Intelligent sensing method and system, network device, storage medium, and program product

Abstract

The present disclosure relates to the technical field of integrated sensing and communications, and relates to an intelligent sensing method and system, a network device, a storage medium, and a program product. The intelligent sensing method is executed by a target SF network element, and comprises: receiving service sensing request information sent by a target AMF network element; determining a target NWDAF network element on the basis of the service sensing request information; sending a model subscription request to the target NWDAF network element; receiving a target model trained by the target NWDAF network element; and on the basis of sensing measurement data and the target model, acquiring a sensing result corresponding to the service sensing request information.

Description

Intelligent sensing methods, systems, network devices, storage media and software products

[0001] Cross-references to related applications

[0002] This application is based on and claims priority to CN application number 202411016917.0, filed on July 26, 2024, the disclosure of which is incorporated herein by reference in its entirety. Technical Field

[0003] This disclosure relates to the field of integrated communication and sensing technology, and in particular to an intelligent sensing method, an intelligent sensing system, a network device, a computer-readable storage medium, and a computer program product. Background Technology

[0004] With the development of wireless communication technology and the increasing demand for high-quality data transmission, communication systems are evolving towards higher levels. Against this backdrop, the integration of sensing and communication technologies has become a highly anticipated cutting-edge technology. The core idea of ​​integrated sensing and communication is to utilize RF (Radio Frequency) signals to simultaneously achieve sensing and communication functions. This allows us to achieve real-time environmental monitoring and rapid data transmission without increasing the burden on additional hardware, and can be used to optimize network resource allocation and improve overall network efficiency.

[0005] Furthermore, the integrated communication and sensing technology can provide users with richer and more accurate services, such as location-based personalized recommendations and intelligent traffic management, thereby significantly improving the user experience and providing strong technical support for various intelligent applications. Summary of the Invention

[0006] According to some embodiments of the first aspect of this disclosure, an intelligent sensing method is provided, executed by a target sensing function (SF) network element, comprising: receiving service sensing request information sent by a target AMF (Access and Mobility Management Function) network element; determining a target Network Data Analysis Function (NWDAF) network element based on the service sensing request information; sending a model subscription request to the target NWDAF network element; receiving a target model trained by the target NWDAF network element; and obtaining a sensing result corresponding to the service sensing request information based on sensing measurement data and the target model.

[0007] In some embodiments, the intelligent sensing method further includes: determining whether to obtain a sensing result corresponding to the service sensing request information through a model based on the service sensing request information; if it is determined that the sensing result should be obtained through a model, checking whether there is an available model in the local environment of the target SF network element that matches the service sensing request information, wherein if there is no available model in the local environment of the target SF network element that matches the service sensing request information, the operation of determining the target NWDAF network element is performed.

[0008] In some embodiments, the intelligent sensing method further includes: if there is an available model in the local environment that matches the business sensing request information, determining the available model in the local environment that matches the business sensing request information as the target model.

[0009] In some embodiments, determining the target NWDAF network element based on the service awareness request information includes: determining the target NWDAF network element based on the service awareness request information, the first registration information of multiple NWDAF network elements, and the second registration information of the target SF network element.

[0010] In some embodiments, the first registration information includes analysis information, service area information, perception support information, model filtering information, and first model interoperability information of the NWDAF network element, wherein the first model interoperability information includes a list of vendors of shareable models, model formats, and model operating environments; and / or the second registration information includes analysis information, service area information, perception support information, and second model interoperability information of the SF network element, wherein the second model interoperability information includes vendor information, supported model formats, and supported model operating environments.

[0011] In some embodiments, determining the target NWDAF network element based on the service awareness request information, the first registration information of multiple NWDAF network elements, and the second registration information of the target SF network element includes: selecting an NWDAF network element that matches the service awareness request information and the second registration information of the target SF network element based on the service awareness request information, the first registration information, and the second registration information of the target SF network element; and determining the NWDAF network element that matches the service awareness request information and the second registration information of the target SF network element as the target NWDAF network element.

