Wireless communication method and communication equipment

Abstract

Provided are a wireless communication method and a communication device, the method comprising: a first device sends first information to a second device, the first information being used to authorize the second device to send a query request for a first model; in the application, the first device authorizes the second device to send the query request for the first model through the first information, so that the opportunity of querying the first model by the second device is limited, and the second device can be prevented from stealing the first model through a large amount of malicious queries.

Description

Wireless communication method and communication device Technical Field

[0001] The present application relates to the field of communication technology, and more specifically to a wireless communication method and communication device. Background Art

[0002] Artificial intelligence / machine learning (AI / ML) models are widely used in wireless communication systems. Typically, AI / ML models are trained on certain devices and then made available to other devices. However, providing models to other devices can pose risks of exposing them. For example, certain devices could potentially steal models by flooding them with malicious queries. Therefore, preventing model theft while other devices are using them remains an unresolved issue.

[0003] Summary of the Invention

[0004] The present application provides a wireless communication method and a communication device. The following introduces various aspects involved in the present application.

[0005] In a first aspect, a wireless communication method is provided, including: a first device sending first information to a second device, where the first information is used to authorize the second device to send a query request for a first model.

[0006] In a second aspect, a wireless communication method is provided, including: a second device receives first information sent by a first device, where the first information is used to authorize the second device to send a query request for a first model.

[0007] According to a third aspect, a communication device is provided, which is a first device and includes: a communication module for sending first information to a second device, where the first information is used to authorize the second device to send a query request for a first model.

[0008] In a fourth aspect, a communication device is provided, which is a second device and includes: a communication module for receiving first information sent by a first device, where the first information is used to authorize the second device to send a query request for a first model.

[0009] In a fifth aspect, a communication device is provided, which is a first device and includes a memory, a processor and a transceiver, the memory is used to store programs, the processor is used to call the programs in the memory, and the transceiver is used to send first information to a second device, and the first information is used to authorize the second device to send a query request for the first model.

[0010] In the sixth aspect, a communication device is provided, which is a second device and includes a memory, a processor and a transceiver, the memory is used to store programs, the processor is used to call the programs in the memory, and the transceiver is used to receive first information sent by the first device, and the first information is used to authorize the second device to send a query request for the first model.

[0011] In a seventh aspect, a device is provided, comprising a processor for calling a program from a memory so that the device executes the method as described in the first aspect or the second aspect.

[0012] In an eighth aspect, a chip is provided, comprising a processor for calling a program from a memory so that a device equipped with the chip executes the method described in the first aspect or the second aspect.

[0013] In a ninth aspect, a computer-readable storage medium is provided, on which a program is stored, wherein the program enables a computer to execute the method as described in the first aspect or the second aspect.

[0014] In a tenth aspect, a computer program product is provided, comprising a program, wherein the program enables a computer to execute the method as described in the first aspect or the second aspect.

[0015] In an eleventh aspect, a computer program is provided, wherein the computer program enables a computer to execute the method as described in the first aspect or the second aspect.

[0016] In this application, the first device authorizes the second device to send a query request for the first model through the first information, which limits the second device's opportunity to query the first model and helps prevent the second device from stealing the first model through a large number of malicious queries. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] FIG1 is a schematic structural diagram of a wireless communication system to which an embodiment of the present application is applicable.

[0018] Figure 2 is a schematic diagram of the structure of an artificial neural network.

[0019] Figure 3 is an example diagram of the AI / ML model lifecycle.

[0020] 4A and 4B are schematic flow charts of the downlink beam scanning process.

[0021] FIG5 is a schematic flowchart of a positioning service based on an AI / ML model.

[0022] FIG6 is a schematic flow chart of the model obfuscation technique.

[0023] FIG7 is a schematic flowchart of a wireless communication method provided in an embodiment of the present application.

[0024] 8A to 8D are diagrams showing examples of the bit structure of the first information.

[0025] FIG9 is an example diagram of a wireless communication method provided in an embodiment of the present application.

[0026] FIG10 is a schematic flowchart of a wireless communication method provided in another embodiment of the present application.

[0027] FIG11 is a schematic flowchart of a wireless communication method provided in another embodiment of the present application.

[0028] FIG12 is a schematic flowchart of a wireless communication method provided in another embodiment of the present application.

[0029] FIG13 is a schematic flowchart of a wireless communication method provided in another embodiment of the present application.

[0030] FIG14 is a schematic structural diagram of the first device provided in an embodiment of the present application.

[0031] FIG15 is a schematic structural diagram of the second device provided in an embodiment of the present application.

[0032] FIG16 is a schematic diagram of the structure of a communication device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0033] The technical solution in this application will be described below with reference to the accompanying drawings.

[0034] Communication system architecture

[0035] FIG1 is a diagram illustrating an exemplary system architecture of a wireless communication system 100 to which embodiments of the present application may be applied. The wireless communication system 100 may include a network device 110 and a terminal device 120. The network device 110 may be a device that communicates with the terminal device 120. The network device 110 may provide communication coverage for a specific geographic area and may communicate with the terminal device 120 within the coverage area.

[0036] FIG1 exemplarily shows a network device and a terminal device. Optionally, the wireless communication system 100 may include one or more network devices 110 and / or one or more terminal devices 120. For a network device 110, the one or more terminal devices 120 may all be located within the network coverage of the network device 110, or all be located outside the network coverage of the network device 110, or some may be located within the coverage of the network device 110 and others outside the network coverage of the network device 110. This is not limited in the embodiments of the present application.

[0037] Optionally, the wireless communication system 100 may further include other network entities such as a network controller and a mobility management entity, which is not limited in the embodiment of the present application.

[0038] It should be understood that the technical solutions of the embodiments of the present application can be applied to various communication systems, such as: fifth generation (5G) system or new radio (NR) system, long term evolution (LTE) system, LTE frequency division duplex (FDD) system, LTE time division duplex (TDD) system, etc. The technical solutions provided in this application can also be applied to future communication systems, such as the sixth generation mobile communication system, satellite communication system, etc.

[0039] The terminal device in the embodiments of the present application may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station (MS), mobile terminal (MT), remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device. The terminal device in the embodiments of the present application may refer to a device that provides voice and / or data connectivity to a user and can be used to connect people, objects and machines, such as a handheld device with wireless connection function, a vehicle-mounted device, etc. The terminal device in the embodiments of the present application can be a mobile phone, a tablet computer, a laptop computer, a PDA, a mobile internet device (MID), a wearable device, a virtual reality (VR) device, an augmented reality (AR) device, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical surgery, a wireless terminal in a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, a wireless terminal in a smart home, etc. Optionally, the UE can be used to act as a base station. For example, the UE can act as a scheduling entity that provides sidelink signals between UEs in vehicle-to-everything (V2X) or device-to-device (D2D). For example, a cellular phone and a car communicate with each other using sidelink signals. The cellular phone and smart home devices communicate without relaying the communication signal through the base station.

