth message being a response message to the seventh message, wherein the fourth message includes at least one task instance corresponding to the first task description information, and the first object includes an artificial intelligence (AI) unit and at least one item in the database.
[0512] In some embodiments of this application, the third network element sends the task instance corresponding to the first task description information to the first network element, including:
[0513] The third network element obtains the tenth message sent by the second network element;
[0514] The third network element interacts with the first network element in a manner related to the task instance, including:
[0515] The third network element obtains the seventh message sent by the first network element or the tenth message sent by the second network element;
[0516] The third network element sends a fourth message to the first network element, the fourth message including at least one task instance corresponding to the first task description information;
[0517] The seventh message includes at least one of the following: the first task description information, the second task description information, the address information of the first object, and the identifier of the first object; the fourth message is a response message to the seventh message.
[0518] The tenth message includes at least one of the following: the first task description information, the second task description information, the address information of the first object, the identifier of the first object, and the address information of the first network element;
[0519] The first object is used to map the first task description information to a task instance, and the first object includes at least one of the following: an artificial intelligence (AI) unit and a database.
[0520] It should be noted that the interaction between the first network element and the second network element has been described in detail in the method embodiment on the first network element side, and will not be repeated here.
[0521] This application also provides a task processing method, including:
[0522] The terminal sends a first message to the first network element, the first message including first task description information;
[0523] The terminal obtains a second message sent by the first network element, the second message including at least one of the following: at least one task list related to the task instance, and at least one candidate task template related to the task instance.
[0524] The task processing method provided in this application can be executed by a task processing device. This application uses the execution of the task processing method by a task processing device as an example to illustrate the task processing device provided in this application.
[0525] This application provides a task processing device. As an example, the task processing device may be a communication device or a component within a communication device, such as a chip. The communication device may be a terminal, a network-side device, or a server, etc. Exemplarily, the terminal may include, but is not limited to, the type of terminal 11 listed above, and the network-side device may include, but is not limited to, the type of network-side device 12 listed above. This application does not impose specific limitations.
[0526] The task processing device includes a receiving module, a transmitting module, and a processing module. These modules can be implemented in software or hardware. When implemented in hardware, the processing module can be implemented by a processor. For example, the processor can include general-purpose processors, special-purpose processors, such as a Central Processing Unit (CPU), microprocessor, Digital Signal Processor (DSP), Artificial Intelligence (AI) processor, Graphics Processing Unit (GPU), Application Specific Integrated Circuit (ASIC), Network Processor (NP), Field Programmable Gate Array (FPGA), or other programmable logic devices, gate circuits, transistors, discrete hardware components, etc. The receiving and transmitting modules can be implemented by a communication interface, which can include one or more of the following: transceiver, pins, circuits, bus, radio frequency unit, etc.
[0527] Specifically, referring to Figure 15, when the task processing device is a network-side device or a component of a network-side device, the task processing device 1500 includes a first receiving module 1501, used to obtain a first message sent by the terminal, the first message including first task description information; and a first processing module 1502, used to obtain a task instance corresponding to the first task description information through at least one of a second network element and a third network element when the task instance corresponding to the first task description information cannot be generated locally on the first network element.
[0528] The apparatus in this application embodiment further includes:
[0529] A first sending module is configured to send a second message to the terminal, the second message including at least one of the following: at least one task list related to the task instance, and at least one candidate task template related to the task instance.
[0530] In the apparatus of this application embodiment, the situation in which the first network element cannot locally generate a task instance corresponding to the first task description information includes at least one of the following:
[0531] The task corresponding to the first task description information does not match the first function, and the first function is the function of the first artificial intelligence AI unit or the first algorithm.
[0532] The business category corresponding to the first task description information does not match the first business category, and the first business category is the business category corresponding to the first artificial intelligence AI unit or the first algorithm.
