Reasoning method based on ai model, communication apparatus, communication device, and medium

Abstract

The present application relates to the field of communications, and discloses a reasoning method based on an AI model in a communication system, a communication apparatus, a communication device, and a medium. The method of the embodiments of the present application comprises: a first device acquiring first information, wherein a first model is deployed on the first device; and on the basis of the first information, adapting the first model into a target task, wherein the first information comprises at least one of the following information: prompt indication information, knowledge indication information, and fine-tuning data set indication information.

Description

Reasoning method, communication device, communication equipment and medium based on AI model

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to the Chinese patent application filed with the China Patent Office on November 20, 2023, with application number 202311551044.9 and invention name “Reasoning method, communication device, communication equipment and medium based on AI model”, the entire contents of which are incorporated by reference into this application. Technical Field

[0003] The present application belongs to the field of communication technology, and specifically relates to an AI model-based reasoning method, communication device, communication equipment and medium. Background Art

[0004] In mobile communication systems, artificial intelligence (AI) is increasingly being incorporated into use cases. For example, at the physical layer, AI-based CSI (channel state information) prediction and feedback compression, AI-based beam management, and AI-based positioning are all examples. To ensure universal applicability across diverse communication scenarios, the application of large models to communication networks has been proposed to address system issues. While large models typically perform better in solving general problems, communication systems present a wide range of diverse challenges, such as beamforming, resource allocation, and channel prediction. Therefore, ensuring the performance of large models in solving specific downstream problems is a pressing issue. Summary of the Invention

[0005] The embodiments of the present application provide an AI model-based reasoning method, communication device, communication equipment and medium, which can improve the model performance when reasoning about downstream problems based on large models.

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

[0007] A first device obtains first information, wherein a first model is deployed on the first device; and the first model is adapted to a target task based on the first information; wherein the first information includes at least one of the following information: prompt indication information, knowledge indication information, and fine-tuning data set indication information.

[0008] In a second aspect, a reasoning method based on an AI model is provided, the method comprising:

[0009] The second device sends first information to the first device, where the first information is used by the first device to adapt the first model to a target task;

[0010] The first information includes at least one of the following information: prompt indication information, knowledge indication information, and fine-tuning data set indication information.

[0011] According to a third aspect, a communication device is provided, including:

[0012] a processing unit configured to obtain first information, wherein a first model is deployed on the communication device; and

[0013] Adapting the first model to a target task based on the first information;

[0014] The first information includes at least one of the following information: prompt indication information, knowledge indication information, and fine-tuning data set indication information.

[0015] In a fourth aspect, a communication device is provided, including:

[0016] A communication unit is used to send first information to a first device, on which a first model is deployed, and the first information is used by the first device to adapt the first model to a target task; wherein the first information includes at least one of the following information: prompt indication information, knowledge indication information, and fine-tuning data set indication information.

[0017] In a fifth aspect, a communication device is provided, which includes a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the method described in any one of the first to second aspects are implemented.

[0018] In a sixth aspect, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method described in any one of the first to second aspects are implemented.

[0019] In the seventh aspect, a wireless communication system is provided, including: a first device and a second device, wherein the first device can be used to execute the steps of the method described in the first aspect, and the second device can be used to execute the steps of the method described in the second aspect.

[0020] In an eighth aspect, a chip is provided, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the method described in any one of the first to second aspects.

[0021] In a ninth aspect, a computer program / program product is provided, wherein the computer program / program product is stored in a storage medium, and the program / program product is executed by at least one processor to implement the steps of the method described in any one of the first to second aspects.

[0022] In an embodiment of the present application, the first device can obtain auxiliary information for reasoning with the first model from the second device, such as prompt indication information, knowledge indication information, fine-tuning data set, etc., so that the inference node can use the first model for reasoning based on the prompt indication information, knowledge indication information, fine-tuning data set, etc., which is conducive to improving the reasoning performance of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] FIG1 is a schematic diagram of a communication system provided in an embodiment of the present application.

[0024] FIG2 is a schematic diagram of an AI model-based reasoning method provided in an embodiment of the present application.

[0025] FIG3 is a schematic interactive diagram of an AI model-based reasoning method provided in an embodiment of the present application.

[0026] FIG4 is a schematic interaction diagram of another AI model-based reasoning method provided in an embodiment of the present application.

[0027] FIG5 is a schematic interaction diagram of another AI model-based reasoning method provided in an embodiment of the present application.

[0028] FIG6 is a schematic diagram of a communication device provided in an embodiment of the present application.

[0029] FIG7 is a schematic diagram of another communication device provided in an embodiment of the present application.

[0030] FIG8 is a schematic diagram of a communication device provided in an embodiment of the present application.

[0031] FIG9 is a hardware structure diagram of a terminal provided in an embodiment of the present application.

[0032] FIG10 is a hardware structure diagram of a network-side device provided in an embodiment of the present application.

[0033] FIG11 is a hardware structure diagram of another network-side device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0034] The following will be combined with the accompanying drawings in the embodiments of this application to clearly describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of this application.

[0035] The terms "first", "second", etc. in this application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable where appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same type, and do not limit the number of objects, for example, the first object can be one or more. In addition, "or" in this application represents at least one of the connected objects. For example, "A or B" covers three options, namely, Option 1: including A but not including B; Option 2: including B but not including A; Option 3: including both A and B. The character " / " generally indicates that the objects associated before and after are in an "or" relationship.

[0036] The term "indication" in this application can be either a direct indication (or explicit indication) or an indirect indication (or implicit indication). A direct indication can be understood as the sender explicitly informing the receiver of specific information, the operation to be performed, or the requested result, etc. in the instruction sent; an indirect indication can be understood as the receiver determining the corresponding information based on the instruction sent by the sender, or making a judgment and determining the operation to be performed or the requested result, etc. based on the judgment result.

[0037] It is worth noting that the technology described in the embodiments of the present application is not limited to the Long Term Evolution (LTE) / LTE-Advanced (LTE-A) system, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA) or other systems. The terms "system" and "network" in the embodiments of the present application are often used interchangeably, and the technology described can be used for the systems and radio technologies mentioned above, as well as for other systems and radio technologies. The following description describes a New Radio (NR) system for illustrative purposes, and NR terminology is used in most of the following description, but these technologies can also be applied to systems other than NR systems, such as 6th generation (6G) systems. th Generation, 6G) communication system.

[0038] FIG1 is a block diagram of a wireless communication system applicable to an embodiment of the present application. The wireless communication system includes a terminal 11 and a network-side device 12. The terminal 11 may be a mobile phone, a tablet computer (Tablet Personal Computer), a laptop computer (Laptop Computer), a notebook computer, a personal digital assistant (PDA), a handheld computer, a netbook, an ultra-mobile personal computer (UMPC), a mobile internet device (MID), an augmented reality (AR), a virtual reality (VR) device, a robot, a wearable device (Wearable Device), an aircraft (Flight Vehicle), a vehicle-mounted device (VUE), a ship-mounted device, a pedestrian user equipment (PUE), a smart home (home appliances with wireless communication capabilities, such as refrigerators, televisions, washing machines, or furniture), a game console, a personal computer (PC), an ATM, or a self-service machine, or other terminal-side devices. Wearable devices include: smart watches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. Among them, the vehicle-mounted device can also be called a vehicle-mounted terminal, vehicle-mounted controller, vehicle-mounted module, vehicle-mounted component, vehicle-mounted chip or vehicle-mounted unit, etc. It should be noted that the specific type of the terminal 11 is not limited in the embodiment of the present application.

[0039] A terminal may also be referred to as user equipment (UE), terminal equipment, access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device, etc.

[0040] The network-side device 12 may include an access network device or a core network device, wherein the access network device may also be referred to as a radio access network (RAN) device, a radio access network function, or a radio access network unit. The access network device may include a base station, a wireless local area network (WLAN) access point (AS), or a wireless fidelity (WiFi) node. Among them, the base station can be referred to as Node B (NB), Evolved Node B (eNB), the next generation Node B (gNB), New Radio Node B (NR Node B), access point, Relay Base Station (RBS), Serving Base Station (SBS), Base Transceiver Station (BTS), radio base station, radio transceiver, Basic Service Set (BSS), Extended Service Set (ESS), Home Node B (HNB), Home Evolved Node B (home evolved Node B), Transmission Reception Point (TRP) or other appropriate terms in the field. As long as the same technical effect is achieved, the base station is not limited to specific technical vocabulary. It should be noted that in the embodiment of the present application, only the base station in the NR system is used as an example for introduction, and the specific type of the base station is not limited.

[0041] The core network device may include but is not limited to at least one of the following: core network node, core network function, mobility management entity (MME), access mobility management function (AMF), session management function (SMF), user plane function (UPF), policy control function (PCF), policy and charging rules function unit (PCRF), edge application server discovery function (EASDF), unified data management (UDM), unified data storage (UDR), home user server (HSS), centralized network configuration (CNC), network storage function (NRF), network exposure function (NEF), local NEF (L-NEF), binding support function (BNSF), network access function (UE ... Function, BSF), application function (Application Function, AF), etc. It should be noted that in the embodiment of the present application, only the core network device in the NR system is introduced as an example, and the specific type of the core network device is not limited.But not limited to at least one of the following: core network node, core network function, Mobility Management Entity (MME), Access and Mobility Management Function (AMF), Session Management Function (SMF), User Plane Function (UPF), Policy Control Function (PCF), Policy and Charging Rules Function (PCRF), Edge Application Server Discovery Function (EASDF), Unified Data Management (UDM), Unified Data Repository (UDR), Home Subscriber Server (HSS), Centralized Network Configuration (CNC), Network Repository Function (NRF), Network Exposure Function (NEF), Local NEF (L-NEF), Binding Support Function (BSF), Application Function (AF), etc. It should be noted that in the embodiments of this application, only the core network equipment in the NR system is introduced as an example, and the specific type of the core network equipment is not limited.

[0042] To facilitate understanding of the embodiments of the present application, the technologies related to the present application are explained.

[0043] 1: Prompt Engineering

[0044] Prompt engineering is a technique in natural language processing (NLP) that creates text snippets, prompts, or templates to guide pre-trained large language models to produce high-quality output for specific tasks or applications. It is widely used in areas such as question answering, summarization, translation, sentiment analysis, and text generation. Prompt engineering can leverage the powerful capabilities of pre-trained large language models to implement a variety of complex natural language processing tasks, reducing reliance on labeled data and model fine-tuning, lowering development costs and time, and improving the interpretability and controllability of pre-trained large language models, thereby increasing user trust and satisfaction. Common prompts include zero-shot prompting, few-shot prompting, and chain of thought prompting.