[0040] The network device in the embodiments of the present application may be a device for communicating with a terminal device, and may also be referred to as an access network device or a radio access network device. For example, the network device may be a base station. The network device in the embodiments of the present application may refer to a radio access network (RAN) node (or device) that connects a terminal device to a wireless network. A base station can broadly cover various names as follows, or be replaced with the following names, such as: NodeB, evolved NodeB (eNB), next generation NodeB (gNB), relay station, access point, transmission point (TRP), transmission point (TP), master station MeNB, secondary station SeNB, multi-standard radio (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), positioning node, etc. A base station can be a macro base station, a micro base station, a relay node, a donor node or the like, or a combination thereof. A base station can also refer to a communication module, modem or chip used to be set in the aforementioned device or apparatus. The base station can also be a mobile switching center and a device that performs base station functions in device-to-device (D2D), V2X, and machine-to-machine (M2M) communications, a network-side device in a 6G network, or a device that performs base station functions in future communication systems. The base station can support networks with the same or different access technologies. The embodiments of this application do not limit the specific technology and specific device form used by the network device.

[0041] Base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move based on the location of the mobile base station. In other examples, a helicopter or drone can be configured to act as a device that communicates with another base station.

[0042] In some deployments, the network device in the embodiments of the present application may refer to a CU or a DU, or the network device may include a CU and a DU. The gNB may also include an AAU.

[0043] The network equipment and terminal devices can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; they can also be deployed in the air on aircraft, balloons, and satellites. The embodiments of this application do not limit the scenarios in which the network equipment and terminal devices are located.

[0044] AI / ML models

[0045] In recent years, artificial intelligence research, exemplified by neural networks (NNs), has achieved remarkable success in numerous fields. In particular, AI / ML models, a key research direction in AI technology, leverage the nonlinear processing capabilities of NNs to successfully solve a range of challenging problems. They have even demonstrated superior performance to humans in areas such as image recognition, speech processing, natural language processing, and gaming, and have therefore garnered increasing attention. Furthermore, AI / ML models offer new avenues for solving problems in the communications field. Existing research demonstrates their significant potential in complex and unknown environment modeling and learning, channel prediction, intelligent signal generation and processing, network status tracking and intelligent scheduling, and network optimization and deployment. Therefore, AI / ML models are expected to promote the evolution of future communications paradigms and transform network architectures, and are of great significance and value to the research of communications technology.

[0046] Artificial neural networks are a common AI / ML model. They can create models based on training data, enabling more accurate predictions. As shown in Figure 2, artificial neural networks typically employ a multi-layer design. By training these multi-layered neural networks layer by layer to learn features, they can significantly enhance their learning and processing capabilities. Consequently, artificial neural networks are widely used in pattern recognition, signal processing, optimization and combination, and anomaly detection.

[0047] The AI / ML model lifecycle can be illustrated in Figure 3, consisting of seven main phases. The first phase is business goal determination, which involves defining the problem the model aims to solve. The second phase is data collection and exploration, where relevant data for model training is collected based on the business goals. The third phase is data processing and feature engineering, which includes data cleaning, splitting the data into training, validation, and test sets, and the feature engineering process of transforming the data. The fourth phase is model training, where different models and training datasets are tested, the appropriate model is selected, and its hyperparameters are fine-tuned for optimal performance. The fifth phase is model testing and validation, where the model is checked against various evaluation metrics (such as accuracy) to ensure that its predictive performance is sufficient for the use case. The sixth phase is model deployment, where the selected and fine-tuned model is deployed for prediction. Model deployment types can include online, batch, and embedded deployment. The seventh phase is model monitoring, where the performance of the deployed model is monitored to ensure it performs well over time.

[0048] Application of AI / ML models

[0049] Beam management is a typical application scenario for AI / ML models in NR systems (AI beam management). AI / ML models help reduce overhead and latency during beam management. Beam management can be divided into uplink and downlink beam management. The following briefly introduces the beam management mechanism, using downlink beam management as an example.

[0050] Downlink beam management may include downlink beam scanning, UE optimal beam reporting, network (NW) indication of downlink beams, and other processes. The downlink beam scanning process may be shown in FIG4 . In FIG4A , the NW scans different transmit beam directions through the synchronization signal and physical broadcast channel block (SSB) and / or channel state information reference signal (CSI-RS) in the downlink reference signal. In FIG4B , the UE may use different receive beams for measurement, so that it may traverse all beam pair combinations and calculate their physical layer reference signal received power (L1-RSRP) values. In the UE optimal beam reporting process, the UE selects the K transmit beams with the highest L1-RSRP by comparing the L1-RSRP values ​​of all measured beam pairs, and then reports them to the NW as uplink control information. Here, L1-RSRP can also be replaced with other beam link indicators, such as the physical layer signal to interference noise ratio (L1-SINR) or the physical layer reference signal received quality (L1-RSRQ). After decoding the UE's beam report, the NW can use medium access control (MAC) or downlink control information (DCI) signaling to carry the transmission configuration indicator (TCI) status (including the transmit beam with SSB or CSI-RS as the reference) to complete the beam indication to the UE. Based on the NW's indication, the UE uses the receive beam corresponding to the transmit beam for reception.

[0051] In the above-mentioned beam management, the AI / ML model can be used to predict the optimal beam to reduce overhead and latency. The AI / ML model can be used for spatial domain beam prediction and time domain beam prediction. Specifically, the AI / ML model can implement beam prediction on beam set A through the measurement results of beam set B. Set B can be a subset of set A, and set B and set A can also be different beam sets (for example, set A uses a narrow beam and set B uses a wide beam). The measurement results on set B can be L1-RSRP, or other auxiliary information, such as beam (pair) identity (ID). When performing beam prediction, the AI / ML model can be deployed on the NW side or on the UE side.

[0052] Positioning is also a typical application scenario for AI / ML models in NR systems (AI positioning). AI / ML models can achieve higher-precision positioning. Currently, the consumer market, such as shopping guides in shopping malls, reverse car search in parking lots, family member prevention, and self-guided exhibition hall tours, as well as vertical industries such as crowd monitoring and analysis, smart warehousing and logistics, intelligent manufacturing, emergency rescue, personnel and asset management, and service robots, all require higher-precision positioning services. High-precision positioning is particularly challenging in complex environments such as non-line of sight (NLOS). However, AI / ML models provide new approaches to solving high-precision positioning problems in complex environments like NLOS.

[0053] AI / ML models can be applied to positioning calculations to improve positioning accuracy and efficiency. For example, as shown in Figure 5, users can feed base station-to-user channel measurement information back to a positioning server, which then uses this information as input to the AI / ML positioning model to determine the user's specific location coordinates. It's worth noting that the AI / ML model used for positioning can also be deployed on the UE side without significantly impacting the model's algorithmic nature.