[0012] In some embodiments, the service-aware request information includes service type information, service requirement information, and target awareness node information.

[0013] In some embodiments, the target SF network element is determined by the target AMF network element from among multiple SF network elements registered to the storage network element based on service awareness request information.

[0014] In some embodiments, the target NWDAF network element is determined from a plurality of NWDAF network elements registered to the storage network element by the target SF network element.

[0015] In some embodiments, the target AMF network element is determined by the NEF (Network Exposure Function) network element based on the service awareness request information.

[0016] In some embodiments, the model subscription request includes model filtering information and second model interoperability information.

[0017] In some embodiments, obtaining the perception result corresponding to the business perception request information based on perception measurement data and a target model includes: collecting perception measurement data; inputting the perception measurement data into the target model to obtain the perception result.

[0018] In some embodiments, the intelligent sensing method further includes: sending the sensing result to the NEF network element so that the sensing result can be forwarded to the AF (Application Function) network element through the NEF network element, wherein the service sensing request information is sent by the AF network element.

[0019] According to some embodiments of the second aspect of this disclosure, an intelligent sensing method is provided, executed by an intelligent sensing system, comprising: a target AMF network element sending service sensing request information to a target SF network element; the target SF network element receiving the service sensing request information sent by the target AMF network element; the target SF network element determining a target NWDAF network element based on the service sensing request information; the target SF network element sending a model subscription request to the target NWDAF network element; the target NWDAF network element receiving the model subscription request and sending a trained target model to the target SF network element; the target SF network element receiving the target model; and the target SF network element obtaining a sensing result corresponding to the service sensing request information based on sensing measurement data and the target model.

[0020] In some embodiments, the intelligent sensing method further includes: the target SF network element determining whether to obtain a sensing result corresponding to the service sensing request information through a model based on the service sensing request information; if it is determined that the sensing result should be obtained through a model, the target SF network element checks whether there is an available model in its local environment that matches the service sensing request information, wherein if there is no available model in the local environment of the target SF network element that matches the service sensing request information, the operation of determining the target NWDAF network element is performed.

[0021] In some embodiments, the intelligent sensing method further includes: when there is an available model in the local environment that matches the service sensing request information, the target SF network element determines the available model in the local environment that matches the service sensing request information as the target model.

[0022] In some embodiments, the target SF network element determines the target NWDAF network element based on the service awareness request information, including: the target SF network element determines the target NWDAF network element based on the service awareness request information, the first registration information of multiple NWDAF network elements, and the second registration information of the target SF network element.

[0023] In some embodiments, the first registration information includes analysis information, service area information, perception support information, model filtering information, and first model interoperability information of the NWDAF network element, wherein the first model interoperability information includes a list of vendors of shareable models, model formats, and model operating environments; and / or the second registration information includes analysis information, service area information, perception support information, and second model interoperability information of the SF network element, wherein the second model interoperability information includes vendor information, supported model formats, and supported model operating environments.

[0024] In some embodiments, the target SF network element determines the target NWDAF network element based on the service awareness request information, the first registration information of multiple NWDAF network elements, and the second registration information of the target SF network element, including: the target SF network element selects an NWDAF network element that matches the service awareness request information and the second registration information of the target SF network element; the target SF network element determines the NWDAF network element that matches the service awareness request information and the second registration information of the target SF network element as the target NWDAF network element.

[0025] In some embodiments, the service-aware request information includes service type information, service requirement information, and target awareness node information.

[0026] In some embodiments, the intelligent sensing method further includes: the target AMF network element receiving service sensing request information sent by the NEF network element; and the target AMF network element determining the target SF network element from multiple SF network elements registered to the storage network element based on the service sensing request information.

[0027] In some embodiments, the target SF network element determines the target NWDAF network element based on the service awareness request information, including: the target SF network element determines the target NWDAF network element from multiple NWDAF network elements registered to the storage network element based on the service awareness request information.

[0028] In some embodiments, the intelligent sensing method further includes: the NEF network element receiving service sensing request information sent by the AF network element; and the NEF network element determining the target AMF network element based on the service sensing request information.

