Ai model-based operation recommendation method and apparatus, and related device

Abstract

The present application relates to the technical field of communications, and discloses an AI model-based operation recommendation method and apparatus, and a related device. The AI model-based operation recommendation method in the embodiments of the present application comprises: on the basis of an AI model and service objective information of a target service, a first device acquires first recommendation information corresponding to the service objective information, the service objective information being used for indicating a service objective that is expected to be achieved, and the first recommendation information being used for determining an operation associated with the target service; and the first device sends first information to a target object or a second device, the first information comprising the first recommendation information, and the target object being a device or function for performing the operation.

Description

Operation recommendation method, device and related equipment based on AI model

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Chinese Patent Application No. 202410136909.3 filed in China on January 31, 2024, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The present application belongs to the field of communication technology, and specifically relates to an operation recommendation method, apparatus, and related equipment based on an artificial intelligence (AI) model. Background Art

[0004] With the development of communication systems, the Network Data Analytics Function (NWDAF) in communication systems usually predicts the service experience value corresponding to the specific network environment configuration and sends it to the consumer device. The consumer device determines the corresponding operation behavior based on the service experience value. However, due to the low level of intelligence of the consumer device, the determined operation behavior cannot adapt to the complex network environment, resulting in poor network performance. Summary of the Invention

[0005] The embodiments of the present application provide an AI model-based operation recommendation method, apparatus, and related equipment, which can solve the problem of poor network performance.

[0006] In the first aspect, an operation recommendation method based on an AI model is provided, comprising:

[0007] The first device obtains, based on the AI ​​model and business objective information of the target business, first recommendation information corresponding to the business objective information, where the business objective information is used to indicate a desired business objective, and the first recommendation information is used to determine an operation associated with the target business;

[0008] The first device sends first information to a target object or a second device, where the first information includes the first recommendation information, and the target object is a device or function that performs the operation.

[0009] Secondly, an operation recommendation method based on an AI model is provided, including:

[0010] The target object receives the first information from the first device or the second information from the second device;

[0011] The first information includes first recommendation information, which is determined based on the AI ​​model and business goal information of the target business, the business goal information is used to indicate the business goal to be achieved, and the first recommendation information is used to determine the operation associated with the target business;

[0012] The second information includes second recommendation information, the second recommendation information is determined based on the first recommendation information, and the target object is a device or function that performs the operation.

[0013] Thirdly, an operation recommendation method based on an AI model is provided, including:

[0014] The second device receives the first information from the first device;

[0015] Among them, the first information includes first recommendation information, which is determined based on the AI ​​model and business goal information of the target business. The business goal information is used to represent the business goal to be achieved, and the first recommendation information is used to determine the operation associated with the target business.

[0016] In a fourth aspect, an operation recommendation device based on an AI model is provided, comprising:

[0017] An acquisition module, configured to acquire, based on the AI ​​model and business objective information of a target business, first recommendation information corresponding to the business objective information, wherein the business objective information is used to indicate a desired business objective, and the first recommendation information is used to determine an operation associated with the target business;

[0018] The first sending module is used to send first information to a target object or a second device, where the first information includes the first recommendation information, and the target object is a device or function that performs the operation.

[0019] In a fifth aspect, an operation recommendation device based on an AI model is provided, comprising:

[0020] a second receiving module, configured to receive first information from the first device or second information from the second device;

[0021] The first information includes first recommendation information, which is determined based on the AI ​​model and business goal information of the target business, the business goal information is used to indicate the business goal to be achieved, and the first recommendation information is used to determine the operation associated with the target business;

[0022] The second information includes second recommendation information, and the second recommendation information is determined based on the first recommendation information.

[0023] In a sixth aspect, an operation recommendation device based on an AI model is provided, comprising:

[0024] a third receiving module, configured to receive first information from the first device;

[0025] Among them, the first information includes first recommendation information, which is determined based on the AI ​​model and business goal information of the target business. The business goal information is used to represent the business goal to be achieved, and the first recommendation information is used to determine the operation associated with the target business.

[0026] In a fifth aspect, a terminal is provided, comprising a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the method described in the second aspect are implemented.

[0027] In a sixth aspect, a terminal is provided, comprising a processor and a communication interface, wherein the communication interface is configured to receive first information from a first device or second information from a second device;

[0028] The first information includes first recommendation information, which is determined based on the AI ​​model and business goal information of the target business, the business goal information is used to indicate the business goal to be achieved, and the first recommendation information is used to determine the operation associated with the target business;

[0029] The second information includes second recommendation information, and the second recommendation information is determined based on the first recommendation information.

[0030] In the seventh aspect, a network side device is provided, which includes a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the program or instructions are executed by the processor, the steps of the method described in the first aspect, or the method described in the second aspect, or the method described in the third aspect are implemented.

[0031] In an eighth aspect, a network side device is provided, including a processor and a communication interface, wherein:

[0032] When the network-side device is a first device, the processor is configured to obtain, based on the AI ​​model and business target information of the target business, first recommendation information corresponding to the business target information, where the business target information is used to indicate a desired business target, and the first recommendation information is used to determine an operation associated with the target business; the communication interface is configured to send first information to a target object or a second device, where the first information includes the first recommendation information, and the target object is a device or function that performs the operation;

[0033] When the network-side device is the target object, the communication interface is used to receive first information from the first device or second information from the second device; wherein the first information includes first recommendation information, the first recommendation information is determined based on the AI ​​model and business target information of the target business, the business target information is used to indicate a desired business target, and the first recommendation information is used to determine an operation associated with the target business; wherein the second information includes second recommendation information, the second recommendation information is determined based on the first recommendation information;

[0034] When the network side device is a second device, the communication interface is used to receive first information from the first device; wherein, the first information includes first recommendation information, the first recommendation information is determined based on the AI ​​model and the business target information of the target business, the business target information is used to represent the business target to be achieved, and the first recommendation information is used to determine the operation associated with the target business.

[0035] In the ninth aspect, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented, or the steps of the method described in the second aspect are implemented, or the method described in the third aspect are implemented.

[0036] In the tenth aspect, a wireless communication system is provided, comprising: a first device, a second device and a target object, wherein the first device can be used to execute the steps of the method described in the first aspect, the second device can be used to execute the steps of the method described in the second aspect, and the target object can be used to execute the steps of the method described in the third aspect.

[0037] In the eleventh aspect, a chip is provided, which includes a processor and a communication interface, the communication interface and the processor are coupled, and the processor is used to run programs or instructions to implement the method as described in the first aspect, or the method as described in the second aspect, or the method as described in the third aspect.

[0038] In the twelfth aspect, a computer program / program product is provided, wherein the computer program / program product includes computer instructions, and the computer program / program product is executed by at least one processor to implement the method as described in the first aspect, or implement the method as described in the second aspect, or implement the method as described in the third aspect.

[0039] In an embodiment of the present application, a first device obtains first recommendation information corresponding to the business target information based on an AI model and the business target information of the target business, wherein the business target information is used to represent the business target to be achieved, and the first recommendation information is used to determine the operation associated with the target business; the first device sends a first message to a target object or a second device, wherein the first message includes the first recommendation information, and the target object is a device or function that performs the operation. In this way, by obtaining the first recommendation information based on the AI ​​model, it is possible to comprehensively consider various factors to obtain recommendation information that is suitable for the current network environment and meets the business target information. Therefore, an embodiment of the present application can improve network performance, thereby improving the reliability of target business execution. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] FIG1 is a block diagram of a wireless communication system applicable to embodiments of the present application;

[0041] FIG2 is a flow chart of an operation recommendation method based on an AI model provided in an embodiment of the present application;

[0042] FIG3 is a second flow chart of an AI model-based operation recommendation method provided in an embodiment of the present application;

[0043] FIG4 is a third flow chart of an AI model-based operation recommendation method provided in an embodiment of the present application;

[0044] FIG5 is a fourth flow chart of an AI model-based operation recommendation method provided in an embodiment of the present application;

[0045] FIG6 is a fifth flow chart of an AI model-based operation recommendation method provided in an embodiment of the present application;

[0046] FIG7 is a structural diagram of an operation recommendation device based on an AI model provided in an embodiment of the present application;

[0047] FIG8 is a second structural diagram of an operation recommendation device based on an AI model provided in an embodiment of the present application;

[0048] FIG9 is a third structural diagram of an AI model-based operation recommendation device provided in an embodiment of the present application;

[0049] FIG10 is a schematic structural diagram of a communication device provided in an embodiment of the present application;

[0050] FIG11 is a schematic structural diagram of a terminal provided in an embodiment of the present application;

[0051] FIG12 is a schematic structural diagram of a network-side device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0052] The terms "first", "second", etc. in this application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable where appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same type, and do not limit the number of objects, for example, the first object can be one or more. In addition, "or" in this application represents at least one of the connected objects. For example, "A or B" covers three options, namely, Option 1: including A but not including B; Option 2: including B but not including A; Option 3: including both A and B. The character " / " generally indicates that the objects associated before and after are in an "or" relationship.

[0053] The term "indication" in this application can be either a direct indication (or explicit indication) or an indirect indication (or implicit indication). A direct indication can be understood as the sender explicitly informing the receiver of specific information, the operation to be performed, or the requested result, etc. in the instruction sent; an indirect indication can be understood as the receiver determining the corresponding information based on the instruction sent by the sender, or making a judgment and determining the operation to be performed or the requested result, etc. based on the judgment result.

[0054] It is worth noting that the technology described in the embodiments of the present application is not limited to the Long Term Evolution (LTE) / LTE-Advanced (LTE-A) system, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA) or other systems. The terms "system" and "network" in the embodiments of the present application are often used interchangeably, and the technology described can be used for the systems and radio technologies mentioned above, as well as for other systems and radio technologies. The following description describes a New Radio (NR) system for illustrative purposes, and NR terminology is used in most of the following description, but these technologies can also be applied to systems other than NR systems, such as 6th generation (6G) systems. thGeneration, 6G) communication system.