[0054] Security of AI / ML models

[0055] AI / ML models provide significant benefits for communication systems, but their application also presents certain security challenges. Typical AI / ML system security issues include software and hardware security, data integrity, model confidentiality, model robustness, and data privacy. Software and hardware security refers to the potential for vulnerabilities in AI / ML systems at the software and hardware levels, which attackers can exploit to attack the system. Data integrity refers to the ability of attackers to inject malicious data or noise during the training phase, impacting the AI / ML model's reasoning capabilities. Data confidentiality refers to the use of models. Model providers often prefer to only provide model query services without disclosing the trained models. However, through repeated queries, attackers can construct a similar model and obtain relevant information about the model. Model robustness refers to the lack of sample coverage during model training, which can lead to a lack of robustness and inability to accurately judge malicious samples. Data privacy refers to the possibility that, even in scenarios where users provide training data, attackers can obtain users' private information by repeatedly querying the trained model.

[0056] The primary sources of these security issues are specific attacks targeting AI / ML systems, such as adversarial example attacks, data poisoning, model theft (model extraction), and AI attacks. Adversarial example attacks involve adding subtle, often undetectable perturbations to a model's input, causing the model to produce an erroneous output with high confidence. Data poisoning involves adding carefully constructed anomalous data to model training data, disrupting the original training data's probability distribution and causing the model to misclassify or cluster under certain conditions. Model theft (model extraction) involves sending inference requests to a target model to execute a large number of queries and using the responses to train another model with the same or similar functionality. Alternatively, reverse engineering techniques can be used to construct a similar model, obtain its internal parameters, or construct a similar replacement model. AI attacks are typical attacks on machine learning systems, impacting data confidentiality and the integrity of data and computations. Other forms of attack can also lead to denial of service, information leakage, or invalid computations.

[0057] To address the aforementioned security challenges, certain security measures can be implemented to protect AI / ML models. The security protection of AI / ML models can be categorized into two aspects: static protection and dynamic protection. Static protection refers to the protection of the model during transmission and storage. Currently, the industry generally adopts a model protection solution based on file encryption. AI / ML model files are transmitted and stored in ciphertext form and decrypted in memory before inference execution. With static protection, the model remains in plaintext in memory during inference, posing the risk of being dumped from memory by an adversary. Dynamic protection refers to the protection of the model at runtime, that is, protecting the model during inference. There are three main technical approaches for dynamic protection: a model protection solution based on a trusted execution environment (TEE), a protection solution based on secret computing, and a model protection solution based on obfuscation.

[0058] A TEE typically refers to a "secure zone" isolated by trusted hardware. AI model files are encrypted, stored, and transmitted in a non-secure zone, and decrypted and executed in the secure zone. This solution offers low inference latency on the central processing unit (CPU), but relies on specific trusted hardware, making deployment challenging. Furthermore, hardware resource constraints make it difficult to protect large-scale deep models, and currently, heterogeneous hardware acceleration is not effectively supported. Protection solutions based on secret state computation rely on cryptographic methods (such as homomorphic encryption and multi-party secure computation) to ensure that the model remains encrypted during transmission, storage, and execution. This solution does not rely on specific hardware, but it incurs significant computational or communication overhead and cannot protect model structural information. Model protection solutions based on obfuscation offer low performance overhead and minimal accuracy loss. Furthermore, they do not rely on specific hardware and can support the protection of large models. Obfuscation-based model protection solutions primarily scramble the model's computational logic, rendering it incomprehensible even to an adversary who gains access to the model during transmission and storage. A typical model obfuscation technique is shown in Figure 6. This technique automatically obfuscates the computational logic of a plaintext AI / ML model, rendering it incomprehensible even to an attacker who gains access to the model during transmission and storage. Furthermore, it supports model obfuscation execution, ensuring confidentiality during model runtime without affecting the original inference results of the model and requiring only minimal inference performance overhead.

[0059] Among the aforementioned security challenges, model confidentiality is currently a major concern. Designing and training AI / ML models requires significant investment in time, data, and computing power. Therefore, protecting model intellectual property (including information such as model structure and parameters) and preventing model theft during operation, transmission, and storage during deployment are crucial. While these security measures can, to a certain extent, prevent model theft during operation, transmission, and storage, they cannot prevent model users from stealing models through large numbers of malicious queries.

[0060] Model monitoring during the AI / ML model lifecycle can, to a certain extent, detect malicious queries involved in model theft. However, model monitoring has a small temporal granularity, and long-term monitoring requires significant resource overhead, which is difficult for communication systems to support. Therefore, model monitoring generally lacks real-time awareness of model performance, and thus cannot promptly detect malicious query attacks. Alternatively, a large number of malicious queries can be countered by requiring the model owner to process only one query within a certain period of time. However, some models have large input data dimensions. When subjected to model theft attacks, even if the model owner does not process the corresponding query, a large amount of input data will still be sent from the attacking device. This invalid data transmission consumes a significant amount of air interface resource overhead. Therefore, how to effectively prevent model users from stealing models through large numbers of malicious queries remains an unresolved issue.

[0061] Based on this, the wireless communication method provided in the embodiment of the present application is described in detail below in conjunction with Figure 7. For ease of understanding, the first device and the second device are used below to represent devices applicable to this method. Among them, the first device may be the owner of the first model, for example, a terminal device or a network device that trains the first model. The second device may be a user of the first model, for example, a terminal device, a network device or other device that has a query requirement for the first model. The terminal device and / or network device here may be any of the terminal devices and / or network devices described above. The other devices here may be devices other than terminal devices and network devices that have a query requirement for the first model, such as a server. The model type of the first model is not specifically limited, and the first model may be the AI / ML model described above. The first model can be used to perform services in a wireless communication system, such as beam prediction services or positioning services.

[0062] Referring to Figure 7, in step S710, the first device sends the first information to the second device. The first information can be used to authorize the second device to send a query request for the first model, where the query request can be a query for the first model. After receiving the first information, the second device can initiate a query request for the first model. The first model can be deployed at the first device, or the first model can also be deployed at the second device. Then the query request of the second device for the first model can be initiated to the first device, or the query request of the second device for the first model can also be initiated to the second device.

[0063] In this application, the first device authorizes the second device to send a query request for the first model through the first information, which limits the second device's opportunity to query the first model and helps prevent the second device from stealing the first model through a large number of malicious queries.

[0064] The first information is described in detail below. The first information may include the number of query requests allowed and / or the decryption information of the first model. The number of query requests allowed can be used to limit the number of times a second device can query the first model, preventing the second device from maliciously querying the first model in a short period of time to steal the model. The decryption information of the first model may be key information used for model decryption. Based on the decryption information, the second device can decrypt the encrypted first model to perform a model query.

[0065] Furthermore, in the case where the first model is deployed on the second device, the first information may include decryption information. As an example, the first device may deploy the first model on the second device in an encrypted manner, and the second device then needs the decryption information of the first device to query the first model. Based on this, the second device can be restricted from querying the first model deployed locally, thereby helping to prevent the second device from stealing the first model deployed locally. The encryption method of the first model may be the static protection method described above, such as deploying the first model on the second device by encrypting the file. Furthermore, the first device may also deploy the first model on the second device by combining dynamic protection and encryption. For example, the first model may be a model that has undergone model obfuscation and is then deployed on the second device in an encrypted manner. Then, when the first model is running on the second device, the second device cannot understand the logic of the first model, which helps to prevent the first model deployed on the second device from being stolen during operation.