[0533] The task corresponding to the first task description information has not been determined;
[0534] The requirement corresponding to the first task description information has not been determined;
[0535] The target corresponding to the first task description information has not been determined;
[0536] The constraints corresponding to the first task description information have not been determined.
[0537] The business category corresponding to the first task description information has not been determined;
[0538] The first task description information is not predefined task description information;
[0539] The first task description information is the description information of the task customized by the terminal;
[0540] The first task description information is information that the first network element has not processed;
[0541] Wherein, the first AI unit is the AI unit on the first network element side, and the first algorithm is the algorithm on the first network element side.
[0542] The apparatus of this application embodiment, wherein the first processing module is used for:
[0543] Send a third message to the second network element, the third message including at least one of the following: first service type information, first task description information, second task description information, and first instruction information;
[0544] Obtain the fourth message sent by the third network element or the fifth message sent by the application programming interface (API);
[0545] Based on the fourth message or the fifth message, obtain at least one task instance corresponding to the task description information;
[0546] The first service type information includes the service type information corresponding to the task description information. The service type information is used to indicate the service classification. The first indication information is used to indicate whether the first network element can generate a task instance corresponding to the first task description information locally.
[0547] The second task description information is task feature information or task auxiliary description information extracted from the first task description information based on a database or AI unit.
[0548] The fourth message includes at least one task instance corresponding to the first task description information, and the fifth message includes at least one task instance corresponding to the first task description information.
[0549] The apparatus in this application embodiment further includes:
[0550] The second receiving module is used to obtain a sixth message sent by the second network element. The sixth message includes at least one of a first object, address information of the first object, and identifier of the first object. The first object is used to map the first task description information to a task instance. The first object includes at least one of an artificial intelligence (AI) unit and a database.
[0551] The first network element sends a seventh message to the third network element, the seventh message including at least one of the following: the first task description information, the second task description information, the address information of the first object, and the identifier of the first object; the fourth message is a response message to the seventh message.
[0552] The apparatus in this application embodiment further includes:
[0553] The third receiving module is used to obtain the eighth message sent by the second network element. The eighth message includes at least one of API, API address, API format information and API name. The API is used to map the first task description information to a task instance.
[0554] The second sending module is used to send a ninth message to the API. The ninth message includes at least one of the following: the first task description information, the second task description information, the API address information, the API name, and task description information that meets the API format. The fifth message is a response message to the ninth message.
[0555] In the apparatus of this application embodiment, when the first network element determines the service category corresponding to the first task description information, but the task corresponding to the first task description information does not match the first function, the service category corresponding to the first task description information does not match the first service category, the constraint conditions corresponding to the first task description information are not determined, the first task description information is not a predefined task description information, the first task description information is a description information of a terminal-customized task, or the first task description information has not been processed by the first network element, the third message includes the first service type information.
[0556] Alternatively, if the first network element fails to determine the task corresponding to the first task description information, fails to determine the requirement corresponding to the first task description information, fails to determine the target corresponding to the first task description information, or fails to determine the service category corresponding to the first task description information, the third message includes at least one of the following: second instruction information, first task description information, second task description information, and first instruction information;
[0557] The second indication information is used to indicate the function of the first object, and the function of the first object includes at least one of the following:
[0558] Determine the requirements corresponding to the task description information;
[0559] Determine the target corresponding to the task description information;
[0560] Determine the business category corresponding to the task description information;
[0561] Identify the task corresponding to the task description information.
[0562] The apparatus of this application embodiment, wherein the first processing module is used for:
[0563] A seventh message is sent to a third network element, the seventh message including at least one of the following: the first task description information, the second task description information, the address information of the first object, and the identifier of the first object, the first object being used to map the first task description information to a task instance, the first object including at least one of the following: an artificial intelligence (AI) unit and a database; the first network element obtains a fourth message sent by the third network element, the fourth message including at least one task instance corresponding to the first task description information.
