Communication method and communication apparatus

Abstract

A communication method and a communication apparatus. A production entity negotiates with a consumption entity by means of a first session associated with a first attribute to confirm the value of the first attribute, and deletes context related to the first session in a timely manner after confirming the value of the first attribute, such that the possibility of conversation content exceeding a context window of a large model is reduced, thereby reducing the possibility of forgetting exchanged information, improving the logic and coherence of conversations, and improving the satisfaction of network management services.

Description

A communication method and a communication device

[0001] This application claims priority to Chinese Patent Application No. 202510124982.3, filed on January 26, 2025, entitled "A Communication Method and Communication Device", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communication technology, and more specifically, to a communication method and a communication device. Background Technology

[0003] With the development of network resource management, management service consumer entities no longer need to directly manage network resources. Instead, they can send messages to management service producer entities, causing these entities to execute network management intentions to achieve specified performance indicators for network devices within a specific range.

[0004] For network management intent, the management service consuming entity and the management service producing entity will engage in multi-round, multi-type interactions based on existing and missing information, and these interactions can be achieved with the assistance of a large model. The large model can generate responses within a context window, which refers to the number of tokens considered by the large model when generating a response. A larger context window helps the large model better understand user input, ensuring the consistency and coherence of its responses. However, considering factors such as computing resources, memory, response quality, and technical implementation, the context window is not infinitely large and is usually limited.

[0005] Network management intent has many attributes. In multi-turn and multi-type interactions, the dialogue may exceed the context window of the large model, affecting the logic and coherence of the conversation and reducing the satisfaction of network management services. Summary of the Invention

[0006] Embodiments of this application provide a communication method and a communication device to ensure the logic and coherence of large-scale model sessions, thereby improving the satisfaction of network management services.

[0007] In a first aspect, embodiments of this application provide a communication method that can be applied to the production entity side, such as the production entity, modules (e.g., circuits, chips or chip systems (e.g., modem chips (also known as baseband chips), or system-on-chip (SoC) chips or system-in-package (SIP) chips containing modem cores) in the production entity), or logical nodes, logical modules or software that can realize all or part of the production entity.

[0008] The method includes: obtaining a first attribute to be confirmed, the first attribute being an attribute of a first network management intent; conducting a first interaction with a consumer entity through a first session to confirm the value of the first attribute, the first session being associated with the first attribute; and deleting the context associated with the first session after confirming the value of the first attribute.

[0009] Based on the above method, the production entity and the consumer entity negotiate and confirm the value of the first attribute through the first session associated with the first attribute, and promptly delete the context related to the first session after confirming the value of the first attribute. This helps to reduce the occurrence of dialogue content exceeding the context window of the large model, thereby reducing the occurrence of forgotten information, improving the logic and coherence of the dialogue, and improving the satisfaction of network management services.

[0010] In conjunction with the first aspect, in some possible implementations, the first session is associated with the first attribute, including: the first interaction affects the value of the first attribute but does not affect the values ​​of the remaining attributes of the first network management intent.

[0011] Based on the above implementation, since the first interaction does not affect the values ​​of the remaining attributes of the first network management intent, deleting the context related to the first session does not affect the remaining attributes of the first network management intent.

[0012] In conjunction with the first aspect or any of its implementations, in some other possible implementations, obtaining the first attribute to be confirmed includes: receiving first information from the consumer entity, the first information being used to indicate the first attribute.

[0013] Based on the above implementation method, the consumer entity can indicate the attribute to be confirmed, which can better meet the needs of the consumer entity or consumer.

[0014] In conjunction with the first aspect or any of its implementations, in some other possible implementations, the first information includes the first attribute. This implementation is simple to implement.

[0015] In conjunction with the first aspect or any of its implementations, in some other possible implementations, the first information includes granularity information and part or all of the first attribute, wherein the granularity information is used to indicate the granularity of the first interaction.

[0016] Based on the above implementation, the consumer entity provides granular information and part or all of the first attribute, which is then determined by the producer entity. This implementation places lower requirements on the consumer entity. Furthermore, it reduces the difficulty of negotiating the value of the first attribute through a first session associated with it, thus allowing for wider adoption of this approach and further reducing the occurrence of dialogue content exceeding the context window of a large model.

[0017] In conjunction with the first aspect or any of its implementations, in some other possible implementations, the first information includes first granularity information and the first attribute, wherein the first granularity information is used to indicate that the granularity of the first interaction is a single attribute.

[0018] For example, the first attribute includes one property.

[0019] In conjunction with the first aspect or any of its implementations, in some other possible implementations, the first information includes second granularity information and part or all of the first attribute, wherein the second granularity information is used to indicate that the granularity of the first interaction is a combined attribute.

[0020] For example, the first attribute includes multiple attributes, and the values ​​of the multiple attributes influence each other.

[0021] Based on the above implementation, the consuming entity and the producing entity can combine and confirm multiple attributes, which can reduce the signaling overhead and transmission resources occupied between the consuming entity and the producing entity. Furthermore, when the first information includes a portion of the first attribute, the signaling overhead and transmission resources occupied between the consuming entity and the producing entity can be further reduced.

[0022] In conjunction with the first aspect or any of its implementations, in some other possible implementations, the plurality of attributes include: a first expected target, a first expected object, and a first context, wherein the first context includes at least one of the following: the context of the first expected target, or the context of the first expected object; or, the plurality of attributes include: a plurality of second expected targets, a second expected object, and a second context, wherein the second context includes at least one of the following: the context of some or all of the plurality of second expected targets, or the context of the second expected object.

[0023] In conjunction with the first aspect or any implementation thereof, in some other possible implementations, the method further includes: receiving second information from the consumer entity before engaging in the first interaction with the consumer entity via the first session, the second information being used to instruct the creation of the first session.

[0024] Based on the above implementation method, the consumer entity can actively instruct the creation of the first session, or in other words, the consumer entity can actively start the first session. This allows a session to be started promptly.

[0025] In conjunction with the first aspect or any of its implementations, in some other possible implementations, the method further includes: after obtaining the first attribute to be confirmed, sending third information to the consumer entity, the third information being used to indicate the start of the first session.

[0026] Based on the above implementation method, the production entity can start the first session.

[0027] In conjunction with the first aspect or any implementation thereof, in some other possible implementations, the method further includes: receiving fourth information from the consuming entity before deleting the context associated with the first session, the fourth information being used to indicate the termination of the first session.

[0028] Based on the above implementation method, the consumer entity can actively end the first session, thus ending a session in a timely manner.

[0029] In conjunction with the first aspect or any of its implementations, in some other possible implementations, the method further includes: updating the first network management intent based on the value of the first attribute.

[0030] In conjunction with the first aspect or any of its implementations, in some other possible implementations, after deleting the context associated with the first session, the method further includes: obtaining a second attribute to be confirmed, the second attribute being an attribute of the first network management intent; performing a second interaction with the consumer entity through a second session to confirm the value of the second attribute, the second session being associated with the second attribute; and deleting the context associated with the second session after confirming the value of the second attribute.

[0031] In conjunction with the first aspect or any of its implementations, in some other possible implementations, the method further includes: generating a first prompt, the first prompt being used to prompt the large model entity to perform a first operation, wherein the first operation includes: confirming the value of the first attribute with the consumer entity based on the first session, and deleting the context associated with the first session after confirming the value of the first attribute; the deletion of the context associated with the first session includes: instructing the large model entity to delete the context associated with the first session.

[0032] Secondly, embodiments of this application provide a communication method that can be applied to the consumer entity side, such as the consumer entity, modules (e.g., circuits, chips, or chip systems (e.g., modem chips, or SoC chips or SIP chips containing modem cores) in the consumer entity, or logical nodes, logical modules, or software that can implement all or part of the consumer entity.

[0033] The method includes: engaging in a first interaction with a production entity through a first session to confirm the value of a first attribute, wherein the first attribute is an attribute of a first network management intent, and the first session is associated with the first attribute.

[0034] Based on the above method, the production entity and the consumer entity confirm the value of the first attribute through negotiation in the first session associated with the first attribute. After confirming the value of the first attribute, the production entity can delete the context related to the first session. This helps to reduce the occurrence of dialogue content exceeding the context window of the large model, thereby reducing the occurrence of forgotten information, improving the logic and coherence of the dialogue, and improving the satisfaction of network management services.

[0035] In conjunction with the second aspect, in some possible implementations, the first session is associated with the first attribute, including: the first interaction affects the value of the first attribute but does not affect the values ​​of the remaining attributes of the first network management intent.

[0036] Based on the above implementation, since the first interaction does not affect the values ​​of the remaining attributes of the first network management intent, deleting the context related to the first session does not affect the remaining attributes of the first network management intent.

[0037] In conjunction with the second aspect or any of its implementations, in some other possible implementations, the method further includes: sending first information to the production entity, the first information being used to indicate the first attribute.

[0038] Based on the above implementation method, the consumer entity can indicate the attribute to be confirmed, which can better meet the needs of the consumer entity or consumer.

[0039] In conjunction with the second aspect or any of its implementations, in some other possible implementations, the first information includes the first attribute. This implementation is simple to implement.

[0040] In conjunction with the second aspect or any of its implementations, in some other possible implementations, the first information includes granularity information and part or all of the first attribute, wherein the granularity information is used to indicate the granularity of the first interaction.

[0041] Based on the above implementation, the consumer entity provides granular information and part or all of the first attribute, which is then determined by the producer entity. This implementation places lower requirements on the consumer entity. Furthermore, it reduces the difficulty of negotiating the value of the first attribute through a first session associated with it, thus allowing for wider adoption of this approach and further reducing the occurrence of dialogue content exceeding the context window of a large model.

[0042] In conjunction with the second aspect or any of its implementations, in some other possible implementations, the first information includes first granularity information and the first attribute, wherein the first granularity information is used to indicate that the granularity of the first interaction is a single attribute.

[0043] For example, the first attribute includes one property.

[0044] In conjunction with the second aspect or any of its implementations, in some other possible implementations, the first information includes second granularity information and part or all of the first attribute, wherein the second granularity information is used to indicate that the granularity of the first interaction is a combined attribute.

[0045] For example, the first attribute includes multiple attributes, and the values ​​of the multiple attributes influence each other.

[0046] Based on the above implementation, the consuming entity and the producing entity can combine and confirm multiple attributes, which can reduce the signaling overhead and transmission resources occupied between the consuming entity and the producing entity. Furthermore, when the first information includes a portion of the first attribute, the signaling overhead and transmission resources occupied between the consuming entity and the producing entity can be further reduced.

[0047] In conjunction with the second aspect or any of its implementations, in some other possible implementations, the plurality of attributes include: a first expected target, a first expected object, and a first context, wherein the first context includes at least one of the following: the context of the first expected target, or the context of the first expected object; or, the plurality of attributes include: a plurality of second expected targets, a second expected object, and a second context, wherein the second context includes at least one of the following: the context of some or all of the plurality of second expected targets, or the context of the second expected object.

[0048] In conjunction with the second aspect or any implementation thereof, in some other possible implementations, the method further includes: sending second information to the production entity before the first interaction with the production entity via the first session, the second information being used to instruct the creation of the first session.

[0049] Based on the above implementation method, the consumer entity can actively instruct the creation of the first session, or in other words, the consumer entity can actively start the first session. This allows a session to be started promptly.

[0050] In conjunction with the second aspect or any of its implementations, in some other possible implementations, the method further includes: receiving third information from the production entity prior to the first interaction with the production entity via the first session, the third information being used to indicate the start of the first session.

[0051] Based on the above implementation method, the production entity can start the first session.

[0052] In conjunction with the second aspect or any of its implementations, in some other possible implementations, the method further includes: after confirming the value of the first attribute or when confirming the first attribute, sending fourth information to the production entity, the fourth information being used to indicate the termination of the first session.

[0053] Based on the above implementation method, the consumer entity can actively end the first session, thus ending a session in a timely manner.

[0054] In conjunction with the second aspect or any of its implementations, in some other possible implementations, after confirming the value of the first attribute, the method further includes: conducting a second interaction with the production entity through a second session to confirm the value of the second attribute, wherein the second attribute is an attribute of the first network management intent, and the second session is associated with the first attribute.

[0055] Thirdly, embodiments of this application provide a communication method that can be applied to the large model entity side, such as the large model entity, modules in the large model entity (e.g., circuits, chips or chip systems (such as modem chips (also known as baseband chips), or system-on-chip (SoC) chips or system-in-package (SIP) chips containing modem cores)), or logical nodes, logical modules or software that can implement all or part of the large model entity.

