Optimization method and apparatus for recommendation model

Abstract

The present application relates to the technical field of artificial intelligence, and provides an optimization method and apparatus for a recommendation model. In the method, a second network element can transmit an expected objective of a user for a recommendation model to a first network element by means of objective information, and the first network element can determine, on the basis of the received objective information, objective parameters capable of influencing the implementation of the expected objective and parameter indicators corresponding to the objective parameters, and transmit the objective parameters and the parameter indicators to the second network element, wherein the parameter indicators are used for indicating the capability of realizing the expected objective by means of the objective parameters. The second network element executes the objective parameters on the basis of the parameter indicators to obtain execution results, and then the first network element and / or the second network element can determine, on the basis whether the execution results reach the expected objective indicated by the objective information, whether to update the recommendation model. In this way, the recommendation model can be updated on the basis of the requirements of a user, thereby improving the efficiency of optimizing the recommendation model, and improving the satisfaction of the user for recommendation information generated by the recommendation model.

Description

Method and device for optimizing recommendation model

[0001] The present application claims priority to the Chinese Patent Application No. 202411111076.1, filed on August 13, 2024, and entitled "Method and device for optimizing recommendation model", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the field of artificial intelligence (AI) technology, and in particular to a method and device for optimizing a recommendation model. BACKGROUND

[0003] Currently, the constantly emerging AI models have shown strong capabilities in knowledge extraction and reasoning. Therefore, exploration based on AI models has rapidly developed in multiple fields such as computer vision, AI science, healthcare, and robotics, and a large number of AI models with different functions have been put into use in daily life. However, for a type of AI models used to generate recommendation strategies in AI models, due to the fact that the preferences of users are not fixed, the recommendation strategies generated by the recommendation model sometimes cannot meet the needs of users. SUMMARY

[0004] The present application provides a method and device for optimizing a recommendation model, which analyzes the expected target of the recommendation model and the corresponding execution result to determine whether to update the recommendation model, so as to make the model more meet the needs of users.

[0005] To achieve the above-mentioned purpose, the present application adopts the following technical solution:

[0006] In a first aspect, a method for optimizing a recommendation model is provided, which can be executed by a first network element. The first network element herein can refer to the first network element itself, or a processor, circuit, module, logic node, chip, or chip system in the first network element that implements the method.

[0007] The method includes: receiving a first message, the first message including target information, the target information being used to indicate an expected target of the recommendation model; sending first recommendation information, the first recommendation information indicating a target parameter and a parameter index corresponding to the target parameter, the target parameter and the parameter index being obtained according to the target information; the target parameter being used to achieve the expected target, and the parameter index being used to indicate the ability of the target parameter to achieve the expected target; receiving an execution result, the execution result being obtained based on the first recommendation information, and the execution result being used to determine whether to update the recommendation model.

[0008] Based on the method provided in the first aspect, the first network element determines, according to the received target information, target parameters that can be used to achieve the expected target and parameter indexes corresponding to the target parameters. The parameter indexes are used to indicate which parameters in the target parameters are executed to achieve the expected target indicated by the target information. The network element receiving the first recommendation information, such as the second network element, can execute the target parameters according to the indication of the parameter indexes to obtain execution results. The first network element can determine whether to update the recommendation model according to whether the execution results meet the expected target. In this way, the recommendation model corresponding to the target information and the execution results can be analyzed to determine whether to update the recommendation model, so that the execution results corresponding to the target parameters generated by the recommendation model are closer and closer to the target information, and the needs of the user are better met.

[0009] As a possible implementation manner, the target information includes at least one of quality of experience information, network function attribute information, or network function service range information. Based on this, the first network element can determine the target parameters and the parameter indexes corresponding to the target parameters according to various target information, analyze whether to update the model according to the execution results of the various target parameters, so as to optimize the recommendation model for various expected targets of the user, and meet the needs of the user from various aspects.

[0010] As a possible implementation manner, the first message further includes candidate parameters, the candidate parameters are related to the expected target, and the candidate parameters are used by the first network element to determine the target parameters. Based on this, the first network element can also refer to the candidate parameters when determining the target parameters according to the target information. For example, the candidate parameters are determined as the target parameters. For another example, one or more parameters are added to the candidate parameters to obtain the target parameters. By referring to the candidate parameters, the overhead of the first network element in determining the target parameters can be reduced, and the time cost of optimizing the model can be saved.

[0011] As a possible implementation manner, the target parameters include at least one of a quality of service parameter or a network element candidate list parameter; and the parameter indexes include at least one of an expected target achievement degree of the target parameters, an expected target relevance, or a target parameter priority. Based on this, the expected target achievement degree, the expected target relevance, or the target parameter priority can be used to indicate the ability of the quality of service parameter to achieve the expected target. The expected target achievement degree, the expected target relevance, or the target parameter priority can be used to indicate the ability of the network element candidate list parameter to achieve the expected target. Thus, the second network element executes the target parameters according to the indication of the parameter indexes to obtain the execution results.

[0012] As a possible implementation manner, the method further includes: receiving a second message, the second message being used to indicate that the execution result is received. Based on this, the first network element can receive the execution result obtained by executing the target parameter after receiving the indication of the second message. That is, the first network element triggers the collection of the execution result of the target parameter by receiving the second message after sending the target parameter and the parameter index corresponding to the target parameter, so as to determine whether to update the recommendation model according to the execution result.

[0013] As a possible implementation manner, the method further includes: receiving a third message, the third message being used to indicate that at least one of the target information or the candidate parameter is updated, the third message including one or more of the following: the updated target information or the updated candidate parameter. Based on this, the first network element can obtain new target information and candidate parameter according to the received updated target information or updated candidate parameter, and then determine the target parameter and the parameter index corresponding to the target parameter again based on the new target information and candidate parameter. In this way, in the case that the target information or the candidate parameter changes, the updated target information or the updated candidate parameter with part of the changes can be sent, so as to save transmission resources and improve the efficiency of model training.

[0014] As a possible implementation manner, the method further includes: determining to update the recommendation model when the execution result and the target information satisfy a first preset condition; wherein the execution result and the target information satisfying the first preset condition includes at least one of the following: a difference between the execution result and the target information is greater than or equal to a first preset threshold; or a ratio of the execution result to the target information is less than or equal to a second preset threshold. Based on this, the first network element can analyze the execution result and the target information, and update the recommendation model when the difference between the execution result and the target information is large. This makes the execution result corresponding to the recommendation information generated by the recommendation model closer to the target information, and more meets the needs of the user. When the difference between the execution result and the target information is small, the execution result can basically meet the needs of the user, and the recommendation model is not updated.

[0015] As a possible implementation manner, the method further includes: receiving a fourth message, the fourth message being used to indicate that the recommendation model used to generate the first recommendation information is updated. Based on this, the first network element can determine to update the recommendation model after receiving the indication of the fourth information. That is, the update of the recommendation model can be triggered by the fourth message, so that the updated recommendation model meets the needs of the user more.

[0016] In a second aspect, a method for optimizing a recommendation model is provided, which can be executed by a second network element. The second network element can refer to the second network element itself, or a processor, circuit, module, logic node, chip, or chip system in the second network element that implements the method.

[0017] The method comprises: sending a first message, the first message comprising target information, the target information being used to indicate an expected target of a recommendation model; receiving first recommendation information, the first recommendation information indicating a target parameter and a parameter index corresponding to the target parameter, the target parameter and the parameter index being obtained according to the target information, the target parameter being used to achieve the expected target, and the parameter index being used to indicate the ability of the target parameter to achieve the expected target; based on the parameter index, executing the target parameter to obtain a corresponding execution result; and sending the execution result, the execution result being used to determine whether to update the recommendation model.

[0018] Based on the method provided in the second aspect, the second network element sends target information corresponding to the expected target of the recommendation model, and executes the target parameter to obtain a corresponding execution result based on the parameter index corresponding to the target parameter received. Whether the execution result meets the expected target can be used to determine whether to update the recommendation model. In this way, the expected target can be set for the recommendation model, and whether to update the recommendation model can be determined by analyzing the target information corresponding to the expected target and the execution result. The execution result corresponding to the target parameter generated by the recommendation model is closer and closer to the target information, and better meets the needs of users.

[0019] As a possible implementation manner, the target information comprises at least one of quality of experience information, network function attribute information, and network function service range information. Based on this, the second network element can send various target information according to various expected targets, receive target parameters and parameter indexes corresponding to the target parameters determined according to the target information, and then execute the target parameters to obtain execution results. The execution results can be used to determine whether to update the model, so as to optimize the recommendation model for various expected targets of users and meet the needs of users from various aspects.