[0564] Alternatively, a ninth message may be sent to the API, the ninth message including at least one of the following: the first task description information, the second task description information, the API address information, the API name, and task description information that meets the API format; the first network element obtains the fifth message sent by the API, the fifth message including at least one task instance corresponding to the first task description information.
[0565] In the apparatus of this application embodiment, where the second network element includes a network element related to AI model management and the third network element includes a network element related to AI service processing, the first object includes an AI unit.
[0566] In the case where the second network element includes a network element related to data management functions, and the third network element includes a network element related to at least one of data generation, storage and forwarding, the first object includes a database;
[0567] In cases where the second network element includes a network element related to API management, the first object includes an API interface.
[0568] Specifically, referring to Figure 16, when the task processing device is a network-side device or a component within a network-side device, the task processing device 1600 includes a second processing module 1601, used to receive a third message from a first network element, the third message including information for indicating first task description information; and to send relevant information of a task instance corresponding to the first task description information to the first network element, wherein the task instance cannot be generated locally on the first network element, and the task instance is determined based on the relevant information of the task instance.
[0569] In this embodiment of the application, the third message includes at least one of the following: first service type information, first task description information, second task description information, and first indication information; the second processing module is used to: send a sixth message or an eighth message to the first network element;
[0570] The sixth message includes at least one of a first object, address information of the first object, and identifier of the first object, wherein the first object is used to map the first task description information to a task instance;
[0571] The eighth message includes at least one of the following: API, API address, API format information, and API name;
[0572] The first object includes an artificial intelligence (AI) unit and at least one item in a database;
[0573] The API is used to map the first task description information to a task instance.
[0574] In this embodiment of the application, the second processing module is used for:
[0575] Send the tenth message to the third network element or the eleventh message to the API;
[0576] in,
[0577] The tenth message includes at least one of the following: the first task description information, the second task description information, the address information of the first object, the identifier of the first object, and the address information of the first network element;
[0578] The eleventh message includes at least one of the following: the first task description information, the second task description information, the API address information, the API name, and task description information that meets the API format;
[0579] The first object includes an artificial intelligence (AI) unit and at least one item in a database;
[0580] The API is used to map the first task description information to a task instance.
[0581] In this embodiment of the application, the second network element includes network elements related to AI model management; or, network elements related to data management functions; or, network elements related to API management.
[0582] Specifically, referring to Figure 17, when the task processing device is a network-side device or a component of a network-side device, the task processing device 1700 includes a third processing module 1701, used to obtain a seventh message sent by a first network element, the seventh message including information for indicating first task description information; and to send a task instance corresponding to the first task description information to the first network element, wherein the task instance cannot be generated locally on the first network element.
[0583] In this embodiment of the application, the seventh message includes at least one of the following: the first task description information, the second task description information, the address information of the first object, and the identifier of the first object;
[0584] The third processing module is used for:
[0585] Send a fourth message to the first network element. The fourth message is a response message to the seventh message. The fourth message includes at least one task instance corresponding to the first task description information. The first object includes an artificial intelligence (AI) unit and at least one item in the database.
[0586] In this embodiment of the application, the third processing module is used for:
[0587] Obtain the tenth message sent by the second network element;
[0588] Send a fourth message to the first network element, the fourth message including at least one task instance corresponding to the first task description information;
[0589] The seventh message includes at least one of the following: the first task description information, the second task description information, the address information of the first object, and the identifier of the first object; the fourth message is a response message to the seventh message.
[0590] The tenth message includes at least one of the following: the first task description information, the second task description information, the address information of the first object, the identifier of the first object, and the address information of the first network element;
[0591] The first object is used to map the first task description information to a task instance, and the first object includes at least one of the following: an artificial intelligence (AI) unit and a database.
[0592] In this embodiment of the application, the third network element includes network elements related to the processing of AI services; or, it includes network elements related to at least one of the generation, storage and forwarding of data.