[0029] In some embodiments, the model subscription request includes model filtering information and second model interoperability information.

[0030] In some embodiments, the process by which the target SF network element obtains the perception result corresponding to the service perception request information based on the perception measurement data and the target model includes: the target SF network element collecting the perception measurement data; and the target SF network element inputting the perception measurement data into the target model to obtain the perception result.

[0031] In some embodiments, the intelligent sensing method further includes: the target SF network element sending the sensing result to the target AMF network element; the target AMF network element forwarding the sensing result to the NEF network element; and the NEF network element forwarding the sensing result to the AF network element.

[0032] In some embodiments, the intelligent sensing method further includes: the AF network element sending service sensing request information to the NEF network element.

[0033] According to some embodiments of the third aspect of this disclosure, a network device is provided, comprising: a first receiving unit configured to receive service awareness request information sent by an AMF network element; a determining unit configured to determine a target NWDAF network element based on the service awareness request information; a sending unit configured to send a model subscription request to the target NWDAF network element; a second receiving unit configured to receive a target model trained by the target NWDAF network element; and an acquiring unit configured to acquire a perception result corresponding to the service awareness request information based on perception measurement data and the target model.

[0034] In some embodiments, the network device is further configured to determine whether to obtain a perception result corresponding to the service perception request information through a model based on the service perception request information; if it is determined that the perception result should be obtained through a model, check whether there is an available model in the local environment of the target SF network element that matches the service perception request information, wherein if there is no available model in the local environment of the target SF network element that matches the service perception request information, the operation of determining the target NWDAF network element is performed.

[0035] In some embodiments, the network device is further configured to identify the available model in the local environment that matches the service-aware request information as the target model, if an available model in the local environment that matches the service-aware request information exists.

[0036] In some embodiments, the determining unit is further configured to determine the target NWDAF network element based on the service-aware request information, the first registration information of a plurality of NWDAF network elements, and the second registration information of the target SF network element.

[0037] In some embodiments, the first registration information includes NWDAF network element analysis information, service area information, perception support information, model filtering information, and first model interoperability information, wherein the first model interoperability information includes a list of vendors of shareable models, model formats, and model operating environments.

[0038] In some embodiments, the second registration information includes analysis information of the SF network element, service area information, perception support information, and second model interoperability information, wherein the second model interoperability information includes vendor information, supported model formats, and supported model operating environments.

[0039] In some embodiments, the determining unit is further configured to select an NWDAF network element that matches the service awareness request information and the second registration information of the target SF network element based on the service awareness request information, the first registration information, and the second registration information of the target SF network element; and determine the NWDAF network element that matches the service awareness request information and the second registration information of the target SF network element as the target NWDAF network element.

[0040] In some embodiments, the service-aware request information includes service type information, service requirement information, and target awareness node information.

[0041] In some embodiments, the target SF network element is determined by the target AMF network element from among multiple SF network elements registered to the storage network element based on service awareness request information.

[0042] In some embodiments, the target NWDAF network element is determined from a plurality of NWDAF network elements registered to the storage network element by the target SF network element.

[0043] In some embodiments, the target AMF network element is determined by the Network Open Function (NEF) network element based on the service-aware request information.

[0044] In some embodiments, the model subscription request includes model filtering information and second model interoperability information.

[0045] In some embodiments, the acquisition unit is further configured to collect sensing measurement data; input the sensing measurement data into the target model; and acquire sensing results.

[0046] In some embodiments, the network device is further configured to send the sensing results to the NEF network element so that the sensing results can be forwarded to the application function AF network element via the NEF network element, wherein the service sensing request information is sent by the AF network element.

[0047] According to some embodiments of the fourth aspect of this disclosure, a network device is provided, including: a memory and a processor coupled to the memory, the processor being configured to execute the intelligent sensing method of any embodiment of this disclosure based on instructions stored in the memory.