[0020] As a possible implementation manner, the first message further comprises a candidate parameter, the candidate parameter being related to the expected target and being used to determine the target parameter. Based on this, the second network element can send the candidate parameter when sending the target information, to assist in determining the target parameter. The candidate parameter sent by the second network element reduces the cost of determining the target parameter, and can save the time cost of optimizing the model.

[0021] As a possible implementation manner, the target parameter includes at least one of a quality of service parameter or a network element candidate list parameter, and the parameter index includes at least one of an expected target achievement degree corresponding to the target parameter, an expected target relevance, or a target parameter priority. Based on this, the at least one of the expected target achievement degree, the expected target relevance, or the target parameter priority can be used to indicate the ability of the at least one of the quality of service parameter or the network element candidate list parameter to achieve the expected target. Therefore, the second network element can adjust the value of the different target parameters and the execution order of the different target parameters according to the indication of the parameter index, and execute the target parameters to obtain an execution result. This makes the execution result closer to the target information.

[0022] As a possible implementation manner, the method further includes: sending a second message, the second message being used to indicate that the execution result is received. Based on this, the second network element can send the execution result obtained by executing the target parameter after sending the second message. That is, the second network element triggers the collection of the execution result of the target parameter by sending the second message, so as to realize the determination of whether to update the recommendation model according to the execution result.

[0023] As a possible implementation manner, the method further includes: sending a third message, the third message being used to indicate that at least one of the target information or the candidate parameter is updated, and the third message including one or more of the updated target information or the updated candidate parameter. Based on this, the second network element can indicate that the new target information and the candidate parameter are determined by sending the updated target information or the updated candidate parameter, and then determine the target parameter and the parameter index corresponding to the target parameter based on the new target information and the candidate parameter. In this way, in the case that the target information or the candidate parameter changes, only the updated target information or the updated candidate parameter that changes partially is sent, so that the transmission resource is saved and the efficiency of model training is improved.

[0024] As a possible implementation manner, the method further includes: when the execution result and the target information satisfy a first preset condition, sending a fourth message, the fourth message being used to indicate that the recommendation model is updated; and the execution result and the target information satisfying the first preset condition includes at least one of the following: a difference between the execution result and the target information being greater than or equal to a first preset threshold; or a ratio of the execution result to the target information being less than or equal to a second preset threshold. Based on this, the second network element can analyze the execution result and the target information, and send the fourth message to indicate that the recommendation model is updated when the difference between the execution result and the target information is large. This makes the execution result corresponding to the recommendation information generated by the recommendation model closer to the target information and more meet the needs of the user. When the difference between the execution result and the target information is small, it indicates that the execution result can basically meet the needs of the user, and the fourth message is not sent.

[0025] In a third aspect, a communication apparatus is provided for implementing the method in the first aspect. The communication apparatus can be a first network element in the first aspect. The communication apparatus comprises modules, units, or means for implementing the corresponding functions of the method. The modules, units, or means can be implemented in hardware, or by software with the support of the hardware.

[0026] In a possible implementation, the communication apparatus can include a processing module and an interface module. The processing module can be configured to implement the processing functions in the first aspect and any possible implementation of the first aspect. The processing module can be, for example, a processor. The interface module, which can also be referred to as an interface unit, is configured to implement the sending and / or receiving functions in the first aspect and any possible implementation of the first aspect. The interface module can be composed of an interface circuit, a transceiver, a transceiver, or a communication interface.

[0027] In a possible implementation, the processing module is configured to control the interface module to receive a first message, the first message including target information, the target information being used to indicate an expected target of a recommendation model; the processing module is further configured to control the interface module to send first recommendation information, the first recommendation information indicating a target parameter and a parameter index corresponding to the target parameter, the target parameter and the parameter index being obtained according to the target information; the target parameter is used to implement the expected target, and the parameter index is used to indicate the ability of the target parameter to implement the expected target; the processing module is further configured to control the interface module to receive an execution result, the execution result being obtained based on the first recommendation information, and the execution result being used to determine whether to update the recommendation model.

[0028] In a possible implementation, the target information includes at least one of quality of experience information, network function attribute information, and network function service range information.

[0029] In a possible implementation, the first message further includes a candidate parameter, the candidate parameter being related to the expected target, and the candidate parameter being used by the first network element to determine the target parameter.

[0030] In a possible implementation, the target parameter includes at least one of a quality of service parameter and a network element candidate list parameter; and the parameter index includes at least one of an expected target achievement degree corresponding to the target parameter, an expected target relevance, and a target parameter priority.

[0031] In a possible implementation, the processing module is further configured to control the interface module to receive a second message, the second message being used to indicate the execution result.

[0032] In a possible implementation, the processing module is further configured to control the interface module to receive a third message, the third message being used to indicate at least one of the updated target information or the candidate parameter, and the third message comprising one or more of the following: the updated target information or the updated candidate parameter.

[0033] In a possible implementation, the processing module is further configured to determine to update the recommendation model when the execution result and the target information satisfy a first preset condition; and the execution result and the target information satisfying the first preset condition comprises at least one of the following: a difference between the execution result and the target information being greater than or equal to a first preset threshold; or a ratio of the execution result to the target information being less than or equal to a second preset threshold.

[0034] In a possible implementation, the processing module is further configured to control the interface module to receive a fourth message, the fourth message being used to indicate to update a recommendation model used to generate the first recommendation information.

[0035] In a fourth aspect, a communication apparatus is provided for implementing the method in the second aspect. The communication apparatus can be the second network element in the second aspect. The communication apparatus includes modules, units, or means corresponding to the method, which can be implemented by hardware, software, or by executing corresponding software by hardware. The hardware or software includes one or more modules or units corresponding to the above functions.

[0036] In a possible implementation, the communication apparatus can include a processing module and an interface module. The processing module can be configured to implement the processing functions in the second aspect and any possible implementation thereof. The processing module can be, for example, a processor. The interface module, which can also be referred to as an interface unit, is configured to implement the sending and / or receiving functions in the second aspect and any possible implementation thereof. The interface module can be composed of an interface circuit, a transceiver, a transceiver, or a communication interface.

[0037] In a possible implementation, the interface module is configured to send a first message, the first message comprising target information used to indicate an expected target of the recommendation model; the interface module is further configured to receive first recommendation information, the first recommendation information indicating a target parameter and a parameter index corresponding to the target parameter, the target parameter and the parameter index being obtained according to the target information, the target parameter being used to implement the expected target, and the parameter index being used to indicate an ability of the target parameter to implement the expected target; the processing module is configured to execute the target parameter to obtain a corresponding execution result based on the parameter index; and the interface module is further configured to send the execution result, the execution result being used to determine whether to update the recommendation model.

[0038] In a possible implementation, the target information includes at least one of quality of experience information, network function attribute information, and network function service range information.

[0039] In a possible implementation, the first message further includes a candidate parameter, the candidate parameter being related to the expected target, and the candidate parameter being used to determine the target parameter.

[0040] In a possible implementation, the target parameter includes at least one of a quality of service parameter or a network element candidate list parameter; and the parameter index includes at least one of an expected target achievement degree corresponding to the target parameter, an expected target relevance, or a target parameter priority.

[0041] In a possible implementation, the interface module is further configured to send a second message, the second message being used to indicate a receiving execution result.

[0042] In a possible implementation, the interface module is further configured to send a third message, the third message being used to indicate at least one of updated target information or an updated candidate parameter, the third message including one or more of the updated target information or the updated candidate parameter.

[0043] In a possible implementation, the interface module is further configured to send a fourth message when the execution result and the target information satisfy a first preset condition, the fourth message being used to indicate an updated recommendation model; and the execution result and the target information satisfying the first preset condition includes at least one of the following: a difference between the execution result and the target information being greater than or equal to a first preset threshold; or a ratio of the execution result to the target information being less than or equal to a second preset threshold.

[0044] In a fifth aspect, a communication apparatus is provided, including: a processor; and a memory storing a computer program (or computer executable instructions) configured to cause the communication apparatus to perform the method of any one of the above aspects. The communication apparatus can be the first network element of the first aspect; or the communication apparatus can be the second network element of the second aspect. Optionally, the number of the processors can be one or more.

[0045] In a possible implementation, the communication apparatus further includes a memory.

[0046] In a possible implementation, the processor and the memory are integrated together; or the memory is independent of the processor.

[0047] In a possible implementation, the communication apparatus further includes a communication interface configured to enable the communication apparatus to communicate with other devices, for example, to send or receive data and / or signals. Exemplarily, the communication interface can be a transceiver, a circuit, a bus, a module, or other types of communication interfaces.