[0593] In this embodiment, a first network element obtains a first message sent by a terminal, the first message including first task description information. If the first network element cannot generate a task instance corresponding to the first task description information locally, the first network element obtains the task instance corresponding to the first task description information through at least one of a second network element and a third network element. In the above solution, when the first network element cannot generate a task instance corresponding to the terminal's first task description information locally, it can obtain the corresponding task instance by using at least one of a second network element and a third network element, thereby solving the problem that a task instance cannot be obtained when the first network element cannot deconstruct or understand the user's intent to obtain the task instance.
[0594] The task processing device provided in this application embodiment can implement the various processes implemented in the method embodiments of Figures 2 to 14 and achieve the same technical effect. To avoid repetition, it will not be described again here.
[0595] Specifically, when the task processing device is a terminal or a component within a terminal, the task processing device includes:
[0596] The third sending module is used to send a first message to the first network element, the first message including first task description information;
[0597] The fourth receiving module is used to obtain a second message sent by the first network element, the second message including at least one of the following: at least one task list related to the task instance, and at least one candidate task template related to the task instance.
[0598] As shown in Figure 18, this application embodiment also provides a communication device 1800, including a processor 1801 and a memory 1802. The memory 1802 stores a program or instructions that can run on the processor 1801. For example, when the communication device 1800 is a terminal, the program or instructions executed by the processor 1801 implement the various steps of the task processing method embodiment executed by the terminal described above. When the communication device 1800 is a network-side device, the program or instructions executed by the processor 1801 implement the various steps of the task processing method embodiment executed by the first network element, the second network element, or the third network element described above, and can achieve the same technical effect. To avoid repetition, it will not be described again here.
[0599] This application also provides a network-side device, including a processor and a communication interface. The communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the steps of the method embodiments shown in FIG2, 13, or 14. This network-side device embodiment corresponds to the above-described network-side device method embodiments. All implementation processes and methods of the above-described method embodiments can be applied to this network-side device embodiment and can achieve the same technical effects.
[0600] Specifically, this application also provides a network-side device. As shown in FIG19, the network-side device 1900 includes a processor 1901, a network interface 1902, and a memory 1903. The network-side device may be the task processing device shown in FIG15, 16, or 17. The network interface 1902 is, for example, a Common Public Radio Interface (CPRI).
[0601] Specifically, the network-side device 1900 in this application embodiment further includes: instructions or programs stored in memory 1903 and executable on processor 1901. Processor 1901 calls the instructions or programs in memory 1903 to execute the methods executed by the modules shown in FIG15, 16 or 17 and achieve the same technical effect. To avoid repetition, it will not be described in detail here.
[0602] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described task processing method embodiments and achieve the same technical effects. To avoid repetition, they will not be described again here.
[0603] The processor mentioned above is the processor in the terminal described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk. In some examples, the readable storage medium may be a non-transient readable storage medium.
[0604] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described task processing method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.
[0605] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.
[0606] This application also provides a computer program / program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the above-described task processing method embodiments, and can achieve the same technical effect. To avoid repetition, it will not be described again here.
[0607] This application embodiment also provides a task processing system, including: a first network element, a second network element, and a third network element. The first network element can be used to execute the steps of the task processing method executed by the first network element as described above. The second network element can be used to execute the steps of the task processing method executed by the second network element as described above. The third network element can be used to execute the steps of the task processing method executed by the third network element as described above.
[0608] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.
[0609] From the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of computer software products plus necessary general-purpose hardware platforms, and of course, they can also be implemented by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disk, etc.) and includes several instructions to cause the terminal or network-side device to execute the methods described in the various embodiments of this application.
[0610] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other implementations under the guidance of this application without departing from the spirit and scope of the claims. All of these implementations are within the protection scope of this application.
Claims
1. A task processing method, comprising: The first network element acquires a first message sent by the terminal, the first message including first task description information; If the first network element is unable to generate a task instance corresponding to the first task description information locally, the first network element obtains the task instance corresponding to the first task description information through at least one of the second network element and the third network element.