[0055] FIG1 is a block diagram of a wireless communication system applicable to an embodiment of the present application. The wireless communication system includes a terminal 11 and a network-side device 12. The terminal 11 may be a mobile phone, a tablet computer (Tablet Personal Computer), a laptop computer (Laptop Computer), a notebook computer, a personal digital assistant (PDA), a handheld computer, a netbook, an ultra-mobile personal computer (UMPC), a mobile internet device (MID), an augmented reality (AR), a virtual reality (VR) device, a robot, a wearable device (Wearable Device), an aircraft (Flight Vehicle), a vehicle-mounted device (VUE), a ship-mounted device, a pedestrian user equipment (PUE), a smart home (home appliances with wireless communication capabilities, such as refrigerators, televisions, washing machines, or furniture), a game console, a personal computer (PC), an ATM, or a self-service machine, or other terminal-side devices. Wearable devices include: smart watches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. Among them, the vehicle-mounted device can also be called a vehicle-mounted terminal, a vehicle-mounted controller, a vehicle-mounted module, a vehicle-mounted component, a vehicle-mounted chip or a vehicle-mounted unit, etc. It should be noted that the specific type of the terminal 11 is not limited in the embodiment of the present application. The network side device 12 may include an access network device or a core network device, wherein the access network device may also be called a radio access network (Radio Access Network, RAN) device, a radio access network function or a radio access network unit. The access network device may include a base station, a wireless local area network (WLAN) access point (AP) or a wireless fidelity (WiFi) node, etc.Among them, the base station can be referred to as Node B (NB), Evolved Node B (eNB), the next generation Node B (gNB), New Radio Node B (NR Node B), access point, Relay Base Station (RBS), Serving Base Station (SBS), Base Transceiver Station (BTS), radio base station, radio transceiver, Basic Service Set (BSS), Extended Service Set (ESS), Home Node B (HNB), Home evolved Node B (home evolved Node B), Transmission Reception Point (TRP) or other appropriate terms in the relevant field. As long as the same technical effect is achieved, the base station is not limited to specific technical vocabulary. It should be noted that in the embodiment of the present application, only the base station in the NR system is used as an example for introduction, and the specific type of the base station is not limited.

[0056] The core network equipment may include but is not limited to at least one of the following: core network node, core network function, mobility management entity (MME), access mobility management function (AMF), session management function (SMF), user plane function (UPF), policy control function (PCF), policy and charging rules function unit (PCRF), edge application service discovery function (EASDF), unified data management (UDM), unified data repository (UDR), home user server (HSS), centralized network configuration (CNC), network storage function (NRF), network exposure function (NEF), local NEF (L-NEF), binding support function (BSF), application function ( Function, AF), Network Data Analytics Function (NWDAF), etc. Among them, NWDAF can be divided into: NWDAF containing (containing) analysis logic function (Analytics logical function, Anlf) or NWDAF containing model training logical function (Model Training logical function, MTLF). It should be noted that in the embodiment of the present application, only the core network device in the NR system is introduced as an example, and the specific type of the core network device is not limited.

[0057] For ease of understanding, some of the contents involved in the embodiments of this application are described below:

[0058] Currently, the Network Data Analytics Function (NWDAF) provides outputs per analytic ID. For example, the key output of observed service experience (OSE) is specified in 23.288. NWDAF predicts the service experience value corresponding to a specific network (NW) environment configuration.

[0059] Consumer devices (such as PCF) will consider the output (such as service experience value) and decide whether and how to perform related operations (actions), such as how to increase bandwidth or how to increase the priority of voice services.

[0060] Due to the low level of intelligence of consumer devices, the determined operation behaviors cannot adapt to the complex network environment, resulting in poor network performance. To this end, the present application proposes an operation recommendation method based on an AI model.

[0061] The following, in combination with the accompanying drawings, describes in detail the operation recommendation method based on the AI ​​model provided in the embodiment of the present application through some embodiments and their application scenarios.

[0062] Referring to FIG2 , an embodiment of the present application provides an operation recommendation method based on an AI model. As shown in FIG2 , the operation recommendation method based on an AI model provided by the embodiment of the present application includes:

[0063] Step 201: The first device obtains first recommendation information corresponding to the business target information based on the AI ​​model and business target information of the target business, where the business target information is used to indicate a desired business target, and the first recommendation information is used to determine an operation associated with the target business.

[0064] Step 202: The first device sends first information to a target object or a second device, where the first information includes the first recommendation information. The target object is a device or function that performs the operation.

[0065] In the embodiment of the present application, the above-mentioned AI model can be understood or replaced by a machine learning (ML) model. The above-mentioned target service can be understood as at least one of a specific application service (such as application) and a general service within the network (such as mobility management, session management, network registration, cell switching, slice selection, etc.).

[0066] Optionally, the first device may be an AI entity (with AI-related functions). For example, the first device may include one or more AI entities. If the first device includes one AI entity, the AI ​​entity may include an AI reasoning function. If the first device includes multiple AI entities, one AI entity includes a reasoning function, and the other AI entities may include an AI training function. The AI ​​entity used for reasoning may request or obtain an AI model used for reasoning from the other AI entities. The AI ​​entity may be understood or replaced by an AI function, an AI device, etc., and is not further limited herein.

[0067] Optionally, in some embodiments, the first device can obtain the first recommendation information based on the business target information of the target business and based on AI model reasoning. In this way, by obtaining the first recommendation information through AI model reasoning, it is possible to comprehensively consider various factors to obtain recommendation information that is suitable for the current network environment and meets the business target information. Therefore, after the target object performs operations associated with the target business based on the first recommendation information, the network performance can be improved, thereby improving the reliability of the execution of the target business. The above-mentioned first recommendation information can be implicit or explicit recommendation information. For example, in one implementation, the first recommendation information does not contain any recommendation indication information in the name or content, and only has a recommendation role in actual function or use; in another implementation, the first recommendation information carries recommendation indication information in the name or content, explicitly indicating the recommendation role.

[0068] Optionally, in some embodiments, the business goal information may include at least one of the following: service metrics; required value of each metric. The business goal may be understood as or replaced by a business requirement value or a business requirement target. In some embodiments, the business goal information may include at least one of the following:

[0069] service MOS ≥ 4;

[0070] The load of a slice should be as small as possible;

[0071] All UEs reside on the 5G network as much as possible.

[0072] Optionally, in some embodiments, the above-mentioned target object is a device or function used to perform the operation. For example, the target object may include at least one of the following: access and mobility management function AMF, session management function SMF, user plane function UPF, policy control function entity PCF, terminal UE, application function AF, access network RAN, operation administration and maintenance (OAM).

[0073] Optionally, in some embodiments, the above-mentioned second device may be a device or function that generates second information based on the first information. For example, the second device may be understood or replaced by a consumer device. Specifically, the second device may include PCF, AMF, SMF, OAM, etc.

[0074] It should be understood that in an embodiment of the present application, the first device obtains the first recommendation information corresponding to the business target information, and can directly send the recommendation information to the target object, that is, the first device sends the first information to the target object; it can also indirectly send the recommendation information to the target object through the second device, that is, the first device sends the first information to the second device, and the second device sends the second information to the target object. The second information is determined based on the first information. For example, the content of the second information can be consistent with the content of the first information, or the second device can obtain the second information after updating at least part of the content of the first information.

[0075] In an embodiment of the present application, a first device obtains first recommendation information corresponding to the business target information based on an AI model and the business target information of the target business, wherein the business target information is used to represent the business target to be achieved, and the first recommendation information is used to determine the operation associated with the target business; the first device sends a first message to a target object or a second device, wherein the first message includes the first recommendation information, and the target object is a device or function that performs the operation. In this way, by obtaining the first recommendation information based on the AI ​​model, it is possible to comprehensively consider various factors to obtain recommendation information that is suitable for the current network environment and meets the business target information. Therefore, an embodiment of the present application can improve network performance, thereby improving the reliability of target business execution.

[0076] Optionally, in some embodiments, the first device may proactively determine the first recommendation information and send the first recommendation information to the target object or the second device, or the second device may request the first recommendation information. For example, in some embodiments, the method further includes:

[0077] The first device receives a request message from the second device, where the request message includes at least one of the following:

[0078] Business target information of the target business;

[0079] AI task type information;

[0080] Business type information of the target business;

[0081] first indication information, where the first indication information is used to indicate a request to obtain recommendation information corresponding to the business target information;

[0082] second indication information, where the second indication information is used to indicate a type of the recommended information requested, where the type of the recommended information includes a recommended operation or a recommended value of a parameter;

[0083] third indication information, where the third indication information is used to indicate the quantity of the recommended information requested;

[0084] Information of a target object, where the information of the target object is used to indicate the target object;

[0085] Network status information, used to indicate current or future network status, and the network status information is used to obtain recommendation information corresponding to the network status;

[0086] Condition information associated with the first recommendation information.

[0087] Optionally, the number of recommendation information requested may be indicated by one or more indicators (one or multiple indicators), or the number N of requests may be indicated, for example, N is equal to 3.

[0088] Optionally, the network status information may include network load, UE location, AMF load, 5QI or QoS parameters of the target service, UE RAT, etc. The network status may include the status of the network device, user-related status, service AF status, etc.

[0089] Optionally, the above-mentioned service objective information may be expressed in the form of a service objective parameter type and a requirement to be achieved for the service objective parameter type. The requirement may be a specific numerical value, a level, or an upper or lower threshold. There may be one or more service objective parameter types, and the corresponding requirements may be one or more, for example, a requested service mean opinion score (MOS) greater than 4 and a requested quality of service (QoS) bit rate greater than 100 Mbps. For example, in some embodiments, the service objective information may be a required service MOS.

[0090] Alternatively, an alternative form of AI task type information can be expressed as a task ID. That is, the AI ​​task type information can be understood or replaced by AI task ID information. The AI ​​task type information is used to indicate the type of AI task or the specific use or purpose of the AI ​​task. For example, if the task ID (analytics ID) is equal to "service experience," it indicates a prediction or guarantee of service experience.