[0048] According to some embodiments of the fifth aspect of this disclosure, an intelligent sensing system is provided, comprising: an SF network element configured as a network device as in any embodiment of this disclosure; an AMF network element configured to send service awareness request information to a target SF network element; and an NWDAF network element configured to receive a model subscription request from the target SF network element and send a trained target model to the target SF network element.

[0049] In some embodiments, the NWDAF network element is further configured to: collect perceptual training data; train the model subscribed to by the model subscription request based on the perceptual training data to obtain the trained target model.

[0050] In some embodiments, the intelligent sensing system further includes: a storage network element configured to receive first registration information from a plurality of NWDAF network elements to register the plurality of NWDAF network elements to the storage network element, and to receive second registration information from a plurality of SF network elements to register the plurality of SF network elements to the storage network element.

[0051] In some embodiments, the AMF network element is further configured to receive service awareness request information and determine the target SF network element from multiple SF network elements registered to the storage network element based on the service awareness request information.

[0052] In some embodiments, the intelligent sensing system further includes: a NEF network element, configured to receive service sensing request information sent by an AF network element, determine a target AMF network element based on the service sensing request information, and send the service sensing request information to the target AMF network element.

[0053] In some embodiments, the NEF network element is also configured to perform an authorization check on the received service awareness request information, and if the authorization check passes, send the service awareness request information to the target AMF network element.

[0054] In some embodiments, the intelligent sensing system further includes: an AF network element, configured to send service sensing request information to a NEF network element and receive sensing results forwarded by the NEF network element.

[0055] According to some embodiments of the sixth aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the intelligent sensing method of any embodiment of this disclosure.

[0056] According to some embodiments of the seventh aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the intelligent sensing method in any embodiment of this disclosure.

[0057] According to some embodiments of the eighth aspect of this disclosure, a computer program is provided, comprising: instructions that, when executed by a processor, cause the processor to perform the intelligent sensing method as described in any embodiment of this disclosure.

[0058] Other features and advantages of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0059] The accompanying drawings, which form part of this specification, illustrate embodiments of this disclosure and, together with the specification, serve to explain the principles of this disclosure.

[0060] This disclosure can be more clearly understood with reference to the accompanying drawings and the following detailed description.

[0061] Figure 1 shows a flowchart of some embodiments of the intelligent sensing method of this disclosure.

[0062] Figure 2 shows flowcharts of some other embodiments of the intelligent sensing method of this disclosure.

[0063] Figure 3 shows a schematic diagram of some embodiments of the network device disclosed herein.

[0064] Figure 4 shows schematic diagrams of some other embodiments of the network devices disclosed herein.

[0065] Figure 5 shows a schematic diagram of some embodiments of the intelligent sensing system of this disclosure.

[0066] Figure 6 shows schematic diagrams of further embodiments of the intelligent sensing method of this disclosure. Detailed Implementation

[0067] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of the present disclosure.

[0068] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0069] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit this disclosure or its application or use.

[0070] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, they should be considered part of the specification.

[0071] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0072] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0073] The inventors of this disclosure have discovered the following problem in the related technology: how to improve the performance and intelligence level of integrated communication and sensing technology.

[0074] In research on communication-aware network architecture, SF network elements are commonly introduced as core network units responsible for collecting and processing environmental sensing data. Current integrated communication-aware technologies generally focus on collecting and transmitting environmental sensing data, lacking application and reasoning capabilities, and thus failing to extend the scope of integrated communication-awareness.

[0075] NWDAF (Network Data Center Amplifier) ​​elements are intelligent network elements that can serve as the core network's big data engine. They are primarily responsible for data acquisition, model training, inference and judgment, and intelligent prediction, outputting analysis results for network, network management, and application execution strategy decisions. With network evolution, network intelligence has become an inevitable trend. Therefore, how to achieve integrated intelligent communication and sensing is a problem that needs to be solved.