[0048] In a possible implementation, the processor and / or the memory further comprise an AI module for implementing AI-related functions. The AI module can implement the method for optimizing the recommendation model according to any of the aspects above in a manner of software, hardware, or a combination of software and hardware.

[0049] In a possible implementation, the communication apparatus is a chip or a chip system. Optionally, when the communication apparatus is a chip system, the chip system can be composed of a chip or can comprise a chip and other discrete devices.

[0050] In a possible implementation, the communication apparatus is a chip or a chip system. Optionally, when the communication apparatus is a chip system, the chip system can be composed of a chip or can comprise a chip and other discrete devices.

[0051] In a sixth aspect, a communication apparatus is provided, comprising: a processor and an interface circuit; the interface circuit is configured to receive a computer program or instructions and transmit the computer program or instructions to the processor; the processor is configured to execute the computer program or instructions, so that the communication apparatus performs the method according to any of the aspects above. The communication apparatus can be the first network element in the first aspect above; or the communication apparatus can be the second network element in the second aspect above. Optionally, the number of the processors can be one or more.

[0052] In a seventh aspect, a computer readable storage medium is provided, which stores instructions, when the instructions are run on a computer, the computer can execute the method according to any of the aspects above.

[0053] In an eighth aspect, a computer program product is provided, which comprises instructions, when the instructions are run on a computer, the computer can execute the method according to any of the aspects above.

[0054] In a ninth aspect, a communication system is provided, which comprises a first network element configured to execute the method according to the first aspect above, and a second network element configured to execute the method according to the second aspect above.

[0055] The technical effects brought by any possible implementation of the third aspect to the ninth aspect can refer to the technical effects brought by any of the first aspect to the second aspect or any possible implementation of any of the aspects, which will not be repeated here.

[0056] It can be understood that the schemes in the aspects above can be combined as long as the schemes are not contradictory. BRIEF DESCRIPTION OF DRAWINGS

[0057] FIG. 1 is a schematic diagram of a communication system architecture provided by an embodiment of the present application;

[0058] FIG. 2 is a schematic diagram of an architecture of a communication network according to an embodiment of the present application;

[0059] FIG. 3 is a schematic diagram of an architecture of a communication network according to an embodiment of the present application;

[0060] FIG. 4 is a schematic diagram of a hardware structure of a communication device according to an embodiment of the present application;

[0061] FIG. 5 is a schematic diagram of a flow of a method for optimizing a recommendation model according to an embodiment of the present application;

[0062] FIG. 6 is a schematic diagram of a detailed flow of a method for optimizing a recommendation model according to an embodiment of the present application;

[0063] FIG. 7 is a schematic diagram of a detailed flow of a method for optimizing a recommendation model according to an embodiment of the present application;

[0064] FIG. 8 is a schematic diagram of a detailed flow of a method for optimizing a recommendation model according to an embodiment of the present application;

[0065] FIG. 9 is a schematic diagram of a structure of a communication device according to an embodiment of the present application. DETAILED DESCRIPTION

[0066] In order to make the recommendation strategy generated by the recommendation model meet the user demand, the present application provides a method and device for optimizing a recommendation model. In the method, a first network element determines a target parameter and a parameter index according to received target information and sends them to a second network element. The second network element executes the target parameter according to the parameter index to obtain an execution result. The first network element and / or the second network element can determine whether to update the recommendation model based on the execution result and the target information. The method realizes updating the recommendation model according to the user demand, improves the optimization efficiency of the recommendation model, and improves the user satisfaction with the recommendation information generated by the recommendation model.

[0067] The embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0068] The method provided by the present application can be used in various communication systems. For example, the communication system can be a universal mobile telecommunications system (UMTS) system, an LTE system, a 5G communication system, a WiFi system, a 3GPP related communication system, a future communication system, or a system integrating multiple systems, etc., without limitation. The 5G can also be referred to as NR. The method provided by the present application is described below taking the communication system 10 shown in FIG. 1 as an example. FIG. 1 is only a schematic diagram and does not constitute a limitation on the applicable scenarios of the technical solutions provided by the present application.

[0069] As shown in FIG. 1, an architecture diagram of a communication system 10 provided by the present application is shown. In FIG. 1, the communication system 10 can include a network element 101 (corresponding to the first network element in the present application) and a network element 102 (corresponding to the second network element in the present application).

[0070] In the present application, the network element 102 can send target information to the network element 101. The target information is used to indicate an expected target of generating recommendation information by the recommendation model. After receiving the target information, the network element 101 can determine the first recommendation information according to the target information, and the first recommendation information includes a target parameter and a corresponding parameter index. The network element 101 can send the first recommendation information to the network element 102. After receiving the first recommendation information, the network element 102 can execute the target parameter according to the parameter index to obtain an execution result, and the network element 102 or the network element 101 can determine whether to update the recommendation model according to the execution result and the target information. In the case of determining to update the recommendation model, the network element 102 can send a third message to the network element 101 to instruct the network element 101 to update the recommendation model.

[0071] In the present application, the network element 101 can be a network element with an analytics logical function (AnLF), and the network element 101 can also be a network element with an AnLF and a recommendation logical function (ReLF). The AnLF and the ReLF can be deployed together in the same core network element, or can also be independently deployed in different core network elements, which is not limited. The network element deploying the AnLF can be referred to as an AnLF network element, and the network element deploying the ReLF can be referred to as a ReLF network element.

[0072] For example, the network element 101 is an existing network element in the core network, such as a NWDAF network element. The NWDAF network element can have an AnLF, a model training logical function (MTLF), and a ReLF; or the NWDAF network element can have an AnLF and an MTLF; or the NWDAF network element can have an AnLF and a ReLF. It should be understood that the above network element names are only examples of the name of the network element 101, and in specific applications, the network element 101 can also be named in other ways, which is not limited.

[0073] In this application, the network element 102 can be a terminal or a user network function (network function, NF). The terminal is a device with wireless transceiver function. The terminal can be deployed on land, including indoor, outdoor, handheld or vehicle-mounted; can also be deployed on water surface (such as ships, etc.); can also be deployed in the air (such as airplanes, balloons and satellites, etc.). The terminal can also be called a terminal device, which can be a user equipment (user equipment, UE), a mobile station (mobile station, MS), a mobile terminal (mobile terminal, MT), etc., or a device for providing voice or data connectivity to users. Among them, the UE includes a handheld device with wireless communication function, a vehicle-mounted device (such as a car, a bicycle, an electric vehicle, an airplane, a ship, a train, a high-speed rail, etc.), a wearable device (such as a smart watch, a smart bracelet, a pedometer, etc.) or a computing device. Exemplarily, the UE can be a mobile phone, a tablet computer, a notebook computer, a palm computer, a mobile internet device (mobile internet device, MID), a satellite terminal or a computer with wireless transceiver function. The UE can also be a virtual reality (virtual reality, VR) terminal device, an augmented reality (augmented reality, AR) terminal device, a wireless modem, a smart point of sale (point of sale, POS) machine, a customer terminal device (customer-premises equipment, CPE), a smart robot, a mechanical arm, a workshop device, a smart home device (such as a refrigerator, a television, an air conditioner, an electric meter, etc.), a wireless terminal in industrial control, a wireless terminal in unmanned driving, a wireless terminal in telemedicine, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home, a vehicle-mounted terminal, a road side unit (road side unit, RSU) with terminal function, or a flight device (such as a smart robot, a hot air balloon, a drone, an airplane), etc. The terminal can also be other devices with terminal function. For example, the terminal can also be a device with terminal function in device to device (device to device, D2D) communication.

[0074] In this application, the user NF includes but is not limited to AMF network element, SMF network element, NRF network element, NWDAF network element, etc. The main functions of each network element are introduced as follows.

[0075] AMF: for access and mobility management, mainly access management function.

[0076] SMF: for session management, managing user session creation, deletion, etc., maintaining session context and user plane forwarding pipeline information.

[0077] UPF: responsible for processing user packets, such as forwarding, charging, lawful monitoring (monitoring), etc.

[0078] NWDAF: can be used to collect data and perform analysis and prediction. Among them, collecting data includes but is not limited to collecting data from other NFs, such as through AMF, SMF, PCF, etc., through NEF or from AF, or from OAM system. Among them, the logical function AnLF is mainly used to perform inference, statistics and / or prediction analysis information according to the request of the user NF, and disclose the analysis service; the logical function MTLF performs model training according to the obtained data to obtain the trained model.

[0079] NRF: used to provide network element discovery function, based on the request of other network elements, provide network element information corresponding to network element type. NRF also provides network element management services, such as network element registration, update, deregistration, and network element state subscription and notification, etc.