[0056] The method includes: receiving a first prompt from a production entity, the first prompt being used to prompt a large model to perform a first operation; performing the first operation according to the first prompt; wherein the first operation includes: confirming the value of a first attribute with a consumer entity through a first session, and deleting the context associated with the first session after confirming the value of the first attribute; wherein the first attribute is an attribute of a first network management intent, and the first session is associated with the first attribute.

[0057] Based on the above method, the value of the first attribute can be confirmed through negotiation in the first session associated with the first attribute, and the context related to the first session can be deleted in a timely manner after the value of the first attribute is confirmed. This helps to reduce the occurrence of dialogue content exceeding the context window of the large model, thereby reducing the occurrence of forgotten information that has been interacted, improving the logic and coherence of the dialogue, and improving the satisfaction of network management services.

[0058] In conjunction with the third aspect, in some possible implementations, the first session is associated with the first attribute, including: the first interaction affects the value of the first attribute but does not affect the values ​​of the remaining attributes of the first network management intent.

[0059] In conjunction with the third aspect or any of its implementations, in some other possible implementations, the first operation further includes at least one of the following: updating the first network management intent based on the value of the first attribute; confirming the value of the second attribute with the consumer entity through a second session; and deleting the context associated with the second session after confirming the value of the second attribute; wherein the second attribute is an attribute of the first network management intent, and the second session is associated with the second attribute.

[0060] Fourthly, embodiments of this application provide a communication method that can be applied to consumer entities and production entities. Unless otherwise specified, consumer entities and production entities can refer to the consumer entities and production entities themselves, or to modules (e.g., circuits, chips, or chip systems (such as modem chips, or SoC chips or SIP chips containing modem cores)) in consumer entities and production entities, or logical nodes, logical modules, or software that can implement all or part of consumer entities and production entities.

[0061] The method includes: a consumer entity sending first information, a producer entity receiving the first information, the first information indicating a first attribute to be confirmed, the first attribute being an attribute of a first network management intent; the producer entity and the consumer entity performing a first interaction through a first session to confirm the value of the first attribute, the first session being associated with the first attribute; after confirming the value of the first attribute, the producer entity deleting the context associated with the first session.

[0062] In conjunction with the fourth aspect, in some possible implementations, the method further includes: the production entity generating a first prompt, the first prompt being used to prompt the large model entity to perform a first operation, wherein the first operation includes: confirming the value of the first attribute with the consumer entity based on the first session, and deleting the context related to the first session after confirming the value of the first attribute; the production entity sending the first prompt, the large model entity receiving the first prompt; and the large model entity performing the first operation according to the first prompt.

[0063] It should be noted that the steps performed by the production entity in the fourth aspect or its implementation can refer to the first aspect or its implementation; the steps performed by the consumer entity in the fourth aspect or its implementation can refer to the second aspect or its implementation; the steps performed by the large model entity in the fourth aspect or its implementation can refer to the third aspect or its implementation; the terms or features that are the same as those in the first, second, and third aspects or their implementations in the fourth aspect or its implementation can refer to the first, second, and third aspects or their implementations; and the technical effects of the fourth aspect or its implementation can refer to the technical effects in the first, second, and third aspects or their implementations, and will not be repeated in the fourth aspect.

[0064] Fifthly, a communication apparatus is provided for performing the method provided in any of the above aspects or implementations thereof. Specifically, the apparatus may include units and / or modules for performing the method provided in any of the above aspects or implementations thereof, such as a processing unit and / or a transceiver unit. The processing unit is used to perform the processing steps in the method provided in any of the above aspects or implementations thereof. The transceiver unit is used to perform the transceiver steps in the method provided in any of the above aspects or implementations thereof.

[0065] In one implementation, the device is a production entity, a consumption entity, or a large model entity. When the device is a production entity, a consumption entity, or a large model entity, the transceiver unit can be a transceiver, or an input / output interface, or a communication interface; the processing unit can be at least one processor. Optionally, the transceiver is a transceiver circuit. Optionally, the input / output interface is an input / output circuit.

[0066] In another implementation, the device is a chip, chip system, or circuit used in a production entity, consumer entity, or large model entity. When the device is a chip, chip system, or circuit used in a production entity, consumer entity, or large model entity, the transceiver unit may be an input / output interface, interface circuit, output circuit, input circuit, pin, or related circuit on the chip, chip system, or circuit; the processing unit may be at least one processor, processing circuit, or logic circuit.

[0067] In a sixth aspect, a communication device is provided, comprising: a memory for storing a program; and at least one processor for executing the computer program or instructions stored in the memory to perform the method provided in any of the foregoing aspects or their implementations.

[0068] In one implementation, the device is a production entity, a consumption entity, or a large model entity.

[0069] In another implementation, the device is a chip, chip system, or circuit used in a production entity, a consumer entity, or a large model entity.

[0070] In a seventh aspect, a communication device is provided, comprising: at least one processor and a communication interface, the at least one processor being configured to obtain a computer program or instructions stored in a memory via the communication interface to execute the method provided in any of the foregoing aspects or their implementations. The communication interface may be implemented in hardware or software.

[0071] In one implementation, the device further includes the memory.

[0072] Eighthly, a processor is provided for executing the methods provided in the above aspects.

[0073] Unless otherwise specified, or if it does not contradict its actual function or internal logic in the relevant description, the transmission and acquisition / reception operations involved in the processor can be understood as processor output and reception, input and other operations, or as transmission and reception operations performed by radio frequency circuits and antennas. This application does not limit them in this regard.

[0074] Ninthly, a computer-readable storage medium is provided that stores program code for execution by a device, the program code including methods for performing any of the foregoing aspects or their implementations.

[0075] In a tenth aspect, a computer program product containing instructions is provided, which, when run on a computer, causes the computer to perform the method provided in any of the foregoing aspects or their implementations.

[0076] Eleventhly, a chip is provided, comprising a processor and a communication interface. The processor reads instructions stored in memory through the communication interface and executes the methods provided in any of the above aspects or their implementations. The communication interface can be implemented in hardware or software.

[0077] Optionally, as one implementation, the chip also includes a memory that stores computer programs or instructions. The processor is used to execute the computer programs or instructions stored in the memory. When the computer programs or instructions are executed, the processor is used to perform the methods provided by any of the above aspects or their implementations.

[0078] When the method provided in this application is executed by a chip, this application does not limit the specific number of chips implementing the method. For example, it can be executed by one chip, or by two or more chips. Furthermore, when the number of chips implementing the method is two or more, the chip manufacturers are not limited; they can be from the same manufacturer or different manufacturers.

[0079] In a twelfth aspect, a communication system is provided, comprising at least one of the production entity, consumption entity, or large model entity described above.

[0080] In a thirteenth aspect, a computer program is provided that, when run on a computer, causes the methods provided by any of the foregoing aspects or their implementations to be executed. Attached Figure Description

[0081] Figure 1 is a schematic structural diagram of an Intent Information Object Class (IOC).

[0082] Figure 2 is a schematic structural diagram of a communication system applicable to an embodiment of this application.

[0083] Figure 3 is a schematic structural diagram of another communication system applicable to the embodiments of this application.

[0084] Figure 4 is a schematic diagram of the possible outcomes of the negotiation intentions of consumer entities and production entities.

[0085] Figure 5 is a schematic diagram of the best possible outcome of the negotiation intentions of the consumer entity and the production entity.

[0086] Figure 6 is a schematic diagram of the potential intended goals and contexts that a production entity recommends to a consumer entity.

[0087] Figure 7 is a schematic diagram of alternatives suggested by consumer entities to production entities.

[0088] Figure 8 is a schematic diagram of alternatives suggested by consumer entities to production entities.

[0089] Figure 9 is an example of multi-round interactions between consumer entities and production entities.

[0090] Figure 10 is a schematic flowchart of a communication method 1000 provided in this application.

[0091] Figure 11 is an example of single attributes and composite attributes.

[0092] Figure 12 is a schematic flowchart of the communication method 1200 provided in this application.

[0093] Figure 13 is a schematic flowchart of the communication method 1300 provided in this application.

[0094] Figure 14 is a schematic flowchart of the communication method 1400 provided in this application.

[0095] Figure 15 is a schematic diagram of a device provided in an embodiment of this application.

[0096] Figure 16 is another structural schematic diagram of the device provided in an embodiment of this application.

[0097] Figure 17 is a schematic diagram of a chip system provided in an embodiment of this application. Detailed Implementation

[0098] Before introducing the embodiments of this application, the following description is provided.

[0099] The terms "for indicating" or "instruction" can include both direct and indirect indication, or they can be explicit and / or implicit. The various numerical designations such as "first," "second," etc., are merely for descriptive convenience and are not intended to limit the scope of the embodiments of this application, such as distinguishing different messages or different information. "Predefined" can be implemented by pre-storing corresponding codes, tables, or other methods that can be used to indicate relevant information in the device; this application does not limit the specific implementation method. The "protocol" involved can refer to standard protocols in the field of communication, such as the Long Term Evolution (LTE) protocol, the New Radio (NR) protocol, and related protocols applied to future communication systems; this application does not limit this. The words "exemplary," "for example," "exemplarily," "as another example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as an "example" in this application should not be construed as being better or more advantageous than other embodiments or designs. The terms "comprising," "including," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized. "A plurality" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, and c can mean: a, or, b, or, c, or, a and b, or, a and c, or, b and c, or, a, b, and c. Here, a, b, and c can be single or multiple. Descriptions involving network element A sending messages, information, or data to network element B, and network element B receiving messages, information, or data from network element A, aim to specify which network element the message, information, or data is to be sent to, without specifying whether they are sent directly or indirectly through other network elements. Descriptions such as “when…”, “under…”, “if”, and “if” all indicate that the device will take corresponding actions under certain objective circumstances. They are not time-limited, nor do they require the device to make a judgment action when implementing the action, nor do they imply any other limitations.

[0100] The technical solution of this application can be applied to various network function virtualization (NFV) systems. This system can use standard formal language to describe current operator service technology solutions, network construction plans, and network operation and maintenance methods as patterns and strategies, and implement the technical solutions and construction plans based on these patterns and strategies. For example, the technical solution of this application can be applied to one or more of the following systems: wireless intent-driven network (wIDN) systems, experiential networked intelligence (ENI) systems, intent-driven management service (IDMS) systems, or open network automation platform (ONAP) systems, etc.

[0101] The embodiments of this application can also be applied to at least one of the following systems: 5th generation (5G) systems or NR systems, LTE systems, long term evolution-advanced (LTE-A) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, etc. They can also be applied to future communication systems. Furthermore, they can be applied to device-to-device (D2D) communication, vehicle-to-everything (V2X) communication, long term evolution-vehicle (LTE-V) communication, long term evolution-machine (LTE-M) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), Internet of Things (IoT) communication systems, narrow band Internet of Things (NB-IoT) systems, or other communication systems. The embodiments of this application can also be applied to satellite communication systems, high altitude platform station (HAPS) communications, unmanned aerial vehicles (UAVs), and other non-terrestrial network (NTN) systems, such as integrated communication and navigation (ICAN) systems, global navigation satellite systems (GNSS), and ultra-dense low-Earth orbit (LEO) satellite communication systems. Furthermore, it can be extended to similar wireless communication systems, such as wireless local area networks (WLANs), wireless-fidelity (WiFi), worldwide interoperability for microwave access (WIMAX), and other communication systems related to the 3rd generation partnership project (3GPP).

[0102] To facilitate understanding of the embodiments of this application, some terms involved in the embodiments of this application will be explained first.

[0103] 1. Network management and network management services

[0104] Network management refers to the management of network resources, including but not limited to monitoring, controlling, and recording the performance and usage of network resources, and issuing management action groups to network resources (such as devices in the network) based on the detected network conditions to ensure the effective operation of the network. For example, network management can include at least one of the following: monitoring, testing, configuring, analyzing, evaluating, or controlling network resources. Network management can also include timely reporting and handling of network failures, and coordinating and maintaining the efficient operation of the network system. Network resources are the objects of network management; they can also be called network objects or managed entities. For example, network resources can be base station equipment, routers, switches, core network equipment, etc.

[0105] Network management service: refers to a service that provides network management functions. The entity that produces this service usually provides network management functions to the entity that consumes the service through a network interface (e.g., a service-based interface).