[0045] In prompt engineering, a description of the task is embedded into the input, guiding the generative AI solution to produce the desired output.

[0046] 2. Knowledge Graph

[0047] A knowledge graph is a knowledge base that uses graph structures or topologies to represent and integrate data. It can store descriptions of relationships between entities (objects, events, situations, or abstract concepts) and also encode semantic relationships between entities. Knowledge graphs have broad application prospects. They can not only improve the effectiveness of data services such as information retrieval, search engines, and recommendation systems, but also support intelligent interactions such as natural language question-answering, dialogue, and reasoning. They possess strong representational capabilities, high flexibility, strong computability, and strong cross-domain capabilities.

[0048] Knowledge graphs store a large amount of knowledge in an explicit and structured manner, which can be used to enhance the knowledge awareness of large models. Incorporating knowledge graphs into large models during the reasoning phase and retrieving knowledge from the knowledge graph can significantly improve the performance of large models in accessing domain-specific knowledge.

[0049] In the field of communications, network data knowledge graphs are mainly used for knowledge representation, association analysis and deep mining, providing effective knowledge rules and knowledge computing support for the intelligentization of communication systems.

[0050] The network structure, terminal type, terminal behavior, data service requirements, and system resources of the communication system are all highly dynamic, time-sensitive, and mutually coupled. Mobile communication data faces many challenges, such as the difficulty in obtaining scattered data, the wide variety and complex structure, and the difficulty in mining complex associations.

[0051] The use of knowledge graphs can effectively clarify the various relationships between data fields and communication network indicators, and further in-depth mining can be carried out based on the established relationships, such as quantifying the degree of correlation between the relationships, characterizing the characteristic attributes of data fields and indicators, etc.

[0052] In some implementations, the knowledge graph can be represented by the correlation between entities. One representation can be:

[0053] (Entity 1, Correlation coefficient between entity 1 and entity 2, entity 2).

[0054] For example, entity 1 is the cell throughput, entity 2 is the L1-RSRP of the strongest beam, and the correlation coefficient is 0.5.

[0055] In other implementations, the knowledge graph can be represented by a subject attribute object (Subject, Predicate, Object, SPO) triple, for example, an SPO triple of (cell id, shaped codebook, codebook indication).

[0056] 3. Knowledge Vector Library

[0057] A knowledge vector library is a database used to store, retrieve, and analyze vectors. It is called a database because it has the following characteristics:

[0058] a) Provide a standard access interface to lower the user's usage threshold;

[0059] b) Provide efficient data organization, retrieval, and analysis capabilities. While storing and retrieving vectors, users generally need to manage structured data, such as supporting the structured data management capabilities of traditional databases.

[0060] Therefore, the knowledge vector library can be simply understood as a database for storing model input feature vectors.

[0061] For example, when using images to search for images, or using voice to search for voice, what is stored and compared in the knowledge vector library is not the images and voice clips, but the "features" extracted by algorithms such as deep learning, such as 256 or 512 floating-point number arrays, which can be represented by vectors in mathematics.

[0062] In some cases, the knowledge vector library can be a model whose input is an image or text. For example, in the field of communications, the input of the model can be the measurement results of wireless signals, and the output is a feature vector that represents the measurement results.

[0063] The following methods can be used locally to use the knowledge graph or knowledge vector library:

[0064] 1) Directly used as input to the model;

[0065] 2) After processing the model input using the knowledge graph, the processed data is fed into the model together with the original model input;

[0066] 3) After processing the model input using the knowledge vector library, the processed data is input into the model together with the original model input, or the processed data is directly input into the model.

[0067] In mobile communication systems, artificial intelligence (AI) is increasingly being integrated into use cases. For example, at the physical layer, AI-based channel state information (CSI) prediction and feedback compression, AI-based beam management, and AI-based positioning are all examples. In some scenarios, AI-based energy conservation and load balancing are also being considered. In the future, even more AI-integrated use cases will emerge in mobile communication systems.

[0068] 4. Fine-tuning

[0069] The large language model is first pre-trained on a large-scale unlabeled text dataset, and then fine-tuned on a set of labeled data for the target task. Fine-tuning allows the large language model to better complete the target task.

[0070] In recent years, large language models have gained widespread attention in fields such as chat and image generation. Therefore, large models are being considered for use in communication networks as a tool to optimize their performance. However, large communication models present two challenges.

[0071] Question 1: Large models are very large. How can we deploy them to devices with limited storage resources, such as base stations or terminals, for inference? A typical approach is to process the large models using compression methods such as quantization and pruning before deploying them to communication devices.

[0072] Problem 2: Large models often solve general problems, but communications encompass many diverse challenges, such as beamforming, resource allocation, and channel prediction. Currently, there is no mature solution in communications systems for matching large models to specific downstream problems.

[0073] Below, in combination with the accompanying drawings, the reasoning method based on the artificial intelligence AI model in the communication system provided by the embodiment of the present application is described in detail through some embodiments and their application scenarios.

[0074] FIG2 shows a schematic diagram of an inference method based on an artificial intelligence (AI) model according to an embodiment of the present application. As shown in FIG2 , the method 200 includes:

[0075] S210: A first device acquires first information, wherein a first model is deployed on the first device;

[0076] S220: Adapt the first model to the target task according to the first information.

[0077] In an embodiment of the present application, the first device can be considered as an inference node, and the first device needs to use the first model to implement inference of the target task.

[0078] In some embodiments, the first model is a compressed AI model. For example, the first model is an AI model that is compressed from a large model. The compression here may include but is not limited to quantization, pruning (for example, deleting some layers in the model, or deleting some nodes in a layer), etc.

[0079] It should be noted that in the embodiments of the present application, the AI ​​model may also be referred to as an AI unit, an ML (machine learning) model, an ML unit, an AI structure, an AI function, an AI feature, a machine learning model, a neural network, a neural network function, a neural network function, etc., or an AI model may also refer to a processing unit that can implement specific algorithms, formulas, processing procedures, capabilities, etc. related to AI, or an AI model may be a processing method, algorithm, function, module or unit for a specific data set, or an AI model may be a processing method, algorithm, function, module or unit running on AI / ML related hardware such as a graphics processing unit (GPU), a neural network processing unit (NPU), a tensor processing unit (TPU), an application specific integrated circuit (ASIC), etc. This application does not make any specific limitations on this.

[0080] In some embodiments, the target task may be a specific task in the communication system, or a downstream task of the task adapted by the first model. By way of example and not limitation, the target task may be tasks such as beam management, positioning, load balancing, resource allocation, CSI prediction, and compressed feedback.

[0081] In some embodiments, the first information includes at least one of the following information:

[0082] Hint instructions, knowledge instructions, and fine-tuning dataset instructions.

[0083] In an embodiment of the present application, the prompt indication information may explicitly or implicitly indicate prompt-related information, the knowledge indication information may explicitly or implicitly indicate knowledge-related information, and the fine-tuning data set indication information may explicitly or implicitly indicate the fine-tuning data set. The present application does not limit the specific indication method.

[0084] In some embodiments, prompt-related information and knowledge-related information can be used to expand the input of the first model and assist the first model in performing accurate reasoning.

[0085] The first device can make the first model better adapted to the target task by prompting relevant information, knowledge-related information or fine-tuning the data set. For example, the first device can prompt or guide the first model to infer the expected output based on the prompt relevant information, thereby improving the reasoning performance of the model. For another example, the first device can combine the knowledge-related information when performing reasoning, and can accurately complete tasks in professional fields and reduce the illusion problem in model reasoning. For another example, the first device can fine-tune the data set to fine-tune the first model so that the reasoning result of the fine-tuned first model is the expected output, thereby improving the reasoning performance of the model.

[0086] In some embodiments, as shown in FIG3 , S210 may include:

[0087] The first device receives the first information sent by the second device.

[0088] In an embodiment of the present application, the second device can be considered as a device that assists the first device in reasoning, or an auxiliary reasoning node. For example, the second device can provide the first device with auxiliary information for obtaining reasoning results, or a fine-tuning data set for fine-tuning the model, so that the first device can adjust the reasoning results of the model according to the auxiliary information, or fine-tune the model according to the fine-tuning data set, so that the fine-tuned model can infer output that meets expectations.

[0089] For example, the first device is a terminal, and the second device is an access network device (such as a base station) or a core network function, such as a core network function with a data storage function, such as a database, a data function or a network storage function (Network Repository Function, NRF), or a unified data management (Unified Data Management, UDM), or a third-party server of the terminal, etc.

[0090] For another example, the first device is an access network device, such as a base station, and the second device is a core network function, such as a core network function with a data storage function (such as a database, a data function or an NRF or an UDM), an AI-related function (such as an AI control function, an AI model management function), an operation and maintenance management (Operation Administration and Maintenance) or an access network control node, etc.

[0091] In some embodiments, if the first device is a terminal and the second device is an access network device, the first information is carried in at least one of the following signaling: layer 1 signaling, layer 2 signaling, layer 3 signaling, AI layer signaling, and data plane signaling. Exemplarily, the layer 1 signaling may include but is not limited to a physical downlink control channel (PDCCH), for example, the first information is carried as downlink control information (DCI) in the PDCCH. The layer 2 signaling may, for example, include but is not limited to a downlink media access control element (MAC CE), and the layer 3 signaling may, for example, include but is not limited to a radio resource control (RRC) signaling.

[0092] In other embodiments, the first device is a terminal, the second device is a core network function, and the first information is carried in at least one of the following signaling: non-access stratum (NAS) signaling, AI layer signaling, and data plane signaling.

[0093] In some embodiments, when the first device is an access network device and the second device is a core network function, the second device may directly send the first information to the first device, or may forward it to the first device through another node (e.g., a central control node). Optionally, the central control node may include, but is not limited to: AMF, AI control node, task control node, collaborative control node.

[0094] In an embodiment of the present application, the AI ​​control node can be used to control AI-related functions; the task control node can be used to control service-related functions, or to control task-related functions. For example, the task may include but is not limited to new network capabilities involving the coordination and deployment of connections, computing, data and algorithm resources in multi-node scenarios to jointly achieve a specific goal; the collaborative control node can be used for collaborative management between multiple functions (such as communication functions, data functions, computing power functions, algorithm functions, and model functions).

[0095] In some embodiments of the present application, as shown in FIG3 , before S210 , the method 200 further includes:

[0096] S203: The first device sends second information to the second device.

[0097] In some embodiments, the second information may be used by the first device to request the first information from the second device.

[0098] For example, when the second device receives the first information from the first device, it is considered that the first device has a need to obtain the first information. Therefore, the second device can send the second information to the first device based on the first information.