[0091] Optionally, for business type information, such as application ID and service ID, the specific business type is represented.

[0092] Optionally, the target object information is used to identify the target object for which the first device is requested to make an operation recommendation, and may specifically include information of one or more target objects, for example, the target object's ID, FQDN, URL, IP address, MAC address, etc.

[0093] Optionally, in some embodiments, the conditional information may include one or more restriction conditions, which are used to indicate the scope of application of the first recommendation information. For example, it may include at least one of the following: a single network slice selection assistance information (Single Network Slice Selection Assistance Information, S-NSSAI) condition of the slice to which the first recommendation information applies, an AOI condition to which the first recommendation information applies, a DNN condition to which the first recommendation information applies, and a bandwidth condition to which the first recommendation information applies.

[0094] For example, in some embodiments, the conditional information includes limiting the slice to slice A, and the first device may generate first recommendation information suitable for switching A based on relevant information of slice A.

[0095] It should be noted that the request message may be a message in a request and response mode, in which the second device specifies a business target information, and the first device feeds back recommended information that can meet the business target information.

[0096] Optionally, the request message can also be a message in a subscription and notification mode. In this mode, the second device specifies a business goal, and the first device feeds back recommendation information when detecting or predicting that the business goal information reaches a threshold value (such as greater than or equal to the threshold value, or less than or equal to the threshold value), so that the target object performs corresponding operations based on the recommendation information, thereby ensuring that the business goal information is met.

[0097] Optionally, in some embodiments, when the first device sends first information to the second device, the first information is used to trigger the second device to send second information to a target object, the second information includes second recommendation information, and the second recommendation information is determined based on the first recommendation information, and the target object is the device or function that performs the operation.

[0098] In an embodiment of the present application, after receiving the above-mentioned first information, the second device can determine the second information based on the first information; and then send the second information to the target object.

[0099] Optionally, the second device determining the second information according to the first information includes:

[0100] The second device determines second recommendation information, where the second recommendation information includes at least one of the following: the first recommendation information, and recommendation information determined based on the first recommendation information;

[0101] The second device generates the second information based on the second recommendation information.

[0102] In the embodiment of the present application, the second device can replace the first recommendation information in the first information to obtain the second information.

[0103] Optionally, in some embodiments, the first information further includes at least one of the following:

[0104] the reason or purpose for the recommendation;

[0105] Information of the target object corresponding to the first recommendation information;

[0106] Forecast information for business objectives;

[0107] Fourth indication information, where the fourth indication information is used to indicate whether alternative recommendation information exists in the first device or to indicate whether the second device or the target object is allowed to request to replace the first recommendation information;

[0108] fifth indication information, where the fifth indication information is used to indicate a type of the first recommendation information, where the type of the first recommendation information includes a recommended operation or a recommended value of a parameter;

[0109] Recommendation indication information (recommendation indication), where the recommendation indication information is used to indicate that the first recommendation information is information of a recommended purpose.

[0110] The prediction information for the service objective can be understood as the predicted service demand or indicator or estimated value that can be achieved after executing the corresponding operation based on the first recommendation information. For example, if the service objective is to ensure that all UEs reside on the 5G network as much as possible, the prediction information corresponding to the service objective can be understood as the estimated 90% of terminals residing on the 5G network; if the service objective is a service MOS ≥ 4, the prediction information corresponding to the service objective can be understood as the predicted service MOS value of 4.5.

[0111] Optionally, in some embodiments, the first recommendation information includes at least one of the following:

[0112] Recommended actions associated with the target service;

[0113] Recommended values ​​for parameters associated with the target service.

[0114] Optionally, the above-mentioned recommended operations can be understood as specific execution operations; such as recommending SMF session control actions, recommending how AMF performs load balancing operations, etc.

[0115] Optionally, the above-mentioned recommended values ​​can be understood as parameter values ​​that assist in determining the execution of specific operations. For example, the SM policy assignment recommended to the SMF or PCF is used to instruct the SMF to perform session control operations based on the recommended SM policy assignment. For example, if the S-NSSAI value of the PDU session is recommended, the SMF selects the slice corresponding to the PDU session based on this value. For another example, a QoS parameter assignment is recommended to the PCF, and the PCF adjusts the QoS parameters of the service based on the QoS parameter assignment.

[0116] Optionally, in some embodiments, the first information includes at least one piece of the first recommendation information;

[0117] Each piece of the first recommendation information includes at least one recommended operation or a recommended value of at least one parameter corresponding to the target object.

[0118] Optionally, in some embodiments, when the first information includes multiple pieces of first recommendation information, the first information further includes at least one of the following:

[0119] sixth indication information, where the sixth indication information is used to indicate the quantity of the first recommended information;

[0120] Identification information of each piece of first recommendation information.

[0121] Optionally, in some embodiments, the method further comprises:

[0122] The first device receives first feedback information from the second device or the target object, where the first feedback information includes at least one of the following:

[0123] seventh indication information, where the seventh indication information is used to indicate whether the second device or the target object accepts the first recommendation information;

[0124] Reason information why the second device or the target object rejects the first recommendation information.

[0125] In the embodiment of the present application, the target object may send feedback information directly to the first device, or may send feedback information indirectly to the first device through a second device. For example, the second device may receive second feedback information from the target object and then determine the first feedback information based on the second feedback information. The second feedback information includes at least one of the following:

[0126] eighth indication information, the eighth indication information being used to indicate whether the target object accepts the second recommendation information;

[0127] The reason why the target object rejects the second recommendation information.

[0128] Optionally, in a case where the second information includes multiple pieces of second recommendation information, the second feedback information further includes identification information of the second recommendation information.

[0129] In the embodiment of the present application, the identification information of the second recommendation information can be specifically understood as the identification information of the second recommendation information being accepted or rejected.

[0130] Optionally, after receiving the second feedback information, the second device may re-determine the second recommendation information. For example, in some embodiments, the second device re-determines the second recommendation information including at least one of the following:

[0131] The second device re-determines second recommendation information based on the first recommendation information;

[0132] The second device reacquires the first recommendation information from the first device, and re-determines the second recommendation information based on the reacquired first recommendation information.

[0133] Optionally, in one example, the second device re-determines the second recommendation information based on the first recommendation information, which may include the following situations: when the second device receives multiple first recommendation information, it reselects a first recommendation information as the second recommendation information, or reselects a first recommendation information and determines the second recommendation information based on the reselected first recommendation information.

[0134] Optionally, in some embodiments, when the first information includes multiple pieces of first recommendation information, the first feedback information further includes identification information of the first recommendation information.

[0135] In the embodiment of the present application, the identification information of the first recommendation information can be specifically understood as the identification information of the first recommendation information being accepted or rejected.

[0136] Optionally, in some embodiments, when the first feedback information includes the seventh indication information, and the seventh indication information indicates that the second device or the target object rejects the first recommendation information, the method further includes:

[0137] The first device redetermines the first recommendation information, and sends the redetermined first recommendation information to the second device or the target object.

[0138] In the embodiment of the present application, when there is only one piece of first recommendation information sent, the first recommendation information can be regenerated; when there are multiple pieces of first recommendation information sent, one piece of first recommendation information can be reselected.

[0139] Optionally, in some embodiments, when the first feedback information includes the seventh indication information, and the seventh indication information indicates that the second device or the target object accepts the first recommendation information, the method further includes:

[0140] The first device sends the identification information of the first recommendation information included in the first feedback information to other target objects.

[0141] In an embodiment of the present application, when the first device sends multiple first recommendation messages, and the second device or target object only accepts one of them and feeds back the accepted first recommendation message to the first device, the first device will send the identification information of the accepted first recommendation message to the other target objects. For example, the first device sends multiple first recommendation messages to each of the multiple target objects, and after receiving the first feedback message sent by one of the target objects, and the first feedback message carries the identification information that only one of the first recommendation messages is accepted, the first device can send the identification information of the first recommendation information carried in the first feedback message to the other target objects. In this way, multiple target objects can use the same first recommendation information in a coordinated manner to avoid uncoordinated operations.

[0142] Optionally, in some embodiments, the first recommendation information includes at least one of the following:

[0143] Information on recommended terminal device policies;

[0144] Information on the recommended access control policy;

[0145] Information about the recommended session control policy.

[0146] Optionally, the terminal device policy may include but is not limited to URSP routing policy, Access Network Discovery & Selection Policy (ANDSP) Proxy policy, etc. In other words, the first recommendation information may include recommended operations or parameter recommended values ​​associated with the terminal's URSP, ANDSP, Proxy policy.

[0147] Optionally, the access control policy may include but is not limited to a service area restrictions policy, an RFSP Index policy, a UE-AMBR policy, a terminal Slice-MBR policy, and an SMF selection policy. In other words, the first recommendation information may include recommended operations or parameter recommended values ​​associated with service area restrictions, RFSP index, UE-AMBR, UE slice-MBR, and SMF selection.

[0148] Optionally, the session control policy may include but is not limited to a QoS control policy, a charging policy, a service diversion policy, etc. In other words, the first recommendation information may include recommended operations or parameter values ​​associated with QoS control, charging, and traffic steering.

[0149] In order to better understand the present application, some specific examples are given below for detailed description.

[0150] Example 1: As shown in FIG3 , in some embodiments, an operation recommendation method based on an AI model may include the following process:

[0151] In step 31, the second device (such as 5G PCF) sends a request message to the first device (such as NWDAF) to obtain first recommendation information corresponding to the operation.

[0152] The operation may be an operation corresponding to the second device, or an operation recommended by another device or entity. The first recommendation information may include at least one of the following: a recommendation on how to set QOS parameters or PCC policies for the PCF, a recommendation on how to set SM policies for the SMF, and an operation recommendation on how to perform network element load balancing for the AMF.

[0153] The content of the request message may refer to the above embodiment and will not be described in detail here.

[0154] In step 32 , the first device obtains one or more first recommendation information based on the AI ​​model and according to the business target information obtained by the second device in step 31 .