[0106] 2. Network Management Intent

[0107] The current 3rd Generation Partnership Project (3GPP) System Aspects Work Group 5 (SA5) adopts a full-scale modeling of network resources and full-scale management of network objects in the definition of traditional interfaces. The network management system directly performs CRUD operations on all network resources (such as network devices) through configuration management, performance management, and fault management. Under this management approach, the management and maintenance threshold for operators is high, and the differentiated implementations by equipment manufacturers make interoperability between vendors difficult. To reduce management complexity and improve operational efficiency in multi-vendor scenarios, standards organizations and projects such as 3GPP and the European Telecommunications Standards Institute (ETSI) have successively researched and standardized network management intent technology. The main solutions can be summarized as follows: the network management system does not directly manage network resources; it only retains the network management intent model, and the interface only transmits vendor-agnostic structured network management intents, thereby shielding the differences in implementation among equipment manufacturers; the structured network management intents are expressed declaratively, that is, the intents only describe "what" and do not involve "how"; after receiving the structured network management intents from the network management system, the equipment management system translates the structured network management intents into network requirements and specific operations based on the network status, and executes the corresponding operations to achieve the network management intents.

[0108] Network management intent refers to the demand for network management services from a network management service consuming entity. It can also be called a network management service demand. This application embodiment does not limit the name, and it will be referred to as intent below. For example, intent can be an optical leased line service intent or an energy-saving intent, such as the intent defined in the 3rd generation partnership project (3GPP) standard specification 28.312.

[0109] Intent-based interaction scenarios primarily involve two roles: network management service consumers and network management service producers. The network management service consumer is the entity that invokes the management service, or in other words, the intent service. The network management service producer is the entity that provides the network management service. A more detailed description of the network management service consumer and producer entities can be found in Figure 3 below.

[0110] An intent can be applied to a network system to achieve a specified performance target for network devices within a specific range. An intent can express expectations for the network system through formal specifications and descriptive information. The formal specifications can refer to the intent-specific syntax or semantics, while the descriptive information can describe at least one of the intent's requirements, objectives, or constraints.

[0111] An intent may contain at least one intent expectation. Each intent expectation may represent the performance requirements of a network management service consuming entity for a specific network object. An intent expectation may consist of at least one expectation target and at least one expectation object. Each expectation target may represent the performance requirements of a specific attribute of the expectation object for the network management service consuming entity. The expectation object may be the network object on which the intent acts, and the expectation object may also be called the acting object. For example, an intent expectation may contain two expectation targets, one of which is an average downlink throughput greater than 5 Mbps, and the other is an end-to-end latency less than 10 milliseconds. If the average downlink throughput of the expectation object is greater than 5 Mbps, then the expectation target regarding downlink throughput is met. If the end-to-end latency of the expectation object is less than 10 milliseconds, then the expectation target regarding latency is met. If both expectation targets of the intent expectation are met, then the intent expectation is satisfied. If one or more intent expectations are not met, or one or more expectation targets are not met, then the intent is not satisfied.

[0112] The satisfaction or non-satisfaction of an intention, expectation, or goal can also be described as: the achievement or non-achievement of an intention, expectation, or goal; the realization or non-realization of an intention, expectation, or goal; or the achievement or non-achievement of an intention, expectation, or goal.

[0113] An intent can also include an intent context. The intent context can represent the constraints or conditions imposed on the intent by the network management service consuming entity. For example, the network management service consuming entity can constrain the duration of the intent's effect through the intent context.

[0114] An intent can also include an expectation context. The expectation context can represent the constraints or conditions that a network management service consumer entity expects regarding an intent. For example, a network management service consumer entity can constrain the duration of the intent expectation through the expectation context.

[0115] The intent may also include a target context, which can represent a constraint or condition imposed on a desired objective by a network management service consumer entity. For example, a network management service consumer entity may constrain the duration of the desired objective through the target context.

[0116] An intent can also include an object context, which can represent the constraints or conditions imposed by the network management service consuming entity on the network object to which the intent acts. For example, the network management service consuming entity can use the object context to indicate the region where the network object to which the intent acts is located.

[0117] For example, the intent can be expressed as:

[0118] For example, the intent can be expressed as: ensure that the handover failure rate of a certain cell is less than 2% when the load is >80%. Here, "certain cell" is the expected object or the object of action, and "certain cell" can correspond to Expectation Object O; "load >80%" is the target context, and "load >80%" can correspond to Target Context (such as C_1); "handover failure rate <2%" is the expected target, and "handover failure rate <2%" can correspond to Expectation Target (such as T_1).

[0119] The intent expectation, expectation target, and intent context described above can be used as information elements in the IOC of the intent creation request. The network management service consumer entity can express its demand for the network management service by sending the above information elements to the network management service producer entity.

[0120] In Intent IOC, information cells can use specific structures to express requirements for network management services.

[0121] For example, Figure 1 shows a schematic structural diagram of an intentional IOC.

[0122] Referring to Figure 1, an Intent IOC includes an Intent Expectation and an Intent Context. An Intent Expectation includes an Expected Object, an Expected Goal, and an Expected Context. An Expected Object includes an Expected Object Context, and an Expected Goal includes a Goal Context. It is understood that non-contextual information elements (such as Intent IOCs, Intent Expectations, Expected Objects, or Expected Goals) can contain contextual information elements (such as Intent Context, Expected Object Context, Goal Context, Expected Context, etc.), and contextual information elements can be used to constrain non-contextual information elements.

[0123] It is understood that Figure 1 is a schematic illustration of the relationship between attributes in an intent IOC. Based on network management service requirements, an intent IOC may also contain other attributes, which this application does not specifically limit. It is also understood that this application does not specifically limit the number of attributes of the same type. For example, an intent IOC may contain one or more parallel intent expectation attributes, and an intent expectation may also contain one or more parallel expectation target attributes.

[0124] 3. Intent Template

[0125] An intent template refers to a standardized description of an intent, also known as a network management service requirement template; however, this application does not limit the terminology used in its embodiments. The intent template can be used to define the syntax and semantics of the various attributes described above. For example, the intent template can specify the field types and value types that each attribute in the IOC can use. As an example, an intent template can include intent expectation description information specifying how the intent expectation is expressed. This intent expectation description information can specify the types of the expected target attributes that the intent expectation can include, such as latency, bandwidth, and maximum number of users. The intent expectation description information can also specify the field type of each expected target; for example, the field type for the latency expected target is a string, the field type for the bandwidth expected target is a string, and the field type for the maximum number of users expected target is an integer. As another example, an intent template can also include intent context description information specifying how the intent context and the expected context are expressed. The intent context description information can be used to specify the field types of the intent context, etc., and this application does not impose any particular limitations on this.

[0126] 4. Intent Expression

[0127] In this embodiment, the intent expression is an informational representation of an intent, which can be an instantiation of an intent template. The intent consumer can instantiate an intent IOC based on the intent template to generate an intent expression, which can then be used for specific network services. For example, an intent expression can be represented by a set of attributes and value key-value pairs (e.g., a list of [attribute, value]).

[0128] For example, the intent expression includes instances of performance metric information, instances of network object information, and instances of context information.

[0129] For example, a performance metric information instance may include the value or range of the target metric requirement corresponding to the performance metric information. For example, the target metric requirement corresponding to the performance metric information template includes a bandwidth parameter, and the performance metric information instance includes a bandwidth parameter value of 20M, or a bandwidth parameter value range of 10M to 15M. For example, the target metric requirement corresponding to the performance metric information template includes a latency parameter, and the latency parameter instance includes a latency parameter value of 2s, or a latency parameter value range of 1s to 5s.

[0130] The target network object indicated by the network object information instance is the instantiation result of the target network object indicated by the network object information template. For example, the target network object indicated by the network object information instance is one of the target network objects indicated by the network object information template, that is, one of the physical or logical entities used to indicate the implementation of network management services. In this case, the network object information instance indicates a specific network object. For example, the network object information template indicates a network service, and the network object information instance indicates an energy-saving service.

[0131] Context information instances are used to indicate the constraints of a schematic expression. For example, a context information instance may include constraint parameters of the intent expression; for instance, a context information instance may include source and destination information corresponding to the target network object indicated by a network object instance.

[0132] Intent expectation information instances include performance metric information instances and network object information instances.

[0133] In this embodiment of the application, the "intent" transmitted via message refers to an intent expression.

[0134] 5. Intent Examples

[0135] An intent instance refers to an intent processing process created locally by a network management service production entity based on a received intent expression (e.g., a performance metric information instance, a network object information instance, or a context information instance).

[0136] An intent processing process is used to process intent expressions. For example, the intent processing process may include an identifier to identify the process; the intent processing process may include computing resources for performing operations such as intent translation and querying a database (e.g., a semantic knowledge base); and it may include storage resources for storing intent expressions, the results of intent translation, etc.

[0137] Intent translation is used to convert intent expressions into corresponding management action groups, which can be instructions that act on physical or logical entities, such as adjusting the antenna tilt angle of a base station or turning on the energy-saving switch of a cell.

[0138] 6. Feasibility check of the intention

[0139] The feasibility check of an intent can be performed by the production entity to check whether the intent is feasible. Upon receiving an intent creation or modification request from a consumer entity, the production entity can automatically perform the feasibility check, thereby obtaining an intent feasibility check report. The feasibility check may include checking the satisfaction of intent fulfillment, or whether there are potential conflicts between one or more intent instances. Potential conflicts include at least one of the following: conflicts between different intents, conflicts between different intent expectations of the same intent, or conflicts between different expected goals of the same intent.

[0140] 7. Large Model

[0141] Large models are used to provide large-scale model services. A large model refers to a neural network model containing an extremely large number of parameters. Large models can also be called foundation models. Large models play a crucial role in many fields and applications, with common applications including natural language processing, computer vision, speech recognition and synthesis, recommender systems, financial risk control, intelligent dialogue systems, game artificial intelligence (AI), and healthcare. In the future, large models will evolve towards multimodal models, which can handle data from multiple modalities; for example, multimodal large models can process natural language as well as text, images, or videos.

[0142] Large language models (LLMs) are a type of large model that is a deep learning model trained on large amounts of text data. LLMs can generate natural language text or understand the meaning of language text. LLMs can handle various natural language tasks, such as text classification, question answering, and dialogue.

[0143] 8. Large Model Application Framework

[0144] The Large Model Application Framework is a framework for developing large model applications. Based on components such as models, prompts, and memory, it provides capabilities such as prompt templates, model orchestration, large model services, and security isolation, helping developers achieve a simple, secure, and reliable experience in building large model applications. The Large Model Application Framework can be represented as a copilot or agent. It can also be replaced with other names, such as an Artificial Intelligence (AI) module, a prompt unit, or a prompt engine.

[0145] The large model application framework can be deployed in consumer entities or in other locations, such as other devices or cloud platforms, without restriction.

[0146] 9. Intelligent Agent

[0147] Intelligent agents generally refer to entities that are capable of taking initiative, possess consciousness or will, and have the ability to make decisions and choices. Common intelligent agents include at least one of the following:

[0148] AI agent / LLM-based agent: Based on the intelligent agent, AI or LLM is used to realize the perception, decision-making and other capabilities of the intelligent agent.

[0149] Autonomous agent: A system that can autonomously perceive its environment, make decisions and execute actions, and can complete tasks independently in complex environments.

[0150] Autonomous networks agent: A self-closing system that, in response to a specific network scenario, can proactively perceive the network state and its environment, analyze the perceived information, make adaptive decisions, and perform corresponding controls to achieve user goals.

[0151] 10. Prompt

[0152] Prompt is an interaction method based on natural language processing. It enables communication between users and machines by parsing natural language. The main implementation of prompt is to convert natural language into machine-recognizable instructions by building a corresponding corpus and semantic parsing model. Prompt can also construct prompts from the original text based on context, thought processes, or cue words to generate more granular tasks, guiding larger models to complete tasks better.

[0153] "Prompt" can also be described as a hint, a message, or a guide.

[0154] 11.token

[0155] In the field of artificial intelligence, especially in natural language processing (NLP), a token refers to the smallest unit or basic element of text processing. A token can be a word, a phrase, a punctuation mark, a subword, or a character, etc. Currently, many large models, whether in terms of their demonstration capabilities or pricing, use tokens as the unit. A token can be described as a word unit.

[0156] 12. Context Window

[0157] The context window refers to the number of tokens a model considers when generating a response. It determines the range of information the model can capture, similar to the contextual information humans rely on when thinking about a problem. A larger context helps the model better understand user input, maintaining coherence and consistency, thereby improving the quality and accuracy of task completion.

[0158] Typically, context windows have limitations:

[0159] 1) Computational resource limitations: Processing and generating a large number of tokens requires significant computational resources and time. To maintain responsiveness in practical applications, models typically set token limits to balance computational resource usage and performance.

[0160] 2) Memory Limitations: When generating text, the model needs to maintain context information in memory. If the generated text is too long, the required memory will increase rapidly, which places very high demands on the hardware, especially when handling multiple concurrent requests.

[0161] 3) Quality control: The longer the generated text, the more difficult it is for the model to maintain contextual consistency, which may result in repetitive, irrelevant or illogical output text.