[0066] The first information may be sent multiple times, and the time interval between two adjacent transmissions of the first information may be determined based on the first time interval. Furthermore, the first time interval may be the minimum time interval between two adjacent transmissions of the first information, that is, the time interval between two adjacent transmissions of the first information is not less than the first time interval. The first device may limit the frequency of sending the first information based on the first time interval, thereby limiting the frequency of querying the first model by the second device, which helps to increase the difficulty of model theft and reduce the air interface resource overhead caused by model theft. Furthermore, the first information may be periodic, that is, the time interval between two adjacent transmissions of the first information may be fixed. Of course, the first information may also be non-periodic, and this application does not limit this.

[0067] The first time interval may be determined based on one or more of the following: configuration information of the first service, where the first service may be a service executed by the first model; and the number of query requests allowed to be sent by the second device based on the first information.

[0068] The size of the first time interval may be related to the configuration information of the first service, and the configuration information of the first service may be determined based on the needs of the first service. First services with different needs may adopt first time intervals of different sizes, which helps to adapt to service needs. As an example, the first service may be a beam prediction service. The configuration of the first time interval may be as shown in Table 1, and may be configured according to whether the beam indication method is dynamic indication or semi-static indication. As another example, the first service may also be a positioning service. The configuration of the first time interval may be as shown in Table 2, configuring a relatively short first time interval for periodic positioning request services, but a longer first time interval when meeting service needs, and configuring a relatively long time interval for non-periodic positioning request services.

[0069] Table 1

[0070] Table 2

[0071] The length of the first time interval can also be related to the number of query requests allowed to be sent by the second device, which can be determined based on the first information. The greater the number of query requests allowed to be sent in the first information, the larger the first time interval can be appropriately configured. In this way, the frequency of sending the first information can be adapted to the number of queries allowed for the first model, thereby further limiting the frequency of the second device querying the first model.

[0072] The first information may also include a first bit, and the value of the first bit may include a first value and / or a second value. The first value may be used to authorize the second device to send a query request, while the second value may be used to prohibit the second device from sending a query request. That is, the first bit may be used to indicate whether the first device authorizes the second device to send a query request. Before sending the first information to the second device, the first device may first determine whether to provide the first model query service to the second device to determine the value of the first bit. The first device may determine whether to provide the first model query service to the second device based on a preliminary preparation process. The preliminary preparation process may include signaling processes such as capability reporting, which are not specifically limited in this application. When the first device determines to provide the first model query service to the second device, the value of the first bit may be set to the first value. Otherwise, when the first device determines not to provide the first model query service to the second device, the value of the first bit may be set to the second value. For example, if the first device believes that the second device may be capable of model theft, the first device may set the value of the first bit to the second value to prohibit the second device from sending query requests. For example, a first device can blacklist the identifiers of second devices with a history of malicious queries. When the first device discovers that the second device's identifier is on the blacklist, it sets the value of the first bit to the second value, prohibiting the second device from sending query requests. Based on the first bit, the first and second devices can effectively determine whether the second device is allowed to query the first model, thereby helping to improve the confidentiality of the first model.

[0073] Furthermore, the first device may determine whether to respond to the query request sent by the second device based on the value of the first bit. As an example, the method shown in Figure 7 may also include steps S720 and S730. In step S720, the first device receives the query request sent by the second device. In step S730, if the value of the first bit recorded by the first device is the first value, the first device sends the query result corresponding to the query request to the second device; and / or, if the value of the first bit recorded by the first device is the second value, the first device does not respond to the query request. That is, the first device may not respond to the query request of the unauthorized second device, thereby helping to further avoid model theft. The query result here can be a direct result or an indirect result obtained by reasoning with the first model. The direct result is the result directly output by the first model after reasoning, and the indirect result is the result obtained after the direct result is processed.

[0074] Furthermore, after the first device sends the query result to the second device, the first device may set the value of the first bit to the second value. When the first device confirms that it can again provide the query service for the first model to the second device, the first device again sets the value of the first bit to the first value. Alternatively, when the first device receives the query request from the first device again, the first device does not respond to the query request. By recording and managing the first bit by the first device, the restrictions imposed by the first device on the second device's query of the first model can be strengthened, thereby helping to further improve the confidentiality of the first model.

[0075] The first information may be sent via a control channel, and the first information may be carried in control channel information or control information. For example, the first information may be carried in DCI or physical downlink control channel (PDCCH) information. For another example, the first information may also be carried in uplink control information (UCI) or physical uplink control channel (PUCCH) information.

[0076] Furthermore, the number of bits occupied by the first information can be determined based on the content included in the first information. For example, the first information includes the first bit, but does not include the number of query requests allowed to be sent and the decryption information of the first model. Then, as shown in Figure 8A or 8B, 1 bit (bit) can be added to the original DCI / PDCCH or UCI / PUCCH information to carry the first information. For another example, the first information includes the decryption information of the first model, but does not include the number of query requests allowed to be sent and the first bit. Then, as shown in Figure 8C or 8D, k bits can be added to the original DCI / PDCCH or UCI / PUCCH information to carry the first information, and the k value can be flexibly configured according to the length of the encrypted information.

[0077] The wireless communication method provided in an embodiment of the present application is described below with reference to FIG9 . As an example, the first information may be query authorization indication (QAI) information, and the first time interval may be a time guard interval (TGI). Furthermore, the QAI may also be referred to as a query authorization indication of model inference.

[0078] The method shown in Figure 9 may include steps S910-S990, wherein the first device is the owner of the first model, and the second device is the queryer of the second model. The first model may be used to execute a certain business, and the first model is deployed on the first device side.

[0079] In step S910, the first device configures a TGI. The first device may configure the TGI according to service requirements to determine a time to send a QAI.

[0080] In step S920, the first device sends the QAI to the second device. After completing the preliminary preparation process, the first device can confirm that it will provide the model inference query service to the second device. The first device can then send the QAI to the second device to authorize the second device to send a query request.

[0081] In step S930, the second device confirms receipt of the QAI. When confirming receipt of the authorization permission from the first device, the second device may initiate a query request to the first device.

[0082] In step S940, the second device sends the model input information to the first device. The second device may initiate a model query request by sending the model input information to the first device.

[0083] In step S950, the first device completes model inference. The first device can input the model input information into the first model, perform model inference, and obtain a model inference result.

[0084] In step S960, the first device sends the model inference result to the second device. The first device can send the direct result of the model inference or the indirect result of the model inference.

[0085] At this point, the two devices have completed the entire process from model query request to model inference execution. In the method shown in Figure 9 , the QAI can be configured by default to only permit a single future query request. Therefore, steps S940-S960 can be executed once per QAI transmission. Of course, the QAI can also be configured to permit multiple, limited transmissions. In this case, steps S940-S960 can be executed a limited number of times per QAI transmission, but not exceeding the number permitted by the QAI.

[0086] As previously mentioned, the TGI can be used to determine the time to send the QAI, so the first device can start timing at step S920. After the TGI configured in S910, as shown in step S970, the first device can send the QAI to the second device again to limit model query requests within a future period of time (a time span specified by a TGI). Subsequent steps can loop through the above process from query request to inference execution, which will not be repeated here.