[0099] In some embodiments, the second information includes at least one of the following:

[0100] Requirement information for reasoning with the first model;

[0101] Auxiliary information used to determine the first information;

[0102] Identification information of at least one event that triggers the first device to send the requirement information or the auxiliary information.

[0103] In some embodiments, the first information is determined based on the second information.

[0104] For example, the auxiliary inference node can determine the first information to be sent to the inference node based on the demand information and / or auxiliary information provided by the inference node, and then send the first information to the first device, so that the first device can use the first information for inference based on the first information, which is conducive to improving the inference performance of the model.

[0105] For example, the second device may select appropriate prompt indication information or knowledge-related information or fine-tune the data set according to the requirement information to meet the reasoning requirements of the first model.

[0106] For another example, the second device may select appropriate prompt indication information or knowledge-related information or a fine-tuning data set based on the auxiliary information to assist the first device in using the first model to infer an expected output.

[0107] In some embodiments, if the first device is a terminal and the second device is an access network device, the second information is carried in at least one of the following signaling: layer 1 signaling, layer 2 signaling, layer 3 signaling, AI layer signaling, and data plane signaling. Exemplarily, the layer 1 signaling may include but is not limited to a physical uplink control channel (PUCCH), for example, the second information is reported as uplink control information (UCI) carried in the PUCCH. The layer 2 signaling may, for example, include but is not limited to an uplink MAC CE, and the layer 3 signaling may, for example, include but is not limited to RRC signaling.

[0108] In some other embodiments, the first device is a terminal, the second device is a core network function, and the second information is carried in at least one of the following signaling: NAS signaling, AI layer signaling, and data plane signaling.

[0109] In some embodiments, when the first device is an access network device and the second device is a core network function, the first device may directly send the second information to the second device, or may forward it to the second device through another node (e.g., a central control node). Optionally, the central control node may include, but is not limited to: AMF, AI control node, task control node, collaborative control node.

[0110] In some embodiments, the requirement information used for the first model to perform reasoning includes but is not limited to at least one of the following:

[0111] Indication of the target tasks to which the AI ​​model needs to be adapted;

[0112] Service Quality of Experience (QoE) requirements for AI models;

[0113] Business processing latency of AI models;

[0114] The business processing accuracy of the AI ​​model;

[0115] The business computing capacity of AI models;

[0116] The data processing scale of AI models.

[0117] For example, the second device may select prompt indication information or knowledge-related information or a fine-tuning dataset related to the target task according to the target task indication.

[0118] For another example, the second device may select prompt indication information or knowledge-related information or a fine-tuning data set that meets QoE requirements, or processing delay, processing accuracy or processing scale, etc.

[0119] In some embodiments, the auxiliary information used to determine the first information includes but is not limited to at least one of the following:

[0120] Identification information of the AI ​​model, function indication of the AI ​​model, characteristic indication of the AI ​​model, and configuration indication of the first device.

[0121] For example, the second device may select prompt indication information or knowledge-related information or a fine-tuning data set related to the function (or characteristic) indicated by the function indication (or characteristic indication).

[0122] For another example, the second device may select, based on the configuration instruction of the first device, knowledge-related information in a field related to the configuration instruction, or a fine-tuning dataset applicable to the configuration instruction.

[0123] In some embodiments, the first device is a terminal, and the second information may be sent under specific circumstances, for example:

[0124] When at least one of the following events occurs, the first device sends the second information to the second device:

[0125] Event 1: a first indication is received, where the first indication is used to instruct activation or switching of a model;

[0126] Event 2: the first device determines to activate or switch a model;

[0127] Event 3: the first device determines that the currently used model does not meet the requirements;

[0128] Event 4: A second indication is received, where the second indication is used to indicate that the currently used model does not meet the requirements.

[0129] In some embodiments, the event that triggers the first device to send the second information to the second device can be predefined, or configured by the network side device. When the event that triggers the second information is met, the first device can send the identification information of the event to the network side device, for example, carried in the second information and sent to the network side device, so that the network side device can be informed of the event that occurred on the first device. Optionally, the first device can also send a characteristic indication and / or function indication of the AI ​​model to the second device. For example, the second information can include the identification information of the event and the characteristic indication and / or function indication of the AI ​​model. The characteristic indication can be used to indicate the characteristics that the first device expects the AI ​​model to implement, and the function indication can be used to indicate the function that the first device expects the AI ​​model to implement.

[0130] In some embodiments, when at least one of the above events occurs, the first device may not send the auxiliary information and / or demand information to the second device, but only send the identification information of the event that occurred on the first device to the second device. Optionally, the first device may also send a characteristic indication and / or function indication of the AI ​​model to the second device to implicitly indicate to the second device that there is a need to obtain the first information. Furthermore, the second device may determine the corresponding first information based on the identification information of the event and send it to the first terminal.

[0131] Therefore, in an embodiment of the present application, when at least one of the above events occurs, the first device sends the second information to the second device, which is conducive to the second device promptly indicating the first information to the first device, so that the first device can use the first information to expand the input of the first model to assist the output of the first model, or adjust the first model so that the output of the first model can match the target task.

[0132] In some embodiments, the first indication may be sent by a network side device. For example, the network side device may control the activation or switching of the model on the first device. For example, the network side device may send a first indication to the first device when the model currently used on the first device does not meet the requirements, so that the first device may activate the first model or switch to the first model according to the first indication.

[0133] In some embodiments, the first device may autonomously determine to activate the first model or switch to the first model when the performance of the currently used model does not meet the requirements.

[0134] In some embodiments, the second indication may be sent by a network side device. For example, when the model currently used on the first device does not meet the requirements, the network side device may send a second indication to the first device to indicate that the model currently used by the first device does not meet the requirements. Furthermore, the first device may independently determine whether to activate the first model or switch to the first model based on the second indication.

[0135] In some embodiments, the model not meeting the requirements may refer to the model not meeting the requirement information, for example, it may include but is not limited to at least one of the following: the model's reasoning does not meet the service quality of experience (Quality of Experience, QoE) does not meet the QoE requirements, the model's service processing delay does not meet the delay requirements, and the model's service processing accuracy does not meet the accuracy requirements.

[0136] In some embodiments of the present application, as shown in FIG3 , the method 200 further includes:

[0137] S202: The first device receives the first model sent by the third device.

[0138] Since the first device needs to perform many communication tasks and has limited storage space, storing all AI models on the first device would consume a large amount of storage space. Therefore, the first model can be stored on the first device. When the first model is needed to perform a task, the first model can be obtained from the third device and further used to perform the task.

[0139] In an embodiment of the present application, the third device can be considered as a storage device of the model, or a model storage node, or an AI model library, or an AI model management function.

[0140] Optionally, the second device and the third device may be the same device, or different devices. For example, the auxiliary inference node and the model storage node may be the same device, or different devices.

[0141] In some embodiments, the first device is a terminal, and the third device is an access network device (e.g., a base station) or a core network function, such as a core network function with a data storage function, such as a database, a data function, or a network repository function (NRF) or UDM, or an AI model library, or an AI model management function or a third-party server of a terminal, etc.

[0142] In other embodiments, the first device is an access network device, and the third device is a core network function, for example, a core network function with a data storage function (such as a database, a data function or an NRF or an UDM), an AI-related function (such as an AI control function, an AI model management function, an AI model library), an operation and maintenance management (Operation Administration and Maintenance) or a third-party server of an access network device, etc.

[0143] In some embodiments, if the first device is a terminal and the third device is an access network device, the first model is carried in at least one of the following signaling: layer 1 signaling, layer 2 signaling, layer 3 signaling, data plane signaling, and AI layer signaling. Exemplarily, the layer 1 signaling may include, but is not limited to, PDCCH. The layer 2 signaling may, for example, include, but is not limited to, downlink MAC CE, and the layer 3 signaling may, for example, include, but is not limited to, RRC signaling.

[0144] In other embodiments, the first device is a terminal, and if the third device is a core network function, the first model is carried in at least one of the following signaling: NAS signaling, data plane signaling, and AI layer signaling.

[0145] In some embodiments of the present application, as shown in FIG3 , before S202 , the method 200 further includes:

[0146] S201: The first device sends third information to the third device. The third information may include model-related information.

[0147] In some embodiments, if the first device is a terminal and the third device is an access network device, the third information is carried in at least one of the following signaling: layer 1 signaling, layer 2 signaling, layer 3 signaling, data plane signaling, and AI layer signaling. Exemplarily, the layer 1 signaling may include, but is not limited to, a PUCCH, for example, where the second information is reported as UCI carried in the PUCCH. The layer 2 signaling may include, but is not limited to, an uplink MAC CE, and the layer 3 signaling may include, but is not limited to, RRC signaling.

[0148] In some embodiments, the first device is a terminal. If the third device is a core network function, the third information is carried in at least one of the following signaling: NAS signaling, data plane signaling, and AI layer signaling.

[0149] In some embodiments, the third information includes but is not limited to at least one of the following:

[0150] Identification information of the AI ​​model, function indication of the AI ​​model, characteristic indication of the AI ​​model, and configuration indication of the first device.

[0151] In some embodiments, the first model is selected based on the third information. For example, the first model is a model that satisfies the identification information, the functional instructions, the specific instructions, or the configuration instructions. Therefore, the third device selects an appropriate model based on the third information and sends it to the first device, which helps meet the inference requirements of the first device.

[0152] In some embodiments, the identification information of the AI ​​model can be, for example, a model identifier (model ID) of the AI ​​model, which can be used for AI structure identification, AI algorithm identification, or identification of a specific data set associated with the AI ​​model, or identification of a specific scenario, environment, channel feature, or device related to AI / ML, or identification of functions, features, capabilities, or modules related to AI / ML. The present invention does not specifically limit this.

[0153] In some embodiments, the characteristic indication of the AI ​​model may explicitly or implicitly indicate features supported by the AI ​​model, such as support for CSI prediction and compression feedback, beam prediction, positioning, load balancing, resource allocation, etc.

[0154] In the embodiments of the present application, the characteristics of the AI ​​model under a specific configuration can be considered as the functions of the AI ​​model.

[0155] For example, the characteristic of the AI ​​model is beam prediction, and the function of the AI ​​model is time domain beam prediction when the base station is configured with 32 transmit beams.

[0156] In some embodiments, the functional indication of the AI ​​model may explicitly or implicitly indicate the functions supported by the AI ​​model, such as supporting CSI prediction and compression feedback under a specific configuration, beam prediction, positioning, load balancing, resource allocation, etc.

[0157] In some embodiments, the configuration indication of the first device includes but is not limited to at least one of the following:

[0158] Number of transmit antennas, number of transmit beams, number of antenna ports, transmit power, antenna gain, beam 3dB bandwidth, spacing, frequency, and system bandwidth.

[0159] The following describes the specific content of each of the first information and the second information in conjunction with specific embodiments.