[0162] 4) Technical Implementation: Existing transformer architectures and implementations have certain limitations on sequence length. During model training and inference, excessively long sequences can lead to an exponential increase in computational complexity.

[0163] Therefore, the limitation of the context window is intended to provide better performance and user experience in practical applications, and it is also an optimization choice under the current technology and hardware conditions.

[0164] The relevant terms used in the embodiments of this application have been explained above, and will not be explained again below. The system architecture applicable to the embodiments of this application will be described below with reference to Figures 2 and 3.

[0165] Figure 2 is a schematic structural diagram of a communication system applicable to an embodiment of this application.

[0166] Management Service Consumer Entity: The entity that invokes the management service is called the management service consumer entity. The management service consumer entity in Figure 2 can be used to invoke the large-scale model management service or the large-scale model service, or in other words, to invoke the large-scale model management service to manage the network system. The management service consumer entity can also be called a large-scale model management service consumer entity, management service consumer network element, management service consumer (MnS consumer), intent management service consumer, service consumer, intent consumer, intent owner, network management service consumer entity, etc. In future communication systems, the management service consumer entity may have other names, which this application does not specifically limit. The capabilities or functions of the management service consumer entity can be deployed on a network element, which is called the management service consumer network element; the capabilities or functions of the management service consumer entity can also be deployed on other devices, which this application embodiment does not limit. For ease of description, this application embodiment uses the management service consumer entity as an example, but all can be replaced by other devices that have deployed the capabilities or functions of the management service consumer entity.

[0167] Management Service Producing Entity: The entity that provides management services is called the management service producing entity. The management service producing entity in Figure 2 can be used to provide large-scale management services or large-scale services. For example, the management service producing entity can receive prompts from management service consuming entities and perform intent management based on the received prompts. The management service producing entity can also be called a large-scale management service producing entity, management service producing network element, intent management service provider, intent service provider, management service producer (MnS producer), intent provider, intent handler, network management service producing entity, etc. In future communication systems, the management service producing entity may have other names, which this application does not specifically limit. The capabilities or functions of the management service producing entity can be deployed on a network element, which is called a management service producing network element; the capabilities or functions of the management service producing entity can also be deployed on other devices, which this application embodiment does not limit. For ease of description, this application embodiment uses the management service producing entity as an example, but all can be replaced by other devices that have deployed the capabilities or functions of the management service producing entity.

[0168] In Figure 2, the management service consumer entity and the management service producer entity perform network management with the assistance of the large model, based on the large model management service (MnS) interface.

[0169] Figure 3 is a schematic structural diagram of another communication system applicable to the embodiments of this application.

[0170] Unlike the communication system shown in Figure 2, the management service consumer and production entities in Figure 3 perform network management with the assistance of a large model, based on an intent-driven management service (MnS) interface. The management service consumer entity in Figure 3 can invoke management services, or intent services, to manage the network system. For example, the management service consumer entity can instantiate intent templates, set intent IOCs to generate intent expressions, and send these expressions to the management service production entity to fulfill expectations for the network system. The management service production entity in Figure 3 can provide network management services. For example, the management service production entity can receive intent expressions from the management service consumer entity and perform intent translation, intent management, and intent execution and maintenance processes based on these expressions. The large model in Figure 3 assists the intent-driven management service. This large model can be deployed within the management service consumer entity, the management service production entity, or a third-party cloud, without restriction.

[0171] The entities in Figures 2 and 3 can be network elements within hardware devices, software functions running on dedicated hardware, or virtualization functions instantiated on a platform (e.g., a cloud platform). It is understood that these entities can be implemented by a single device or by multiple devices working together. Furthermore, these entities can also be functional modules within a system, such as a network management system (NMS), an equipment management system (EMS), or functional modules within a device, such as one or more functional modules within network equipment (NE). Network equipment can be a base station or a core network element.

[0172] As an example, the management service consumer entity can be deployed within the NMS, while the management service production entity can be deployed within different EMSs. The interaction between the management service consumer entity and the management service production entity can be achieved through the interface between the NMS and the EMS.

[0173] As another example, the management service consumer entity can be deployed within the EMS, while the management service production entity can be deployed within different NEs. The interaction between the management service consumer entity and the management service production entity can be achieved through the interface between the NMS and the EMS.

[0174] Optionally, the aforementioned communication system may also include other devices or network elements, such as a knowledge base or a network twin service production entity. A network twin service production entity may be, for example, a network digital twin (NDT) system or an entity deployed with an NDT system, which can be used to provide network management services.

[0175] The solution proposed in this application can also be applied to other systems that contain the corresponding entities. This application does not limit the scope of the solution, and the embodiments of this application do not impose any specific limitations on this.

[0176] It should be noted that the management service consumer entity and / or management service producer entity in Figures 2 and 3 can be an agent, or can refer to an entity in general.

[0177] It should be understood that the network architecture and business scenarios described in the embodiments of this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0178] For the sake of simplicity, the following text will refer to network management intent as intent, management service consumer entity as consumer entity, management service producer entity as producer entity, and entity with deployed large model as large model entity.

[0179] Currently, consumer entities and production entities engage in multi-round, multi-type interactions based on all existing and missing information. These interactions range from simple queries based on single attributes (such as retrieving fixed information related to that attribute) to more complex information retrieval processes. Figures 4 through 8 illustrate several negotiation methods between consumer and production entities.

[0180] Figure 4 illustrates the possible outcomes of a negotiation between a consumer entity and a production entity regarding their intentions. The intention created by the consumer entity can be evaluated by the production entity to determine the possible outcomes. The consumer entity can request the production entity to provide a list of possible outcomes for a given intention, and the production entity can then provide the consumer entity with a range of possible outcomes and their impact. These outcomes can include possible results for the intention, the desired outcome, or the desired goal.

[0181] Figure 5 is a schematic diagram illustrating the optimal possible outcomes of a negotiation between a consumer entity and a production entity regarding their intentions. The intention created by the consumer entity can be evaluated by the production entity to determine the possible outcomes. The consumer entity can request the production entity to provide the optimal possible outcomes for a given intention, intention expectation, or desired goal. The production entity can then provide the consumer entity with a list of optimal possible outcomes and their impact. These outcomes can include possible implementations of the intention, intention expectation, or desired goal.

[0182] Figure 6 illustrates how a producer recommends potential achievable intents and contexts to a consumer. If a consumer wants to achieve a given intent, and the producer confirms that the intent cannot be achieved, the producer can recommend potential achievable intents and contexts to the consumer. The consumer can then modify its intent based on the producer's recommendations.

[0183] Figure 7 is a schematic diagram illustrating how a consumer entity suggests alternatives to a production entity. The consumer entity wants to achieve a given intention, and the production entity confirms that this intention can be achieved. However, the production entity has multiple alternatives that can achieve this intention. The production entity can provide these alternatives and their corresponding effects to the consumer entity and request the consumer entity to provide a preferred alternative. The consumer entity can provide the production entity with one or more of the following: its preferred alternative, a utility function, or the relative level of satisfaction achieved by each alternative. The production entity can then select and implement the alternative based on the information provided by the consumer entity.

[0184] Figure 8 is a schematic diagram of a consumer entity suggesting preferred alternatives to a production entity. The consumer entity wants to achieve a given intention, and the production entity has multiple alternatives related to achieving that intention. The production entity independently selects the alternative to apply. After confirming that these alternatives do not yield better results, the production entity reports the achieved result (an imperfect implementation) to the consumer entity and indicates that if the consumer entity is dissatisfied with the result, it should provide additional information to help select a better alternative.

[0185] For a more detailed description of Figures 4 through 8, please refer to the intent negotiation in protocol 3GPP TR 28.914.

[0186] As can be seen from the above, the intent has a multi-layered structure and many attributes, as detailed below:

[0187] 1) Intents contain intention expectations, and intention expectations contain expected goals and expected objects, and these attributes each have their own context;

[0188] 2) A single attribute and / or a combination of multiple attributes in the intent may require multiple rounds of negotiation.

[0189] Figure 9 is an example of multi-round interactions between consumer entities and production entities.

[0190] Step 901: The consumer entity requests the production entity to conduct a feasibility check on the intention.

[0191] Step 902: After a feasibility check, the scope of the production entity's feedback intent to the consumer entity is not clearly expressed.

[0192] Step 903: The consumer entity can query the production entity for information related to the area of ​​effect.

[0193] Step 904: The producing entity returns information related to the scope of action to the consuming entity.

[0194] Steps 901-904 involve the consumer entity and the production entity negotiating for a single attribute (scope of action).

[0195] Consumer entities and production entities can also negotiate on combined attributes, as shown in steps 905-910.

[0196] Step 905: The consumer entity requests the producer entity to provide the best possible outcome for realizing the intent.

[0197] Step 906: The producing entity recommends the best target and context to the consuming entity.

[0198] Step 907: The consumer entity is dissatisfied with the production entity's recommendation and sends the following information to the production entity: 1) For expectation 1, please list all possible values ​​and their corresponding impacts; 2) For expectation 2, provide preference information (such as prioritizing energy saving).

[0199] Step 908, the producing entity provides the consuming entity with the following information: 1) for expectation 1, all possible values ​​and their corresponding effects; 2) for expectation 2, the best target and context recommended again based on preferences.

[0200] Step 909: The consumer entity sends new information related to the attributes to be confirmed to the producer entity.

[0201] Negotiation between consumer and producer entities can be achieved with the aid of a large model. This large model needs to generate responses within a context window; however, considering factors such as computing resources, memory, response quality, and technical implementation, the context window is not infinitely large and usually has limitations. In multi-turn, multi-type interactions, excessive conversation content may accumulate and exceed the context window of the large model. Once the conversation content exceeds the context window, attributes from earlier communications may be forgotten, potentially affecting the logic and coherence of subsequent dialogues. Furthermore, the longer the context, the greater the response latency of the large model, which can impact consumer satisfaction with the intent service.

[0202] To address the aforementioned issues, this application provides a communication method and a communication device to ensure the logic and coherence of large-scale model sessions, thereby improving the satisfaction of network management services.

[0203] The method embodiments of this application are described below.

[0204] Figure 10 is a schematic flowchart of a communication method 1000 provided in this application.

[0205] The method shown in Figure 10 can be performed by a consumer entity and a production entity. Unless otherwise specified, "consumer entity" or "production entity" can refer to the consumer entity or production entity itself, or a component in the consumer entity or production entity (e.g., a circuit, chip, or chip system (such as a modem chip, or a SoC chip or SIP chip containing a modem core, etc.), or a logic module or software that can implement all or part of the functions of the consumer entity or the production entity.

[0206] It should be noted that the large model involved in the embodiments of this application can be deployed within or outside the production entity, without limitation. When the large model is deployed outside the production entity, the production entity can generate an effect prompt based on the expression of the consumer entity and send it to the large model. In this case, the embodiment of this application refers to the entity with the large model deployed as the large model entity.

[0207] Method 1000 may include some or all of the following.

[0208] Step 1001: The production entity obtains the first attribute to be confirmed.

[0209] The first attribute is the attribute of the first intent. "The first attribute is pending confirmation" can be understood as: the value or information of the first attribute needs to be confirmed. "Pending confirmation" can also be replaced with: pending interaction or negotiation, etc. The first intent can be of various types. The type of the first intent can be related to the goal contained within it. For example, the goal of the intent may include achieving a performance metric value within a corresponding performance metric range. When the performance metric is a throughput metric, such as an average downlink throughput greater than or equal to 5 Mbps, the intent can be called a throughput intent; when the performance metric is an energy-saving metric, such as energy saving greater than or equal to 10 kilowatts, the intent can be called an energy-saving intent.

[0210] The embodiments of this application do not limit the implementation method of the production entity obtaining the first attribute.

[0211] In some implementations, the production entity can perform a feasibility check on the initial intent, identify ambiguous attributes, and form a set of attributes to be confirmed, which includes the initial attribute.

[0212] In other implementations, the consumer entity can send first information to the producer entity, and correspondingly, the producer entity can receive first information from the consumer entity, wherein the first information is used to indicate a first attribute. The first information can be carried in a first message. The embodiments of this application do not limit the type of the first message. Exemplarily, the first message is used to modify a first intent, such as an intent modification message. Exemplarily, the first message is used to request negotiation, such as a negotiation request message. Exemplarily, the first message is used to request negotiation, such as a negotiation request message.

[0213] The embodiments of this application do not limit the implementation of the first information.