[0080] Optionally, the communication system 10 can also include at least one of the following: SMF network element, AMF network element and NRF network element (not shown in FIG. 1).

[0081] Optionally, the above communication system 10 can be applicable to the 5G network currently under discussion, and can also be applicable to future communication networks, etc., and the embodiments of the present application do not make specific limitations thereto.

[0082] Exemplarily, the communication system 10 is applicable to the 5G network shown in FIG. 2. The 5G network includes terminal devices, access network devices, and core network devices. The terminal devices access a data network (DN) through the access network devices and the core network devices. The core network devices include some or all network functions of the following network elements: a unified data management (UDM) network element, a network exposure function (NEF) network element, an application function (AF) network element, a policy control function (PCF) network element, an access and mobility management function (AMF) network element, a session management function (SMF) network element, a user plane function (UPF) network element, a network data analytics function (NWDAF) network element, and a network repository function (NRF) network element, etc.

[0083] In FIG. 2, the terminal accesses the 5G network through the RAN node, communicates with the AMF network element through the N1 interface (N1 for short), and the RAN node communicates with the AMF network element through the N2 interface (N2 for short) and communicates with the UPF network element through the N3 interface (N3 for short). The SMF network element communicates with the UPF network element through the N4 interface (N4 for short), and the UPF network element accesses the DN through the N6 interface (N6 for short). In addition, the AMF network element, the SMF network element, the UDM network element, the NEF network element, the PCF network element, the NRF network element, the NWDAF network element, or the AF network element, etc. shown in FIG. 3 can interact with each other through a service interface. For example, the service interface provided by the AMF network element to the outside is Namf; the service interface provided by the SMF network element to the outside is Nsmf; the service interface provided by the UDM network element to the outside is Nudm; the service interface provided by the NEF network element to the outside is Nnef; the service interface provided by the PCF network element to the outside is Npcf; the service interface provided by the NRF network element to the outside is Nnrf; the service interface provided by the AF network element to the outside is Naf, and the service interface provided by the NWDAF network element to the outside is Nuwdaf.

[0084] It can be understood that the device or entity corresponding to the network element 101 in the communication system 10 is the NWDAF network element in the 5G network shown in FIG. 3. The NWDAF network element has an AnLF, or has an AnLF and a ReLF. The network element or entity corresponding to the network element 102 in the communication system 10 is the terminal or other user NF in the 5G network shown in FIG. 2, which is not limited here.

[0085] For example, referring to FIG. 3, taking the network element 101 as the NWDAF network element, the NWDAF network element includes an analysis module, an acquisition module, and a recommendation model, and the first network element is configured to update the recommendation model. The first network element can include the analysis module and the acquisition module, the acquisition module can be configured to receive target information from the second network element, and the analysis module is configured to analyze the target information to obtain a target parameter and a parameter index corresponding to the target parameter and send the target parameter and the parameter index to the second network element. The recommendation model is configured to receive a recommendation monitoring request from the second network element and respond to the recommendation monitoring request of the second network element.

[0086] It can be understood that the communication system 10 shown in FIG. 1 is only used for example and is not used to limit the technical solutions of the present application. Those skilled in the art should understand that in the specific implementation process, the communication system 10 can also include other network elements, and the number of each network element can also be determined according to specific needs, which is not limited.

[0087] Optionally, each network element or device (such as the network element 101, the network element 102, etc.) in FIG. 1 of the present application can also be referred to as a communication device, which can be a general-purpose device or a special-purpose device, and the present application does not make specific limitations.

[0088] Optionally, the related functions of each network element or device (such as the network element 101, the network element 102, etc.) in FIG. 1 of the present application can be implemented by one device, or by multiple devices together, or by one or more functional modules in a device, and the present application does not make specific limitations. It can be understood that the above functions can be network elements in hardware devices, software functions running on special hardware, or a combination of hardware and software, or virtualized functions instantiated on a platform (such as a cloud platform).

[0089] In specific implementation, each network element or device (such as the network element 101, the network element 102, etc.) in FIG. 1 of the present application can adopt the composition structure shown in FIG. 4, or include the components shown in FIG. 4. FIG. 4 shows a hardware structure schematic diagram of a communication device applicable to the present application. It can be understood that the communication device 40 includes means of necessary forms such as modules, units, elements, circuits, or interfaces, which are properly configured together to execute the schemes provided by the present application. For example, the communication device 40 includes one or more processors 401 for implementing the methods provided by the present application.

[0090] The processor 401 can be a general processor or a special-purpose processor, etc. For example, the processor 401 can be a baseband processor or a central processing unit (CPU). The baseband processor can be used to process communication protocols and communication data, and the CPU can be used to control the communication device 40 (such as the network element 101, the network element 102, etc.), execute software programs, and process data of the software programs. Optionally, in one design, the processor 401 can include a program 405 (which can also be referred to as code or instructions sometimes), which can be run on the processor 401 to enable the communication device 40 to perform the methods described in the embodiments below. In another possible design, the communication device 40 includes a circuit (not shown in FIG. 4) for implementing the recommended model optimization function in the embodiments below.

[0091] Optionally, the communication device 40 can include one or more memories 403. The memory 403 can be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM), a cache, or other type of dynamic storage device that can store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disk storage, a magnetic disk storage or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited thereto. The memory provided in the present application can generally be non-volatile. Optionally, the memory 403 has a program 407 (which can also be referred to as code or instructions sometimes) stored thereon, which can be run on the processor 401 to enable the communication device 40 to perform the methods described in the method embodiments below.

[0092] Optionally, the processor 401 can include an AI module 406, and / or the memory 403 can include an AI module 408. The AI module described above is used to implement AI-related functions. The AI module can be implemented by software, hardware, or a combination of software and hardware to implement the recommended model optimization method.

[0093] Optionally, the processor 401 and / or the memory 403 can also store data. The processor 401 and the memory 403 can be separately arranged, or integrated together.

[0094] Optionally, the communication apparatus 40 can also include a transceiver 402 and / or an antenna 404. The processor 401 can also be referred to as a processing unit, and controls the communication apparatus 40. The transceiver 402 can also be referred to as a transceiving unit, a transceiver, a transceiving circuit, or a transceiver, etc., and is configured to realize the transceiving function of the communication apparatus 40 through the antenna 404.

[0095] It can be understood that the constituent structures shown in FIG. 4 do not constitute a limitation on the communication apparatus, and the communication apparatus can include more or fewer components than those shown in FIG. 4, or combine certain components, or arrange different components.

[0096] The method provided by the present application will be described below with reference to the accompanying drawings. Each network element in the following embodiments can have the components shown in FIG. 4, and will not be described herein.

[0097] It can be understood that, in the present application, the first network element and the second network element can perform some or all of the steps in the present application, which are only examples, and the present application can also perform other steps or variations of various steps. In addition, each step can be performed in a different order as presented in the present application, and it is possible that not all steps in the present application are performed.

[0098] It can be understood that, in the method provided by the present application below, the first network element and the second network element are taken as an example to illustrate the method as the execution subject of the interaction, but the present application does not limit the execution subject of the interaction. For example, the first network element in the method provided by the following embodiments of the present application can also be a chip, a chip system, or a processor supporting the first network element to implement the method, and can also be a logical node, a logical module, or software capable of implementing all or part of the functions of the first network element; the second network element in the method provided by the following embodiments of the present application can also be a chip, a chip system, or a processor supporting the second network element to implement the method, and can also be a logical node, a logical module, or software capable of implementing all or part of the functions of the second network element.

[0099] The method provided by the present application will be described below with reference to the accompanying drawings. Each network element or device in the following embodiments can have the components shown in FIG. 4, and will not be described herein.

[0100] It can be understood that the names of messages between the network elements in the following embodiments of the present application or the names of parameters in the messages are only examples, and other names can also be used in specific implementations, which are not limited in the present application.

[0101] It can be understood that, in the present application, " / " can represent that the objects before and after the " / " are in an "or" relationship. For example, A / B can represent A or B; "and / or" can be used to describe the existence of three relationships between the associated objects. For example, A and / or B can represent three cases: A exists alone, A and B exist simultaneously, and B exists alone, where A and B can be singular or plural. In addition, expressions such as "at least one of A, B, and C" or "at least one of A, B, or C" are generally used to represent any one of the following: A exists alone; B exists alone; C exists alone; A and B exist simultaneously; A and C exist simultaneously; B and C exist simultaneously; and A, B, and C exist simultaneously. The above is an example of A, B, and C with three elements to illustrate the alternative items of the project, and when there are more elements in the expression, the meaning of the expression can be obtained according to the foregoing rules.