[0155] The one or more first recommendation information are not limited to the second device, but may also be directed to other functional entities.

[0156] Optionally, the AI ​​model can be pre-trained by the first device, or obtained by the first device from another first device, which is not further limited here. The model generation method can be a traditional centralized model training method, a distributed model training method, or a general large model generation method, etc., which is not limited here.

[0157] Step 33: The first device sends first information to the second device, where the first information is used to inform the second device of the first recommendation information determined by the first device.

[0158] Optionally, the first information may include at least one of the following:

[0159] 1. The recommended value for the target object is used to instruct the target object to perform the corresponding operation, such as the SM policy information recommended to the SMF (used to instruct the SMF to perform session control operations according to it. For example, the S-NSSAI value of the recommended PDU session is used, and the SMF selects the slice corresponding to the PDU session accordingly), the recommended value of the QoS parameter recommended to the PCF (used to instruct the PCF to set the QoS parameters of the service according to the information. For example, if the recommended QoS bit rate is > 100Mbps, the PCF sets the authorized QoS bit rate value in the QCI or QoS characteristics), and the load balancing recommendation recommended to the AMF (used to instruct the AMF to perform load control operations according to the information, for example, it is recommended that the AMF load CPU occupancy is less than 60%, and the AMF sets the user value accordingly).

[0160] In one example, the first information may include multiple alternative recommendation values, where each alternative recommendation value includes a combination of recommendation values ​​for one or more target objects, and the recommendation value for a target object may also be a combination of multiple recommendation values ​​for the target object, as shown in Table 1.

[0161] Table 1:

[0162] In one example, the first information includes only one recommended value, i.e., a recommended value that the first device can select from multiple optional recommended values. The first device can determine the final recommended value based on a specific configuration or algorithm. In this case, the first device can optionally send an indication message to inform the second device or the target object that the recommended value is one of the alternatives, i.e., that the recommended value can be modified.

[0163] 2. Recommended operations for the target object. This differs from the aforementioned recommended values ​​in that the first device directly recommends actions for the target object, such as recommended SMF session control actions and recommended AMF load balancing operations. In one implementation, the first information may include multiple alternative recommended operations, each of which includes recommended operations for one or more target objects. The recommended operation for a target object may also be a combination of multiple operations for different aspects of the object.

[0164] 3. Information on the purpose or reason of the recommendation, which is used to explain the reason or purpose for the first device to send the above-mentioned recommended value or recommended operation. For example, the reason information is that the service experience statistics do not meet the standards, or the service experience is expected to fall short of the standards, etc. The sending of this purpose or reason information generally occurs in a scenario where the first device is subscribed to monitor service target information for a relatively long period of time, that is, when the first device detects that the service target information cannot be achieved, the first device sends the recommended value or recommended operation to the target object, and the first device also sends the above-mentioned purpose or reason for the recommendation to the target object.

[0165] 4. Information about the target object.

[0166] 5. Predicted information about the business objective corresponding to the first recommendation information. When the first device sends multiple optional recommendation values ​​or multiple optional recommended actions (i.e., multiple alternatives), the business objective here can also be a prediction of the business objectives that can be achieved by different alternatives. For example, alternative 1 is expected to achieve a service MOS of 4, and alternative 2 is expected to achieve a service MOS of 4.5.

[0167] Optionally, before step 33, the second device may inform the first device whether the request message is accepted or executed, specifically in the form of a response to the request message.

[0168] It should be noted that the first device sending the content of the first information to the second device, and the second device subsequently deciding whether to send part or all of the content to the target object, is only one implementation method. In some embodiments, the first device can also directly send part or all of the content of the first information to one or more target objects. The one or more target objects can be notified by the second device or determined by the first device itself.

[0169] Step 34: The second device sends second information to one or more target objects, for notifying the target objects of recommendation information.

[0170] The second information may include at least one of the following:

[0171] Recommended value for the target object. For example, when the target object is AMF, the recommended information here is AMF load < 65%;

[0172] Recommended actions for the target object. For example, when the target object is AMF, the recommended action here is to remove 20% of idle or low activity UEs in the AMF;

[0173] Prediction information of the business goal that can be achieved by the second recommendation information (ie, the recommended value or recommended action).

[0174] It should be noted that the content contained in the second information is determined based on the content in the first information. In one example, the second device can directly send the recommended value for the target object received from the first device to the target object device (i.e., forward it). In another example, the second device can also add its own judgment logic therein, combine the content of the received first information with its own information input, and determine the second information for the target object. For example, the PCF, as the second device, receives the first information from the first device, which contains recommended values ​​for multiple target objects, such as the S-NSSAI for service flow recommended for SMF, the DNN for service flow and location for UE recommended for AMF, etc. The PCF sets the UE AM policy based on the recommended information for AMF, and sends the UE AM policy to the AMF to perform the corresponding access control operation. The PCF sets the UE SM policy based on the recommended information for SMF, and sends the UE SM policy to the SMF to perform the corresponding session control operation, etc.

[0175] Optionally, before step 34, the second device may determine a recommended operation corresponding to each target object, and then send the corresponding recommended operation to the target object.

[0176] Step 35: The target object performs a corresponding operation according to the second information.

[0177] In one example, the target object may directly execute the recommended operation in the second information, or execute the operation corresponding to the recommended value in the second information.

[0178] In one example, the target object only uses the content in the second information as a reference to determine whether to perform and what operation to perform.

[0179] Optionally, in a case where the second information includes a recommended value of the target object, the target object may determine the operation to be performed according to the recommended value in the second information.

[0180] Example 2: As shown in FIG4 , in some embodiments, an operation recommendation method based on an AI model may include the following process:

[0181] Step 41 and step 42 are the same as step 31 and step 32, and are not described again here.

[0182] Step 43: The first device directly sends the first information to the target object.

[0183] Step 44 is the same as step 35 and will not be described again here.

[0184] Optionally, if the second device is one of the target objects, the first device may send the first information to the second device, and the second device executes step 44 .

[0185] Example 3: In some embodiments, the main idea of ​​AI obtaining the first recommendation information corresponding to the business goal information based on the AI ​​model and the business goal information of the target business is: based on the AI ​​model, when the model output result Y is specified, infer the model input X corresponding to Y.

[0186] For example, according to the requirements of the second device (Y = business target information, such as service MOS ≥ 3.0), based on the AI ​​model, the first device integrates multiple influencing factors (other constraints, or specified requirements, such as x i <100), reverse inference to get the model input X, that is, x=f -1 (y), where X is a multi-input vector (x1, x2, x3…x n ), and each element in the X vector corresponds to a different network operation.

[0187] The corresponding expression of the AI ​​model is: y = f(x) = w0x0 + w1x1 + ... + w D x D ;

[0188] In this embodiment:

[0189] 1. Assume that the AI ​​model already exists (trained by the first device itself, or obtained from other first devices, or other methods).

[0190] 2. Given business goal information or condition information, the business goal information or condition information may include one or more actual business goals (such as Y = service mos ≥ 3), as well as other constraints (x i =GBR<100Mbps, x j =MBR<256Mbps).

[0191] 3. Based on the AI ​​model and the above business target information, the first device can use a multi-objective optimization method (such as the NSGA method) to determine the value of the corresponding model input X vector. Where X=(x1,x2…x n ), each element x i May correspond to one or more network operations, such as x i =GBR corresponds to the air interface of the access network equipment to ensure bandwidth resource allocation and regulation operations.

[0192] 4. Optionally, in one implementation, the first device obtains X=(x1, x2…x n ) vector value as the recommendation information for the corresponding network-related equipment, such as x1 = 4G RAT, x2 = UE location = TAI 1, ....x i =GBR=100Mbps, x j =MBR=256Mbps….

[0193] In another implementation, the first device may be configured to generate a 10 ... n ) vector value, mapping out the recommended operation information of network-related devices, such as action 1 (AMF needs to trigger the UE RFSP to switch from the index corresponding to 5G RAT to the index corresponding to 4G RAT, RFSP index1->RFSP index 2), action 2 (RAN needs to adjust the air interface bandwidth resources of the GBR corresponding to the UE service flow from 50MHZ to 100MHZ);

[0194] It should be noted that the first device obtains X = (x1, x2…x n ) There may be multiple values ​​that meet the above business target information or condition information.

[0195] Example 4: In some embodiments, the network recommendation scheme for service MOS score is as follows:

[0196] 1. The PCF (a second device) sends a request message to the NWDAF (a first device), specifying a communication service target, such as a service MOS ≥ 4 for application ID 1. Optionally, the request type may also be specified as QoS parameter setting, requesting the first device to recommend QoS parameter settings.

[0197] 2. NWDAF performs model inference based on the AI ​​model and business target information to obtain the model input X = (x1, x2…x n The specific method of reverse reasoning can be a multi-objective optimization method.

[0198] 3. NWDAF is based on X=(x1,x2…x n ) vector value, obtain the corresponding operation recommendations for various target objects. Among them, the X vector can have multiple possible combinations, for example, according to recommendation 1: x1 = 4G RAT, x2 = UE location = TAI 1, ....x i =GBR=100Mbps…, or recommendation 2: x1=5G RAT, x2=UE location=TAI 2,….x i =GBR=200Mbps….

[0199] 4. Furthermore, NWDAF maps the target object action combination corresponding to each combination of X vectors and sends each action combination to the corresponding target object for execution.

[0200] 5 , an embodiment of the present application further provides an operation recommendation method based on an AI model. As shown in FIG5 , the operation recommendation method based on an AI model includes:

[0201] Step 501: The target object receives first information from a first device or second information from a second device;

[0202] The first information includes first recommendation information, which is determined based on the AI ​​model and business goal information of the target business, the business goal information is used to indicate the business goal to be achieved, and the first recommendation information is used to determine the operation associated with the target business;

[0203] The second information includes second recommendation information, the second recommendation information is determined based on the first recommendation information, and the target object is a device or function that performs the operation.