[0160] In some embodiments, the prompt indication information is related to the target task.

[0161] In some implementations, the prompt indication information explicitly indicates prompt-related information related to the target task.

[0162] Exemplarily, the prompt indication information includes but is not limited to at least one of the following:

[0163] The chain of thought related to the stated target task;

[0164] Prompt text related to the target task;

[0165] Prompt files related to the target task;

[0166] The prompt code related to the target task.

[0167] In some embodiments, the thought chain associated with the target task may include one or more of a plurality of candidate thought chains, which may be predefined or indicated by a network-side device. For example, when it is necessary to match the first model to the target task, the second device may select one or more thought chains from the plurality of candidate thought chains and indicate them to the first device.

[0168] In some embodiments, the prompt text associated with the target task may include one or more of a plurality of candidate prompt texts, which may be predefined or indicated by a network-side device. For example, the second device may select one or more prompt texts from the plurality of candidate prompt texts and indicate them to the first device.

[0169] In some embodiments, the prompt file associated with the target task may include one or more of a plurality of candidate prompt files, which may be predefined or indicated by a network-side device. For example, the second device may select one or more prompt files from the plurality of candidate prompt files and indicate them to the first device.

[0170] In some embodiments, the prompt code associated with the target task may include one or more of a plurality of candidate prompt codes, which may be predefined or indicated by a network-side device. For example, the second device may select one or more prompt codes from the plurality of candidate prompt codes and indicate them to the first device.

[0171] In some other implementations, the prompt indication information implicitly indicates prompt-related information related to the target task.

[0172] Exemplarily, the prompt indication information includes but is not limited to at least one of the following:

[0173] Identification of thought chains related to the target task;

[0174] Prompt text labels related to the target task;

[0175] The prompt file identifier related to the target task;

[0176] A prompt code identifier related to the target task;

[0177] The address of the prompt file related to the target task.

[0178] Optionally, when the first information is transmitted via NAS signaling, the prompt indication information may include a prompt file address related to the target task.

[0179] In some embodiments, multiple thought chain identifiers can be predefined or preconfigured (for example, pre-indicated by a network side device), and each thought chain identifier corresponds to a thought chain. For example, the second device can select one or more thought chain identifiers from the multiple thought chain identifiers and indicate them to the first device. Furthermore, the first device can determine the corresponding thought chain based on the indicated thought chain identifier, and further perform reasoning based on the thought chain.

[0180] In some embodiments, multiple prompt text identifiers can be predefined or preconfigured (for example, pre-indicated by a network side device), and each prompt text identifier corresponds to a piece of prompt text. For example, the second device can select one or more prompt text identifiers from the multiple prompt text identifiers and indicate them to the first device. Furthermore, the first device can determine the corresponding prompt text based on the indicated prompt text identifier, and further perform inference based on the prompt text.

[0181] In some embodiments, multiple prompt file identifiers can be predefined or preconfigured (for example, pre-indicated by a network-side device), and each prompt file identifier corresponds to a prompt file. For example, the second device can select one or more prompt file identifiers from the multiple prompt file identifiers and indicate them to the first device. Furthermore, the first device can determine the corresponding prompt file based on the indicated prompt file identifier, and further perform reasoning based on the prompt file.

[0182] In some embodiments, multiple prompt code identifiers can be predefined or preconfigured (for example, pre-indicated by a network side device), and each prompt code identifier corresponds to a prompt code. For example, the second device can select one or more prompt code identifiers from the multiple prompt code identifiers to indicate to the first device. Furthermore, the first device can determine the corresponding prompt code based on the indicated prompt code identifier, and further perform inference based on the prompt code.

[0183] In some embodiments, multiple prompt file addresses can be predefined or preconfigured (for example, pre-indicated by a network side device), and each prompt file address corresponds to a prompt file. For example, the second device can select one or more prompt file addresses from the multiple prompt file addresses and indicate them to the first device. Furthermore, the first device can obtain the corresponding prompt file according to the indicated prompt file address, and further perform reasoning based on the prompt file.

[0184] In some embodiments, the target task is beam prediction, and the prompt indication information may be:

[0185] When the model input is the beam qualities of eight fixed beam patterns over four historical time units, the model output is the strongest beam identifier for one future time unit. For example, the time unit period is 40ms.

[0186] In an embodiment of the present application, the knowledge indication information may explicitly or implicitly indicate knowledge-related information (e.g., knowledge graph-related information, knowledge vector library-related information). For example, the knowledge indication information includes at least one of the knowledge graph indication information and the knowledge vector library indication information.

[0187] In some embodiments, the knowledge indication information is related to the target task. For example, the knowledge indication information is used to indicate the knowledge in the field to which the target task belongs or the scenario corresponding to the target task, such as a knowledge graph, a knowledge vector library, etc.

[0188] In some implementations, the knowledge graph indication information may explicitly indicate knowledge graph related information.

[0189] Exemplarily, the knowledge graph indication information includes but is not limited to at least one of the following:

[0190] The relationships between entities in the knowledge graph;

[0191] Attribute information of entities in the knowledge graph;

[0192] The data structure of the knowledge graph;

[0193] The correlation between entities in the knowledge graph;

[0194] The subject attribute object (Subject, Predicate, Object, SPO) triple of the statement in the knowledge graph;

[0195] Knowledge graph file.

[0196] In some embodiments, the relationship between entities in the knowledge graph can be expressed in the following format:

[0197] (Entity 1, Relationship, Entity 2).

[0198] Optionally, the relationship between entities may include but is not limited to hierarchical relationship, inheritance relationship, etc.

[0199] In some embodiments, the attribute information of an entity in a knowledge graph can be represented in the following format:

[0200] (entity, attribute name, attribute value).

[0201] In some embodiments, the data structure of the knowledge graph can be used to describe the nodes in the knowledge graph and the relationships between them. For example, the relationship between nodes can be represented by a triple, for example, a relationship can be (node ​​1, edge, node 2).

[0202] In some embodiments, the correlation between entities in the knowledge graph can be expressed in the following format:

[0203] (Entity 1, Correlation coefficient between entity 1 and entity 2, entity 2).

[0204] For example, entity 1 is the cell throughput, entity 2 is the L1-RSRP of the strongest beam, and the correlation coefficient is 0.8.

[0205] In some embodiments, the SPO triples of a sentence in the knowledge graph are used to describe the subject, predicate, and object of the sentence.

[0206] In other implementations, the knowledge graph indication information may implicitly indicate knowledge graph related information.

[0207] Exemplarily, the knowledge graph indication information includes but is not limited to at least one of the following:

[0208] Knowledge graph identification;

[0209] Knowledge graph file address.

[0210] Optionally, when the first device is a terminal and the second device is a core network function, the knowledge graph file address can be transmitted via NAS signaling.

[0211] In some embodiments, multiple knowledge graph identifiers can be predefined or preconfigured (for example, pre-indicated by a network-side device), and each knowledge graph identifier corresponds to a knowledge graph. For example, the second device can select one or more knowledge graph identifiers from the multiple knowledge graph identifiers and indicate them to the first device. Furthermore, the first device can determine the corresponding knowledge graph based on the indicated knowledge graph identifier, and further perform reasoning based on the knowledge graph.

[0212] In some embodiments, multiple knowledge graph file addresses can be predefined or preconfigured (for example, pre-indicated by a network-side device), and each knowledge graph file address corresponds to a knowledge graph file. For example, the second device can select one or more knowledge graph file addresses from the multiple knowledge graph file addresses and indicate them to the first device. Furthermore, the first device can obtain the corresponding knowledge graph file according to the indicated knowledge graph file address, and further perform reasoning based on the knowledge graph file.

[0213] In some embodiments, the target task is beam prediction, and the knowledge graph can be used in the following ways:

[0214] Based on the cell identification and target task, the knowledge graph can be used to retrieve the cell transmission beam configuration, such as the direction of the transmission beam or the shaped codebook.

[0215] In some implementations, the knowledge vector library indication information may implicitly indicate the knowledge vector library related information.

[0216] Exemplarily, the knowledge vector library indication information includes but is not limited to at least one of the following:

[0217] Knowledge vector library identifier;

[0218] Knowledge vector library file address.

[0219] Optionally, when the first information is transmitted via NAS signaling, the knowledge indication information may include a knowledge vector library file address related to the target task.

[0220] In some embodiments, multiple knowledge vector library identifiers can be predefined or preconfigured (for example, pre-indicated by a network side device), and each knowledge vector library identifier corresponds to a knowledge vector library. For example, the second device can select one or more knowledge vector library identifiers from the multiple knowledge vector library identifiers and indicate them to the first device. Furthermore, the first device can determine the corresponding knowledge vector library based on the indicated knowledge vector library identifier, and further perform reasoning based on the knowledge vector library.

[0221] In some embodiments, multiple knowledge vector library file addresses can be predefined or preconfigured (for example, pre-indicated by a network side device), and each knowledge vector library file address corresponds to a knowledge vector library file. For example, the second device can select one or more knowledge vector library file addresses from the multiple knowledge vector library file addresses and indicate them to the first device. Furthermore, the first device can obtain the corresponding knowledge vector library file according to the indicated knowledge vector library file address, and further perform reasoning based on the knowledge vector library file.

[0222] In some embodiments, the target task is beam prediction, and the knowledge vector library can be used as follows:

[0223] According to the cell identification and target task, the knowledge vector library is used to obtain the cell transmission beam configuration, such as the direction of the transmission beam or the feature vector related to the shaped codebook.

[0224] In some embodiments, the fine-tuning dataset indication information is used to indicate input information and label information of the first model, where the input information of the first model is related to the target task. Therefore, the first device trains the first model based on the input information and label information of the first model to fine-tune the first model, thereby making the fine-tuned first model suitable for the target task.

[0225] In some embodiments, the fine-tuning dataset indication information may explicitly indicate the fine-tuning dataset, for example, the fine-tuning dataset indication information includes the input information and label information of the first model, or may also implicitly indicate the fine-tuning dataset, for example, the fine-tuning dataset indication information includes an identifier of the fine-tuning dataset, which corresponds to a fine-tuning dataset.

[0226] In some embodiments, the fine-tuning dataset may be determined based on a dataset reported from at least one terminal.

[0227] Optionally, considering data privacy, sensitive data in the fine-tuning dataset can be privatized. For example, the data in a fine-tuning dataset can be obtained using the same privatization method.

[0228] In some embodiments, the input information of the first model includes but is not limited to at least one of the following:

[0229] Wireless signal measurement results, perception results, and wireless statistical characteristics.