2. The method according to claim 1, further comprising: The first network element sends a second message to the terminal, the second message including at least one of the following: at least one task list related to the task instance, and at least one candidate task template related to the task instance.
3. The method of claim 1 or 2, wherein, The first network element is unable to generate a task instance corresponding to the first task description information locally in at least one of the following situations: The task corresponding to the first task description information does not match the first function, and the first function is the function of the first artificial intelligence AI unit or the first algorithm. The business category corresponding to the first task description information does not match the first business category, and the first business category is the business category corresponding to the first artificial intelligence AI unit or the first algorithm. The task corresponding to the first task description information has not been determined; The requirement corresponding to the first task description information has not been determined; The target corresponding to the first task description information has not been determined; The constraints corresponding to the first task description information have not been determined. The business category corresponding to the first task description information has not been determined; The first task description information is not predefined task description information; The first task description information is the description information of the task customized by the terminal; The first task description information is information that the first network element has not processed; Wherein, the first AI unit is the AI unit on the first network element side, and the first algorithm is the algorithm on the first network element side.
4. The method according to any one of claims 1 to 3, wherein, The first network element obtains the task instance corresponding to the first task description information through at least one of the second and third network elements, including: The first network element sends a third message to the second network element, the third message including at least one of the following: first service type information, first task description information, second task description information, and first instruction information; The first network element receives the fourth message sent by the third network element or receives the fifth message sent by the application programming interface (API); The first network element obtains at least one task instance corresponding to the task description information based on the fourth message or the fifth message; The first service type information includes the service type information corresponding to the task description information. The service type information is used to indicate the service classification. The first indication information is used to indicate whether the first network element can generate a task instance corresponding to the first task description information locally. The second task description information is task feature information or task auxiliary description information extracted from the first task description information based on a database or AI unit. The fourth message includes at least one task instance corresponding to the first task description information, and the fifth message includes at least one task instance corresponding to the first task description information.
5. The method of claim 4, wherein, Before the first network element receives the fourth message sent by the third network element, the process also includes: The first network element obtains a sixth message sent by the second network element. The sixth message includes at least one of a first object, address information of the first object, and identifier of the first object. The first object is used to map the first task description information to a task instance. The first object includes at least one of an artificial intelligence (AI) unit and a database. The first network element sends a seventh message to the third network element, the seventh message including at least one of the following: the first task description information, the second task description information, the address information of the first object, and the identifier of the first object; the fourth message is a response message to the seventh message.
6. The method of claim 4, wherein, Before the first network element receives the fifth message sent by the application programming interface (API), the process also includes: The first network element obtains the eighth message sent by the second network element. The eighth message includes at least one of API, API address, API format information and API name. The API is used to map the first task description information to a task instance. The first network element sends a ninth message to the API, the ninth message including at least one of the following: the first task description information, the second task description information, the API address information, the API name, and task description information that meets the API format, and the fifth message is a response message to the ninth message.
7. The method according to any one of claims 4 to 6, wherein, If the first network element determines the service category corresponding to the first task description information, but the task corresponding to the first task description information does not match the first function, the service category corresponding to the first task description information does not match the first service category, the constraint conditions corresponding to the first task description information are not determined, the first task description information is not a predefined task description information, the first task description information is a description information of a terminal-customized task, or the first task description information has not been processed by the first network element, the third message includes the first service type information. Alternatively, if the first network element fails to determine the task corresponding to the first task description information, fails to determine the requirement corresponding to the first task description information, fails to determine the target corresponding to the first task description information, or fails to determine the service category corresponding to the first task description information, the third message includes at least one of the following: second instruction information, first task description information, second task description information, and first instruction information; The second indication information is used to indicate the function of the first object, and the function of the first object includes at least one of the following: Determine the requirements corresponding to the task description information; Determine the target corresponding to the task description information; Determine the business category corresponding to the task description information; Identify the task corresponding to the task description information.