[0204] Optionally, when the target object receives the first information from the first device, the method further includes:

[0205] The target object sends first feedback information to the first device, where the first feedback information includes at least one of the following:

[0206] seventh indication information, the seventh indication information being used to indicate whether the target object accepts the first recommendation information;

[0207] The reason why the target object rejects the first recommendation information.

[0208] Optionally, in a case where the first information includes multiple pieces of first recommendation information, the first feedback information further includes identification information of the first recommendation information.

[0209] Optionally, when the first feedback information includes the seventh indication information, and the seventh indication information indicates that the target object rejects the first recommendation information, the method further includes:

[0210] The target object receives the first recommendation information newly determined from the first device.

[0211] Optionally, when the target object receives the second information from the second device, the method further includes:

[0212] The target object sends second feedback information to the second device;

[0213] The second feedback information includes at least one of the following:

[0214] eighth indication information, the eighth indication information being used to indicate whether the target object accepts the second recommendation information;

[0215] The reason why the target object rejects the second recommendation information.

[0216] Optionally, in a case where the second information includes multiple pieces of second recommendation information, the second feedback information further includes identification information of the second recommendation information.

[0217] Optionally, when the second feedback information includes the eighth indication information, and the eighth indication information indicates that the target object rejects the second recommendation information, the method further includes:

[0218] The target object receives the second recommendation information newly determined from the second device.

[0219] Optionally, the method further includes:

[0220] The target object determines whether to accept the target recommendation information, where the target recommendation information is the first recommendation information or the second recommendation information.

[0221] Optionally, the target recommendation information includes at least one of the following:

[0222] Recommended actions associated with the target service;

[0223] Recommended values ​​for parameters associated with the target service.

[0224] Optionally, when the target object accepts the target recommendation information, the method further includes:

[0225] The target object determines a target operation according to the target recommendation information;

[0226] The target object performs the target operation.

[0227] Optionally, the target object determines a target operation according to the target recommendation information, including at least one of the following:

[0228] Determining the target operation according to the recommended operation associated with the target business in the target recommendation information;

[0229] The target operation is determined according to the recommended value of the parameter associated with the target service in the target recommendation information.

[0230] Optionally, the target object includes at least one of the following: access and mobility management function AMF, session management function SMF, user plane function UPF, policy control function entity PCF, terminal UE, application function AF, access network RAN, operation and maintenance management OAM.

[0231] 6 , an embodiment of the present application further provides an operation recommendation method based on an AI model. As shown in FIG6 , the operation recommendation method based on an AI model includes:

[0232] Step 601: The second device receives first information from the first device;

[0233] Among them, the first information includes first recommendation information, which is determined based on the AI ​​model and business goal information of the target business. The business goal information is used to represent the business goal to be achieved, and the first recommendation information is used to determine the operation associated with the target business.

[0234] Optionally, the method further includes:

[0235] The second device determines second information based on the first information;

[0236] The second device sends the second information to the target object;

[0237] The second information includes second recommendation information, the second recommendation information is determined based on the first recommendation information, and the target object is a device or function that performs the operation.

[0238] Optionally, the second device determining the second information according to the first information includes:

[0239] The second device determines second recommendation information, where the second recommendation information includes at least one of the following: the first recommendation information, and recommendation information determined based on the first recommendation information;

[0240] The second device generates the second information based on the second recommendation information.

[0241] Optionally, the method further includes

[0242] The second device receives second feedback information from the target object;

[0243] The second feedback information includes at least one of the following:

[0244] eighth indication information, the eighth indication information being used to indicate whether the target object accepts the second recommendation information;

[0245] The reason why the target object rejects the second recommendation information.

[0246] Optionally, in a case where the second information includes multiple pieces of second recommendation information, the second feedback information further includes identification information of the second recommendation information.

[0247] Optionally, the method further includes: the second device determining first feedback information based on the second feedback information.

[0248] Optionally, when the second feedback information includes the eighth indication information, and the eighth indication information indicates that the target object rejects the second recommendation information, the method further includes:

[0249] The second device re-determines the second recommendation information;

[0250] The second device sends the re-determined second recommendation information to the target object.

[0251] Optionally, the second device re-determining the second recommendation information includes at least one of the following:

[0252] The second device re-determines second recommendation information based on the first recommendation information;

[0253] The second device reacquires the first recommendation information from the first device, and re-determines the second recommendation information based on the reacquired first recommendation information.

[0254] Optionally, the second recommendation information includes at least one of the following:

[0255] Recommended actions associated with the target service;

[0256] Recommended values ​​for parameters associated with the target service.

[0257] Optionally, the second information includes at least one piece of the second recommendation information;

[0258] Each piece of the second recommendation information includes at least one recommended operation or a recommended value of at least one parameter corresponding to the target object.

[0259] Optionally, when the second information includes multiple pieces of second recommendation information, the second information further includes at least one of the following:

[0260] ninth indication information, where the ninth indication information is used to indicate the quantity of the second recommended information;

[0261] Identification information of each piece of second recommendation information.

[0262] Optionally, the second information further includes at least one of the following:

[0263] the reason or purpose for the recommendation;

[0264] Forecast information for business objectives;

[0265] tenth indication information, where the tenth indication information is used to indicate whether alternative recommendation information exists in the second device or to indicate whether the target object is allowed to request to replace the second recommendation information;

[0266] eleventh indication information, the eleventh indication information being used to indicate a type of the second recommendation information, wherein the type of the second recommendation information includes a recommended operation or a recommended value of a parameter;

[0267] Recommendation indication information, where the recommendation indication information is used to indicate that the second recommendation information is information of a recommended purpose.

[0268] Optionally, the second recommendation information includes at least one of the following:

[0269] information indicating a recommended terminal device policy;

[0270] Information indicating a recommended access control policy;

[0271] Information indicating the recommended session control policy.

[0272] Optionally, the method further includes:

[0273] The second device sends a request message to the first device, where the request message includes at least one of the following:

[0274] Business target information of the target business;

[0275] AI task type information;

[0276] Business type information of the target business;

[0277] first indication information, where the first indication information is used to indicate a request to obtain recommendation information corresponding to the business target information;

[0278] second indication information, where the second indication information is used to indicate a type of the recommended information requested, where the type of the recommended information includes a recommended operation or a recommended value of a parameter;

[0279] third indication information, where the third indication information is used to indicate the quantity of the recommended information requested;

[0280] Information of a target object, where the information of the target object is used to indicate the target object;

[0281] Network status information, used to indicate current or future network status, and the network status information is used to obtain recommendation information corresponding to the network status;

[0282] Condition information associated with the first recommendation information.

[0283] Optionally, the method further includes:

[0284] The second device sends first feedback information to the first device, where the first feedback information includes at least one of the following:

[0285] seventh indication information, where the seventh indication information is used to indicate whether the target object or the second device accepts the first recommendation information;

[0286] Reason information why the target object or the second device rejects the first recommendation information.

[0287] Optionally, in a case where the first information includes multiple pieces of first recommendation information, the first feedback information further includes identification information of the first recommendation information.

[0288] Optionally, the target object includes at least one of the following: access and mobility management function AMF, session management function SMF, user plane function UPF, policy control function entity PCF, terminal UE, application function AF, access network RAN, operation and maintenance management OAM.

[0289] The AI ​​model-based operation recommendation method provided in the embodiments of the present application can be executed by an AI model-based operation recommendation device. In the embodiments of the present application, the AI ​​model-based operation recommendation device executing the AI ​​model-based operation recommendation method is used as an example to illustrate the AI ​​model-based operation recommendation device provided in the embodiments of the present application.

[0290] 7 , an embodiment of the present application further provides an AI model-based operation recommendation apparatus, which is applied to a first device. As shown in FIG7 , the AI ​​model-based operation recommendation apparatus 700 includes:

[0291] An acquisition module 701 is configured to acquire, based on an AI model and business objective information of a target business, first recommendation information corresponding to the business objective information, wherein the business objective information is used to indicate a desired business objective, and the first recommendation information is used to determine an operation associated with the target business;

[0292] The first sending module 702 is configured to send first information to a target object or a second device, where the first information includes the first recommendation information. The target object is a device or function that performs the operation.

[0293] Optionally, the AI ​​model-based operation recommendation device 700 further includes:

[0294] The first receiving module is configured to receive a request message from the second device, where the request message includes at least one of the following:

[0295] Business target information of the target business;

[0296] AI task type information;

[0297] Business type information of the target business;

[0298] first indication information, where the first indication information is used to indicate a request to obtain recommendation information corresponding to the business target information;

[0299] second indication information, where the second indication information is used to indicate a type of the recommended information requested, where the type of the recommended information includes a recommended operation or a recommended value of a parameter;

[0300] third indication information, where the third indication information is used to indicate the quantity of the recommended information requested;

[0301] Information of a target object, where the information of the target object is used to indicate the target object;

[0302] Network status information, used to indicate current or future network status, and the network status information is used to obtain recommendation information corresponding to the network status;

[0303] Condition information associated with the first recommendation information.

[0304] Optionally, when sending first information to a second device, the first information is used to trigger the second device to send second information to a target object, the second information includes second recommendation information, and the second recommendation information is determined based on the first recommendation information.

[0305] Optionally, the first information further includes at least one of the following:

[0306] the reason or purpose for the recommendation;

[0307] Information of the target object corresponding to the first recommendation information;

[0308] Forecast information for business objectives;

[0309] Fourth indication information, where the fourth indication information is used to indicate whether alternative recommendation information exists in the first device or to indicate whether the second device or the target object is allowed to request to replace the first recommendation information;

[0310] fifth indication information, where the fifth indication information is used to indicate a type of the first recommendation information, where the type of the first recommendation information includes a recommended operation or a recommended value of a parameter;

[0311] Recommendation indication information, where the recommendation indication information is used to indicate that the first recommendation information is information of a recommended purpose.

[0312] Optionally, the first recommendation information includes at least one of the following:

[0313] Recommended actions associated with the target service;

[0314] Recommended values ​​for parameters associated with the target service.