[0230] In some embodiments, the measurement result of the wireless signal may be a measurement result obtained by measuring the wireless signal, and the wireless signal may include but is not limited to an uplink signal (e.g., an uplink reference signal), a downlink signal (e.g., a downlink reference signal), and a sidelink signal (e.g., a sidelink reference signal).

[0231] Exemplarily, the measurement result of the wireless signal may include but is not limited to:

[0232] Rank Indication (RI);

[0233] Precoding Matrix Indicator (PMI);

[0234] Channel Quality Indicator (CQI)

[0235] Reference Signal Receiving Quality (RSRQ);

[0236] Reference Signal Receiving Power (RSRP);

[0237] Signal to Interference plus Noise Ratio (SINR);

[0238] Signal to Noise Ratio (SNR)

[0239] Received Signal Strength Indication (RSSI).

[0240] In some embodiments, the sensing result is obtained by sensing a wireless signal.

[0241] In some embodiments, the perception result obtained through the wireless signal includes at least one of the following:

[0242] First-level measurement quantities (representing received signal / original channel information). Examples include but are not limited to: received signal / channel response complex results, amplitude / phase, I-channel / Q-channel and their operation results (operations include addition, subtraction, multiplication, division, matrix addition, subtraction, multiplication, matrix transposition, trigonometric operations, square root operations, and power operations, as well as threshold detection results and maximum / minimum value extraction results of the above operation results; operations also include Fast Fourier Transform (FFT) / Inverse Fast Fourier Transform (IFFT), Discrete Fourier Transform (DFT) / Inverse Discrete Fourier Transform (IDFT), 2D-FFT, 3D-FFT, matched filtering, autocorrelation operation, wavelet transform and digital filtering, as well as threshold detection results and maximum / minimum value extraction results of the above operation results);

[0243] The second-level measurement quantity (basic measurement quantity) includes: time delay, Doppler, angle, intensity, and their multi-dimensional combination representation;

[0244] Level 3 measurement quantities (basic attributes / states), including but not limited to: distance, speed, direction, spatial position, acceleration;

[0245] Level 4 measurements (advanced attributes / states) include, but are not limited to: target presence, trajectory, movement, expression, vital signs, quantity, imaging results, weather, air quality, shape, material, and composition.

[0246] In other embodiments, the perception results may also be obtained through a third-party device.

[0247] Exemplarily, the third-party device includes at least one of the following:

[0248] Cameras, radars, lidar, global positioning system GPS, inertial measurement unit.

[0249] In some embodiments, the lidar-related perception result includes at least one of the following:

[0250] LiDAR point cloud data. Each point in the LiDAR point cloud data includes: X / Y / Z position information and additional information;

[0251] The angle and distance of the target obtained from the LiDAR point cloud data;

[0252] Visually relevant measurements of objects identified from LiDAR point cloud data, such as people and vehicles;

[0253] The number of objects identified from the LiDAR point cloud data.

[0254] In some embodiments, the additional information in the lidar point cloud data includes at least one of the following:

[0255] Intensity: The return intensity of the laser pulse that generated the lidar point;

[0256] Echo number: Echo number is the total number of echoes for a given pulse;

[0257] Point classification: Each post-processed lidar point can have a classification that defines the type of object that reflected the lidar pulse. LiDAR points can be divided into many categories, such as ground, bare earth, top of tree canopy, and water.

[0258] Red, Green, and Blue (RGB): RGB bands can be used as attributes of lidar data. This attribute usually comes from the effects collected during lidar measurement.

[0259] Global Positioning System (GPS) time: GPS timestamp of the laser point emitted from the aircraft;

[0260] Scan Angle:

[0261] Scan direction: The direction of travel of the laser scanning mirror. A value of 1 represents a positive scanning direction and a value of 0 represents a negative scanning direction.

[0262] In some embodiments, the visually relevant measurements of the target identified from the lidar point cloud data include at least one of the following:

[0263] visual images;

[0264] the luminosity of the image pixels;

[0265] RGB values ​​of image pixels;

[0266] Visual features of objects identified from images, such as people, vehicles, etc.

[0267] The angle and distance of the target identified from the image (especially for binocular vision);

[0268] The number of objects identified in the image.

[0269] In some embodiments, the radar-related perception result includes at least one of the following:

[0270] Radar point cloud, each point in the point cloud includes: at least one of range / speed / azimuth / pitch angle, or at least one of X / Y / Z / speed;

[0271] The distance, speed, and angle of the identified target;

[0272] radar imaging;

[0273] The number of targets.

[0274] In some embodiments, the inertial measurement unit-related perception result includes at least one of the following:

[0275] Acceleration: at least one of the three directions X / Y / Z;

[0276] Speed: at least one of the three directions X / Y / Z;

[0277] Angular velocity: around at least one of the three axes X / Y / Z.

[0278] In some embodiments, the perception results related to other third-party devices may include at least one of the following:

[0279] Target presence, trajectory, movement, expression, vital signs, quantity, imaging results, weather, air quality, shape, material, composition, etc.

[0280] In some embodiments, the wireless statistical characteristics include at least one of the following:

[0281] Blockage probability, user status, user behavior, and switching failure rate.

[0282] The blockage probability may refer to the probability that the service beam is blocked.

[0283] In some embodiments, the user status includes at least one of the following:

[0284] Registration Management (RM) state, Connection Management (CM) state, Radio Resource Control (RRC) connection management state.

[0285] Exemplarily, the RM status may include an RM deregistered (RM DEREGISTERED) state and an RM registered (RM REGISTERED) state.

[0286] Exemplarily, the CM state may include a CM idle (CM_IDLE) state and a CM connected (CM_CONNECTED) state.

[0287] Exemplarily, the RRC connection management state may include an RRC connected (RRC-connected) state, an RRC idle (RRC-idle) state, and an RRC inactive (RRC-inactive) state.

[0288] In some embodiments, the user behavior includes at least one of the following:

[0289] Behavior in RRC idle state, behavior in RRC inactive state, and behavior in RRC connected state.

[0290] Exemplarily, the behavior in the RRC idle state includes at least one of the following:

[0291] Public Land Mobile Network (PLMN) selection, neighbor measurement, cell selection, cell reselection, Tracking Area (TA) update, paging monitoring, and obtaining system messages.

[0292] Exemplarily, the behavior in the RRC inactive state includes at least one of the following:

[0293] Neighboring cell measurement, cell reselection, cell selection, RAN notification area (RNA) update, RAN paging monitoring, and obtaining system information.

[0294] Exemplarily, the behavior in the RRC connected state includes at least one of the following:

[0295] Serving cell channel quality measurement and reporting, neighboring cell measurement and measurement report reporting, PDCCH monitoring, monitoring of control channels related to shared data channels (to sense whether there is related scheduling), and obtaining system messages.

[0296] In some embodiments, taking beam prediction as an example, the model input in the fine-tuning dataset may include the following information:

[0297] Wireless measurement quantity: L1-RSRP and its transmit beam identifier;

[0298] Perception information: 2D / 3D map of the wireless environment collected by the camera;

[0299] Wireless statistical characteristics: obstruction probability.

[0300] In some embodiments of the present application, when the first device is a terminal, the method 200 further includes:

[0301] The terminal sends at least one of fourth information and first capability information to the network side device, wherein the fourth information is used to indicate the auxiliary information required by the terminal to perform reasoning based on the first model, and the first capability information is used to indicate the ability of the terminal to perform reasoning based on the first model.

[0302] In some embodiments, the fourth information or the first capability information can be used by the network side device to determine the first information to indicate to the terminal.

[0303] Illustratively, the fourth information includes but is not limited to at least one of the following:

[0304] Instruction information for adapting prompts to the target task;

[0305] Indicative information for adapting knowledge to the target task;

[0306] Instructions for fine-tuning a dataset for adapting the target task.

[0307] Optionally, the indication information for adapting the prompt of the target task can be used to indicate the prompt that the terminal expects to use, and the indication information can indicate one or more prompts. For example, the network side device can select one or more prompts from the prompts that the terminal expects to use and indicate them to the terminal through the first information.

[0308] Optionally, the indication information for the prompt for adapting the target task may explicitly or implicitly indicate the prompt for adapting the target task.

[0309] Exemplarily, the indication information for adapting the prompt of the target task may include, but is not limited to, at least one of the following:

[0310] A chain of thought that is suitable for the target task;

[0311] Prompt text for adapting to the target task;

[0312] A prompt file for adapting the target task;

[0313] A prompt code for adapting the target task;

[0314] A thought chain identifier for adapting to the target task;

[0315] A prompt text identifier for adapting to the target task;

[0316] A prompt file identifier for adapting the target task;

[0317] A prompt code identifier for adapting to the target task;

[0318] The prompt file address used to adapt the target task.

[0319] Optionally, the indication information of the knowledge used to adapt the target task may be used to indicate the knowledge that the terminal expects to use, and the indication information may indicate one or more pieces of knowledge. For example, the network side device may select one or more pieces of knowledge from the knowledge that the terminal expects to use and indicate them to the terminal through the first information.

[0320] Optionally, the indication information of the knowledge used to adapt the target task may explicitly or implicitly indicate the knowledge used to adapt the target task.

[0321] In some embodiments, the indicative information for adapting the knowledge of the target task may include indicative information of a knowledge graph and / or indicative information of a knowledge vector library for adapting the target task. For example, the indicative information of the knowledge graph is one or more knowledge graph identifiers, or a knowledge graph group identifier, a knowledge graph file address, etc., or explicitly indicates one or more knowledge graphs. For example, the indicative information of the knowledge vector library is used to indicate one or more knowledge vector library identifiers, or explicitly indicates one or more knowledge vector libraries.

[0322] Exemplarily, the indication information of the knowledge graph includes at least one of the following:

[0323] The relationships between entities in the knowledge graph;

[0324] Attribute information of entities in the knowledge graph;

[0325] The data structure of the knowledge graph;

[0326] The correlation between entities in the knowledge graph;

[0327] SPO triples of sentences in the knowledge graph;

[0328] Knowledge graph file;

[0329] Knowledge graph identification;

[0330] Knowledge graph file address.

[0331] Optionally, the indication information of the fine-tuning dataset for adapting the target task may be used to indicate the fine-tuning dataset that the terminal desires to use. The indication information may indicate one or more fine-tuning datasets. For example, the network-side device may select one or more fine-tuning datasets from the knowledge that the terminal desires to use and indicate them to the terminal via the first information.

[0332] Optionally, the fine-tuning dataset indicated by the indication information may include at least one of a plurality of predefined or preconfigured fine-tuning datasets, wherein each fine-tuning dataset may include a set of input information and label information.

[0333] Optionally, the indication information of the fine-tuning dataset used to adapt the target task may explicitly or implicitly indicate one or more fine-tuning datasets used to adapt the target task. For example, the indication information may indicate identification information of the fine-tuning dataset, or explicitly indicate one or more fine-tuning datasets.