[0076] To address the aforementioned issues, this disclosure proposes an intelligent sensing method. This method identifies a target NWDAF (Network Data Analytics Function) network element based on service sensing request information from the target SF (Sensing Function). A trained target model is then obtained from the target NWDAF network element. Finally, the sensing result corresponding to the service sensing request information is obtained based on the sensing measurement data and the target model. In other words, the target model trained by the NWDAF network element infers the sensing measurement data collected by the target SF network element to obtain the corresponding sensing result. This method expands the application of sensing data, improves the effective utilization rate of sensing data, and enhances the performance and intelligence level of integrated communication sensing. The specific details are as follows.

[0077] Figure 1 shows a flowchart of some embodiments of the intelligent sensing method of this disclosure.

[0078] As shown in Figure 1, the intelligent sensing method includes steps 110 to 150, wherein the intelligent sensing method is executed by the target SF network element.

[0079] In some embodiments, the target SF network element is determined by the target AMF network element from among multiple SF network elements registered to the storage network element based on service awareness request information.

[0080] In some embodiments, the target AMF network element can select a suitable target SF network element based on the target area information or target location information in the service awareness request information.

[0081] In some embodiments, the storage network element may be an NRF (Network Repository Function) network element.

[0082] In some embodiments, the target AMF network element is determined by the Network Open Function (NEF) network element based on the service-aware request information.

[0083] In some embodiments, if it is area-oriented perception, the NEF network element will select the AMF network element serving the area based on the area information in the service perception request information of the AF network element. If it is target-oriented perception, the NEF network element will select the AMF network element serving the area based on the target location information in the service perception request information of the AF network element. If the target itself has a UE communication module and possesses UE capabilities (e.g., a vehicle), then target-oriented perception can be considered as perceiving the area surrounding the UE. In this case, the serving AMF network element of the UE can be selected as the target AMF network element, and the NEF will obtain the AMF information serving the UE through the UDM network element.

[0084] The NEF network element determines the target AMF network element based on the service perception request information. In other words, the NEF network element determines the target AMF network element based on the target perception node information in the service perception request information. Since the target AMF network element must be the service AMF network element of the terminal participating in perception, more efficient and accurate perception service triggering is achieved.

[0085] In step 110, a service awareness request message sent by the target AMF network element is received.

[0086] In some embodiments, the service-aware request information includes service type information, service requirement information, and target awareness node information.

[0087] In some embodiments, service type information may be, for example, dynamic map, vehicle tracking, etc.; service requirement information may be, for example, perception resolution, perception accuracy, duration, target area information, latency, etc.; target perception node information may be, for example, UE information.

[0088] In some embodiments, after the target SF network element receives the service awareness request information sent by the target AMF network element, it will determine whether to obtain the perception result corresponding to the service awareness request information through the model based on the service awareness request information.

[0089] In some embodiments, the determination of whether to obtain the perception result corresponding to the business perception request information through the model can be based on factors such as the amount of computation, the accuracy requirements, and the perception environment.

[0090] In some embodiments, when it is determined that the perception result is obtained through the model, it is checked whether there is an available model in the local environment of the target SF network element that matches the service perception request information. If there is no available model in the local environment of the target SF network element that matches the service perception request information, the operation of determining the target NWDAF network element is performed.

[0091] By determining whether to obtain perception results through the model based on business perception request information, and only obtaining perception results through the model when certain conditions are met, the accuracy and efficiency of intelligent perception are improved.

[0092] In some embodiments, if a usable model matching the business-aware request information exists in the local environment, the usable model matching the business-aware request information in the local environment is determined as the target model.

[0093] By determining whether a usable model matching the service perception request information exists in the local environment of the target SF network element, if a usable model matching the service perception request information exists in the local environment, there is no need to redetermine the target NWDAF network element and the training model, thus improving the efficiency of intelligent perception.

[0094] In step 120, the target NWDAF network element is determined based on the service awareness request information.

[0095] In some embodiments, the target NWDAF network element can be determined based on the service-aware request information, the first registration information of multiple NWDAF network elements, and the second registration information of the target SF network element.