[0315] Optionally, the first information includes at least one piece of the first recommendation information;

[0316] Each piece of the first recommendation information includes at least one recommended operation or a recommended value of at least one parameter corresponding to the target object.

[0317] Optionally, when the first information includes multiple pieces of first recommendation information, the first information further includes at least one of the following:

[0318] sixth indication information, where the sixth indication information is used to indicate the quantity of the first recommended information;

[0319] Identification information of each piece of first recommendation information.

[0320] Optionally, the AI ​​model-based operation recommendation device 700 further includes:

[0321] The first receiving module is configured to receive first feedback information from the second device or the target object, where the first feedback information includes at least one of the following:

[0322] seventh indication information, where the seventh indication information is used to indicate whether the second device or the target object accepts the first recommendation information;

[0323] Reason information why the second device or the target object rejects the first recommendation information.

[0324] Optionally, in a case where the first information includes multiple pieces of first recommendation information, the first feedback information further includes identification information of the first recommendation information.

[0325] Optionally, the first sending module 702 is also used to redetermine the first recommendation information and send the redetermined first recommendation information to the second device or the target object when the first feedback information includes the seventh indication information and the seventh indication information indicates that the second device or the target object rejects the first recommendation information.

[0326] Optionally, the first sending module 702 is also used to send the identification information of the first recommendation information contained in the first feedback information to other target objects when the first feedback information contains the seventh indication information and the seventh indication information indicates that the second device or the target object accepts the first recommendation information.

[0327] Optionally, the first recommendation information includes at least one of the following:

[0328] information indicating a recommended terminal device policy;

[0329] Information indicating a recommended access control policy;

[0330] Information indicating the recommended session control policy.

[0331] Optionally, the target object includes at least one of the following: access and mobility management function AMF, session management function SMF, user plane function UPF, policy control function entity PCF, terminal UE, application function AF, access network RAN, operation and maintenance management OAM.

[0332] Optionally, the second device includes a PCF.

[0333] 8 , an embodiment of the present application further provides an AI model-based operation recommendation device. As shown in FIG8 , the AI ​​model-based operation recommendation device 800 includes:

[0334] A second receiving module 801 is configured to receive first information from a first device or second information from a second device;

[0335] The first information includes first recommendation information, which is determined based on the AI ​​model and business goal information of the target business, the business goal information is used to indicate the business goal to be achieved, and the first recommendation information is used to determine the operation associated with the target business;

[0336] The second information includes second recommendation information, and the second recommendation information is determined based on the first recommendation information.

[0337] Optionally, the AI ​​model-based operation recommendation device 800 further includes:

[0338] The second sending module is configured to send first feedback information to the first device when the target object receives the first information from the first device, where the first feedback information includes at least one of the following:

[0339] seventh indication information, the seventh indication information being used to indicate whether the target object accepts the first recommendation information;

[0340] The reason why the target object rejects the first recommendation information.

[0341] Optionally, in a case where the first information includes multiple pieces of first recommendation information, the first feedback information further includes identification information of the first recommendation information.

[0342] Optionally, the second receiving module 801 is further configured to receive the first recommendation information re-determined from the first device when the first feedback information includes the seventh indication information and the seventh indication information indicates that the target object rejects the first recommendation information.

[0343] Optionally, the AI ​​model-based operation recommendation device 800 further includes:

[0344] A second sending module, configured to send second feedback information to the second device;

[0345] The second feedback information includes at least one of the following:

[0346] eighth indication information, the eighth indication information being used to indicate whether the target object accepts the second recommendation information;

[0347] The reason why the target object rejects the second recommendation information.

[0348] Optionally, in a case where the second information includes multiple pieces of second recommendation information, the second feedback information further includes identification information of the second recommendation information.

[0349] Optionally, the second receiving module 801 is further configured to receive the second recommendation information re-determined from the second device when the second feedback information includes the eighth indication information and the eighth indication information indicates that the target object rejects the second recommendation information.

[0350] Optionally, the AI ​​model-based operation recommendation device 800 further includes:

[0351] The second determining module is configured to determine whether to accept the target recommendation information, where the target recommendation information is the first recommendation information or the second recommendation information.

[0352] Optionally, the target recommendation information includes at least one of the following:

[0353] Recommended actions associated with the target service;

[0354] Recommended values ​​for parameters associated with the target service.

[0355] Optionally, the AI ​​model-based operation recommendation device 800 further includes:

[0356] The execution module is used to determine a target operation according to the target recommendation information when the target object accepts the target recommendation information; and execute the target operation.

[0357] Optionally, the execution module is specifically configured to execute at least one of the following:

[0358] Determining the target operation according to the recommended operation associated with the target business in the target recommendation information;

[0359] The target operation is determined according to the recommended value of the parameter associated with the target service in the target recommendation information.

[0360] Optionally, the target object includes at least one of the following: access and mobility management function AMF, session management function SMF, user plane function UPF, policy control function entity PCF, terminal UE, application function AF, access network RAN, operation and maintenance management OAM.

[0361] 9 , an embodiment of the present application further provides an AI model-based operation recommendation device. As shown in FIG9 , the AI ​​model-based operation recommendation device 900 includes:

[0362] A third receiving module 901 is configured to receive first information from a first device;

[0363] Among them, the first information includes first recommendation information, which is determined based on the AI ​​model and business goal information of the target business. The business goal information is used to represent the business goal to be achieved, and the first recommendation information is used to determine the operation associated with the target business.

[0364] Optionally, the AI ​​model-based operation recommendation device 900 further includes:

[0365] a first determining module, configured to determine second information based on the first information;

[0366] A third sending module, configured to send the second information to a target object;

[0367] The second information includes second recommendation information, the second recommendation information is determined based on the first recommendation information, and the target object is a device or function that performs the operation.

[0368] Optionally, the first determination module is specifically used to determine second recommendation information, where the second recommendation information includes at least one of the following: first recommendation information, recommendation information determined based on the first recommendation information; and generating the second information based on the second recommendation information.

[0369] Optionally, the third receiving module 901 is further configured to receive second feedback information from the target object;

[0370] The second feedback information includes at least one of the following:

[0371] eighth indication information, the eighth indication information being used to indicate whether the target object accepts the second recommendation information;

[0372] The reason why the target object rejects the second recommendation information.

[0373] Optionally, in a case where the second information includes multiple pieces of second recommendation information, the second feedback information further includes identification information of the second recommendation information.

[0374] Optionally, the AI ​​model-based operation recommendation device 900 further includes:

[0375] A first determining module is configured to determine first feedback information based on the second feedback information.

[0376] Optionally, the AI ​​model-based operation recommendation device 900 further includes:

[0377] The third sending module is configured to, when the second feedback information includes the eighth indication information and the eighth indication information indicates that the target object rejects the second recommendation information, redetermine the second recommendation information; and send the redetermined second recommendation information to the target object.

[0378] Optionally, the method is specifically configured to perform at least one of the following:

[0379] re-determining second recommendation information based on the first recommendation information;

[0380] The first recommendation information is re-acquired from the first device, and the second recommendation information is re-determined based on the re-acquired first recommendation information.

[0381] Optionally, the second recommendation information includes at least one of the following:

[0382] Recommended actions associated with the target service;

[0383] Recommended values ​​for parameters associated with the target service.

[0384] Optionally, the second information includes at least one piece of the second recommendation information;

[0385] Each piece of the second recommendation information includes at least one recommended operation or a recommended value of at least one parameter corresponding to the target object.

[0386] Optionally, when the second information includes multiple pieces of second recommendation information, the second information further includes at least one of the following:

[0387] ninth indication information, where the ninth indication information is used to indicate the quantity of the second recommended information;

[0388] Identification information of each piece of second recommendation information.

[0389] Optionally, the second information further includes at least one of the following:

[0390] the reason or purpose for the recommendation;

[0391] Forecast information for business objectives;

[0392] tenth indication information, where the tenth indication information is used to indicate whether alternative recommendation information exists in the second device or to indicate whether the target object is allowed to request to replace the second recommendation information;

[0393] eleventh indication information, the eleventh indication information being used to indicate a type of the second recommendation information, wherein the type of the second recommendation information includes a recommended operation or a recommended value of a parameter;

[0394] Recommendation indication information, where the recommendation indication information is used to indicate that the second recommendation information is information of a recommended purpose.

[0395] Optionally, the second recommendation information includes at least one of the following:

[0396] information indicating a recommended terminal device policy;

[0397] Information indicating a recommended access control policy;

[0398] Information indicating the recommended session control policy.

[0399] Optionally, the AI ​​model-based operation recommendation device 900 further includes:

[0400] A third sending module is configured to send a request message to the first device, where the request message includes at least one of the following:

[0401] Business target information of the target business;

[0402] AI task type information;

[0403] Business type information of the target business;

[0404] first indication information, where the first indication information is used to indicate a request to obtain recommendation information corresponding to the business target information;

[0405] second indication information, where the second indication information is used to indicate a type of the recommended information requested, where the type of the recommended information includes a recommended operation or a recommended value of a parameter;

[0406] third indication information, where the third indication information is used to indicate the quantity of the recommended information requested;

[0407] Information of a target object, where the information of the target object is used to indicate the target object;

[0408] Network status information, used to indicate current or future network status, and the network status information is used to obtain recommendation information corresponding to the network status;

[0409] Condition information associated with the first recommendation information.

[0410] Optionally, the AI ​​model-based operation recommendation device 900 further includes:

[0411] A third sending module is configured to send first feedback information to the first device, where the first feedback information includes at least one of the following:

[0412] seventh indication information, where the seventh indication information is used to indicate whether the target object or the second device accepts the first recommendation information;

[0413] Reason information why the target object or the second device rejects the first recommendation information.

[0414] Optionally, in a case where the first information includes multiple pieces of first recommendation information, the first feedback information further includes identification information of the first recommendation information.

[0415] Optionally, the target object includes at least one of the following: access and mobility management function AMF, session management function SMF, user plane function UPF, policy control function entity PCF, terminal UE, application function AF, access network RAN, operation and maintenance management OAM.