[0102] In order to facilitate the description of the technical solutions of the present application, in the present application, "first", "second", and the like can be used to distinguish functionally identical or similar technical features. The "first", "second", and the like do not limit the quantity and execution order, and the "first", "second", and the like do not necessarily mean different. In the present application, the words "exemplary" or "for example" are used to represent examples, illustrations, or descriptions. Any embodiment or design scheme described as "exemplary" or "for example" should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. The use of "exemplary" or "for example" is intended to present the relevant concept in a specific manner and facilitate understanding.

[0103] It can be understood that the "embodiments" mentioned throughout the specification mean that the specific features, structures, or characteristics related to the embodiments are included in at least one embodiment of the present application. Therefore, the various embodiments throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures, or characteristics can be combined in one or more embodiments in any suitable manner. It can be understood that in various embodiments of the present application, the size of the sequence number of each process does not mean the order of execution, and the execution order of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the present application.

[0104] It can be understood that in the present application, "when", "in the case of", "if", and "if" all refer to making corresponding processing under certain objective circumstances, and are not limited to time, and do not require a judgment action when implemented. It also does not mean that there are other limitations.

[0105] It can be understood that some optional features in the present application can be implemented independently in some scenarios, without relying on other features, such as the scheme currently based on, to solve the corresponding technical problems and achieve the corresponding effects, and can also be combined with other features according to the needs in some scenarios. Correspondingly, the devices given in the present application can also implement these features or functions, which will not be repeated here.

[0106] It can be understood that the same step or step or technical feature with the same function in the present application can be mutually referenced and learned between different embodiments.

[0107] In some embodiments, as shown in FIG. 5, a recommended model optimization method provided by the present application can include the following steps:

[0108] S501: The second network element sends a first message to the first network element. Correspondingly, the first network element receives the first message from the second network element.

[0109] In the present application, the first network element can be the network element 101 in the communication system shown in FIG. 1, and the second network element can be the network element 102 in the communication system shown in FIG. 1. The second network element can determine the first message and send the first message to the first network element.

[0110] The first message includes target information, which is used to indicate the expected target of the recommended model in the first network element. The second network element can indicate the expected target of the recommended model to the first network element through the target information. In some examples, the target information can be determined by user demand, or can be determined by the application layer demand of the second network element.

[0111] Optionally, the target information includes at least one of quality of experience information, network function attribute information, or network function service range information. Optionally, the quality of experience information can include QoE, the network function attribute information can include network element load, and the network function service range can include the service range of the network element.

[0112] For example, when the second network element requires the quality of experience to reach the expected target, the requirement can be sent to the first network element through the quality of experience information. When the second network element requires the network function attribute to reach the expected target, the requirement can be sent to the first network element through the network function attribute information. When the second network element requires the network function service range to reach the expected target, the requirement can be sent to the first network element through the network function service range information. The target information can also include other information representing the expected target of the second network element, which is not limited herein. It can be understood that the first network element can obtain different types of performance requirements required by the second network element by receiving different types of target information. In some embodiments, the first network element determines the first recommendation information for achieving the expected target of the recommendation model according to the received target information, and the first recommendation information can indicate the target parameter and the parameter index corresponding to the target parameter. For example, the first recommendation information can include the target parameter and the above-mentioned parameter index, or the first recommendation information can include the identifier of the target parameter and the identifier of the above-mentioned parameter index. The first recommendation information can be used to indicate the execution of the above-mentioned target parameter. In this application, the number of target parameters can be one or more. When the number of target parameters is more than one, each target parameter can correspond to one parameter index, or multiple target parameters can correspond to one parameter index, which is not limited.

[0113] Optionally, the second network element can also send the candidate parameter corresponding to the target information when sending the target information, for example, the first message also includes the candidate parameter. The candidate parameter is related to the expected target and can be used to determine the target parameter. Therefore, the candidate parameter can provide a reference for the first network element to determine the target parameter, so as to reduce the pressure of the first network element when determining the target parameter. At the same time, it also realizes the combination of the results of the second network element and the first network element for determining the target parameter, so as to improve the user's satisfaction with the target parameter.

[0114] In some embodiments, the first network element determines the first recommendation information for achieving the expected target of the recommendation model according to the received target information and the candidate parameter, and the first recommendation information can include the target parameter and the parameter index corresponding to the target parameter. The first recommendation information can be used to indicate the execution of the above-mentioned target parameter.

[0115] In some examples, when determining the first recommendation information, the first network element can increase the parameter on the basis of the candidate parameter to obtain the target parameter, and determine the parameter index corresponding to the target parameter; or the first network element can take the candidate parameter as the target parameter, and determine the parameter index corresponding to the target parameter.

[0116] S502: The first network element sends the first recommendation information to the second network element. Correspondingly, the second network element receives the first recommendation information from the first network element.

[0117] As described in S501, the first recommendation information indicates the target parameters and the corresponding parameter indicators. The parameter indicators are used to indicate the ability of the target parameters to achieve the expected target, that is, the influence of each target parameter on the recommendation model to achieve the expected target is different, and the parameter indicators represent the information of the influence of the target parameters on the recommendation model to achieve the expected target.

[0118] Optionally, the target parameters include at least one of a service quality parameter or a network element candidate list parameter, and the parameter indicators include at least one of an expected target achievement degree, an expected target relevance, or a target parameter priority corresponding to the target parameters. The service quality parameter can be a QoS parameter, and the network element candidate list can be an instance list of a certain type of network element.

[0119] It can be understood that the service quality parameter and the network element candidate list parameter have different abilities to achieve the expected target of the recommendation model, that is, the service quality parameter and the network element candidate list parameter have different influences on the recommendation model to achieve the expected target. The first network element can indicate the difference between the abilities or influences of the target parameters to the second network element through at least one of the expected target achievement degree, the expected target relevance, or the target parameter priority. For example, when the expected target completion degree of the service quality parameter is greater than the expected target completion degree of the network element candidate list, the second network element preferentially executes the service quality parameter. When the expected target relevance of the network element candidate list is greater than the expected target relevance of the service quality parameter, the second network element preferentially executes the network element candidate list.

[0120] Optionally, the first network element indicates the second network element to execute the target parameters to obtain the execution results according to the indication of the parameter indicators by indicating the target parameters and the corresponding parameter indicators. When executing the target parameters, the second network element can make corresponding adjustments according to the possible value range and combination mode of the target parameters according to the parameter indicators, and execute the target parameters to obtain the corresponding execution results.

[0121] For example, the second network element can indicate the combination order of the service quality parameter and the network element candidate list parameter through the target parameter priority, and indicate the priority of executing the service quality parameter and the network element candidate list parameter through the expected target achievement degree and / or the expected target relevance, and execute at least one of the service quality parameter and the network element candidate list parameter based on the target achievement degree, the expected target relevance, and the target parameter priority to obtain the corresponding execution results.

[0122] S503: The second network element sends the execution results of the target parameters to the first network element. Correspondingly, the first network element receives the execution results of the target parameters from the second network element.

[0123] In this application, the execution results can be used to determine whether to update the recommendation model.

[0124] In a possible implementation, the first network element can actively trigger the recommendation monitoring, acquire the execution result obtained by the second network element executing the target parameter, and determine whether to update the recommendation model based on the execution result.

[0125] Optionally, the first network element or the execution result can be acquired by receiving the execution result from the second network element, and determining whether to update the recommendation model according to the execution result. In addition, the first network element can also acquire other network data, network performance, and the like related to the execution result. The recommendation model update is performed together with the detection information, which is not limited herein.

[0126] In another possible implementation, the first network element can be passively triggered to perform the recommendation monitoring based on the indication of the second network element, acquire the execution result obtained by the second network element executing the target parameter, and update the recommendation model based on the execution result.

[0127] Optionally, referring to FIG. 6, after performing S501, the method can further include:

[0128] S501a: The second network element sends a fourth message to the first network element. Correspondingly, the first network element receives the fourth message sent by the second network element.

[0129] The fourth message is used to indicate that the target information or the candidate parameter in the first message is updated. When the first network element receives the fourth message, the target information and the candidate parameter in the first message are updated, and S502 and subsequent steps are re-executed.

[0130] Exemplarily, the fourth message includes one or more of the following: updated target information or updated candidate parameter. The updated target information or the updated candidate parameter is used to indicate the changed target information or the changed candidate parameter. The first network element can determine the target parameter and the corresponding parameter index according to the updated target information and the updated candidate parameter after receiving the fourth message.