[0334] Exemplarily, the first capability information includes but is not limited to at least one of the following:

[0335] identification information of the first model supported by the terminal;

[0336] whether the terminal supports adapting the first model to the target task based on the prompt information;

[0337] whether the terminal supports adapting the first model to the target task based on a fine-tuning dataset;

[0338] whether the terminal supports adapting the first model to the target task based on knowledge information;

[0339] Indication information of prompts supported by the terminal;

[0340] information indicating the knowledge supported by the terminal;

[0341] Indication information of the fine-tuning datasets supported by the terminal.

[0342] Among them, the specific implementation of the indication information of the prompt supported by the terminal refers to the description of the indication information of the prompt used to adapt the target task, the specific implementation of the indication information of the knowledge supported by the terminal refers to the description of the indication information of the knowledge used to adapt the target task, and the specific implementation of the indication information of the fine-tuning data set supported by the terminal refers to the description of the indication information of the fine-tuning data set used to adapt the target task. For the sake of brevity, they are not repeated here.

[0343] In some embodiments, the first model may be considered as a model for adapting to the target task, and the identification information of the first model supported by the terminal may be identification information of a model supported by the terminal that can adapt to the target task.

[0344] In some embodiments, the first capability information may be used by the network-side device to determine whether to indicate the first information to the terminal and / or the content of the first information sent to the terminal.

[0345] For example, when the terminal supports adapting the first model to the target task based on prompt information, prompt indication information can be sent to the terminal, or, when the terminal supports adapting the first model to the target task based on knowledge information, prompt knowledge indication information can be sent to the terminal, or, when the terminal supports adapting the first model to the target task based on a fine-tuning dataset, prompt fine-tuning dataset indication information can be sent to the terminal.

[0346] For another example, when the terminal supports multiple prompt information, the network side device can select target prompt information from the multiple prompt information and send it to the terminal through the first information, or, when the terminal supports multiple knowledge information, the network side device can select target knowledge information from the multiple knowledge information and send it to the terminal through the first information, or, when the terminal supports multiple fine-tuning data sets, the network side device can select target fine-tuning data set from the multiple fine-tuning data sets and send it to the terminal through the first information.

[0347] In some embodiments, the terminal sends at least one of the fourth information and the first capability information to the network side device during a model registration (or model identification) process or a capability reporting process.

[0348] It should be understood that the fourth information and the first capability information may be reported to the network side device via one signaling, or may be reported to the network side device via different signaling, and this application does not limit this.

[0349] The following describes the AI ​​model-based reasoning method provided by this application in conjunction with the specific embodiments shown in Figures 4 and 5.

[0350] In the example of FIG4 , the first device is a terminal, the second device is an access network device or a core network function, the third device is an access network device or a core network function, and the first model is deployed on the first device.

[0351] As shown in FIG4 , the reasoning method may include the following steps:

[0352] S403: The terminal sends second information to the access network device or the core network function.

[0353] The second information includes requirement information for reasoning with the first model and / or auxiliary information for determining the first information.

[0354] S404: The access network device or the core network function sends first information to the terminal, wherein the first information is determined based on the second information.

[0355] The first information includes at least one of prompt indication information, knowledge indication information, and fine-tuning data set indication information.

[0356] In some embodiments, before S403, the method further includes:

[0357] S401, the terminal may send third information to the access network device or the core network function;

[0358] S402: The terminal receives a first model sent by an access network device or a core network function.

[0359] In the example of FIG5 , the first device is an access network device, the second device is a core network function, the third device is a core network function, and the first model is deployed on the first device.

[0360] As shown in FIG5 , the reasoning method may include the following steps:

[0361] S503: The access network device sends second information to the core network function.

[0362] The second information includes requirement information for reasoning with the first model and / or auxiliary information for determining the first information.

[0363] S504: The core network function sends first information to the access network device, where the first information is determined based on the second information.

[0364] The first information includes at least one of prompt indication information, knowledge indication information, and fine-tuning data set indication information.

[0365] In some embodiments, before S503, the method further includes:

[0366] S501, the access network device may send third information to the core network function;

[0367] S502: The access network device receives a first model sent by the core network function.

[0368] In summary, in an embodiment of the present application, the first device (such as an inference node) can obtain auxiliary information for first model reasoning from an auxiliary inference node, such as prompt indication information, knowledge indication information, fine-tuning data set, etc., so that the inference node can use the first model for reasoning based on the prompt indication information, knowledge indication information, fine-tuning data set, etc., which is conducive to improving the reasoning performance of the model.

[0369] The above text, in combination with Figures 2 to 5, describes in detail the method embodiment of the present application. The following text, in combination with Figures 6 to 11, describes in detail the device embodiment of the present application. It should be understood that the device embodiment and the method embodiment correspond to each other, and similar descriptions can refer to the method embodiment.

[0370] In the embodiment of the present application, the inference method based on the AI ​​model in the communication system provided by the embodiment of the present application can be executed by a communication device. In the embodiment of the present application, the communication device provided by the embodiment of the present application is described by taking the communication device in the communication system executing the inference method based on the AI ​​model in the communication system as an example.

[0371] FIG6 shows a schematic block diagram of a communication device 600 according to an embodiment of the present application. As shown in FIG6 , the communication device 600 includes:

[0372] The processing unit 610 is configured to obtain first information, wherein a first model is deployed on the communication device 600;

[0373] Adapting the first model to a target task based on the first information;

[0374] The first model is a compressed AI model, and the first information includes at least one of the following information:

[0375] Hint instructions, knowledge instructions, and fine-tuning dataset instructions.

[0376] In some embodiments, the prompt indication information includes at least one of the following:

[0377] The chain of thought related to the stated target task;

[0378] Prompt text related to the target task;

[0379] Prompt files related to the target task;

[0380] a prompt code related to the target task;

[0381] Identification of thought chains related to the target task;

[0382] Prompt text labels related to the target task;

[0383] The prompt file identifier related to the target task;

[0384] A prompt code identifier related to the target task;

[0385] The address of the prompt file related to the target task.

[0386] In some embodiments, the knowledge indication information includes at least one of knowledge graph indication information and knowledge vector library indication information;

[0387] The knowledge graph indication information includes at least one of the following:

[0388] The relationships between entities in the knowledge graph;

[0389] Attribute information of entities in the knowledge graph;

[0390] The data structure of the knowledge graph;

[0391] The correlation between entities in the knowledge graph;

[0392] The subject attribute object SPO triple of the sentence in the knowledge graph;

[0393] Knowledge graph file;

[0394] Knowledge graph identification;

[0395] Knowledge graph file address.

[0396] In some embodiments, the fine-tuning dataset indication information is used to indicate input information and label information of the first model, where the input information of the first model is related to the target task.

[0397] In some embodiments, the input information of the first model includes at least one of the following:

[0398] Wireless signal measurement results, perception results, and wireless statistical characteristics.

[0399] In some embodiments, the sensing result is obtained by sensing a wireless signal, or by a third-party device, wherein the third-party device includes at least one of the following:

[0400] Cameras, radars, lidar, global positioning system GPS, inertial measurement unit.

[0401] In some embodiments, the wireless statistical characteristics include at least one of the following:

[0402] Occlusion probability, user status, user behavior, and switching failure rate.

[0403] In some embodiments, the user status includes at least one of the following:

[0404] Registration management state, connection management state, radio resource control RRC connection management state.

[0405] In some embodiments, the user behavior includes at least one of the following:

[0406] Behavior in RRC idle state, behavior in RRC inactive state, and behavior in RRC connected state.

[0407] In some embodiments, the communication device further includes

[0408] a communication unit, configured to receive the first information from a second device;

[0409] The communication device 600 is a terminal, and the second device is an access network device or a core network function; or

[0410] The communication device 600 is an access network device, and the second device is a core network function.

[0411] In some embodiments, the communication device 600 is a terminal, the second device is an access network device, and the first information is carried in at least one of the following signaling: layer 1 signaling, layer 2 signaling, layer 3 signaling, AI layer signaling, and data plane signaling; or

[0412] The communication device 600 is a terminal, the second device is a core network function, and the first information is carried in at least one of the following signaling: non-access layer NAS signaling, AI layer signaling, and data plane signaling.

[0413] In some embodiments, the communication device 600 is a terminal, and the communication device further includes

[0414] a communication unit, configured to send second information to the second device, where the second information includes at least one of the following:

[0415] Requirement information for reasoning with the first model;

[0416] Auxiliary information used to determine the first information;

[0417] Identification information of at least one event that triggers the first device to send the requirement information or the auxiliary information.

[0418] In some embodiments, the first information is determined based on the second information.

[0419] In some embodiments, the auxiliary information for determining the first information includes at least one of the following:

[0420] Identification information of the AI ​​model, function indication of the AI ​​model, characteristic indication of the AI ​​model, and configuration indication of the communication device 600.

[0421] In some embodiments, the requirement information used for reasoning with the first model includes at least one of the following:

[0422] Indication of the target tasks to which the AI ​​model needs to be adapted;

[0423] Service Quality of Experience (QoE) requirements for AI models;

[0424] Business processing latency of AI models;

[0425] The business processing accuracy of the AI ​​model;

[0426] The business computing capacity of AI models;

[0427] The data processing scale of AI models.

[0428] In some embodiments, the communication device 600 is a terminal, the second device is an access network device, and the second information is carried in at least one of the following signaling: layer 1 signaling, layer 2 signaling, layer 3 signaling, AI layer signaling, and data plane signaling; or

[0429] The communication device 600 is a terminal, the second device is a core network function, and the second information is carried in at least one of the following signaling: NAS signaling, AI layer signaling, and data plane signaling.

[0430] In some embodiments, the communication device 600 is a terminal, and the communication device further includes:

[0431] a communication unit, configured to send the second information to the second device when at least one of the following events occurs:

[0432] receiving a first instruction, wherein the first instruction is used to instruct activation or switching of a model;

[0433] The communication device 600 determines to activate or switch a model;

[0434] The communication device 600 determines that the currently used model does not meet the requirements;

[0435] A second indication is received, where the second indication is used to indicate that the currently used model does not meet the requirement.

[0436] In some embodiments, the communication device further includes

[0437] a communication unit, configured to receive the first model sent by a third device;

[0438] The communication device 600 is a terminal, and the third device is an access network device or a core network function or a third-party external server; or

[0439] The communication device 600 is an access network device, and the third device is a core network function or a third-party external server.

[0440] In some embodiments, the communication device further comprises:

[0441] a communication unit, configured to send third information to the third device, wherein the first model is selected based on the third information;

[0442] The third information includes at least one of the following:

[0443] Identification information of the AI ​​model, function indication of the AI ​​model, characteristic indication of the AI ​​model, and configuration indication of the communication device 600.