[0416] The AI ​​model-based operation recommendation device in the embodiment of the present application can be an electronic device, such as an electronic device with an operating system, or a component in an electronic device, such as an integrated circuit or chip. The electronic device can be a terminal or other device other than a terminal. For example, the terminal can include but is not limited to the types of terminals 11 listed above, and other devices can be servers, network attached storage (NAS), etc., which are not specifically limited in the embodiment of the present application.

[0417] The AI ​​model-based operation recommendation device provided in the embodiment of the present application can implement the various processes implemented in the method embodiments of Figures 2 to 6 and achieve the same technical effects. To avoid repetition, it will not be repeated here.

[0418] As shown in Figure 10, an embodiment of the present application also provides a communication device 1000, including a processor 1001 and a memory 1002, and the memory 1002 stores a program or instruction that can be run on the processor 1001. When the program or instruction is executed by the processor 1001, the various steps of the above-mentioned AI model-based operation recommendation method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0419] The present application also provides a terminal including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is configured to execute a program or instruction to implement the steps of the method embodiment shown in FIG5 . This terminal embodiment corresponds to the aforementioned terminal-side method embodiment, and each implementation process and implementation method of the aforementioned method embodiment is applicable to this terminal embodiment and can achieve the same technical effects. Specifically, FIG11 is a schematic diagram of the hardware structure of a terminal implementing an embodiment of the present application.

[0420] The terminal 1100 includes but is not limited to: a radio frequency unit 1101, a network module 1102, an audio output unit 1103, an input unit 1104, a sensor 1105, a display unit 1106, a user input unit 1107, an interface unit 1108, a memory 1109 and at least some of the components of the processor 1110.

[0421] Those skilled in the art will appreciate that the terminal 1100 may also include a power supply (such as a battery) to power various components. The power supply may be logically connected to the processor 1110 via a power management system, thereby enabling the power management system to manage charging, discharging, and power consumption. The terminal structure shown in FIG11 does not limit the terminal. The terminal may include more or fewer components than shown, or combine certain components, or arrange the components differently, which will not be described in detail here.

[0422] It should be understood that in an embodiment of the present application, the input unit 1104 may include a graphics processing unit (GPU) 11041 and a microphone 11042, and the graphics processor 11041 processes the image data of a static picture or video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 1106 may include a display panel 11061, and the display panel 11061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 1107 includes a touch panel 11071 and at least one of other input devices 11072. The touch panel 11071 is also called a touch screen. The touch panel 11071 may include two parts: a touch detection device and a touch controller. Other input devices 11072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which will not be repeated here.

[0423] In the embodiment of the present application, after receiving downlink data from a network-side device, the RF unit 1101 may transmit the data to the processor 1110 for processing. Furthermore, the RF unit 1101 may send uplink data to the network-side device. Typically, the RF unit 1101 includes, but is not limited to, an antenna, an amplifier, a transceiver, a coupler, a low-noise amplifier, a duplexer, and the like.

[0424] The memory 1109 can be used to store software programs or instructions and various data. The memory 1109 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, applications or instructions required for at least one function (such as a sound playback function, an image playback function, etc.). In addition, the memory 1109 may include a volatile memory or a non-volatile memory. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DRRAM). The memory 1109 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

[0425] Processor 1110 may include one or more processing units. Optionally, processor 1110 integrates an application processor and a modem processor. The application processor primarily handles operations related to the operating system, user interface, and application programs, while the modem processor primarily processes wireless communication signals, such as a baseband processor. It is understood that the modem processor may not be integrated into processor 1110.

[0426] The radio frequency unit 1101 is configured to receive first information from a first device or second information from a second device;

[0427] The first information includes first recommendation information, which is determined based on the AI ​​model and business goal information of the target business, the business goal information is used to indicate the business goal to be achieved, and the first recommendation information is used to determine the operation associated with the target business;

[0428] The second information includes second recommendation information, and the second recommendation information is determined based on the first recommendation information.

[0429] It can be understood that the implementation process of each implementation method mentioned in this embodiment can refer to the relevant description of the first device side method embodiment and achieve the same or corresponding technical effects. To avoid repetition, it will not be repeated here.

[0430] The present application also provides a network-side device, including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is configured to execute a program or instruction to implement the steps of the method embodiment shown in Figures 2, 5, or 6. This network-side device embodiment corresponds to the aforementioned network-side device method embodiment, and each implementation process and implementation method of the aforementioned method embodiment is applicable to this network-side device embodiment and can achieve the same technical effects.

[0431] Specifically, the embodiment of the present application further provides a network side device. As shown in FIG12 , the network side device 1200 includes: a processor 1201, a network interface 1202, and a memory 1203. The network interface 1202 is, for example, a common public radio interface (CPRI).

[0432] Specifically, the network side device 1200 of the embodiment of the present application also includes: instructions or programs stored in the memory 1203 and executable on the processor 1201. The processor 1201 calls the instructions or programs in the memory 1203 to execute the methods executed by the modules shown in Figures 7, 8 or 9, and achieves the same technical effect. To avoid repetition, it will not be described here.

[0433] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the above-mentioned AI model-based operation recommendation method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0434] The processor is the processor in the terminal described in the above embodiment. The readable storage medium includes a computer-readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk. In some examples, the readable storage medium may be a non-transitory readable storage medium.

[0435] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned AI model-based operation recommendation method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0436] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0437] An embodiment of the present application further provides a computer program / program product, which includes computer instructions. The computer program / program product is executed by at least one processor to implement the various processes of the above-mentioned AI model-based operation recommendation method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0438] An embodiment of the present application also provides a wireless communication system, including: a first device, a second device and a target object, wherein the first device can be used to execute the steps of the AI ​​model-based operation recommendation method on the first device side as described above, the second device can be used to execute the steps of the AI ​​model-based operation recommendation method on the second device side as described above, and the target object can be used to execute the steps of the AI ​​model-based operation recommendation method on the target object side as described above.

[0439] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0440] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of a computer software product plus a necessary general hardware platform, or of course, by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disk, etc.) and includes a number of instructions for enabling a terminal or network-side device to execute the methods described in each embodiment of the present application.

[0441] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms of implementation methods without departing from the purpose of this application and the scope of protection of the claims. These implementation methods are all within the protection of this application.

Claims

1. An operation recommendation method based on an artificial intelligence (AI) model, comprising: The first device obtains, based on the AI model and business objective information of the target business, first recommendation information corresponding to the business objective information, where the business objective information is used to indicate a desired business objective, and the first recommendation information is used to determine an operation associated with the target business; The first device sends first information to a target object or a second device, where the first information includes the first recommendation information, and the target object is a device or function that performs the operation.

2. The method according to claim 1, wherein The method further comprises: The first device receives a request message from the second device, where the request message includes at least one of the following: Business target information of the target business; AI task type information; Business type information of the target business; first indication information, where the first indication information is used to indicate a request to obtain recommendation information corresponding to the business target information; second indication information, where the second indication information is used to indicate a type of the recommended information requested, where the type of the recommended information includes a recommended operation or a recommended value of a parameter; third indication information, where the third indication information is used to indicate the quantity of the recommended information requested; Information of a target object, where the information of the target object is used to indicate the target object; Network status information, used to indicate current or future network status, and the network status information is used to obtain recommendation information corresponding to the network status; Condition information associated with the first recommendation information.

3. The method according to claim 1 or 2, wherein: In the case where the first device sends first information to the second device, the first information is used to trigger the second device to send second information to the target object, the second information includes second recommendation information, and the second recommendation information is determined based on the first recommendation information.

4. The method according to any one of claims 1 to 3, wherein: The first information also includes at least one of the following: the reason or purpose for the recommendation; Information of the target object corresponding to the first recommendation information; Forecast information for business objectives; Fourth indication information, where the fourth indication information is used to indicate whether alternative recommendation information exists in the first device or to indicate whether the second device or the target object is allowed to request to replace the first recommendation information; fifth indication information, where the fifth indication information is used to indicate a type of the first recommendation information, where the type of the first recommendation information includes a recommended operation or a recommended value of a parameter; Recommendation indication information, where the recommendation indication information is used to indicate that the first recommendation information is information of a recommended purpose.

5. The method according to any one of claims 1 to 4, wherein: The first recommendation information includes at least one of the following: Recommended actions associated with the target service; Recommended values for parameters associated with the target service.

6. The method according to any one of claims 1 to 5, wherein: The first information includes at least one piece of the first recommendation information; Each piece of the first recommendation information includes at least one recommended operation or a recommended value of at least one parameter corresponding to the target object.

7. The method according to any one of claims 1 to 6, wherein: In the case where the first information includes multiple pieces of first recommendation information, the first information further includes at least one of the following: sixth indication information, where the sixth indication information is used to indicate the quantity of the first recommended information; Identification information of each piece of first recommendation information.

8. The method according to any one of claims 1 to 7, wherein The method further comprises: The first device receives first feedback information from the second device or the target object, where the first feedback information includes at least one of the following: seventh indication information, where the seventh indication information is used to indicate whether the second device or the target object accepts the first recommendation information; Reason information why the second device or the target object rejects the first recommendation information.

9. The method according to claim 8, wherein In a case where the first information includes a plurality of pieces of first recommendation information, the first feedback information further includes identification information of the first recommendation information.

10. The method according to claim 8 or 9, wherein: In a case where the first feedback information includes the seventh indication information, and the seventh indication information indicates that the second device or the target object rejects the first recommendation information, the method further includes: The first device redetermines the first recommendation information, and sends the redetermined first recommendation information to the second device or the target object.

11. The method according to claim 8, wherein When the first feedback information includes the seventh indication information, and the seventh indication information indicates that the second device or the target object accepts the first recommendation information, the method further includes: The first device sends the identification information of the first recommendation information included in the first feedback information to other target objects.

12. The method according to any one of claims 1 to 11, wherein: The first recommendation information includes at least one of the following: information indicating a recommended terminal device policy; Information indicating a recommended access control policy; Information indicating the recommended session control policy.