[0214] Implementation Method 1: The first information includes a first attribute. This can be understood as follows: when a consumer entity wants to interact with a production entity about a first attribute, the consumer entity can include the first attribute in the first information sent to the production entity. For example, if the first attribute is the expected object of an energy consumption target, the first information can include both the energy consumption target and the expected object. Alternatively, if the first attribute includes the energy consumption target, the expected object, the object context, and the target context, the first information can include these three elements. Another example is that the first attribute includes the expected context, the expected object, the object context, the energy consumption target, the target context of the energy consumption target, the energy efficiency target, and the context of the energy efficiency target. The first information can include the expected context, the expected object, the object context, the energy consumption target, the target context of the energy consumption target, the energy efficiency target, and the context of the energy efficiency target.

[0215] In implementation method 2, the first information includes granularity information and part or all of the first attribute. The granularity information indicates the granularity of the interaction, or in other words, whether the attribute to be confirmed (i.e., part or all of the first attribute) included in the first information has a dependency relationship with other attributes. "Particle size" can also be replaced with "type". If the granularity information indicates that the attribute to be confirmed included in the first information has no dependency relationship with other attributes, then the attribute to be confirmed can be directly confirmed individually through interaction. If the granularity information indicates that the attribute to be confirmed included in the first information has a dependency relationship with other attributes, the production entity can obtain the first attribute based on the granularity information and the attribute to be confirmed (part or all of the first attribute) included in the first information, and confirm the first attribute as a combination.

[0216] The embodiments of this application do not limit the specific classification of interaction granularity.

[0217] In some implementations, interaction granularity can include single-attribute granularity and composite-attribute granularity.

[0218] For example, the first information includes first granularity information, which indicates that the interaction granularity is single-attribute granularity. In this case, the attribute to be confirmed included in the first information is the first attribute, and the attribute to be confirmed can be directly interacted with and confirmed individually. For example, the first attribute includes one attribute. For example, single-attribute-based interaction can be applied to scenarios where the value of the interacting attribute or information is not affected by other attributes and can be interacted with independently. Single-attribute-based interaction requires the large model to have basic knowledge of the relevant attributes.

[0219] For example, the first information includes second granularity information, which indicates that the interaction granularity is a composite attribute granularity. In this case, the attribute to be confirmed included in the first information may be the first attribute or a part of the first attribute. There are dependencies between the attributes to be confirmed included in the first information and / or the attributes to be confirmed included in the first information are dependent on other attributes. For example, the first attribute includes multiple attributes, and the values ​​of these multiple attributes influence each other. The attribute to be confirmed included in the first information and other attributes that this attribute depends on can form an attribute combination. For example, an attribute combination includes a desired target, a desired object, and a corresponding context. In this case, the production entity can obtain the first attribute (i.e., the attribute combination with dependencies) based on the granularity information and the attribute to be confirmed included in the first information. When confirming the value of the attribute to be confirmed included in the first information, the values ​​of each attribute are comprehensively confirmed on a unit basis, using the first attribute as the unit.

[0220] Combined attributes can be single-objective combined attributes or multi-objective combined attributes.

[0221] The attribute combination containing a single-objective combined attribute can include one or more attributes of a single objective. For example, the first attribute is a single-objective combined attribute, which may include a first desired objective, a first desired object, and a first context, wherein the first context may include at least one of the following: the context of the first desired objective, or the context of the first desired object. For example, interaction based on single-objective combined attributes is suitable for scenarios where one wants to confirm whether a relevant objective can be achieved and / or improved based on historical information. Interaction based on single-objective combined attributes requires the large model to have information update capabilities.

[0222] For example, the first attribute may be an energy consumption target, a desired object, an object context, and a target context. The first information may carry at least one of the energy consumption target, the desired object, the object context, or the target context, as well as second granularity information. After receiving the first information, the production entity learns from the second granularity information that the interaction granularity is a combined attribute granularity. Then, based on the attribute to be confirmed carried in the first information (i.e., at least one of the energy consumption target, the desired object, the object context, or the target context), it determines that the first attribute is an energy consumption target, the desired object, the object context, and the target context.

[0223] The attribute combination containing a multi-objective combined attribute can include multiple attributes of multiple objectives. For example, the first attribute is a multi-objective combined attribute, which can include multiple second desired objectives, second desired objects, and a second context. The second context includes at least one of the following: the context of some or all of the multiple second desired objectives, the context of the second desired object, and the desired context. For example, interaction based on multi-objective combined attributes is suitable for situations where there may be conflicts between desired objectives, requiring a comprehensive determination of the optimal value of the desired objective. Interaction based on multi-objective combined attributes requires the large model to have conflict recognition capabilities.

[0224] For example, the first attribute may be the expected context, the expected object, the object context, the energy consumption target, the target context of the energy consumption target, the energy efficiency target, and the context of the energy efficiency target. The first information may carry at least one of the expected context, the expected object, the object context, the energy consumption target, the target context of the energy consumption target, the energy efficiency target, and the context of the energy efficiency target, as well as the second granularity information. After receiving the first information, the production entity learns from the second granularity information that the interaction granularity is the combined attribute granularity. Then, based on the attribute to be confirmed carried in the first information (i.e., at least one of the expected context, the expected object, the object context, the energy consumption target, the target context of the energy consumption target, the energy efficiency target, and the context of the energy efficiency target), it determines that the first attribute is the expected context, the expected object, the object context, the energy consumption target, the target context of the energy consumption target, the energy efficiency target, and the context of the energy efficiency target.

[0225] Figure 11 is an example of single attributes and composite attributes.

[0226] As shown in Figure 11, the intent includes two expectations, namely Expectation 1 and Expectation 2. Expectation 1 includes two expected targets, namely Expected Target 1 and Expected Target 2. Expectation 2 also includes two expected targets, namely Expected Target 3 and Expected Target 4. If the value or information of Object Context 2 is not affected by other attributes, then the attribute of Object Context 2 is a single attribute and can be queried independently. Target 3, Target Context 3, Expected Object 2, and Object Context 2 are interdependent and can be combined as an attribute to comprehensively confirm the value or information. In this case, Target 3, Target Context 3, Expected Object 2, and Object Context 2 can be a single-target combined attribute. Expectation 1, Expected Object 1, Object Context 1, Target 1, Target Context 1, Target 2, Target Context 2, and Expected Context 1 are interdependent and can be combined as an attribute to comprehensively confirm the value or information. In this case, Expectation 1, Expected Object 1, Object Context 1, Target 1, Target Context 1, Target 2, Target Context 2, and Expected Context 1 can be a multi-target combined attribute.

[0227] Step 1002: The production entity and the consumer entity conduct a first interaction through a first session to confirm the value of the first attribute.

[0228] The first interaction can include one or more interactions, without limitation. "Interaction" can also be replaced with "negotiation," "dialogue," etc.

[0229] The first session is associated with the first attribute. The association of the first session with the first attribute can be understood as follows: the first session is dedicated to the first attribute, or the first interaction conducted through the first session affects the value of the first attribute without affecting the values ​​of the remaining attributes of the first network management intent, or the first interaction conducted through the first session is dedicated to determining the value of the first attribute.

[0230] It should be understood that the value of the first attribute can refer to the specific value of the first attribute, or it can refer to the value of a characteristic related to the first attribute, such as the specific target name of the first attribute. Taking energy consumption target as an example, the value of the first attribute can be the specific energy consumption value of the energy consumption target, or it can be an energy consumption adjustment percentage, etc.

[0231] The embodiments of this application do not limit the timing of the start of the first session.

[0232] In some implementations, the consumer entity can proactively create or initiate the first session.

[0233] For example, a consumer entity can indirectly instruct the creation or initiation of a first session. This could be achieved by sending rules / policies / guidelines / instructions to a producer entity to indirectly instruct the creation or initiation of the first session. For instance, a consumer entity can indirectly instruct the creation or initiation of a first session through first information. In other words, upon receiving the first information, the producer entity can create or initiate a first session for a first attribute based on that information. Creating or initiating a first session for a first attribute can be understood as configuring or assigning a session identifier to the first attribute to identify interactions related to that attribute.

[0234] For example, a consumer entity can directly instruct the creation or initiation of a first session. In this case, before the first interaction via the first session, the consumer entity can also send a second message to the producer entity. The producer entity receives the second message from the consumer entity, which instructs the creation or initiation of the first session. For instance, if the first session is a sub-section, the second message can carry a sub-section attribute. When the sub-section attribute is set to "on," it means the producer entity needs to create or initiate a sub-section. It should be understood that the second message and the first message can be carried in the same message or in different messages, without restriction.

[0235] Optionally, after the production entity creates the first session, the production entity may also send a third message to the consumer entity. Accordingly, the consumer entity receives the third message from the production entity, which is used to indicate the start of the first session.

[0236] In other implementations, the producing entity may proactively create or initiate the first session. For example, if the producing entity obtains the first attribute based on a feasibility check of the intent, it can create or initiate the first session after obtaining the first attribute to negotiate the value of the first attribute with the consuming entity.

[0237] For example, a producer entity can indirectly instruct the creation or initiation of a first session. For instance, a producer entity can indirectly instruct the creation or initiation of a first session by sending information related to a first attribute to a consumer entity.

[0238] For example, a producer entity can directly instruct the creation or initiation of a first session. In this case, before the first interaction via the first session, the producer entity can also send third information to the consumer entity. Accordingly, the consumer entity receives the third information from the producer entity, which indicates the start of the first session. For example, if the first session is a sub-session, the third information can carry sub-session attributes. When the sub-session attribute is set to "on," it means that a sub-session has started. It should be understood that the information related to the first attribute in the third information can be carried in the same message or in different messages, without restriction.

[0239] The embodiments of this application do not limit the timing of the end of the first session.

[0240] In some implementations, the consumer entity can proactively end the first session.

[0241] For example, a consumer entity can indirectly indicate the termination of the first session. For instance, the consumer entity can indirectly indicate the creation or start of the first session using information used to confirm the value of the first attribute. In other words, after receiving information to confirm the value of the first attribute, the producer entity can terminate the first session associated with the first attribute based on the first information. Terminating the first session associated with the first attribute can mean: deleting the first session, or deleting the context associated with the first session.

[0242] For example, the consumer entity can directly instruct the creation or initiation of a first session. In this case, after the first interaction through the first session, i.e., after confirming the value of the first attribute, the consumer entity can also send a fourth message to the producer entity. Accordingly, the producer entity receives the fourth message from the consumer entity, whereby the fourth message indicates the end of the first session. For example, if the first session is a sub-session, the fourth message can carry the sub-session identifier and sub-session attributes. When the sub-session attribute is set to "off," it means that the producer entity needs to end the sub-session. It should be understood that the fourth message and the information used to confirm the value of the first attribute can be carried in the same message or in different messages, without limitation.

[0243] In other implementations, the production entity may terminate the first session. For example, in a scenario where the production entity obtains the first attribute based on a feasibility check of the intent, or where the production entity obtains the first attribute based on granular information sent by the consumer entity and part or all of the first attribute, the production entity terminates the first session associated with the first attribute after confirming the value of the first attribute.

[0244] Optionally, the producing entity can also indicate to the consuming entity that the first session has ended.

[0245] Step 1003: After confirming the value of the first attribute, the production entity deletes the context associated with the first session.

[0246] For example, the context associated with the first session may include at least one of the following: the identifier of the first session, or the dialogue in the first session.

[0247] The context related to the first session can also be replaced with: the context of interaction through the first session, the dialogue content of interaction through the first session, the information of interaction through the first session, the message of interaction through the first session, the dialogue of interaction through the first session, the dialogue content related to the first session, the dialogue related to the first session, the interaction content related to the first session, or the interaction information related to the first session, etc.

[0248] In method 1000, the producing entity and the consuming entity negotiate and confirm the value of the first attribute through the first session associated with the first attribute, and promptly delete the context related to the first session after confirming the value of the first attribute. This helps to reduce the occurrence of dialogue content exceeding the context window of the large model, thereby reducing the occurrence of forgotten information, improving the logic and coherence of the dialogue, and improving the satisfaction of network management services.

[0249] In some other embodiments of this application, method 1000 may further include: after confirming the value of the first attribute, the production entity updates the first intent according to the value of the first attribute. Specifically, after confirming the value of the first attribute and before deleting the context related to the first session, the production entity updates the value of the first attribute to the structured first intent.

[0250] In some other embodiments of this application, if there are still attributes to be confirmed subsequently, such as a second attribute to be confirmed, then method 1000 may further include: after deleting the context associated with the first session, obtaining the second attribute to be confirmed, wherein the second attribute is an attribute of the first intent; then performing a second interaction with the consumer entity through a second session associated with the second attribute to confirm the value of the second attribute; and after confirming the value of the second attribute, deleting the context associated with the second session. Detailed descriptions of these steps can be found in steps 1001 to 1003, and will not be elaborated further.