[0087] As described above, the first model can be used to perform services in a wireless communication system. For ease of understanding, the wireless communication method provided by the embodiments of the present application is introduced below with examples of different service scenarios in combination with Examples 1 to 4. Among them, Examples 1 and 2 take the first model being used to perform beam prediction services as an example. Examples 3 and 4 take the first model being used to perform positioning services as an example. For example, in the following embodiments, the first information may be QAI, and the first time interval may be TGI.

[0088] Example 1

[0089] In the first embodiment, a beam prediction model (first model) trained by a network device (first device) provides a query service to a terminal device (second device). The beam prediction model is deployed on the network device, and the terminal device queries the beam prediction model by sending a query request to the network device. Based on this, the method provided in this application can be shown in Figure 10, including steps S1010-S1090.

[0090] In step S1010, the network device configures the TGI. In this embodiment, the network device configures the TGI based on the configuration information of the beam prediction service. Based on the configuration information, the beam indication mode of the beam prediction service is dynamic indication, so the TGI configured by the network device is relatively short, namely 1 time slot.

[0091] In step S1020, the network device sends the QAI for the beam prediction model inference service to the terminal device. The QAI includes the first bit, and the bits occupied by the QAI may be as shown in Figure 8A or Figure 8B. If the network device determines to provide the beam prediction model query service to the terminal device, the value of the first bit may be 1 (indicating that the UE is permitted to make one future query request).

[0092] In step S1030, the terminal device confirms receipt of the authorization permission from the network device. Based on the first bit in the QAI, the terminal device can confirm receipt of the authorization permission from the network device, and then the terminal device can initiate a query request to the network device.

[0093] In step S1040, the terminal device reports the measurement result of beam set B to the network device. The measurement result of beam set B can be used as input information of the beam prediction model.

[0094] In step S1050, the network device completes model inference. After receiving the measurement results for beam set B from the terminal device, the network device verifies the value of the first bit in the QAI corresponding to the terminal device. If the value of the first bit is 0, the network device does not perform any inference-related operations. If the value of the first bit is 1, the network device inputs the measurement results for beam set B into the beam prediction model to obtain an inference result, which is further processed into a beam indication.

[0095] In step S1060, the network device sends a beam indication to the terminal device. Subsequently, the network device may modify the value of the first bit to 0 (indicating that the UE is prohibited from initiating a query request). At this point, the terminal device completes a query of the beam prediction model.

[0096] In addition, the network device starts timing at step S1020. After the time interval configured by the TGI (one time slot) has passed, the network device may set the value of the first bit to 1. As shown in step S1070, the network device may again send the QAI to the terminal device to authorize the terminal device to query the beam prediction model. Subsequent steps may loop through the above process from query request to inference execution, and will not be further described here.

[0097] Based on the method shown in Figure 10, the frequency with which terminal devices query the beam prediction model deployed on network devices is limited by the network devices. This helps prevent terminal devices from stealing models through multiple queries within a short period of time. Furthermore, when encountering malicious query attacks from terminal devices, this method avoids the significant waste of air interface resources caused by reporting large amounts of input information.

[0098] Example 2

[0099] In the second embodiment, the beam prediction model (first model) trained by the network device (first device) provides a query service for the terminal device (second device). The network device deploys the obfuscated beam prediction model in an encrypted file on the terminal device, and the terminal device queries the beam prediction model by sending a query request to its local machine. Based on this, the method provided by this application can be shown in Figure 11, including steps S1110-S1160.

[0100] In step S1110, the network device sends the encrypted beam prediction model to the terminal device. When the terminal device queries the beam prediction model locally, it needs the key generated by the network device to decrypt the model.

[0101] In step S1120, the network device configures the TGI. In this embodiment, the network device configures the TGI based on the configuration information for the beam prediction service. Based on the configuration information, the beam prediction service uses a semi-static beam indication method. Therefore, the TGI configured by the network device is longer, 10 time slots.

[0102] In step S1130, the network device sends the QAI of the beam prediction model inference service to the terminal device. The QAI can be used to indicate the number of times the terminal device queries the model and carry the key information of the model. The bits occupied by the QAI can be as shown in Figure 8C or Figure 8D.

[0103] In step S1140, the terminal device performs a beam prediction model inference. Based on the key information in the QAI, the terminal device confirms receipt of authorization from the network device. The terminal device uses this key information to decrypt the model file and input the beam measurement results into the model to obtain an inference result. The terminal device further processes the inference result into beam indication information to guide beam switching. After completing an inference, the beam prediction model is automatically encrypted and cannot be re-inferred to produce the correct query result.

[0104] Furthermore, the network device starts timing at step S1120. After the TGI configured interval (10 time slots) has passed, as shown in step S1150, the network device can again send the QAI containing the latest key information to the terminal device. Subsequent steps can loop through the above process from query request to inference execution, and will not be further described here.

[0105] Based on the method shown in FIG11 , the frequency with which the terminal device queries the locally deployed beam prediction model is limited by the network device, which helps to prevent the terminal device from stealing the locally deployed model.

[0106] Example 3

[0107] In Example 3, a positioning model (first model) trained by a terminal device (first device) provides a query service for a network device (second device). The positioning model is deployed on the terminal device, and the network device queries the positioning model by sending a query request to the terminal device. Based on this, the method provided by this application can be shown in Figure 12, including steps S1210-S1290.

[0108] In step S1210, the terminal device configures a TGI. In this embodiment, the terminal device configures the TGI based on the configuration information of the positioning service. Based on the configuration information, the positioning service is used for periodic positioning service requests, so the TGI configured by the terminal device is relatively short, i.e., 1 second.

[0109] In step S1220, the terminal device sends the QAI for the positioning model inference service to the network device. The QAI includes the first bit, and the bits occupied by the QAI may be as shown in Figure 8A or Figure 8B. If the terminal device determines to provide the positioning model query service to the network device, the value of the first bit may be 1 (indicating that the UE is permitted to make one future query request).

[0110] In step S1230, the network device confirms receipt of the authorization permission from the terminal device. Based on the first bit in the QAI, the network device can confirm receipt of the authorization permission from the terminal device, and then the network device can initiate a query request to the terminal device.

[0111] In step S1240 , the network device sends a location query request and a reference signal for positioning measurement to the terminal device.

[0112] In step S1250, the terminal device completes positioning-related measurement and inference services. After receiving the positioning request sent by the network device, the terminal device verifies the value of the first bit in the QAI corresponding to the network device. If the value of the first bit is 0, the terminal device does not perform any inference-related operations. If the value of the first bit is 1, the terminal device processes the reference signal of the positioning measurement to obtain measurement information, inputs it into the positioning model to obtain location information, and further processes it into location indication information or location-related control information.

[0113] In step S1260, the terminal device sends the location indication information of the terminal device to the network device. Subsequently, the terminal device may modify the value of the first bit to 0 (indicating that the UE is prohibited from initiating a query request). At this point, the network device completes a query of the positioning model.