8. The method according to any one of claims 1 to 3, wherein, The first network element obtains the task instance corresponding to the first task description information through at least one of the second and third network elements, including: The first network element sends a seventh message to the third network element, the seventh message including at least one of the following: first task description information, second task description information, address information of a first object, and identifier of a first object, the first object being used to map the first task description information to a task instance, the first object including at least one of an artificial intelligence (AI) unit and a database; the first network element obtains a fourth message sent by the third network element, the fourth message including at least one task instance corresponding to the first task description information. Alternatively, the first network element sends a ninth message to the API, the ninth message including at least one of the following: the first task description information, the second task description information, the API address information, the API name, and task description information that meets the API format; the first network element obtains the fifth message sent by the API, the fifth message including at least one task instance corresponding to the first task description information.
9. The method of claim 5, 7, or 8, wherein, In the case where the second network element includes a network element related to AI model management and the third network element includes a network element related to AI service processing, the first object includes an AI unit; In the case where the second network element includes a network element related to data management functions, and the third network element includes a network element related to at least one of data generation, storage and forwarding, the first object includes a database; In cases where the second network element includes a network element related to API management, the first object includes an API interface.
10. A task processing method, comprising: The second network element receives a third message from the first network element, the third message including information for indicating the first task description information; The second network element sends relevant information about the task instance corresponding to the first task description information to the first network element. The task instance cannot be generated locally on the first network element, and the task instance is determined based on the relevant information of the task instance.
11. The method of claim 10, wherein, The third message includes at least one of the following: first business type information, first task description information, second task description information, and first instruction information; The second network element sends relevant information about the task instance corresponding to the first task description information to the first network element, including: The second network element sends a sixth message or an eighth message to the first network element; The sixth message includes at least one of a first object, address information of the first object, and identifier of the first object, wherein the first object is used to map the first task description information to a task instance; The eighth message includes at least one of the following: API, API address, API format information, and API name; The first object includes an artificial intelligence (AI) unit and at least one item in a database; The API is used to map the first task description information to a task instance.
12. The method according to claim 10 or 11, further comprising: The second network element sends the tenth message to the third network element or sends the eleventh message to the API; The tenth message includes at least one of the following: the first task description information, the second task description information, the address information of the first object, the identifier of the first object, and the address information of the first network element; The eleventh message includes at least one of the following: the first task description information, the second task description information, the API address information, the API name, and task description information that meets the API format; The first object includes an artificial intelligence (AI) unit and at least one item in a database; The API is used to map the first task description information to a task instance.
13. The method according to any one of claims 10 to 12, wherein, The second network element includes network elements related to AI model management; or, network elements related to data management functions; or, network elements related to API management.
14. A task processing method, comprising: The third network element obtains the seventh message sent by the first network element, the seventh message including information for indicating the first task description information; The third network element sends the task instance corresponding to the first task description information to the first network element, wherein the task instance cannot be generated locally on the first network element.
15. The method of claim 14, wherein, The seventh message includes at least one of the following: the first task description information, the second task description information, the address information of the first object, and the identifier of the first object; The third network element sends the task instance corresponding to the first task description information to the first network element, including: The first network element sends a fourth message to the first network element, the fourth message being a response message to the seventh message, wherein the fourth message includes at least one task instance corresponding to the first task description information, and the first object includes an artificial intelligence (AI) unit and at least one item in the database.
16. The method of claim 15, wherein, The third network element sends the task instance corresponding to the first task description information to the first network element, including: The third network element obtains the tenth message sent by the second network element; The third network element sends a fourth message to the first network element, the fourth message including at least one task instance corresponding to the first task description information; The seventh message includes at least one of the following: the first task description information, the second task description information, the address information of the first object, and the identifier of the first object; the fourth message is a response message to the seventh message. The tenth message includes at least one of the following: the first task description information, the second task description information, the address information of the first object, the identifier of the first object, and the address information of the first network element; The first object is used to map the first task description information to a task instance, and the first object includes at least one of the following: an artificial intelligence (AI) unit and a database.