[0251] In the embodiments of this application, the interaction between the consumer entity and the producer entity is implemented with the assistance of a large model. Therefore, method 1000 may further include: generating a first prompt, which prompts the large model to perform a first operation, wherein the first operation includes: confirming the value of a first attribute with the consumer entity based on a first session, and deleting the context associated with the first session after confirming the value of the first attribute. Optionally, the first operation may further include at least one of the following: updating a first intent based on the value of the first attribute; confirming the value of a second attribute with the consumer entity through a second session, and deleting the context associated with the second session after confirming the value of the second attribute.

[0252] It should be understood that the consumer entity can generate the first prompt and send it to the production entity (or the large model within the production entity), or the consumer entity can provide the information to generate the first prompt, and then the production entity can generate the first prompt based on the information provided by the consumer entity and provide it to the large model; there is no restriction. It should also be understood that when the large model is deployed outside the production entity, the production entity providing the first prompt to the large model can mean that the production entity sends the first prompt to the large model entity.

[0253] Below are some examples of the first prompt based on granular information.

[0254] Example 1: When the interaction granularity is single attribute granularity, the first prompt is as follows:

[0255] {

[0256] Template Name: "Intent Translation - Single Attribute Confirmation";

[0257] "Template Description": "This template is used when, in expressing intent in natural language, it is necessary to communicate in depth about one or more individual attributes to confirm the value of the attribute."

[0258] Template Content: "1. You are an intent translation expert who translates user intents expressed in natural language into structured intents. 2. Create separate subsections for attributes that the user has not clearly expressed or that the user requires further confirmation for. 3. Dialogue within a subsection only affects the value of the corresponding attribute, not the values ​​of other attributes. After confirming the value of the corresponding attribute, update it in the structured intent and delete all interaction contexts within the subsection. 4. Create a subsection for the next attribute to be confirmed, indicating that all attribute values ​​have been cleared or that the attributes the user needs to communicate have been communicated."

[0259] }

[0260] Example 2: When the interaction granularity is a single-target composite attribute granularity, the first prompt is as follows:

[0261] {

[0262] Template Name: "Intent Translation - Combined Attribute Confirmation (Single Target)";

[0263] "Template Description": "This template is used when expressing intent in natural language, and further in-depth communication is needed regarding the combination of attributes containing a single objective to confirm the attribute values ​​within the combination."

[0264] Template Content: "1. You are an intent translation expert who translates user intents expressed in natural language into structured intents. 2. Create separate subsections for attributes that the user has not clearly expressed or for attribute combinations that the user requires further confirmation of. A complete combination includes the target, the target object, and its context. 3. The values ​​of attributes within a combination may affect each other. Please consider the attributes within the combination as a whole, combined with historical combination values, to determine whether it is reasonable. 4. Dialogue within a subsection only affects the values ​​within the corresponding attribute combination, not the values ​​of other attributes. After confirming the values ​​within the corresponding attribute combination, update it in the structured intent and delete all interaction context within the subsection. 5. Create a subsection for the next attribute combination to be confirmed, until all attribute values ​​have been cleared or the attribute combinations that the user needs to communicate have been communicated."

[0265] }

[0266] Example 3,

[0267] {

[0268] Template Name: "Intent Translation - Combined Attribute Confirmation (Multi-Target)";

[0269] "Template Description": "This template is used when expressing intent in natural language, and additional in-depth communication is needed for attribute combinations that contain multiple objectives to confirm the attribute values ​​within the combination."

[0270] Template Content: "1. You are an intent translation expert who translates user intents expressed in natural language into structured intents. 2. Create separate subsections for attributes that the user has not clearly expressed or for attribute combinations that the user requires further confirmation for. A complete combination includes the target, the target object, and its context. When the user expresses a single attribute, the entire expectation including the attribute is considered as a complete combination. 3. The values ​​of attributes within a combination may affect each other. Please treat the attributes within the combination as a whole, and if necessary, call other functional modules (such as digital twins) to determine whether the target value is reasonable and whether there are any conflicts between targets. 4. Dialogue within a subsection only affects the values ​​within the corresponding attribute combination, and does not affect the values ​​of other attributes. After confirming the values ​​within the corresponding attribute combination, only retain the values ​​of the attributes within the combination and delete all interaction context within the subsection. 5. Create a subsection for the next attribute combination to be confirmed, until all attribute values ​​have been cleared or the attribute combinations that the user needs to communicate have been communicated."

[0271] It should be noted that the first, second, third, or fourth information mentioned above can be an attribute of the intent IOC in the corresponding message, an attribute of the intent IOC in the corresponding message, or a message element independent of the intent IOC in the corresponding message, without restriction.

[0272] The following section provides a detailed description of Method 1000, using the example of a consumer entity actively creating a sub-session and a large model being deployed within a production entity.

[0273] Figure 12 is a schematic flowchart of the communication method 1200 provided in this application.

[0274] In method 1200, entity #1 can correspond to the consumer entity mentioned above, and entity #2 can correspond to the producer entity mentioned above.

[0275] Method 1200 may include at least a portion of the following:

[0276] Step 1201: Entity #1 sends an intent creation request to entity #2, and correspondingly, entity #2 receives the intent creation request from entity #1.

[0277] Among them, intent creation requests include intents expressed in natural language.

[0278] For example, Entity #1 could be a customer's self-developed information technology (IT) system, etc. Entity #2 could be a vendor's equipment network management system, mobile broadband automation engine (MAE), etc.

[0279] Step 1202: Entity #2 transforms the intent expressed in natural language into a structured intent, identifies unclear attributes (or ambiguous attributes) through operations such as feasibility checks, and determines the set of attributes to be confirmed.

[0280] Step 1203: Entity #2 sends a set of attributes to be confirmed to entity #1, and correspondingly, entity #1 receives the set of attributes to be confirmed from entity #2.

[0281] The set of attributes to be confirmed can also be replaced with: one or more attributes to be confirmed, or attribute information to be confirmed, or attributes to be confirmed, etc.

[0282] It should be noted that steps 1201 to 1203 are optional.

[0283] Step 1204: Entity #1 sends information #1 to entity #2, and correspondingly, entity #2 receives information #1 from entity #1.

[0284] Here, information #1 is used to indicate the start of a sub-section, such as the sub-section attribute included in information #1 being set to "on" (subSection = on), and information #1 includes attribute #1 (such as the scope). Information #1 can correspond to the first and second information mentioned above. Attribute #1 can be an attribute from the set of attributes to be confirmed in step 1203, or it can be other attributes that entity #1 expects to interact with or confirm, without restriction.

[0285] Step 1205: Entity #2 obtains information related to attribute #1 and sends the information related to attribute #1 to entity #1 through sub-session #1.

[0286] Optionally, entity #2 can create session #1 for attribute #1.

[0287] The information related to attribute #1 can be information stored, retrieved, and maintained by entity #2. For example, if attribute #1 is region A, the information related to attribute #1 can be the cells in service in region A stored or maintained in entity #2.

[0288] Step 1206: Entity #1 sends new information related to attribute #1 to entity #2 through sub-session #1 based on the information related to attribute #1 returned by entity #2.

[0289] Entities #1 and #2 can repeat steps 1205 and 1206 until entity #1 confirms the value of attribute #1. Repeated steps 1205 and 1206 correspond to the first interaction described above.

[0290] For example, within sub-session #1, or through sub-session #1, entity #1 and entity #2 can interact as follows:

[0291] {

[0292] Entity 2: You need to select the object type for region A. Optional values ​​include wireless subnet, slice subnet, and core subnet.

[0293] Entity 1: Wireless subnet.

[0294] Entity 2: Optionally, you can further restrict the wireless subnet of Area A, such as its standard and frequency band.

[0295] Entity 1: Only for NR.

[0296] Entity 2: The target of the operation is "all NR wireless subnets within Area A".

[0297] }

[0298] Step 1207: After entity #2 sends the final value of attribute #1 to entity #1, entity #1 sends information #3 to entity #2, and correspondingly, entity #2 receives information #3 from entity #1.

[0299] As an example, message #3 is used to indicate the value of attribute #1 for confirmation, acceptance, or agreement, and to indicate the end of sub-session #1, such as when the sub-session attribute included in message #3 is set to off.

[0300] As another example, message #3 is used to indicate the value of attribute #1, indicating confirmation, acceptance, or agreement. Entity #1 can directly indicate the end of sub-session #1 through other messages or information, such as when the sub-session attribute is set to "off" (subSection = off).

[0301] In step 1208, entity #2 updates the value of the confirmed attribute #1 in the structured intent and deletes the sub-session #1 associated with attribute #1.

[0302] Based on method 1200, the active creation and timely deletion of sub-sessions by entity 1 can minimize the possibility of dialogue content exceeding the token limit of the context window, reduce the occurrence of forgotten information, thereby improving the logic and coherence of the dialogue and enhancing customer satisfaction.

[0303] The following example illustrates Method 1000 in detail, using the example of a consumer entity providing interaction granularity information to instruct a production entity to create a sub-session and a large model being deployed within the production entity.

[0304] Figure 13 is a schematic flowchart of the communication method 1300 provided in this application.

[0305] Method 1300 may include at least a portion of the following:

[0306] In method 1300, entity #1 can correspond to the consumer entity mentioned above, and entity #2 can correspond to the producer entity mentioned above.

[0307] Step 1301: Entity #1 sends an intent creation request or intent modification request to entity #2, and correspondingly, entity #2 receives the intent creation request or intent modification request from entity #1.

[0308] The intent creation request or intent modification request includes an intent expressed in natural language. In method 1300, the intent creation request or intent modification request may also include granularity information and attribute #2 to be confirmed, whereby the granularity information indicates the granularity of the interaction.

[0309] Example a, the intent to create a request or intent to modify a request includes: ensuring that the average throughput of area A is greater than 10Mbps, while the energy consumption is less than 20KWh, the time is from 12:00 to 22:00 on November 1, 2024, the interaction granularity is a single attribute, and the attribute to be confirmed #2 is the target object (i.e., area A).

[0310] Example b, the intent to create a request or intent to modify a request includes: ensuring that the average throughput of all wireless subnets in area A is greater than 10Mbps, while the power consumption is <20KWh, the time is from 12:00 to 22:00 on November 1, 2024, the interaction granularity is a combined attribute (or a combined attribute based on a single target), and the attribute to be confirmed #2 is throughput.

[0311] For example, entity #1 can be a consumer entity, such as a customer's self-developed IT system. Entity #2 can be a production entity, such as a manufacturer's equipment network management system or MAE.

[0312] Step 1302: Entity #2 transforms the intent expressed in natural language into a structured intent, identifies other unclear attributes (or ambiguous attributes) through operations such as feasibility checks, and determines the set of attributes to be confirmed.

[0313] It should be noted that step 1302 is an optional step.

[0314] Step 1303: Entity #2 creates a sub-session #2 for at least one attribute to be confirmed (including attribute #2) and obtains information related to at least one attribute to be confirmed.

[0315] Example c, combined with example a, entity #2 creates a sub-session #2 for the target object and retrieves information related to region A.

[0316] In Example d, combined with Example b, entity #2 creates subsession #2 for the attribute combination "Average throughput of all wireless subnets in region A" (a complete combination includes target, target, and context).

[0317] In step 1304, entity #2 sends information #4 to entity #1 through sub-session #2, and correspondingly, entity #1 receives information #4 from entity #2.

[0318] As an example, message #4 is used to indicate the start of sub-session #2, such as the sub-session attribute included in message #4 being set to "on" (subSection = on), and message #4 also includes information related to at least one attribute to be confirmed.

[0319] As another example, message #4 includes information related to at least one attribute to be confirmed. Entity #2 directly indicates the start of sub-session #2 via a separate message.

[0320] Step 1305: Entity #1 sends new information related to at least one attribute to be confirmed to Entity #2 through sub-session #2, based on the information returned by Entity #2 related to at least one attribute to be confirmed.

[0321] Entities #1 and #2 can repeat steps 1304 and 1305 until entity #1 confirms the value of at least one attribute to be confirmed. Repeated steps 1304 and 1305 can correspond to the first interaction described above.

[0322] For example, referring to example a, within sub-session #2, or through sub-session #2, entities #1 and #2 can interact as follows:

[0323] {

[0324] Entity 2: You need to select the object type for region A. Optional values ​​include wireless subnet, slice subnet, and core subnet.

[0325] Entity 1: Wireless subnet.

[0326] Entity 2: Optionally, you can further restrict the wireless subnet of Area A, such as its standard and frequency band.

[0327] Entity 1: Only for NR.