[0444] In some embodiments, the communication device 600 is a terminal, the third device is an access network device, and the third information or the first model is carried in at least one of the following signaling: layer 1 signaling, layer 2 signaling, layer 3 signaling, data plane signaling, AI layer signaling; or

[0445] The communication device 600 is a terminal, the third device is a core network function, and the third information or the first model is carried in at least one of the following signaling: NAS signaling, data plane signaling, and AI layer signaling.

[0446] In some embodiments, the configuration indication of the communication device 600 is used to indicate at least one of the following:

[0447] Number of transmit antennas, number of transmit beams, number of antenna ports, transmit power, antenna gain, beam 3dB bandwidth, spacing, frequency, and system bandwidth.

[0448] In some embodiments, the communication device 600 is a terminal, and the communication device further includes:

[0449] A communication unit, used to send at least one of fourth information and first capability information to a network side device, wherein the fourth information is used to indicate auxiliary information required by the terminal for reasoning based on the first model, and the first capability information is used to indicate the ability of the terminal to reason based on the first model.

[0450] In some embodiments, the fourth information includes at least one of the following:

[0451] Instruction information for adapting prompts to the target task;

[0452] Indicative information for adapting knowledge to the target task;

[0453] Instructions for fine-tuning a dataset for adapting the target task.

[0454] In some embodiments, the first capability information includes at least one of the following:

[0455] identification information of the first model supported by the terminal;

[0456] whether the terminal supports adapting the first model to the target task based on the prompt information;

[0457] whether the terminal supports adapting the first model to the target task based on a fine-tuning dataset;

[0458] whether the terminal supports adapting the first model to the target task based on knowledge information;

[0459] Indication information of prompts supported by the terminal;

[0460] information indicating the knowledge supported by the terminal;

[0461] Indication information of the fine-tuning datasets supported by the terminal.

[0462] In some embodiments, the communication device 600 is a terminal, and the communication device further includes:

[0463] A communication unit is used to send at least one of the fourth information and the first capability information to the network side device during a model registration process or a capability reporting process.

[0464] Alternatively, in some embodiments, the communication unit may be a communication interface or a transceiver, or an input / output interface of a communication chip or a system on chip. The processing unit may be one or more processors.

[0465] It should be understood that the communication device 600 according to the embodiment of the present application may correspond to the first device in the method embodiment of the present application, and the above-mentioned and other operations and / or functions of each unit in the communication device 600 are respectively for realizing the corresponding processes of the first device in the method embodiment shown in Figures 2 to 5 and achieving the same technical effects. To avoid repetition, they will not be repeated here.

[0466] FIG7 shows a schematic block diagram of a communication device 700 according to an embodiment of the present application. As shown in FIG7 , the communication device 700 includes:

[0467] A communication unit 710 is configured to send first information to a first device, where a first model is deployed on the first device, and the first information is used by the first device to adapt the first model to a target task;

[0468] The first information includes at least one of the following information:

[0469] Hint instructions, knowledge instructions, and fine-tuning dataset instructions.

[0470] In some embodiments, the prompt indication information includes at least one of the following:

[0471] The chain of thought related to the stated target task;

[0472] Prompt text related to the target task;

[0473] Prompt files related to the target task;

[0474] a prompt code related to the target task;

[0475] Identification of thought chains related to the target task;

[0476] Prompt text labels related to the target task;

[0477] The prompt file identifier related to the target task;

[0478] A prompt code identifier related to the target task;

[0479] The address of the prompt file related to the target task.

[0480] In some embodiments, the knowledge indication information includes at least one of knowledge graph indication information and knowledge vector library indication information;

[0481] The knowledge graph indication information includes at least one of the following:

[0482] The relationships between entities in the knowledge graph;

[0483] Attribute information of entities in the knowledge graph;

[0484] The data structure of the knowledge graph;

[0485] The correlation between entities in the knowledge graph;

[0486] The subject attribute object SPO triple of the sentence in the knowledge graph;

[0487] Knowledge graph file;

[0488] Knowledge graph identification;

[0489] Knowledge graph file address.

[0490] In some embodiments, the fine-tuning dataset indication information is used to indicate input information and label information of the first model, where the input information of the first model is related to the target task.

[0491] In some embodiments, the input information of the first model includes at least one of the following:

[0492] Wireless signal measurement results, perception results, and wireless statistical characteristics.

[0493] In some embodiments, the sensing result is obtained by sensing a wireless signal, or by a third-party device, wherein the third-party device includes at least one of the following:

[0494] Cameras, radars, lidar, global positioning system GPS, inertial measurement unit.

[0495] In some embodiments, the wireless statistical characteristics include at least one of the following:

[0496] Occlusion probability, user status, user behavior, and switching failure rate.

[0497] In some embodiments, the user status includes at least one of the following:

[0498] Registration management state, connection management state, radio resource control RRC connection management state.

[0499] In some embodiments, the user behavior includes at least one of the following:

[0500] Behavior in RRC idle state, behavior in RRC inactive state, and behavior in RRC connected state.

[0501] In some embodiments, the first device is a terminal, the communication apparatus 700 is an access network device, and the first information is carried in at least one of the following signaling: layer 1 signaling, layer 2 signaling, layer 3 signaling, AI layer signaling, and data plane signaling; or

[0502] The first device is a terminal, the communication device 700 is a core network function, and the first information is carried in at least one of the following signaling: non-access layer NAS signaling, AI layer signaling, and data plane signaling.

[0503] In some embodiments, the first device is a terminal, and the communication unit is further configured to:

[0504] receiving second information sent by the first device, where the second information includes at least one of the following:

[0505] Requirement information for reasoning with the first model;

[0506] Auxiliary information used to determine the first information;

[0507] Identification information of at least one event that triggers the first device to send the requirement information or the auxiliary information.

[0508] In some embodiments, the first information is determined based on the second information.

[0509] In some embodiments, the auxiliary information used to determine the first information includes at least one of the following:

[0510] Identification information of the AI ​​model, function indication of the AI ​​model, characteristic indication of the AI ​​model, and configuration indication of the first device.

[0511] In some embodiments, the requirement information used for reasoning with the first model includes at least one of the following:

[0512] Indication of the target tasks to which the AI ​​model needs to be adapted;

[0513] Service Quality of Experience (QoE) requirements for AI models;

[0514] Business processing latency of AI models;

[0515] The business processing accuracy of the AI ​​model;

[0516] The business computing capacity of AI models;

[0517] The data processing scale of AI models.

[0518] In some embodiments, the first device is a terminal, the communication apparatus 700 is an access network device, and the second information is carried in at least one of the following signaling: layer 1 signaling, layer 2 signaling, layer 3 signaling, AI layer signaling, and data plane signaling; or

[0519] The first device is a terminal, the communication device 700 is a core network function, and the second information is carried in at least one of the following signaling: NAS signaling, AI layer signaling, and data plane signaling.

[0520] Optionally, in some embodiments, the communication unit may be a communication interface or a transceiver, or an input / output interface of a communication chip or a system on chip.

[0521] It should be understood that the communication device 700 for signal forwarding according to the embodiment of the present application may correspond to the second device in the method embodiment of the present application, and the above-mentioned and other operations and / or functions of each unit in the communication device 700 are respectively for realizing the corresponding processes of the second device in the method embodiment shown in Figures 2 to 5 and achieving the same technical effects. To avoid repetition, they will not be repeated here.

[0522] In some embodiments, the apparatus 600 and apparatus 700 in the embodiments of the present application may be electronic devices, such as electronic devices with an operating system, or components in electronic devices, such as integrated circuits or chips. The electronic device may be a terminal, or may be other devices other than a terminal. For example, the terminal may include but is not limited to the types of terminal 11 listed above, and other devices may be servers, network attached storage (NAS), etc., which are not specifically limited in the embodiments of the present application.

[0523] As shown in Figure 8, an embodiment of the present application also provides a communication device 1000, including a processor 1001 and a memory 1002, and the memory 1002 stores a program or instruction that can be run on the processor 1001. For example, when the communication device 1000 is a first device, the program or instruction is executed by the processor 1001 to implement the steps performed by the first device in the above-mentioned reasoning method embodiment, and can achieve the same technical effect. For example, when the communication device 1000 is a second device, the program or instruction is executed by the processor 1001 to implement the steps performed by the second device in the above-mentioned reasoning method embodiment, and can achieve the same technical effect. For example, when the communication device 1000 is a third device, the program or instruction is executed by the processor 1001 to implement the steps performed by the third device in the above-mentioned reasoning method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0524] The present application also provides a terminal including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is configured to execute a program or instruction to implement the steps of the method embodiments shown in Figures 2 to 5. This terminal embodiment corresponds to the aforementioned terminal-side method embodiment, and each implementation process and implementation method of the aforementioned method embodiment is applicable to this terminal embodiment and can achieve the same technical effects. Specifically, Figure 9 is a schematic diagram of the hardware structure of a terminal implementing an embodiment of the present application.

[0525] The terminal 1100 includes but is not limited to: a radio frequency unit 1101, a network module 1102, an audio output unit 1103, an input unit 1104, a sensor 1105, a display unit 1106, a user input unit 1107, an interface unit 1108, a memory 1109 and at least some of the components of the processor 1110.

[0526] Those skilled in the art will appreciate that the terminal 1100 may also include a power supply (such as a battery) to power various components. The power supply may be logically connected to the processor 1110 via a power management system, thereby enabling the power management system to manage charging, discharging, and power consumption. The terminal structure shown in FIG9 does not limit the terminal. The terminal may include more or fewer components than shown, or may combine certain components, or have different component arrangements, which will not be described in detail here.

[0527] It should be understood that in an embodiment of the present application, the input unit 1104 may include a graphics processing unit (GPU) 11041 and a microphone 11042, and the graphics processor 11041 processes the image data of a static picture or video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 1106 may include a display panel 11061, and the display panel 11061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 1107 includes a touch panel 11071 and at least one of other input devices 11072. The touch panel 11071 is also called a touch screen. The touch panel 11071 may include two parts: a touch detection device and a touch controller. Other input devices 11072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which will not be repeated here.

[0528] In the embodiment of the present application, after receiving downlink data from a network-side device, the RF unit 1101 may transmit the data to the processor 1110 for processing. Furthermore, the RF unit 1101 may send uplink data to the network-side device. Typically, the RF unit 1101 includes, but is not limited to, an antenna, an amplifier, a transceiver, a coupler, a low-noise amplifier, a duplexer, and the like.