17. The method of any one of claims 14 to 16, wherein, The third network element includes network elements related to the processing of AI services; or, it includes network elements related to at least one of the generation, storage and forwarding of data.
18. A task processing apparatus, comprising: The first receiving module is used to acquire a first message sent by the terminal, the first message including first task description information; The first processing module is used to obtain the task instance corresponding to the first task description information through at least one of the second network element and the third network element when the task instance corresponding to the first task description information cannot be generated locally on the first network element.
19. The apparatus of claim 18, further comprising: A first sending module is configured to send a second message to the terminal, the second message including at least one of the following: at least one task list related to the task instance, and at least one candidate task template related to the task instance.
20. The apparatus of claim 18 or 19, wherein, The first network element is unable to generate a task instance corresponding to the first task description information locally in at least one of the following situations: The task corresponding to the first task description information does not match the first function, and the first function is the function of the first artificial intelligence AI unit or the first algorithm. The business category corresponding to the first task description information does not match the first business category, and the first business category is the business category corresponding to the first artificial intelligence AI unit or the first algorithm. The task corresponding to the first task description information has not been determined; The requirement corresponding to the first task description information has not been determined; The target corresponding to the first task description information has not been determined; The constraints corresponding to the first task description information have not been determined. The business category corresponding to the first task description information has not been determined; The first task description information is not predefined task description information; The first task description information is the description information of the task customized by the terminal; The first task description information is information that the first network element has not processed; Wherein, the first AI unit is the AI unit on the first network element side, and the first algorithm is the algorithm on the first network element side.
21. The apparatus of any one of claims 18 to 20, wherein, The first processing module is used for: Send a third message to the second network element, the third message including at least one of the following: first service type information, first task description information, second task description information, and first instruction information; Obtain the fourth message sent by the third network element or the fifth message sent by the application programming interface (API); Based on the fourth message or the fifth message, obtain at least one task instance corresponding to the task description information; The first service type information includes the service type information corresponding to the task description information. The service type information is used to indicate the service classification. The first indication information is used to indicate whether the first network element can generate a task instance corresponding to the first task description information locally. The second task description information is task feature information or task auxiliary description information extracted from the first task description information based on a database or AI unit. The fourth message includes at least one task instance corresponding to the first task description information, and the fifth message includes at least one task instance corresponding to the first task description information.
22. The apparatus of claim 21, further comprising: The second receiving module is used to obtain a sixth message sent by the second network element. The sixth message includes at least one of a first object, address information of the first object, and identifier of the first object. The first object is used to map the first task description information to a task instance. The first object includes at least one of an artificial intelligence (AI) unit and a database. The first network element sends a seventh message to the third network element, the seventh message including at least one of the following: the first task description information, the second task description information, the address information of the first object, and the identifier of the first object; the fourth message is a response message to the seventh message.
23. The apparatus of claim 21, further comprising: The third receiving module is used to obtain the eighth message sent by the second network element. The eighth message includes at least one of API, API address, API format information and API name. The API is used to map the first task description information to a task instance. The second sending module is used to send a ninth message to the API. The ninth message includes at least one of the following: the first task description information, the second task description information, the API address information, the API name, and task description information that meets the API format. The fifth message is a response message to the ninth message.
24. The apparatus of any one of claims 21 to 23, wherein, If the first network element determines the service category corresponding to the first task description information, but the task corresponding to the first task description information does not match the first function, the service category corresponding to the first task description information does not match the first service category, the constraint conditions corresponding to the first task description information are not determined, the first task description information is not a predefined task description information, the first task description information is a description information of a terminal-customized task, or the first task description information has not been processed by the first network element, the third message includes the first service type information. Alternatively, if the first network element fails to determine the task corresponding to the first task description information, fails to determine the requirement corresponding to the first task description information, fails to determine the target corresponding to the first task description information, or fails to determine the service category corresponding to the first task description information, the third message includes at least one of the following: second instruction information, first task description information, second task description information, and first instruction information; The second indication information is used to indicate the function of the first object, and the function of the first object includes at least one of the following: Determine the requirements corresponding to the task description information; Determine the target corresponding to the task description information; Determine the business category corresponding to the task description information; Identify the task corresponding to the task description information.