[0096] In some embodiments, it should be noted that the target NWDAF network element is determined based on the service awareness request information, the first registration information of multiple NWDAF network elements, and the second registration information of the target SF network element. The first registration information includes the NWDAF network element's analysis information, service area information, awareness support information, model filtering information, and first model interoperability information. The first model interoperability information includes a list of vendors of shareable models, model formats, and model operating environments. And / or the model filtering information in the first registration information of the NWDAF network element helps to select from multiple NWDAF network elements an NWDAF network element that includes an available model that matches the service awareness request information.

[0097] In some embodiments, the second registration information includes analysis information of the SF network element, service area information, perception support information, and second model interoperability information, wherein the second model interoperability information includes vendor information, supported model formats, and supported model operating environments.

[0098] In some embodiments, the second model interoperability information includes vendor information (e.g., vendor identifier) ​​of the SF network element, as well as supported model formats and supported model operating environments, which helps the target SF network element determine a suitable NWDAF network element as the target NWDAF network element. Here, a suitable NWDAF network element refers to an NWDAF network element that supports the subscription and sharing of models that match the service-aware request information.

[0099] By adding model interoperability information (second model interoperability information and second model interoperability information) to both the second registration information of the SF network element and the first registration information of the NWDAF network element, the smooth collaboration between the SF network element and the NWDAF network element, as well as the smooth operation of model subscription, training and sharing, are ensured.

[0100] By adding second model interoperability information to the second registration information of the SF network element, the SF network element is enhanced, ensuring the feasibility of collaboration between the SF network element and the NWDAF network element. In other words, whether the SF network element and the NWD network element can collaborate can be determined based on whether the second model interoperability information of the SF network element and the first model interoperability information of the NWDAF network element match.

[0101] In some embodiments, the target NWDAF network element is determined based on the service awareness request information, the first registration information of multiple NWDAF network elements, and the second registration information of the target SF network element. For example, the NWDAF network element that matches the service awareness request information and the second registration information of the target SF network element can be selected based on the service awareness request information, the first registration information, and the second registration information of the target SF network element; and the NWDAF network element that matches the service awareness request information and the second registration information of the target SF network element is determined as the target NWDAF network element.

[0102] In some embodiments, the target NWDAF network element is determined from a plurality of NWDAF network elements registered to the storage network element by the target SF network element.

[0103] In some embodiments, if the target SF network element selects multiple suitable NWDAF network elements from the storage network elements, then any suitable NWDAF network element can be selected as the target NWDAF network element.

[0104] In step 130, a model subscription request is sent to the target NWDAF network element.

[0105] In some embodiments, the model subscription request includes model filtering information and second model interoperability information.

[0106] In some embodiments, based on the model filtering information in the model subscription request, an available model that matches the service awareness request information can be selected from multiple models in the target NWDAF network element.

[0107] In some embodiments, the model subscription request includes second model interoperability information, which helps the target NWDAF network element to confirm whether the target SF network element is in the list of vendors that the target NWDAF network element can share models with. It can also confirm whether the model format and model operating environment supported by the target SF network element are consistent with the model format and model operating environment supported by the target NWDAF network element itself, so as to ensure the smooth sharing of models and thus ensure the stability and security of intelligent sensing.

[0108] In some embodiments, after receiving a model subscription request, the target NWDAF network element collects perceptual training data and uses the perceptual training data to train and update the model requested in the model subscription request.

[0109] In step 140, the target model trained by the target NWDAF network element is received.

[0110] In some embodiments, the target SF network element may be co-located with or embedded within the AnLF (Analytic Logic Function) module responsible for model inference, enabling the target SF network element to use the target model to infer perception results based on perception measurement data.

[0111] By combining the integrated communication sensing technology (SF network element) with the analytical capabilities of the NWDAF network element, the optimal allocation of network resources is achieved, the user experience is improved, the intelligence of the integrated communication sensing technology is guaranteed, and the evolution of network intelligence is promoted.

[0112] In some embodiments, after the target NWDAF network element trains the model, the target model is obtained. The target NWDAF network element can store the target model in the ADRF (Analytics Data Repository Function) network element and return the target model to the target SF network element.