[0131] Optionally, referring to FIG. 6, before performing S503, the method further includes:

[0132] S503a: The second network element sends a second message to the first network element. Correspondingly, the first network element receives the second message from the second network element.

[0133] The second message is used to instruct the first network element to acquire the execution result. It can be understood that the first network element can acquire the execution result from the second network element after receiving the indication of the second message, and update the recommendation model based on the execution result.

[0134] Optionally, the second message comprises a target parameter. The second network element can instruct the first network element to obtain an execution result corresponding to the target parameter through the second message, so as to train the recommendation model according to the indicated execution result corresponding to the target parameter.

[0135] Optionally, referring to FIG. 6, after performing S503, the method further comprises:

[0136] S504: When the execution result and the target information satisfy a first preset condition, the first network element updates the recommendation model.

[0137] In one possible implementation, the first network element can actively trigger the update of the recommendation model according to the execution result, that is, after receiving the execution result, the first network element determines whether to update the recommendation model according to the comparison result between the execution result and the target information. For example, when the difference between the recommendation information and the target information is large, it indicates that the execution result fails to achieve the expected target of the recommendation model, and thus the recommendation model can be updated; when the difference between the recommendation information and the target information is small, it indicates that the execution result basically achieves the expected target of the recommendation model, and thus the recommendation model is not updated.

[0138] For example, when the difference between the recommendation information and the target information is large, it indicates that the execution result fails to achieve the expected target of the recommendation model, and thus the recommendation model can be updated; when the difference between the recommendation information and the target information is small, it indicates that the execution result basically achieves the expected target of the recommendation model, and thus the recommendation model is not updated.

[0139] In another possible implementation, the first network element can passively trigger the update of the model according to the instruction of the second network element, that is, the second network element can determine whether to update the recommendation model according to the comparison result between the execution result and the target information. In this case, the second network element can not send the execution result to the first network element.

[0140] For example, when the difference between the recommendation information and the target information is large, it indicates that the execution result fails to achieve the expected target of the recommendation model, and thus the recommendation model can be updated; when the difference between the recommendation information and the target information is small, it indicates that the execution result basically achieves the expected target of the recommendation model, and thus the recommendation model is not updated.

[0141] Optionally, referring to FIG. 6, before performing S504, the method further comprises:

[0142] S504a: When the execution result and the target information satisfy the first preset condition, the second network element sends a third message to the first network element. Correspondingly, the first network element receives the third message from the second network element.

[0143] The third message instructs the first network element to update the recommended network model. After receiving the third message, the first network element updates the recommended model.

[0144] For example, when the difference between the execution result and the target information is greater than a preset threshold, or the ratio of the execution result to the target information is less than a preset threshold, the second network element sends the third message to the first network element. It can be understood that when the execution result satisfies the above-mentioned first preset condition, the execution result cannot meet the expected target, and therefore the third message needs to be sent to instruct the first network element to update the recommended model to optimize the user experience. When the execution result does not satisfy the above-mentioned first preset condition, it indicates that the execution result can meet the user's expected target, and therefore the recommended model does not need to be updated.

[0145] The above embodiment specifically describes a recommended model optimization method, which can also be used in the following scenarios:

[0146] In some embodiments, referring to FIG. 7, the following takes the first network element as ANLF and the second network element as user NF as an example to introduce the application scenario of the above-mentioned recommended model optimization method. When the ANLF and the RELF are deployed in the same core network element NWDAF, the functions of the first network element in the above-mentioned embodiment are implemented by the ANLF. In addition, the scene also includes SMF, AMF, NRF and MTLF assisting the user NF and the NWDAF to implement a recommended model optimization method, which can include:

[0147] S701: The user NF sends a recommendation policy subscription or request (i.e., the first message in the above-mentioned embodiment) to the ANLF.

[0148] The recommendation policy subscription or request includes target information. For example, the target information can include one or more of the following: QoE, expected NF attribute. For example, the expected NF attribute includes NF type, service range, etc.

[0149] Optionally, the recommendation policy subscription or request also includes candidate parameters. For example, the candidate parameters can include QoS parameters, network element candidate list, flow control policy, etc.

[0150] In some examples, the recommendation policy subscription or request also includes user NF identifier, monitoring time interval, etc.

[0151] S702: The ANLF invokes the model of the MTLF, and the MTLF subscribes to the model monitoring of the ANLF.

[0152] Optionally, MTLF is used to collect data from various data sources to update the recommendation model.

[0153] S703: AnLF analyzes and makes recommendations based on target information and candidate parameters, and outputs the first recommendation information.

[0154] The first recommendation information is used to indicate the target parameters and their corresponding metrics. In some examples, the metrics include the degree of achievement of the target parameters, the correlation between the target parameters and the expected goals, and the parameter priority or ranking.

[0155] Optionally, AnLF analyzes and makes recommendations based on the target information and candidate parameters, and outputs the first recommendation.

[0156] S704: AnLF sends a recommendation response to user NF, which includes the first recommendation information. Correspondingly, user NF receives the recommendation response from AnLF.

[0157] S705: User NF executes the target parameters indicated by the first recommendation information based on the received first recommendation information.

[0158] Optionally, before executing the target parameters indicated by the target parameters, the user NF can modify the target parameters accordingly based on the parameter indicators.

[0159] After the user executes the target parameters in NF, there are two ways to trigger NWDAF for recommendation monitoring, and the result will determine whether the recommendation model needs to be updated.

[0160] Method 1: Triggered via user NF

[0161] S706: User NF sends a monitoring request or subscription for the recommendation strategy to NWDAF (i.e., the second message in the aforementioned embodiment).

[0162] Optionally, the monitoring request or subscription for the recommended strategy may include the target parameters for the user's NF execution.

[0163] S707a: After AnLF receives a monitoring request or subscription for a recommendation strategy, it triggers AnLF to monitor the user's NF for recommendations, obtains the execution results, and analyzes the results to determine whether the recommendation model needs to be updated or optimized.

[0164] Method 2: Triggered via NWDAF

[0165] S707b: AnLF triggers NWDAF to collect and analyze data, including collecting the target parameters and execution results from the user's NF, and analyzing and determining whether the recommendation model needs to be updated or optimized.

[0166] There are two ways to determine whether the recommendation model needs to be updated or optimized.

[0167] Way one: determining whether to update the recommendation model through AnLF.

[0168] S708a: After receiving the execution result, if the execution result of the target parameter does not achieve the expectation, that is, the difference between the execution result and the target information is large, the AnLF triggers the update of the recommendation model.

[0169] Way two: determining whether to update the recommendation model through the user NF.

[0170] S708b: The user NF compares the execution result with the target information, and if the execution result of the target parameter does not achieve the expectation, that is, the difference between the execution result and the target information is large, the user NF sends a model update request (i.e., the third message in the foregoing embodiment) to the AnLF. After receiving the model update request, the AnLF updates the recommendation model.

[0171] S709: If the AnLF updates or optimizes the recommendation model, the AnLF sends a model update request to the MTLF, and the model update request contains the execution result and the target information of the user NF, the target parameter, and the like.

[0172] S710: The MTLF collects data from various data sources, and re-trains and optimizes the recommendation model.

[0173] Optionally, the MTLF reports the result of optimizing the recommendation model to the AnLF.

[0174] In some embodiments, during the application of the recommendation model, steps S703-S710 are repeatedly executed, so as to realize the training of the recommendation model during the application of the recommendation model.

[0175] S711: If the user NF updates the target information or the candidate parameter, the user NF sends a monitoring update request (i.e., the fourth message in the foregoing embodiment) to the AnLF, and the monitoring update request contains the updated target information and the candidate parameter.

[0176] S712: The AnLF sends a monitoring update response to the user NF.

[0177] In some embodiments, after the user NF sends the monitoring update request to the AnLF, the user NF and the AnLF repeatedly execute steps S702-S711, so as to realize the process of re-optimizing the recommendation model according to the updated target information, which is not described herein.

[0178] S713: The user NF sends a request for subscribing to the suspension of the recommendation strategy to the AnLF.

[0179] S714: The user NF sends a request for subscribing to the recommended policy recovery to the AnLF.

[0180] Optionally, the request for subscribing to the recommended policy suspension and the request for subscribing to the recommended policy recovery can each include monitoring indication, target information, candidate parameter, and the like.

[0181] In some other embodiments, referring to FIG. 8, the application scenarios of the optimization method of the recommended model are introduced below by taking the first network element as the ANLF and the ReLF and the second network element as the user NF. When the ANLF and the ReLF are independently deployed in different core network elements, the ReLF combines the ANLF to implement the functions implemented by the first network element in the foregoing embodiments. In addition, the scenario also includes the SMF, the AMF, the NRF, and the MTLF assisting the user NF and the NWDAF to implement an optimization method of a recommended model, which can include the following steps.