25. The apparatus of any one of claims 18 to 20, wherein, The first processing module is used for: A seventh message is sent to a third network element, the seventh message including at least one of the following: first task description information, second task description information, address information of a first object, and identifier of a first object, the first object being used to map the first task description information to a task instance, the first object including at least one of an artificial intelligence (AI) unit and a database; the first network element obtains a fourth message sent by the third network element, the fourth message including at least one task instance corresponding to the first task description information. Alternatively, a ninth message may be sent to the API, the ninth message including at least one of the following: the first task description information, the second task description information, the API address information, the API name, and task description information that meets the API format; the first network element obtains the fifth message sent by the API, the fifth message including at least one task instance corresponding to the first task description information.
26. The apparatus of claim 22, 24, or 25, wherein, In the case where the second network element includes a network element related to AI model management and the third network element includes a network element related to AI service processing, the first object includes an AI unit; In the case where the second network element includes a network element related to data management functions, and the third network element includes a network element related to at least one of data generation, storage and forwarding, the first object includes a database; In cases where the second network element includes a network element related to API management, the first object includes an API interface.
27. A task processing apparatus, comprising: The second processing module is configured to receive a third message from the first network element, the third message including information for indicating the first task description information; Send relevant information about the task instance corresponding to the first task description information to the first network element, wherein the task instance cannot be generated locally on the first network element, and the task instance is determined based on the relevant information of the task instance.
28. The apparatus of claim 27, wherein, The third message includes at least one of the following: first business type information, first task description information, second task description information, and first instruction information; The second processing module is used for: Send the sixth or eighth message to the first network element; The sixth message includes at least one of a first object, address information of the first object, and identifier of the first object, wherein the first object is used to map the first task description information to a task instance; The eighth message includes at least one of the following: API, API address, API format information, and API name; The first object includes an artificial intelligence (AI) unit and at least one item in a database; The API is used to map the first task description information to a task instance.
29. A task processing apparatus, comprising: The third processing module is used to obtain the seventh message sent by the first network element, the seventh message including information for indicating the first task description information; Send the task instance corresponding to the first task description information to the first network element, wherein the task instance cannot be generated locally on the first network element.
30. The apparatus of claim 29, wherein, The seventh message includes at least one of the following: the first task description information, the second task description information, the address information of the first object, and the identifier of the first object; The third processing module is used for: Sending the task instance corresponding to the first task description information to the first network element includes: The first network element sends a fourth message to the first network element, the fourth message being a response message to the seventh message, wherein the fourth message includes at least one task instance corresponding to the first task description information, and the first object includes an artificial intelligence (AI) unit and at least one item in the database.
31. A network-side device, comprising a processor and a memory, the memory storing a program or instructions executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the task processing method as claimed in any one of claims 1 to 9, or implement the steps of the task processing method as claimed in any one of claims 10 to 13, or implement the steps of the task processing method as claimed in any one of claims 14 to 17.
32. A readable storage medium storing a program or instructions that, when executed by a processor, implement the steps of the task processing method as claimed in any one of claims 1 to 9, or implement the steps of the task processing method as claimed in any one of claims 10 to 13, or implement the steps of the task processing method as claimed in any one of claims 14 to 17.
33. A computer program product comprising computer instructions that, when executed by a processor, implement the steps of the task processing method as described in any one of claims 1 to 9, or implement the steps of the task processing method as described in any one of claims 10 to 13, or implement the steps of the task processing method as described in any one of claims 14 to 17.