[0114] In addition, the terminal device starts timing at step S1220. After the time interval (1s) configured by the TGI has elapsed, the terminal device may set the value of the first bit to 1. As shown in step S1270, the terminal device may again send the QAI of the positioning model inference service to the network device to authorize the network device to query the positioning model. Subsequent steps may loop through the above process from query request to inference execution, which will not be further described here.

[0115] Based on the method shown in Figure 12, the frequency with which network devices query the positioning model deployed on terminal devices is limited by the terminal devices, helping to prevent network devices from stealing models through multiple queries in a short period of time. Furthermore, when encountering malicious query attacks from network devices, this can avoid the significant waste of air interface resources caused by reporting large amounts of input information.

[0116] Example 4

[0117] In the fourth embodiment, the positioning model (first model) trained by the terminal device (first device) provides a query service for the network device (second device). The terminal device deploys the obfuscated positioning model as an encrypted file on the network device, which then queries the positioning model by sending a query request to the terminal device. Based on this, the method provided by this application can be shown in Figure 13, including steps S1310-S1360.

[0118] In step S1310, the terminal device sends the encrypted positioning model to the network device. When the network device queries the positioning model locally, it needs the key generated by the terminal device to decrypt the model.

[0119] In step S1320, the terminal device configures a TGI. In this embodiment, the terminal device configures the TGI based on the configuration information of the positioning service. Based on the configuration information, the positioning service is used for non-periodic positioning request services. Therefore, the TGI configured by the terminal device is relatively long, 100 seconds.

[0120] In step S1330, the terminal device sends the QAI of the positioning model inference service to the network device. The QAI can be used to indicate the number of times the network device queries the model and carry the key information of the model. The bits occupied by the QAI can be as shown in Figure 8C or Figure 8D.

[0121] In step S1340, the network device performs a positioning model inference. Based on the key information in the QAI, the network device confirms receipt of the terminal device's authorization. The network device uses this key information to decrypt the model file, completing the model inference. After the inference is completed, the positioning model is automatically encrypted and cannot be re-inferred to produce the correct query result.

[0122] In addition, after sending the QAI, the terminal device starts timing. After the time interval (100s) configured by TGI, as shown in step S1350, the terminal device can again send the QAI of the positioning model inference service to the network device to authorize the network device to query the positioning model.

[0123] Based on the method shown in FIG13 , the frequency with which a network device queries a positioning model deployed locally is limited by the terminal device, which helps to prevent the network device from stealing the model deployed locally.

[0124] The method embodiments of the present application are described in detail above, and the device embodiments of the present application are described in detail below. It should be understood that the description of the method embodiments corresponds to the description of the device embodiments, so for parts not described in detail, reference can be made to the above method embodiments.

[0125] Figure 14 is a schematic diagram of the structure of a first device provided in an embodiment of the present application. The first device 1400 in Figure 14 includes a communication module 1410, which can be used to send first information to a second device, and the first information can be used to authorize the second device to send a query request for the first model.

[0126] In some implementations, the first information may include one or more of the following information: the number of times the query request is allowed to be sent; and decryption information of the first model.

[0127] In some implementations, when the first model is deployed on the second device, the first information may include decryption information.

[0128] In some implementations, the time interval between two consecutive transmissions of the first information may be determined based on the first time interval.

[0129] In some implementations, the first time interval may be the minimum time interval between two consecutive transmissions of the first information.

[0130] In some implementations, the first time interval may be determined based on one or more of the following: configuration information of the first service, the first service being a service executed by the first model; and the number of query requests allowed to be sent by the second device based on the first information.

[0131] In some implementations, the first information may include a first bit, the value of the first bit may include a first value and / or a second value, the first value may be used to authorize the second device to send a query request, and the second value may be used to prohibit the second device from sending a query request.

[0132] In some implementations, the communication module 1410 can also be used to receive a query request sent by a second device; and, if the value of the first bit recorded by the first device is a first value, send a query result corresponding to the query request to the second device; and / or if the value of the first bit recorded by the first device is a second value, do not respond to the query request.

[0133] In some implementations, the first device 1400 may further include a setting module 1420 , which may be configured to set the value of the first bit to the second value after the communication module 1410 sends the query result to the second device.

[0134] In some implementations, the first model may be deployed at the first device; or, the first model may also be deployed at the second device.

[0135] In some implementations, the first model can be used to perform beam prediction services or positioning services.

[0136] In some implementations, the first device may be an owner of the first model, and the second device may be a user of the first model.

[0137] Figure 15 is a schematic diagram of the structure of a second device provided in an embodiment of the present application. The second device 1500 in Figure 15 includes a communication module 1510, which can be used to receive first information sent by the first device, and the first information can be used to authorize the second device to send a query request for the first model.

[0138] In some implementations, the first information may include one or more of the following information: the number of times the query request is allowed to be sent; and decryption information of the first model.

[0139] In some implementations, when the first model is deployed on the second device, the first information may include decryption information.

[0140] In some implementations, the time interval between two consecutive transmissions of the first information may be determined based on the first time interval.

[0141] In some implementations, the first time interval may be the minimum time interval between two consecutive transmissions of the first information.

[0142] In some implementations, the first time interval may be determined based on one or more of the following: configuration information of the first service, the first service being a service executed by the first model; and the number of query requests allowed to be sent by the second device based on the first information.

[0143] In some implementations, the first information may include a first bit, the value of the first bit may include a first value and / or a second value, the first value may be used to authorize the second device to send a query request, and the second value may be used to prohibit the second device from sending a query request.

[0144] In some implementations, the first model may be deployed at the first device; or, the first model may also be deployed at the second device.

[0145] In some implementations, the first model can be used to perform beam prediction services or positioning services.

[0146] In some implementations, the first device may be an owner of the first model, and the second device may be a user of the first model.

[0147] Figure 16 is a schematic diagram of the structure of a communication device provided in an embodiment of the present application. The communication device 1600 in Figure 16 can be used to implement the method described in the above method embodiment. The device 1600 can be a chip, a terminal device, or a base station.

[0148] The communication device 1600 may include one or more processors 1610. The processor 1610 may support the device 1600 to implement the method described in the above method embodiment. The processor 1610 may be a general-purpose processor or a special-purpose processor. For example, the processor may be a central processing unit (CPU). Alternatively, the processor may be another general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, etc. The general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0149] The communication device 1600 may further include one or more memories 1620. The memories 1620 store programs that can be executed by the processor 1610, causing the processor 1610 to perform the methods described in the above method embodiments. The memories 1620 may be independent of the processor 1610 or integrated into the processor 1610.

[0150] The communication device 1600 may further include a transceiver 1630. The processor 1610 may communicate with other devices or chips via the transceiver 1630. For example, the processor 1610 may transmit and receive data with other devices or chips via the transceiver 1630.

[0151] It should be understood that in the embodiment of the present application, the processor 1610 can adopt a general central processing unit (CPU), a microprocessor, an application specific integrated circuit (ASIC), or one or more integrated circuits to execute relevant programs to implement the technical solutions provided in the embodiment of the present application.