[0182] S801: The user NF sends a recommended policy subscription or request (i.e., the first message in the foregoing embodiments) to the ReLF.

[0183] The recommended policy subscription or request includes target information. For example, the target information can include one or more of the following: QoE, expected NF attribute, e.g., the expected NF attribute includes NF type, service range, and the like.

[0184] Optionally, the recommended policy subscription or request also includes candidate parameter. For example, the candidate parameter can include QoS parameter, network element candidate list, and the like.

[0185] In some examples, the recommended policy subscription or request also includes user NF identifier, monitoring time interval, and the like.

[0186] S802: The ReLF sends an analysis function subscription message to the AnLF. Correspondingly, the AnLF receives the subscription message from the ReLF.

[0187] The subscription message carries the target information.

[0188] S803: The AnLF performs analysis and recommendation according to the target information and the candidate parameter, and outputs first recommended information.

[0189] The first recommended information is used to indicate target parameter and corresponding parameter index. In some examples, the parameter index includes target achievement degree of the target parameter, relevance between the target parameter and the expected target, parameter priority or ranking, and the like.

[0190] Optionally, the AnLF performs analysis and recommendation according to the target information and the candidate parameter, and outputs first recommended information.

[0191] S804: AnLF sends an analysis response to ReLF. Correspondingly, ReLF receives the analysis response from AnLF.

[0192] S805: ReLF sends a recommendation response to user NF, the recommendation response including the first recommendation information. Correspondingly, user NF receives the recommendation response from AnLF.

[0193] S806: user NF executes the target parameter indicated by the target parameter according to the received first recommendation information to meet the expected target.

[0194] Optionally, before executing the target parameter indicated by the target parameter, user NF can make corresponding modification to the target parameter according to the parameter index.

[0195] After user NF executes the target parameter, there are two ways to trigger NWDAF to make recommendation monitoring and judge whether the recommendation model needs to be updated according to the execution result.

[0196] Method one: triggered by user NF

[0197] S807: user NF sends a monitoring request or subscription of recommendation strategy to NWDAF (i.e. the second message in the foregoing embodiment).

[0198] Optionally, the monitoring request or subscription of recommendation strategy contains the target parameter executed by user NF.

[0199] S808a: after ReLF receives the monitoring request or subscription of recommendation strategy, ReLF triggers to make recommendation monitoring and obtains the execution result, and analyzes whether the recommendation model needs to be updated or optimized according to the execution result.

[0200] Method two: triggered by NWDAF

[0201] S808b: ReLF triggers NWDAF to collect data for analysis, including collecting the executed target parameter and execution result from user NF, and analyzing whether the recommendation model needs to be updated or optimized.

[0202] After ReLF receives the execution result, there are two ways to judge whether the recommendation model needs to be updated or optimized.

[0203] Method one: ReLF judges whether to update the recommendation model.

[0204] S809a: after ReLF receives the execution result, if the execution result of the target parameter does not reach the expectation, ReLF triggers to update the recommendation model.

[0205] Optionally, the difference between the execution result and the target information is large, and ReLF triggers to update the recommendation model.

[0206] Way two: judging whether to update the recommendation model by the user NF.

[0207] S809b: The user NF compares the execution result and the target information. If the execution result of the target parameter does not reach the expectation, that is, the difference between the execution result and the target information is large, the user NF sends a model update request (i.e., the third message in the foregoing embodiment) to the ReLF. After receiving the model update request, the ReLF updates the recommendation model.

[0208] S810: If the ReLF updates or optimizes the recommendation model, the ReLF sends a model update request to the MTLF, which includes the execution result and the target information of the user NF, the target parameter, and the like.

[0209] S811: The MTLF collects data from various data sources, re-trains and optimizes the recommendation model.

[0210] Optionally, the MTLF reports the result of optimizing the recommendation model to the ReLF.

[0211] In some embodiments, during the application of the recommendation model, steps S803-S810 are repeatedly executed, so as to realize the training of the recommendation model during the application of the recommendation model.

[0212] S812: If the user NF updates the target information or the candidate parameter, the user NF sends a monitoring update request (i.e., the fourth message in the foregoing embodiment) to the ReLF, which includes the updated target information and the candidate parameter.

[0213] S813: The ReLF sends a monitoring update response to the user NF.

[0214] In some embodiments, after the user NF sends the monitoring update request to the ReLF, the user NF and the ReLF repeatedly execute steps S802-S811, so as to realize the process of re-optimizing the recommendation model according to the updated target information, which is not described herein.

[0215] S814: The user NF sends a request for subscribing to the suspension of the recommendation strategy to the ReLF.

[0216] S815: The user NF sends a request for subscribing to the resumption of the recommendation strategy to the ReLF.

[0217] Optionally, the request for subscribing to the suspension of the recommendation strategy and the request for subscribing to the resumption of the recommendation strategy can include the monitoring indication, the target information, the candidate parameter, and the like.

[0218] The above describes the scheme provided by the present application mainly from the perspective of interaction between network elements. Correspondingly, the present application also provides a communication apparatus, which can be the first network element in the above method embodiments, or an apparatus comprising the first network element, or a component applicable to the first network element; the communication apparatus can also be the second network element in the above method embodiments, or an apparatus comprising the second network element, or a component applicable to the second network element. It can be understood that the first network element and the like described above comprise the hardware structure and / or software module for performing the respective functions in order to achieve the above functions. Those skilled in the art should easily realize that, in combination with the unit and algorithm operation of the examples described in the embodiments disclosed herein, the present application can be realized in the form of hardware or a combination of hardware and computer software. Whether a certain function is realized in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0219] The present application can divide the functional modules of the first network element or the second network element according to the above method examples. For example, each functional module can be divided according to each function, or two or more functions can be integrated in one processing module. The integrated module can be realized in the form of hardware or software functional module. It can be understood that the division of modules in the present application is illustrative, and is only a logical functional division. Actual implementation can have another division manner.

[0220] For example, in the case of dividing each functional module in an integrated manner, FIG. 9 shows a structural schematic diagram of a communication apparatus 90. The communication apparatus 90 comprises an interface module 901 and a processing module 902. The interface module 901, which can also be referred to as an interface unit, is used to perform a transceiving operation. For example, it can be an interface circuit, a transceiver, a transceiver or a communication interface, etc. The processing module 902, which can also be referred to as a processing unit, is used to perform an operation other than the transceiving operation. For example, it can be a processing circuit or a processor, etc.

[0221] In some embodiments, the communication apparatus 90 can further comprise a storage module (not shown in FIG. 9) for storing program instructions and data.

[0222] In an example, the communication apparatus is the first network element, which can be used to realize the method performed by the first network element in any one of the foregoing embodiments.

[0223] For example, in a possible implementation, the interface module 901 is configured to receive a first message, the first message comprising target information, the target information being used to indicate an expected target of the recommendation model; the interface module 901 is further configured to send first recommendation information, the first recommendation information indicating a target parameter and a parameter index corresponding to the target parameter, the target parameter and the parameter index being obtained according to the target information; the target parameter is used to achieve the expected target, and the parameter index is used to indicate an ability of the target parameter to achieve the expected target; the processing module 902 is configured to receive an execution result, the execution result being obtained based on the first recommendation information, and the execution result being used to determine whether to update the recommendation model.

[0224] In an example, the communication apparatus is a second network element, and can be used to implement the method performed by the second network element in any of the foregoing embodiments.

[0225] For example, the interface module 901 is configured to send a first message, the first message comprising target information, the target information being used to indicate an expected target of the recommendation model; the interface module 901 is further configured to receive first recommendation information, the first recommendation information indicating a target parameter and a parameter index corresponding to the target parameter, the target parameter and the parameter index being obtained according to the target information, the target parameter being used to achieve the expected target, and the parameter index being used to indicate an ability of the target parameter to achieve the expected target; the processing module 902 is configured to execute the target parameter based on the parameter index to obtain a corresponding execution result; and the interface module 901 is further configured to send the execution result, the execution result being used to determine whether to update the recommendation model.

[0226] When the communication apparatus is used to implement the functions of the first network element or the second network element, other functions that the communication apparatus 90 can implement can be referred to the related description of the embodiment shown in FIG. 5.

[0227] In a simple embodiment, those skilled in the art can conceive that the communication apparatus 90 can adopt the form shown in FIG. 4. For example, the processor 401 in FIG. 4 can execute the method described in the foregoing method embodiments by invoking the computer-executed instructions stored in the memory 403, so that the communication apparatus 90 executes the method.