[0328] Entity 2: The target of the operation is "all NR wireless subnets within Area A".

[0329] }

[0330] For example, referring to example b, within sub-session #2, or through sub-session #2, entities #1 and #2 can interact as follows:

[0331] {

[0332] Entity 2: Setting the average throughput of all wireless subnets in Area A to 10Mbps is reasonable, with a historical high of 15Mbps.

[0333] Consumer: Then set the target to 15Mbps.

[0334] Entity 2: The average throughput of all wireless subnets within Area A will be set to 15 Mbps.

[0335] }

[0336] Step 1306: After entity #2 sends the final value of attribute #1 to entity #1, entity #1 sends information #5 to entity #2, and correspondingly, entity #2 receives information #5 from entity #1.

[0337] As an example, message #5 is used to indicate confirmation, acceptance, or agreement to the value of at least one attribute to be confirmed, and to indicate the end of sub-session #2, such as when the sub-session attribute included in message #5 is set to "off".

[0338] As another example, message #5 is used to indicate confirmation, acceptance, or agreement to the value of at least one attribute to be confirmed. Entity #1 can directly indicate the end of sub-session #2 through other messages or information, such as the sub-session attribute being set to "off" (subSection = off).

[0339] In step 1307, entity #2 updates the value of at least one confirmed attribute to the structured intent, deletes sub-session #2, and creates sub-session #3 for the next attribute or combination of attributes to be interacted with.

[0340] In method 1300, the total number of child sessions created is greater than 1 in the following two cases:

[0341] 1) When the interaction granularity is a single attribute, and the number of interaction attributes is greater than 1;

[0342] 2) When the interaction granularity is a combination of attributes based on a single goal, the number of interaction attributes is greater than 1, and the number of expectations to which the interaction attributes belong is greater than 1.

[0343] In method 1300, entity 1 instructs entity 2 to create a sub-session by sending granular information. Entity 2 autonomously creates the sub-session based on the granular information, reducing the transmission resources required for entity 1 to send multiple sub-session creation requests. Simultaneously, entity 2 can precisely define the scope of attributes associated with a sub-session based on the granular information, helping to further prevent dialogue content from exceeding the context window's token limit and reducing the likelihood of forgetting previously interacted information. This further improves the logic and coherence of the dialogue, comprehensively enhancing customer satisfaction. Furthermore, this method reduces the difficulty of negotiating attribute values ​​through sub-sessions associated with attributes, allowing for more frequent use of this approach and further reducing the occurrence of dialogue content exceeding the context window's token limit.

[0344] The following describes method 1000 in detail, taking as examples a consumer entity providing interaction granularity information to instruct a production entity to create a sub-session, a large model being deployed outside the production entity, and a large model being an LLM.

[0345] Figure 14 is a schematic flowchart of the communication method 1400 provided in this application.

[0346] Method 1400 may include at least a portion of the following.

[0347] In method 1400, entity #1 can correspond to the consumer entity mentioned above, and entity #2 can correspond to the producer entity mentioned above.

[0348] Step 1401: Entity #1 sends an intent creation request or intent modification request to entity #2, and correspondingly, entity #2 receives the intent creation request or intent modification request from entity #1.

[0349] The intent creation request or intent modification request includes an intent expressed in natural language. In method 1400, the intent creation request or intent modification request may also include granularity information and attribute #2 to be confirmed, the granularity information being used to indicate the granularity of the interaction.

[0350] It should be noted that the implementation method of step 1401 can refer to step 1301.

[0351] Step 1402: Entity #2 generates the corresponding prompt based on the intent to create a request or intent to modify a request.

[0352] Specifically, entity #2 generates the corresponding prompt based on the expression of entity #1 (or the consumer).

[0353] An example of prompt template content can be shown below:

[0354] {

[0355] 1. You are an intent translation expert. If the user expresses their intent in natural language, you will translate the user's intent in natural language into structured intent.

[0356] 2. Create a separate sub-session for the attribute that the user requires further confirmation of.

[0357] 3. Dialogue within a sub-session only affects the value of the corresponding attribute, not the values ​​of other attributes. After confirming the value of the corresponding attribute, update it in the structured intent and delete all interaction contexts within the sub-session.

[0358] 4. Start a sub-session for the next attribute to be confirmed, until all attribute values ​​are clear or all attributes that the user needs to communicate have been communicated.

[0359] }

[0360] In step 1403, entity #2 sends the prompt generated in step 1402 to the LLM, and correspondingly, the LLM receives the LLM from entity #2.

[0361] Step 1404: Upon receiving the prompt, the LLM creates a sub-session #4 for at least one attribute to be confirmed. Examples can be found in examples c and d of method 1300.

[0362] It should be understood that the LLM creating a sub-session #4 for at least one attribute to be confirmed can be understood as: entity #2 creating a sub-session #4 for at least one attribute to be confirmed by calling the LLM.

[0363] Step 1405, entity #2 obtains information related to at least one attribute to be confirmed through sub-session #4.

[0364] Entity #2 obtains information related to at least one attribute to be confirmed through sub-session #4. This can be understood as: Entity #2 calls LLM through sub-session #4 to obtain information related to at least one attribute to be confirmed.

[0365] In step 1406, entity #2 sends information #6 to entity #1 through sub-session #4, and correspondingly, entity #1 receives information #6 from entity #2.

[0366] As an example, message #6 is used to indicate the start of sub-session #4, such as the sub-session attribute included in message #6 being set to "on" (subSection = on), and message #6 also includes information related to at least one attribute to be confirmed.

[0367] As another example, message #6 includes information related to at least one attribute to be confirmed. Entity #2 directly instructs sub-session #4 to begin via a separate message.

[0368] Step 1407: Entity #1 sends new information related to at least one attribute to be confirmed to entity #2 through sub-session #4, based on the information returned by entity #2 related to at least one attribute to be confirmed.

[0369] Entities #1 and #2 may repeat steps 1406 and 1407 until entity #1 confirms the value of at least one attribute to be confirmed. Repeated steps 1406 and 1407 may correspond to the first interaction described above. An example of the interaction between entities #1 and #2 can be found in step 1305.

[0370] It should be understood that the interaction between entity #1 and entity #2 can be interpreted as: entity #1 interacts with the LLM through entity #2, or entity #2 interacts with entity #1 based on the assistance of the LLM when entity #1 interacts with entity #2.

[0371] Step 1408: After entity #2 sends the final value of attribute #1 to entity #1, entity #1 sends information #7 to entity #2, and correspondingly, entity #2 receives information #7 from entity #1.

[0372] As an example, message #7 is used to indicate confirmation, acceptance, or agreement to the value of at least one attribute to be confirmed, and to indicate the end of sub-session #4, such as when the sub-session attribute included in message #7 is set to "off".

[0373] As another example, message #7 is used to indicate confirmation, acceptance, or agreement to the value of at least one attribute to be confirmed. Entity #1 can directly indicate the end of sub-session #4 through other messages or information, such as the sub-session attribute being set to "off" (subSection = off).

[0374] In step 1409, entity #2 updates the value of at least one confirmed attribute to the structured intent, deletes sub-session #4, and creates sub-session #5 for the next attribute or combination of attributes to be interacted with.

[0375] It should be understood that entity #2 updating to the structured intent, deleting sub-session #4, and creating sub-session #5 can be understood as entity #2 requesting, instructing, or invoking LLM to update to the structured intent, delete sub-session #4, and create sub-session #5.

[0376] Similarly, in method 1400, the total number of sub-sessions created is greater than 1 in the following two cases:

[0377] 1) When the interaction granularity is a single attribute, and the number of interaction attributes is greater than 1;

[0378] 2) When the interaction granularity is a combination of attributes based on a single goal, the number of interaction attributes is greater than 1, and the number of expectations to which the interaction attributes belong is greater than 1.

[0379] In method 1400, entity 1 instructs entity 2 to create a sub-session by sending granular information. Entity 2 then autonomously creates the sub-session by calling the LLM based on the granular information. This reduces the transmission resources required for entity 1 to send multiple sub-session creation requests. Simultaneously, entity 2 can precisely define the scope of attributes associated with a sub-session based on the granular information, helping to further prevent dialogue content from exceeding the context window's token limit and reducing the likelihood of forgetting previously interacted information. This further improves the logic and coherence of the dialogue, ultimately enhancing customer satisfaction. Furthermore, this method reduces the difficulty of negotiating attribute values ​​through sub-sessions associated with attributes, allowing for more frequent use of this approach and further reducing the occurrence of dialogue content exceeding the context window's token limit.

[0380] The method embodiments provided in this application have been described in detail above with reference to Figures 1 to 14. The device embodiments of this application will be described below with reference to Figures 15 to 17.

[0381] It is understood that, in order to achieve the functions in the above embodiments, the apparatuses in Figures 15 to 17 include hardware structures and / or software modules corresponding to the execution of each function. These apparatuses can be used to implement the functions of the production entity, consumption entity, or large model entity in the above method embodiments, and thus can also achieve the beneficial effects of the above method embodiments. Those skilled in the art should readily recognize that, based on the units and method steps of the various examples described in conjunction with the embodiments disclosed in this application, this application can be implemented in hardware or a combination of hardware and computer software.

[0382] Figure 15 is a schematic diagram of a device provided in an embodiment of this application.

[0383] This application embodiment can divide the production entity, consumption entity, or large model entity into functional units according to the above method examples. For example, each function can be divided into different functional units, or two or more functions can be integrated into one unit. Each function can be implemented in hardware or as a software functional module. It should be noted that the division shown in Figure 15 is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0384] As shown in Figure 15, the device 10 includes a transceiver unit 11 and a processing unit 12. Optionally, the device 10 also includes a storage unit 13 for storing instructions and / or data.

[0385] When the device 10 is used to implement the function of the production entity in the above method embodiments, the transceiver unit 11 is used to execute the transceiver steps of the production entity, such as steps 1002, 1201, 1203, 1204, 1205, 1206, 1207, 1301, 1304, 1305, 1306, 1401, 1403, 1406, 1407 or 1408, and the processing unit 12 is used to execute the processing steps 1001, 1003, 1202, 1208, 1302, 1303, 1307, 1402, 1404, 1405 or 1409 of the production entity. When device 10 is used to implement the function of the consumer entity in the above method embodiments, transceiver unit 11 is used to execute the transceiver steps of the consumer entity, such as steps 1002, 1201, 1203, 1204, 1205, 1206, 1207, 1301, 1304, 1305, 1306, 1401, 1406, 1407 or 1408, and processing unit 12 is used to execute the processing steps of the consumer entity. When device 10 is used to implement the function of the large model entity in the above method embodiments, transceiver unit 11 is used to execute the transceiver steps of the large model entity, such as step 1403, and processing unit 12 is used to execute the processing steps of the large model entity, such as steps 1404, 1405 or 1409.

[0386] For a more detailed description of the transceiver unit 11 and the processing unit 12, please refer to the relevant descriptions in the above method embodiments, which will not be repeated here.

[0387] Figure 16 is another structural schematic diagram of the device provided in an embodiment of this application.

[0388] The device 20 includes a processing circuit 21. The processing circuit 21 is coupled to a memory 23, which stores instructions. When the device 20 is used to implement the method described above, the processing circuit 21 executes the instructions in the memory 23 to implement the function of the processing unit 12 described above.

[0389] Optionally, the device 20 further includes a memory 23 for implementing the functions of the aforementioned memory unit 13.

[0390] Optionally, the device 20 further includes a transceiver circuit 22. The transceiver circuit can be referred to as a communication interface. The processing circuit 21 and the transceiver circuit 22 are coupled to each other. It is understood that the transceiver circuit 22 can be a transceiver or an input / output interface. When the device 20 is used to implement the method described above, the processing circuit 21 executes instructions to implement the function of the processing unit 12, and the transceiver circuit 22 implements the function of the transceiver unit 11.

[0391] Optionally, device 20 can be a production entity, a consumer entity, or a large model entity, and correspondingly, the transceiver circuit can be a transceiver.

[0392] Optionally, device 20 can be a chip used in production entities, consumer entities, or large model entities, and correspondingly, the transceiver circuit can be an input / output interface.

[0393] For example, when device 20 is a chip applied to a production entity, a consumer entity, or a large-scale model entity, the chip implements the functions of the production entity, consumer entity, or large-scale model entity in the above method embodiments. The chip receives information from other modules (such as radio frequency modules or antennas) in the production entity, consumer entity, or large-scale model entity, which is sent to the production entity, consumer entity, or large-scale model entity by other devices; or, the chip sends information to other modules (such as radio frequency modules or antennas) in the production entity, consumer entity, or large-scale model entity, which is sent to other devices by the production entity, consumer entity, or large-scale model entity.