[0152] The memory 1620 may include a read-only memory and a random access memory, and provides instructions and data to the processor 1610. A portion of the processor 1610 may also include a non-volatile random access memory. For example, the processor 1610 may also store information about the device type.

[0153] During implementation, each step of the above method can be completed by an integrated logic circuit of the hardware in the processor 1610 or by instructions in the form of software. The method for requesting uplink transmission resources disclosed in conjunction with the embodiments of the present application can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor. The software module can be located in a mature storage medium in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 1620, and the processor 1610 reads the information in the memory 1620 and completes the steps of the above method in combination with its hardware. To avoid repetition, it will not be described in detail here.

[0154] It should be understood that in the embodiments of the present application, the processor 1610 may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0155] The present application also provides a computer-readable storage medium for storing a program. The computer-readable storage medium can be applied to the first device or the second device provided in the present application, and the program enables a computer to execute the wireless communication method in each embodiment of the present application.

[0156] The present application also provides a computer program product. The computer program product includes a program. The computer program product can be applied to the first device or the second device provided in the present application, and the program enables a computer to execute the wireless communication method in each embodiment of the present application.

[0157] The embodiments of the present application also provide a computer program. The computer program can be applied to the first device or the second device provided in the embodiments of the present application, and the computer program enables a computer to execute the wireless communication method in each embodiment of the present application.

[0158] It should be understood that all or part of the functions of the communication device in this application can also be implemented through software functions running on hardware, or through virtualization functions instantiated on a platform (such as a cloud platform).

[0159] It should be understood that the terms "system" and "network" in this application can be used interchangeably. In addition, the terms used in this application are only used to explain the specific embodiments of this application and are not intended to limit this application. The terms "first", "second", "third", and "fourth" in the specification and claims of this application and the accompanying drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

[0160] In the embodiments of this application, the term "indication" may refer to a direct indication, an indirect indication, or an indication of an association. For example, "A indicates B" may refer to a direct indication of B, e.g., B can obtain information through A; it may refer to an indirect indication of B, e.g., A indicates C, e.g., B can obtain information through C; or it may refer to an association between A and B.

[0161] In the embodiment of the present application, "B corresponding to A" means that B is associated with A and B can be determined based on A. However, it should be understood that determining B based on A does not mean determining B based solely on A, but B can also be determined based on A and / or other information.

[0162] In the embodiments of the present application, the term "corresponding" may indicate a direct or indirect correspondence between the two, or an association relationship between the two, or a relationship between indication and indication, configuration and configuration, etc.

[0163] In the embodiments of this application, the term "and / or" is simply a description of the association relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this document generally indicates that the related objects are in an "or" relationship.

[0164] In the embodiments of this application, the term "include" can refer to direct inclusion or indirect inclusion. Alternatively, the term "include" in the embodiments of this application can be replaced with "indicates" or "is used to determine." For example, "A includes B" can be replaced with "A indicates B" or "A is used to determine B."

[0165] In various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0166] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0167] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0168] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0169] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be read by a computer or a data storage device such as a server or data center that includes one or more available media integrated therein. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital versatile disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0170] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A wireless communication method, characterized in that, it includes: A first device sends first information to a second device, and the first information is used to authorize the second device to send a query request for a first model.

2. The method according to claim 1, characterized in that, the first information includes one or more of the following information: The number of times the query request is allowed to be sent; The decryption information of the first model.

3. The method according to claim 2, characterized in that, when the first model is deployed in the second device, the first information includes the decryption information.

4. The method according to any one of claims 1 to 3, characterized in that, the time interval between two adjacent transmissions of the first information is determined based on a first time interval.

5. The method according to claim 4, characterized in that, the first time interval is the minimum time interval between two adjacent transmissions of the first information.

6. The method according to claim 4 or 5, characterized in that, the first time interval is determined based on one or more of the following: The configuration information of a first service, where the first service is the service executed by the first model; The number of times the query request allowed to be sent by the second device based on the first information.

7. The method according to any one of claims 1 to 6, characterized in that, the first information includes a first bit, and the value of the first bit includes a first value and / or a second value. The first value is used to authorize the second device to send the query request, and the second value is used to prohibit the second device from sending the query request.

8. The method according to claim 7, characterized in that, the method further includes: The first device receives the query request sent by the second device; If the value of the first bit recorded by the first device is the first value, the first device sends the query result corresponding to the query request to the second device; and / or, If the value of the first bit recorded by the first device is the second value, the first device does not respond to the query request.

9. The method according to claim 8, characterized in that, the method further includes: After the first device sends the query result to the second device, the first device sets the value of the first bit to the second value.

10. The method according to any one of claims 1 to 9, characterized in that, the first model is deployed at the first device; or, the first model is deployed at the second device.

11. The method according to any one of claims 1 to 10, characterized in that, the first model is used to execute a beam prediction service or a positioning service.

12. The method according to any one of claims 1 to 11, characterized in that, the first device is the owner of the first model, and the second device is the user of the first model.

13. A wireless communication method, characterized in that, it includes: A second device receives first information sent by a first device, and the first information is used to authorize the second device to send a query request for a first model.

14. The method according to claim 13, wherein, the first information includes one or more of the following information: the number of times of allowing to send the query request; the decryption information of the first model.

15. The method according to claim 14, wherein, when the first model is deployed in the second device, the first information includes the decryption information.

16. The method according to any one of claims 13 to 15, wherein, the time interval between two adjacent transmissions of the first information is determined based on a first time interval.

17. The method according to claim 16, wherein, the first time interval is the minimum time interval between two adjacent transmissions of the first information.

18. The method according to claim 16 or 17, wherein, the first time interval is determined based on one or more of the following: the configuration information of the first service, and the first service is the service executed by the first model; the number of times of the query request allowed to be sent by the second device based on the first information.

19. The method according to any one of claims 13 to 18, wherein, the first information includes a first bit, and the value of the first bit includes a first value and / or a second value. The first value is used to authorize the second device to send the query request, and the second value is used to prohibit the second device from sending the query request.

20. The method according to any one of claims 13 to 19, wherein, the first model is deployed at the first device; or the first model is deployed at the second device.

21. The method according to any one of claims 13 to 20, wherein, the first model is used to execute a beam prediction service or a positioning service.

22. The method according to any one of claims 13 to 21, wherein, the first device is the owner of the first model, and the second device is the user of the first model.

23. A communication device, the communication device is a first device, wherein, comprising: a communication module, configured to send first information to a second device, and the first information is used to authorize the second device to send a query request for a first model.

24. The communication device according to claim 23, wherein, the first information includes one or more of the following information: the number of times of allowing to send the query request; the decryption information of the first model.

25. The communication device according to claim 24, wherein, when the first model is deployed in the second device, the first information includes the decryption information.

26. The communication device according to any one of claims 23 to 25, wherein, the time interval between two adjacent transmissions of the first information is determined based on a first time interval.

27. The communication device according to claim 26, wherein, the first time interval is the minimum time interval between two adjacent transmissions of the first information.