[0228] For example, the functions / implementation processes of the processing module 902 and the interface module 901 in FIG. 9 can be implemented by the processor 401 in FIG. 4 invoking the computer-executed instructions stored in the memory 403. Alternatively, the functions / implementation processes of the processing module 902 in FIG. 9 can be implemented by the processor 401 in FIG. 4 invoking the computer-executed instructions stored in the memory 403, and the functions / implementation processes of the interface module 901 in FIG. 9 can be implemented by the transceiver 402 in FIG. 4.

[0229] It can be understood that one or more of the above modules or units can be implemented in software, hardware or a combination of both. When any of the above modules or units is implemented in software, the software exists in the form of computer program instructions and is stored in the memory, and the processor can be used to execute the program instructions and implement the above method flow. The processor can be built in the SoC (System on Chip) or ASIC, or be a separate semiconductor chip. The processor further includes the core for executing software instructions to perform operations or processing, and can further include necessary hardware accelerators, such as field programmable gate array (FPGA), PLD (programmable logic device), or logic circuit for implementing special logic operations.

[0230] When any of the above modules or units is implemented in hardware, the hardware can be any one or any combination of CPU, microprocessor, digital signal processing (DSP) chip, microcontroller unit (MCU), artificial intelligence processor, ASIC, SoC, FPGA, PLD, special purpose digital circuit, hardware accelerator or non-integrated discrete device, which can run necessary software or be independent of software to execute the above method flow.

[0231] Optionally, the present application also provides a chip system, including: at least one processor and an interface, the at least one processor is coupled with the memory through the interface, when the at least one processor executes the computer program or instructions in the memory, the method in any of the above method embodiments is executed. In a possible implementation manner, the chip system further includes the memory. Optionally, the chip system can be composed of a chip, or can include the chip and other discrete devices, and the present application does not make specific limitation hereon.

[0232] Optionally, the present application also provides a computer readable storage medium. All or part of the processes in the above method embodiments can be instructed by a computer program to relevant hardware to complete, the program can be stored in the above computer readable storage medium, and the program can include the processes of the above method embodiments when executed. The computer readable storage medium can be an internal storage unit of the communication device of any of the above embodiments. For example, the hard disk or memory of the communication device. The above computer readable storage medium can also be an external storage device of the above communication device. For example, the plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. equipped on the above communication device. Further, the above computer readable storage medium can include both the internal storage unit and the external storage device of the above communication device. The above computer readable storage medium is used to store the above computer program and other programs and data required by the above communication device. The above computer readable storage medium can also be used to temporarily store data that has been output or will be output.

[0233] Optionally, the present application also provides a computer program product. All or part of the processes in the above method embodiments can be instructed by a computer program to relevant hardware to complete, the program can be stored in the above computer program product, and the program can include the processes of the above method embodiments when executed.

[0234] Optionally, the present application also provides a computer instruction. All or part of the processes in the above method embodiments can be instructed by a computer instruction to relevant hardware (such as a computer, a processor, a first network element, or a second network element, etc.) to complete. The program can be stored in the above computer readable storage medium or the above computer program product.

[0235] Optionally, the present application also provides a communication system, including the first network element and the second network element in the embodiment shown in Fig. 5.

[0236] Optionally, the present application also provides a communication system, including the first network element and the second network element in the embodiment shown in Fig. 6.

[0237] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional modules is taken as an example for illustration, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above.

[0238] In several embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other manners. For example, the embodiments of the apparatus described above are merely schematic. For example, the division of the modules or units is only a logical function division, and there can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another device, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between different units, or the among different units, can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0239] The units described as separated components can or can not be physically separated, and the components displayed as units can be located in one place or can be distributed to multiple places. Some or all of the units can be selected according to actual needs to achieve the purposes of the embodiments of the present application.

[0240] In addition, each functional unit in the embodiments of the present application can be integrated in a processing unit, or each unit can exist physically as a separate unit, or two or more units can be integrated in one unit. The integrated unit can be implemented in the form of hardware, or in the form of a software functional unit.

[0241] The above describes only specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any changes or replacements within the technical scope disclosed in the present application should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An optimization method for a recommendation model, characterized in that, The method comprises: receiving a first message, the first message comprising target information, the target information being used to indicate an expected target of a recommendation model; sending first recommendation information, the first recommendation information indicating a target parameter and a parameter index corresponding to the target parameter, the target parameter and the parameter index being obtained according to the target information, the target parameter being used to achieve the expected target, and the parameter index being used to indicate an ability of the target parameter to achieve the expected target; receiving an execution result, the execution result being obtained based on the first recommendation information, and the execution result being used to determine whether to update the recommendation model.

2. The method of claim 1, wherein, The target information comprises at least one of quality of experience information, network function attribute information, or network function service range information.

3. The method according to claim 1 or 2, characterized in that, The first message further comprises a candidate parameter, the candidate parameter being related to the expected target, and the candidate parameter being used to determine the target parameter.

4. The method according to any one of claims 1 to 3, characterized in that, The target parameter comprises at least one of a quality of service parameter or a network element candidate list parameter; and the parameter index comprises at least one of an expected target achievement degree corresponding to the target parameter, an expected target relevance, or a target parameter priority.

5. The method according to any one of claims 1 to 4, characterized in that, The method further comprises: receiving a second message, the second message being used to indicate the execution result.

6. The method of claim 3, wherein, The method further comprises: receiving a third message, the third message being used to indicate at least one of updated target information or updated candidate parameter, the third message comprising one or more of the updated target information or the updated candidate parameter.

7. The method according to any one of claims 1 to 6, characterized in that, The method further comprises: determining to update the recommendation model when the execution result and the target information satisfy a first preset condition; The execution result and the target information satisfying the first preset condition comprises at least one of: a difference between the execution result and the target information being greater than or equal to a first preset threshold; or a ratio of the execution result to the target information being less than or equal to a second preset threshold.

8. An optimization method for a recommendation model, characterized in that, The method comprises: sending a first message, the first message comprising target information, the target information being used to indicate an expected target of a recommendation model; receiving first recommendation information, the first recommendation information indicating a target parameter and a parameter index corresponding to the target parameter, the target parameter and the parameter index being obtained according to the target information, the target parameter being used to achieve the expected target, and the parameter index being used to indicate an ability of the target parameter to achieve the expected target; based on the parameter index, executing the target parameter to obtain a corresponding execution result; sending the execution result, the execution result being used to determine whether to update the recommendation model.

9. The method of claim 8, wherein, The target information comprises at least one of quality of experience information, network function attribute information, or network function service range information.

10. The method according to claim 8 or 9, characterized in that, The first message further comprises a candidate parameter, the candidate parameter being related to the expected target, and the candidate parameter being used to determine the target parameter.

11. The method according to any one of claims 8-10, characterized in that, The target parameter comprises at least one of a quality of service parameter or a network element candidate list parameter; and the parameter index comprises at least one of an expected target achievement degree corresponding to the target parameter, an expected target relevance, or a target parameter priority.

12. The method according to any one of claims 8-11, characterized in that, The method further includes: sending a second message, the second message being used to indicate the execution result.

13. The method of claim 10, wherein, The method further includes: sending a third message, the third message being used to indicate updating at least one of the target information or the candidate parameter, the third message including one or more of the following: updated target information or updated candidate parameter.

14. The method according to any one of claims 8-13, characterized in that, The method further includes: when the execution result and the target information satisfy a first preset condition, sending a fourth message, the fourth message being used to indicate updating the recommendation model; wherein the execution result and the target information satisfy the first preset condition, including at least one of the following: a difference between the execution result and the target information is greater than or equal to a first preset threshold; or a ratio of the execution result to the target information is less than or equal to a second preset threshold.

15. A communications device, characterized by The communication device includes units or modules for performing the method of any one of claims 1-7, or units or modules for performing the method of any one of claims 8-14.

16. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer program instructions, which when executed, implement the method of any one of claims 1-7, or implement the method of any one of claims 8-14.

17. A computer program product comprising instructions, characterized in that, When the computer program product is running on a computer, it causes the method of any one of claims 1-7 to be implemented, or causes the method of any one of claims 8-14 to be implemented.

18. A communications device, characterized by including: a processor coupled to a memory, the memory being used to store programs or instructions, when the programs or instructions are executed by the processor, causing the device to perform the method of any one of claims 1-7, or perform the method of any one of claims 8-14.

19. A communication system, characterized by including: a device for performing the method of any one of claims 1-7, and a device for performing the method of any one of claims 8-14.

Images