[0394] Figure 17 is a schematic diagram of a chip system provided in an embodiment of this application. The chip system 30 (or may also be called a processing system) includes logic circuitry 31 and an input / output interface 32.

[0395] The logic circuit 31 can be a processing circuit in the chip system 30. The logic circuit 31 can be coupled to a memory unit, calling instructions from the memory unit, enabling the chip system 30 to implement the methods and functions of the embodiments of this application. The input / output interface 32 can be an input / output circuit in the chip system 30, outputting processed information from the chip system 30, or inputting data or signaling information to be processed into the chip system 30 for processing.

[0396] As an alternative, the chip system 30 may also include a memory unit.

[0397] As one approach, the chip system 30 is used to implement the operations performed by the production entity, the consumer entity, or the large model entity in the various method embodiments described above.

[0398] For example, logic circuit 31 is used to implement processing-related operations performed by the production entity, consumption entity, or large model entity in the above method embodiments; input / output interface 32 is used to implement sending and / or receiving-related operations performed by the production entity, consumption entity, or large model entity in the above method embodiments.

[0399] This application also provides a communication device including a processing circuit coupled to a memory for storing computer programs or instructions and / or data. The processing circuit is used to execute the computer programs or instructions stored in the memory, or to read the data stored in the memory, to perform the methods in the above-described method embodiments. Optionally, the processing circuit may be one or more. Optionally, the communication device includes a memory. Optionally, the memory may be one or more. Optionally, the memory may be integrated with the processing circuit, or may be separately disposed.

[0400] This application also provides a chip including a processing circuit coupled to a memory for storing computer programs or instructions. The processing circuit executes the computer programs or instructions stored in the memory to implement the methods performed by a production entity, a consumer entity, or a large model entity in the above-described method embodiments. The memory may be located within the chip or independently of the chip, and is not limited thereto.

[0401] This application also provides a computer-readable storage medium having stored thereon computer instructions for implementing the methods executed by a production entity, a consumer entity, or a large model entity in the above-described method embodiments.

[0402] This application also provides a computer program product comprising instructions which, when executed by a computer, implement the methods performed by a production entity, a consumer entity, or a large model entity in the above-described method embodiments.

[0403] This application also provides a computer program that, when executed by a computer, implements the methods performed by a production entity, a consumer entity, or a large model entity in the above-described method embodiments.

[0404] This application also provides a communication system that includes at least one of the production entity, consumption entity, or large model entity in the above embodiments.

[0405] The explanations and beneficial effects of the relevant contents in any of the devices provided above can be found in the corresponding method embodiments provided above, and will not be repeated here.

[0406] It is understood that the processing circuit in the embodiments of this application may be a processor or a circuit in a processor for performing processing operations. The processor may include one or more of the following: a central processing unit (CPU), a digital signal processor (DSP), a microprocessor unit (MPU), a microcontroller unit (MCU), a graphics processing unit (GPU), a field programmable gate array (FPGA), an artificial intelligence processor (AI processor), or a neural processing unit (NPU).

[0407] The aforementioned memory may include one or more of the following storage media: random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), phase-change memory (PCM), resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), cache, register, read-only memory (ROM), flash memory, erasable programmable read-only memory (EPROM), hard disk, etc. In one example, computer program instructions for executing the above embodiments may be stored in non-volatile memory, such as the aforementioned memory 23 or at least a portion of the storage cells (e.g., one or more of ROM, flash memory, EPROM, or hard disk).

[0408] The method steps in the embodiments of this application can be implemented in hardware or by a processor executing software instructions. The software instructions can consist of corresponding software modules, which can be stored in random access memory, flash memory, read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, registers, hard disks, portable hard disks, compact disc read-only memory (CD-ROM), or any other form of storage medium well known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside in an application-specific integrated circuit (ASIC). Furthermore, the ASIC can reside in a production entity, a consumer entity, or a large-scale model entity. Alternatively, the processor and storage medium can exist as discrete components in a production entity, a consumer entity, or a large-scale model entity.

[0409] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described in the embodiments of this application are performed entirely or partially. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user equipment, or other programmable device. The computer program or instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer program or instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; it can also be an optical medium, such as a digital video optical disc; or it can be a semiconductor medium, such as a solid-state drive.

[0410] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of different embodiments are consistent and can be referenced by each other. The technical features of different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0411] Unless otherwise stated, all technical and scientific terms used in the embodiments of this application have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in this application is for the purpose of describing specific embodiments only and is not intended to limit the scope of this application. It should be understood that the above are illustrative examples, and the examples above are merely to help those skilled in the art understand the embodiments of this application, and are not intended to limit the embodiments of the application to the specific numerical values ​​or specific scenarios exemplified. Those skilled in the art can obviously make various equivalent modifications or variations based on the examples given above, and such modifications and variations also fall within the scope of the embodiments of this application.

Claims

1. A communication method, characterized in that, The method includes: Obtain the first attribute to be confirmed, where the first attribute is an attribute of the first network management intent; The first session is used to interact with the consumer entity to confirm the value of the first attribute, and the first session is associated with the first attribute. After confirming the value of the first attribute, delete the context associated with the first session.

2. The method according to claim 1, characterized in that, The first session is associated with the first attribute, including: The first interaction affects the value of the first attribute but does not affect the values ​​of the remaining attributes of the first network management intent.

3. The method according to claim 1 or 2, characterized in that, The process of obtaining the first attribute to be confirmed includes: Receive first information from the consumer entity, the first information being used to indicate the first attribute.

4. The method according to claim 3, characterized in that, The first information includes the first attribute; or, The first information includes first granularity information and the first attribute, wherein the first granularity information is used to indicate that the granularity of the first interaction is a single attribute, and the first attribute includes one attribute; or, The first information includes part or all of the second granularity information and the first attribute. The second granularity information is used to indicate that the granularity of the first interaction is a combined attribute. The first attribute includes multiple attributes, and the values ​​of the multiple attributes influence each other.

5. The method according to claim 4, characterized in that, The plurality of attributes includes: a first expected target, a first expected object, and a first context, wherein the first context includes at least one of the following: the context of the first expected target, or the context of the first expected object; or, The plurality of attributes include: a plurality of second expected targets, a second expected object, and a second context, wherein the second context includes at least one of the following: the context of some or all of the plurality of second expected targets, or the context of the second expected object.

6. The method according to any one of claims 3 to 5, characterized in that, The method further includes: Before engaging in the first interaction with the consumer entity through the first session, second information is received from the consumer entity, the second information being used to instruct the creation of the first session.

7. The method according to any one of claims 3 to 6, characterized in that, The method further includes: After obtaining the first attribute to be confirmed, a third message is sent to the consumer entity, the third message being used to indicate the start of the first session.

8. The method according to any one of claims 3 to 7, characterized in that, The method further includes: Before deleting the context associated with the first session, a fourth message is received from the consuming entity, the fourth message indicating the termination of the first session.

9. The method according to any one of claims 1 to 8, characterized in that, The method further includes: Update the first network management intent based on the value of the first attribute.

10. The method according to any one of claims 1 to 9, characterized in that, After deleting the context associated with the first session, the method further includes: Obtain the second attribute to be confirmed, where the second attribute is an attribute of the first network management intent; The second session is used to conduct a second interaction with the consumer entity to confirm the value of the second attribute, and the second session is associated with the second attribute; After confirming the value of the second attribute, delete the context associated with the second session.

11. The method according to any one of claims 1 to 10, characterized in that, The method further includes: generating a first prompt, the first prompt being used to prompt the large model entity to perform a first operation, wherein the first operation includes: confirming the value of the first attribute with the consumer entity based on the first session, and deleting the context related to the first session after confirming the value of the first attribute; The deletion of context associated with the first session includes: instructing the large model entity to delete the context associated with the first session.

12. A communication method, characterized in that, The method includes: The first session is used to conduct a first interaction with the production entity to confirm the value of the first attribute, which is an attribute of the first network management intent, and the first session is associated with the first attribute.

13. The method according to claim 12, characterized in that, The first session is associated with the first attribute, including: The first interaction affects the value of the first attribute but does not affect the values ​​of the remaining attributes of the first network management intent.

14. The method according to claim 12 or 13, characterized in that, The method further includes: Send a first message to the production entity, the first message being used to indicate the first attribute.

15. The method according to claim 14, characterized in that, The first information includes the first attribute; or, The first information includes first granularity information and the first attribute, wherein the first granularity information is used to indicate that the granularity of the first interaction is a single attribute, and the first attribute includes one attribute; or, The first information includes part or all of the second granularity information and the first attribute. The second granularity information is used to indicate that the granularity of the first interaction is a combined attribute. The first attribute includes multiple attributes, and the values ​​of the multiple attributes influence each other.

16. The method according to claim 15, characterized in that, The plurality of attributes includes: a first expected target, a first expected object, and a first context, wherein the first context includes at least one of the following: the context of the first expected target, or the context of the first expected object; or, The plurality of attributes include: a plurality of second expected targets, a second expected object, and a second context, wherein the second context includes at least one of the following: the context of some or all of the plurality of second expected targets, or the context of the second expected object.

17. The method according to any one of claims 14 to 16, characterized in that, The method further includes: Before engaging in the first interaction with the production entity via the first session, a second message is sent to the production entity, the second message indicating the creation of the first session.

18. The method according to any one of claims 14 to 17, characterized in that, The method further includes: Before engaging in the first interaction with the production entity via the first session, third information is received from the production entity, the third information indicating the commencement of the first session.

19. The method according to any one of claims 14 to 18, characterized in that, The method further includes: After confirming the value of the first attribute or while confirming the first attribute, a fourth message is sent to the production entity, the fourth message being used to indicate the end of the first session.

20. The method according to any one of claims 12 to 19, characterized in that, After confirming the value of the first attribute, the method further includes: The second session is used to conduct a second interaction with the production entity to confirm the value of the second attribute, which is an attribute of the first network management intent, and the second session is associated with the first attribute.

21. A communication method, characterized in that, The method includes: Receive a first prompt from the production entity, which prompts the large model to perform a first operation. Based on the first prompt, perform the first operation; The first operation includes: confirming the value of the first attribute with the consuming entity through the first session, and deleting the context related to the first session after confirming the value of the first attribute. Wherein, the first attribute is an attribute of the first network management intent, and the first session is associated with the first attribute.

22. The method according to claim 21, characterized in that, The first session is associated with the first attribute, including: The first interaction affects the value of the first attribute but does not affect the values ​​of the remaining attributes of the first network management intent.

23. The method according to claim 21 or 22, characterized in that, The first operation further includes at least one of the following: Update the first network management intent based on the value of the first attribute; The value of the second attribute is confirmed with the consumer entity through the second session, and the context associated with the second session is deleted after the value of the second attribute is confirmed. The second attribute is an attribute of the first network management intent, and the second session is associated with the second attribute.

24. A communication method, characterized in that, The method includes: The consumer entity sends the first information, and the production entity receives the first information. The first information is used to indicate the first attribute to be confirmed. The first attribute is an attribute of the first network management intent. The production entity and the consumer entity interact through a first session to confirm the value of the first attribute, and the first session is associated with the first attribute. After confirming the value of the first attribute, the production entity deletes the context associated with the first session.

25. The method according to claim 24, characterized in that, The method further includes: The production entity generates a first prompt, which prompts the large model entity to perform a first operation. The first operation includes: confirming the value of the first attribute with the consumer entity based on the first session, and deleting the context related to the first session after confirming the value of the first attribute. The production entity sends the first prompt, and the large model entity receives the first prompt. The large model entity performs the first operation based on the first prompt.

26. A communication device, characterized in that, The device includes a processor and an interface circuit, the interface circuit being used to receive signals from other devices besides the communication device and transmit them to the processor, or to send signals from the processor to other devices besides the communication device, the processor being used to implement the method as described in any one of claims 1 to 25 via logic circuits or execution code instructions.

27. The communication device according to claim 26, characterized in that, The communication device is a chip or chip system.

28. A computer-readable storage medium, characterized in that, The storage medium stores a computer program or instructions, which, when executed by a communication device, implement the method as described in any one of claims 1 to 25.

29. A communication system, characterized in that, It includes at least one of the following devices: a communication device for performing the method as claimed in any one of claims 1 to 11, a communication device for performing the method as claimed in any one of claims 12 to 20, or a communication device for performing the method as claimed in any one of claims 21 to 23.

30. A computer program product, characterized in that, It includes a computer program or instructions that, when executed in a computer, implement the steps of the method as claimed in any one of claims 1 to 25.

31. A communication device, characterized in that, It includes units and / or modules for performing the method as described in any one of claims 1 to 25.

Images