13. An operation recommendation method based on an AI model, comprising: The target object receives the first information from the first device or the second information from the second device; The first information includes first recommendation information, which is determined based on the AI model and business goal information of the target business, the business goal information is used to indicate the business goal to be achieved, and the first recommendation information is used to determine the operation associated with the target business; The second information includes second recommendation information, the second recommendation information is determined based on the first recommendation information, and the target object is a device or function that performs the operation.

14. The method according to claim 13, wherein In the case where the target object receives the first information from the first device, the method further includes: The target object sends first feedback information to the first device, where the first feedback information includes at least one of the following: seventh indication information, the seventh indication information being used to indicate whether the target object accepts the first recommendation information; The reason why the target object rejects the first recommendation information.

15. The method according to claim 14, wherein In a case where the first information includes a plurality of pieces of first recommendation information, the first feedback information further includes identification information of the first recommendation information.

16. The method according to claim 14 or 15, wherein: In a case where the first feedback information includes the seventh indication information, and the seventh indication information indicates that the target object rejects the first recommendation information, the method further includes: The target object receives the first recommendation information newly determined from the first device.

17. The method according to claim 13, wherein: In the case where the target object receives the second information from the second device, the method further includes: The target object sends second feedback information to the second device; The second feedback information includes at least one of the following: eighth indication information, the eighth indication information being used to indicate whether the target object accepts the second recommendation information; The reason why the target object rejects the second recommendation information.

18. The method according to claim 17, wherein In a case where the second information includes a plurality of pieces of second recommendation information, the second feedback information further includes identification information of the second recommendation information.

19. The method according to claim 17 or 18, wherein In a case where the second feedback information includes the eighth indication information, and the eighth indication information indicates that the target object rejects the second recommendation information, the method further includes: The target object receives the second recommendation information newly determined from the second device.

20. The method according to any one of claims 13 to 19, wherein The method further comprises: The target object determines whether to accept the target recommendation information, where the target recommendation information is the first recommendation information or the second recommendation information.

21. The method according to claim 20, wherein The target recommendation information includes at least one of the following: Recommended actions associated with the target service; Recommended values for parameters associated with the target service.

22. The method according to claim 20 or 21, wherein In a case where the target object accepts the target recommendation information, the method further includes: The target object determines a target operation according to the target recommendation information; The target object performs the target operation.

23. The method according to claim 22, wherein The target object determines a target operation according to the target recommendation information, including at least one of the following: Determining the target operation according to the recommended operation associated with the target business in the target recommendation information; The target operation is determined according to the recommended value of the parameter associated with the target service in the target recommendation information.

24. An operation recommendation method based on an AI model, comprising: The second device receives the first information from the first device; Among them, the first information includes first recommendation information, which is determined based on the AI model and business goal information of the target business. The business goal information is used to represent the business goal to be achieved, and the first recommendation information is used to determine the operation associated with the target business.

25. The method according to claim 24, wherein The method further comprises: The second device determines second information based on the first information; The second device sends the second information to the target object; The second information includes second recommendation information, the second recommendation information is determined based on the first recommendation information, and the target object is a device or function that performs the operation.

26. The method according to claim 24, wherein The second device determining the second information according to the first information includes: The second device determines second recommendation information, where the second recommendation information includes at least one of the following: the first recommendation information, and recommendation information determined based on the first recommendation information; The second device generates the second information based on the second recommendation information.

27. The method according to claim 25 or 26, wherein The method further includes The second device receives second feedback information from the target object; The second feedback information includes at least one of the following: eighth indication information, the eighth indication information being used to indicate whether the target object accepts the second recommendation information; The reason why the target object rejects the second recommendation information.

28. The method according to claim 27, wherein In a case where the second information includes a plurality of pieces of second recommendation information, the second feedback information further includes identification information of the second recommendation information.

29. The method according to claim 27, wherein The method further comprises: The second device determines first feedback information based on the second feedback information.

30. The method of claim 27, wherein: In a case where the second feedback information includes the eighth indication information, and the eighth indication information indicates that the target object rejects the second recommendation information, the method further includes: The second device re-determines the second recommendation information; The second device sends the re-determined second recommendation information to the target object.

31. The method according to claim 30, wherein The second device re-determining the second recommendation information includes at least one of the following: The second device re-determines second recommendation information based on the first recommendation information; The second device reacquires the first recommendation information from the first device, and re-determines the second recommendation information based on the reacquired first recommendation information.

32. The method according to any one of claims 25 to 31, wherein The second recommendation information includes at least one of the following: Recommended actions associated with the target service; Recommended values for parameters associated with the target service.

33. The method according to any one of claims 25 to 32, wherein: The second information includes at least one piece of the second recommendation information; Each piece of the second recommendation information includes at least one recommended operation or at least one recommended value of a parameter corresponding to the target object.

34. The method according to any one of claims 25 to 33, wherein In the case where the second information includes multiple pieces of second recommendation information, the second information further includes at least one of the following: ninth indication information, where the ninth indication information is used to indicate the quantity of the second recommended information; Identification information of each piece of second recommendation information.

35. The method according to any one of claims 25 to 34, wherein The second information further includes at least one of the following: the reason or purpose for the recommendation; Forecast information for business objectives; tenth indication information, where the tenth indication information is used to indicate whether alternative recommendation information exists in the second device or to indicate whether the target object is allowed to request to replace the second recommendation information; eleventh indication information, the eleventh indication information being used to indicate a type of the second recommendation information, wherein the type of the second recommendation information includes a recommended operation or a recommended value of a parameter; Recommendation indication information, where the recommendation indication information is used to indicate that the second recommendation information is information of a recommended purpose.

36. The method according to any one of claims 25 to 35, wherein: The second recommendation information includes at least one of the following: information indicating a recommended terminal device policy; Information indicating a recommended access control policy; Information indicating the recommended session control policy.

37. The method according to any one of claims 24 to 36, wherein The method further comprises: The second device sends a request message to the first device, where the request message includes at least one of the following: Business target information of the target business; AI task type information; Business type information of the target business; first indication information, where the first indication information is used to indicate a request to obtain recommendation information corresponding to the business target information; second indication information, where the second indication information is used to indicate a type of the recommended information requested, where the type of the recommended information includes a recommended operation or a recommended value of a parameter; third indication information, where the third indication information is used to indicate the quantity of the recommended information requested; Information of a target object, where the information of the target object is used to indicate the target object; Network status information, used to indicate current or future network status, and the network status information is used to obtain recommendation information corresponding to the network status; Condition information associated with the first recommendation information.

38. The method according to any one of claims 24 to 37, wherein The method further comprises: The second device sends first feedback information to the first device, where the first feedback information includes at least one of the following: seventh indication information, where the seventh indication information is used to indicate whether the target object or the second device accepts the first recommendation information; Reason information why the target object or the second device rejects the first recommendation information.

39. The method according to claim 38, wherein In a case where the first information includes a plurality of pieces of first recommendation information, the first feedback information further includes identification information of the first recommendation information.

40. An operation recommendation device based on an AI model, comprising: An acquisition module, configured to acquire, based on the AI model and business objective information of a target business, first recommendation information corresponding to the business objective information, wherein the business objective information is used to indicate a desired business objective, and the first recommendation information is used to determine an operation associated with the target business; The first sending module is used to send first information to a target object or a second device, where the first information includes the first recommendation information, and the target object is a device or function that performs the operation.

41. The apparatus according to claim 40, wherein Also includes: The first receiving module is configured to receive a request message from the second device, where the request message includes at least one of the following: Business target information of the target business; AI task type information; Business type information of the target business; first indication information, where the first indication information is used to indicate a request to obtain recommendation information corresponding to the business target information; second indication information, where the second indication information is used to indicate a type of the recommended information requested, where the type of the recommended information includes a recommended operation or a recommended value of a parameter; third indication information, where the third indication information is used to indicate the quantity of the recommended information requested; Information of a target object, where the information of the target object is used to indicate the target object; Network status information, used to indicate current or future network status, and the network status information is used to obtain recommendation information corresponding to the network status; Condition information associated with the first recommendation information.

42. An operation recommendation device based on an AI model, comprising: a second receiving module, configured to receive first information from the first device or second information from the second device; The first information includes first recommendation information, which is determined based on the AI model and business goal information of the target business, the business goal information is used to indicate the business goal to be achieved, and the first recommendation information is used to determine the operation associated with the target business; The second information includes second recommendation information, and the second recommendation information is determined based on the first recommendation information.

43. An operation recommendation device based on an AI model, comprising: a third receiving module, configured to receive first information from the first device; Among them, the first information includes first recommendation information, which is determined based on the AI model and business goal information of the target business. The business goal information is used to represent the business goal to be achieved, and the first recommendation information is used to determine the operation associated with the target business.

44. The apparatus of claim 43, wherein: The device further comprises: a first determining module, configured to determine second information based on the first information; A third sending module, configured to send the second information to a target object; The second information includes second recommendation information, the second recommendation information is determined based on the first recommendation information, and the target object is a device or function that performs the operation.

45. A terminal comprising a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the programs or instructions are executed by the processor, the steps of the AI model-based operation recommendation method according to any one of claims 13 to 23 are implemented.

46. A network-side device comprising a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the programs or instructions are executed by the processor, the steps of the AI model-based operation recommendation method as described in any one of claims 1 to 39 are implemented.

47. A readable storage medium storing a program or instruction, wherein the program or instruction, when executed by a processor, implements the steps of the operation recommendation method based on the AI model as described in any one of claims 1 to 39.

48. A computer program product, wherein The method comprises computer instructions which, when executed by a processor, implement the steps of the operation recommendation method based on the AI model as described in any one of claims 1 to 39.

49. A computer program product, wherein the computer program product is stored in a storage medium and is executed by at least one processor to implement the AI model-based operation recommendation method according to any one of claims 1 to 39.

50. A chip comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is configured to run a program or instruction to implement the AI model-based operation recommendation method according to any one of claims 1 to 39.

Images