28. The communication device according to claim 26 or 27, wherein, The first time interval is determined based on one or more of the following: Configuration information of the first service, where the first service is the service executed by the first model; The number of query requests that the second device is allowed to send based on the first information.

29. The communication device according to any one of claims 23 to 28, wherein, The first information includes a first bit, and the value of the first bit includes a first value and / or a second value. The first value is used to authorize the second device to send the query request, and the second value is used to prohibit the second device from sending the query request.

30. The communication device according to claim 29, wherein, The communication module is further configured to: Receive the query request sent by the second device; If the value of the first bit recorded by the first device is the first value, send the query result corresponding to the query request to the second device; and / or, If the value of the first bit recorded by the first device is the second value, do not respond to the query request.

31. The communication device according to claim 30, wherein, The first device further includes: A setting module, configured to set the value of the first bit to the second value after the communication module sends the query result to the second device.

32. The communication device according to any one of claims 23 to 31, wherein, The first model is deployed at the first device; or, the first model is deployed at the second device.

33. The communication device according to any one of claims 23 to 32, wherein, The first model is used to execute a beam prediction service or a positioning service.

34. The communication device according to any one of claims 23 to 33, wherein, The first device is the owner of the first model, and the second device is the user of the first model.

35. A communication device, where the communication device is a second device, wherein, It includes: A communication module, configured to receive first information sent by a first device, where the first information is used to authorize the second device to send a query request for a first model.

36. The communication device according to claim 35, wherein, The first information includes one or more of the following information: The number of times the query request is allowed to be sent; The decryption information of the first model.

37. The communication device according to claim 36, wherein, When the first model is deployed at the second device, the first information includes the decryption information.

38. The communication device according to any one of claims 35 to 37, wherein, The time interval between two adjacent transmissions of the first information is determined based on a first time interval.

39. The communication device according to claim 38, wherein, The first time interval is the minimum time interval between two adjacent transmissions of the first information.

40. The communication device according to claim 38 or 39, wherein, The first time interval is determined based on one or more of the following: Configuration information of the first service, where the first service is the service executed by the first model; The number of times of the query request that the second device is allowed to send based on the first information.

41. The communication device according to any one of claims 35 to 40, characterized in that the first information includes a first bit, and the value of the first bit includes a first value and / or a second value. The first value is used to authorize the second device to send the query request, and the second value is used to prohibit the second device from sending the query request.

42. The communication device according to any one of claims 35 to 41, characterized in that the first model is deployed at the first device; or, the first model is deployed at the second device.

43. The communication device according to any one of claims 35 to 42, characterized in that the first model is used to execute a beam prediction service or a positioning service.

44. The communication device according to any one of claims 35 to 43, characterized in that the first device is the owner of the first model, and the second device is the user of the first model.

45. A communication device, where the communication device is a first device, characterized in that it includes a memory, a processor, and a transceiver. The memory is used to store a program, the processor is used to call the program in the memory, and the transceiver is used to send first information to a second device. The first information is used to authorize the second device to send a query request for the first model.

46. The communication device according to claim 45, characterized in that the first information includes one or more of the following information: the number of times of allowing the query request to be sent; the decryption information of the first model.

47. The communication device according to claim 46, characterized in that when the first model is deployed at the second device, the first information includes the decryption information.

48. The communication device according to any one of claims 45 to 47, characterized in that the time interval between two adjacent transmissions of the first information is determined based on a first time interval.

49. The communication device according to claim 48, characterized in that the first time interval is the minimum time interval between two adjacent transmissions of the first information.

50. The communication device according to claim 48 or 49, characterized in that the first time interval is determined based on one or more of the following: Configuration information of the first service, where the first service is the service executed by the first model; The number of times of the query request that the second device is allowed to send based on the first information.

51. The communication device according to any one of claims 45 to 50, characterized in that the first information includes a first bit, and the value of the first bit includes a first value and / or a second value. The first value is used to authorize the second device to send the query request, and the second value is used to prohibit the second device from sending the query request.

52. The communication device according to claim 51, characterized in that the transceiver is further used for: Receive the query request sent by the second device; If the value of the first bit recorded by the first device is the first value, send the query result corresponding to the query request to the second device; and / or, If the value of the first bit recorded by the first device is the second value, do not respond to the query request.

53. The communication device according to claim 52, characterized in that, the processor is configured to: after the transceiver sends the query result to the second device, set the value of the first bit to the second value.

54. The communication device according to any one of claims 45 to 53, characterized in that, the first model is deployed at the first device; or, the first model is deployed at the second device.

55. The communication device according to any one of claims 45 to 54, characterized in that, the first model is used to perform beam prediction service or positioning service.

56. The communication device according to any one of claims 45 to 55, characterized in that, the first device is the owner of the first model, and the second device is the user of the first model.

57. A communication device, the communication device is the second device, characterized in that, it includes a memory, a processor and a transceiver, the memory is used to store programs, the processor is used to call the programs in the memory, and the transceiver is used to receive the first information sent by the first device, and the first information is used to authorize the second device to send a query request for the first model.

58. The communication device according to claim 57, characterized in that, the first information includes one or more of the following information: the number of times the query request is allowed to be sent; the decryption information of the first model.

59. The communication device according to claim 58, characterized in that, when the first model is deployed at the second device, the first information includes the decryption information.

60. The communication device according to any one of claims 57 to 59, characterized in that, the time interval between two adjacent transmissions of the first information is determined based on a first time interval.

61. The communication device according to claim 60, characterized in that, the first time interval is the minimum time interval between two adjacent transmissions of the first information.

62. The communication device according to claim 60 or 61, characterized in that, the first time interval is determined based on one or more of the following: the configuration information of the first service, where the first service is the service executed by the first model; the number of query requests that the second device is allowed to send based on the first information.

63. The communication device according to any one of claims 57 to 62, characterized in that, the first information includes a first bit, and the value of the first bit includes a first value and / or a second value, the first value is used to authorize the second device to send the query request, and the second value is used to prohibit the second device from sending the query request.

64. The communication device according to any one of claims 57 to 63, ​ It is characterized in that the first model is deployed at the first device; or, the first model is deployed at the second device.

65. The communication device according to any one of claims 57 to 64, It is characterized in that the first model is used to perform beam prediction services or positioning services.

66. The communication device according to any one of claims 57 to 65, It is characterized in that the first device is the owner of the first model, and the second device is the user of the first model.

67. A device, It is characterized in that it includes a processor for calling a program from a memory to enable the device to execute the method according to any one of claims 1-12 or 13-22.

68. A chip, It is characterized in that it includes a processor for calling a program from a memory so that the device installed with the chip executes the method according to any one of claims 1-12 or 13-22.

69. A computer-readable storage medium, It is characterized in that a program is stored thereon, and the program enables a computer to execute the method according to any one of claims 1-12 or 13-22.

70. A computer program product, It is characterized in that it includes a program, and the program enables a computer to execute the method according to any one of claims 1-12 or 13-22.

71. A computer program, It is characterized in that the computer program enables a computer to execute the method according to any one of claims 1-12 or 13-22.

Images