[0529] The memory 1109 can be used to store software programs or instructions and various data. The memory 1109 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, applications or instructions required for at least one function (such as a sound playback function, an image playback function, etc.). In addition, the memory 1109 may include a volatile memory or a non-volatile memory. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DRRAM). The memory 1109 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

[0530] Processor 1110 may include one or more processing units. Optionally, processor 1110 integrates an application processor and a modem processor. The application processor primarily handles operations related to the operating system, user interface, and application programs, while the modem processor primarily processes wireless communication signals, such as a baseband processor. It is understood that the modem processor may not be integrated into processor 1110.

[0531] It can be understood that the implementation process of each implementation method mentioned in this embodiment can refer to the relevant description of the method embodiments shown in Figures 2 to 5, and achieve the same or corresponding technical effects. To avoid repetition, they will not be repeated here.

[0532] The present application also provides a network-side device, including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is configured to execute a program or instruction to implement the steps of the method embodiments shown in Figures 2 to 5. This network-side device embodiment corresponds to the above-mentioned access network device-side or core network function-side method embodiments, and each implementation process and implementation method of the above-mentioned method embodiments are applicable to this network-side device embodiment and can achieve the same technical effects.

[0533] Specifically, embodiments of the present application also provide a network-side device. As shown in Figure 10, the network-side device 1200 includes an antenna 1201, a radio frequency device 1202, a baseband device 1203, a processor 1204, and a memory 1205. Antenna 1201 is connected to radio frequency device 1202. In the uplink direction, radio frequency device 1202 receives information via antenna 1201 and sends the received information to baseband device 1203 for processing. In the downlink direction, baseband device 1203 processes the information to be transmitted and sends it to radio frequency device 1202. Radio frequency device 1202 processes the received information and then sends it through antenna 1201.

[0534] The method executed by the network-side device in the above embodiment may be implemented in the baseband device 1203 , which includes a baseband processor.

[0535] The baseband device 1203 may, for example, include at least one baseband board, on which multiple chips are arranged, as shown in Figure 10, one of which is, for example, a baseband processor, which is connected to the memory 1205 through a bus interface to call the program in the memory 1205 and execute the network device operations shown in the above method embodiment.

[0536] The network side device may further include a network interface 1206 , which is, for example, a Common Public Radio Interface (CPRI).

[0537] Specifically, the network side device 1200 of the embodiment of the present application also includes: instructions or programs stored in the memory 1205 and executable on the processor 1204. The processor 1204 calls the instructions or programs in the memory 1205 to execute the methods executed by the modules shown in Figures 6 to 7 and achieve the same technical effects. To avoid repetition, they will not be elaborated here.

[0538] Specifically, the embodiment of the present application further provides a network-side device. As shown in FIG11 , the network-side device 1300 includes a processor 1301, a network interface 1302, and a memory 1303. The network interface 1302 is, for example, a common public radio interface (CPRI).

[0539] Specifically, the network side device 1300 of an embodiment of the present invention also includes: instructions or programs stored in the memory 1303 and executable on the processor 1301. The processor 1301 calls the instructions or programs in the memory 1303 to execute the methods executed by the modules shown in Figures 6 to 7 and achieve the same technical effects. To avoid repetition, they will not be elaborated here.

[0540] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the embodiment of the reasoning method based on the AI ​​model in the above-mentioned communication system are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0541] The processor is a processor in the communication device, communication equipment, terminal, or network-side device described in the above embodiments. The readable storage medium includes a computer-readable storage medium, such as a computer read-only memory (ROM), random access memory (RAM), a magnetic disk, or an optical disk. In some examples, the readable storage medium may be a non-transitory readable storage medium.

[0542] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the embodiment of the reasoning method based on the AI ​​model in the above-mentioned communication system, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0543] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0544] An embodiment of the present application further provides a computer program / program product, which is stored in a storage medium and is executed by at least one processor to implement the various processes of the embodiment of the AI ​​model-based reasoning method in the above-mentioned communication system, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0545] An embodiment of the present application also provides a communication system, including: a first device, a second device, and a third device, wherein the first device can be used to execute the steps performed by the first device in the AI ​​model-based reasoning method in the communication system as described above, the second device can be used to execute the steps performed by the second device in the AI ​​model-based reasoning method in the communication system as described above, and the third device can be used to execute the steps performed by the third device in the AI ​​model-based reasoning method in the communication system as described above.

[0546] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0547] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of a computer software product plus a necessary general-purpose hardware platform, or of course, by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disk, etc.) and includes a number of instructions for enabling a terminal or network-side device to execute the methods described in each embodiment of the present application.

[0548] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms of implementation methods without departing from the purpose of this application and the scope of protection of the claims. These implementation methods are all within the protection of this application.

Claims

1. A reasoning method based on an artificial intelligence (AI) model, comprising: A first device acquires first information associated with a target task, wherein a first model is deployed on the first device; Adapting the first model to a target task according to the first information; The first information includes at least one of the following information: prompt indication information, knowledge indication information, and fine-tuning data set indication information.

2. The method according to claim 1, wherein: The prompt indication information includes at least one of the following: The chain of thoughts related to the stated goal task; Prompt text related to the target task; Prompt files related to the target task; a prompt code associated with the target task; Identification of thought chains related to the target task; Prompt text labels related to the target task; The reminder file identifier related to the target task; A prompt code identifier related to the target task; The address of the prompt file related to the target task.

3. The method according to claim 1 or 2, wherein: The knowledge indication information includes at least one of knowledge graph indication information and knowledge vector library indication information; The knowledge graph indication information includes at least one of the following: The relationships between entities in the knowledge graph; Attribute information of entities in the knowledge graph; The data structure of the knowledge graph; The correlation between entities in the knowledge graph; The subject attribute object SPO triple of the sentence in the knowledge graph; Knowledge graph files; Knowledge graph identification; Knowledge graph file address.

4. The method according to any one of claims 1 to 3, wherein: The fine-tuning dataset indication information is used to indicate input information and label information of the first model, where the input information of the first model is related to the target task; The input information of the first model includes at least one of the following: Measurement results, perception results, and wireless statistical characteristics of wireless signals; The sensing result is obtained by sensing the wireless signal, or by a third-party device, wherein the third-party device includes at least one of the following: Cameras, radars, lidar, global positioning system GPS, inertial measurement units; The wireless statistical characteristics include at least one of the following: Occlusion probability, user status, user behavior, switching failure rate; The user status includes at least one of the following: Registration management status, connection management status, radio resource control RRC connection management status; The user behavior includes at least one of the following: Behavior in RRC idle state, behavior in RRC inactive state, and behavior in RRC connected state.

5. The method according to any one of claims 1 to 4, wherein: The first device acquires first information, including: The first device receives the first information from the second device; The first device is a terminal, and the second device is an access network device or a core network function; or The first device is an access network device, and the second device is a core network function.

6. The method according to claim 5, wherein: The method further comprises: The first device sends second information to the second device, where the second information includes at least one of the following: Requirement information for performing reasoning on the first model; Auxiliary information used to determine the first information; identification information of at least one event that triggers the first device to send the requirement information or the auxiliary information; The auxiliary information used to determine the first information includes at least one of the following: Identification information of the AI ​​model, a function indication of the AI ​​model, a characteristic indication of the AI ​​model, and a configuration indication of the first device; The requirement information used for the first model to perform reasoning includes at least one of the following: Indication of target tasks that the AI ​​model needs to adapt to; Service quality of experience (QoE) requirements for AI models; Business processing latency of AI models; The accuracy of AI model’s business processing; The business computing volume of AI models; The data processing scale of AI models.

7. The method according to claim 6, wherein: The first device is a terminal, and the first device sends second information to the second device, including: When at least one of the following events occurs, sending the second information to the second device: A first indication is received, where the first indication is used to instruct activation or switching of a model; The first device determines to activate or switch a model; The first device determines that the currently used model does not meet the requirements; A second indication is received, where the second indication is used to indicate that the currently used model does not meet the requirement.

8. The method according to claim 6, wherein: The configuration indication of the first device is used to indicate at least one of the following: Number of transmit antennas, number of transmit beams, number of antenna ports, transmit power, antenna gain, beam 3dB bandwidth, spacing, frequency, and system bandwidth.

9. The method according to any one of claims 1 to 8, wherein: When the first device is a terminal, the method further includes: The terminal sends at least one of fourth information and first capability information to the network side device, wherein the fourth information is used to indicate auxiliary information required for the terminal to perform reasoning based on the first model, and the first capability information is used to indicate the ability of the terminal to perform reasoning based on the first model.

10. The method according to claim 9, wherein: The fourth information includes at least one of the following: Indicative information for adapting prompts for the target task; Indicative information for adapting the knowledge of the target task; Indicative information of a fine-tuning dataset adapted to the target task.

11. The method according to claim 9 or 10, wherein: The first capability information includes at least one of the following: identification information of the first model supported by the terminal; Whether the terminal supports adapting the first model to the target task based on the prompt information; Whether the terminal supports adapting the first model to the target task based on a fine-tuning dataset; whether the terminal supports adapting the first model to the target task based on knowledge information; Indicative information of prompts supported by the terminal; Indicative information of knowledge supported by the terminal; Indicative information of the fine-tuning datasets supported by the terminal.

12. The method according to any one of claims 9 to 11, wherein: The terminal sends at least one of the fourth information and the first capability information to the network side device, including: The terminal sends at least one of the fourth information and the first capability information to the network side device during a model registration process or a capability reporting process.

13. A reasoning method based on an artificial intelligence (AI) model, comprising: The second device sends first information to the first device, the first model is deployed on the first device, and the first information is used by the first device to adapt the first model to the target task; The first information includes at least one of the following information: Hint instructions, knowledge instructions, fine-tuning dataset instructions.

14. A communication device, comprising: a processing unit, configured to obtain first information, wherein a first model is deployed on the communication device; Adapting the first model to a target task according to the first information; The first information includes at least one of the following information: prompt indication information, knowledge indication information, and fine-tuning data set indication information.

15. A communication device, comprising: A communication unit, configured to send first information to a first device, on which a first model is deployed, and the first information is used by the first device to adapt the first model to a target task; The first information includes at least one of the following information: Hint instructions, knowledge instructions, fine-tuning dataset instructions.

16. A communication device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 12 or the steps of the method according to claim 13 are implemented.

17. A readable storage medium storing a program or an instruction, wherein the program or the instruction, when executed by a processor, implements the steps of the method according to any one of claims 1 to 12, or the steps of the method according to claim 13.

18. A chip, wherein: The chip includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the method according to any one of claims 1 to 13.

19. A computer program product, wherein: The program product is executed by at least one processor to implement the method according to any one of claims 1 to 13.

20. An electronic device, configured to execute the method according to any one of claims 1 to 13.

Images