[0113] In step 150, the perception results corresponding to the business perception request information are obtained based on the perception measurement data and the target model.

[0114] In some embodiments, the target SF network element can collect sensing measurement data in real time and process the sensing measurement data using a target model.

[0115] Through the collaboration between SF network elements and NWDAF network elements, the subscription, training, and inference of the model (i.e., the perception model) are realized.

[0116] Real-time collection and processing of sensing measurement data by target SF network elements helps optimize the allocation of sensing network resources and improve the overall efficiency of the sensing network.

[0117] In some embodiments, the target SF network element will collect different sensing measurement data according to different sensing modes.

[0118] In some embodiments, if the sensing mode is base station self-sensing and self-receiving, the target SF network element will collect sensing measurement data at the base station side (RAN); if the sensing mode is base station-to-base station sensing, the target SF network element will collect sensing measurement data at multiple base station sides; if the sensing mode is UE-to-base station sensing, the target SF network element will collect sensing measurement data at both the UE side and the base station side; if the sensing mode is UE-self-sensing and self-receiving, the target SF network element will collect sensing measurement data at the UE side; if the sensing mode is UE-to-UE sensing, the target SF network element will collect sensing measurement data at multiple UE sides; if the sensing mode is base station-to-UE sensing, the target SF network element will collect sensing measurement data at both the UE side and the base station side.

[0119] By combining the sensing measurement data collected by SF network elements with the analytical capabilities of NWDAF network elements, deeper data fusion and intelligent analysis can be achieved, thereby optimizing network performance and improving user experience.

[0120] Through collaboration between SF network elements and NWDAF network elements, the sensing capabilities of SF network elements are enhanced, improving the performance and intelligence level of integrated communication and sensing.

[0121] In some embodiments, for example, sensing measurement data can be collected through a target SF network element, and then the sensing measurement data can be input into a target model to obtain sensing results corresponding to the service sensing request information.

[0122] In some embodiments, after obtaining the perception result corresponding to the service perception request information, the target SF network element can send the obtained perception result to the NEF network element, so that the NEF network element can forward the perception result to the AF network element, wherein the service perception request information is sent by the AF network element.

[0123] In some embodiments, the AF network element triggers intelligent sensing by sending a service awareness request message.

[0124] In the above embodiments, the target SF determines the target NWDAF network element based on the service perception request information, the target NWDAF network element obtains the trained target model, and finally, based on the perception measurement data and the target model, the perception result corresponding to the service perception request information is obtained, thus improving the performance and intelligence level of integrated communication and perception. Specifically, the target SF network element can collect and process perception measurement data in real time, and the SF network element helps optimize network resource allocation, improving the overall network efficiency. Furthermore, through the collaboration between the SF network element and the NWDAF network element (i.e., the target SF network element determines the target NWDAF network element, and the target NWDAF network element provides the trained target model to the target SF network element), the data fusion and intelligent analysis capabilities of the integrated communication and perception technology are improved, making it possible to obtain more accurate perception results.

[0125] Figure 2 shows flowcharts of some other embodiments of the intelligent sensing method of this disclosure.

[0126] As shown in Figure 2, the intelligent sensing method includes steps 210 to 270, wherein the intelligent sensing method is executed by the intelligent sensing system.

[0127] In step 210, the target AMF network element sends a service awareness request to the target SF network element.

[0128] In some embodiments, the service-aware request information includes service type information, service requirement information, and target awareness node information.

[0129] In some embodiments, the target AMF network element receives service awareness request information sent by the NEF network element.

[0130] In some embodiments, the target AMF network element determines the target SF network element from multiple SF network elements registered to the storage network element based on the service awareness request information.

[0131] In some embodiments, the NEF network element can receive service awareness request information sent by the AF network element; the NEF network element determines the target AMF network element based on the service awareness request information.

[0132] In some embodiments, the AF network element sends service awareness request information to the NEF network element.

[0133] In step 220, the target SF network element receives service awareness request information sent by the target AMF network element.

[0134] In some embodiments, when the target SF network element receives service awareness request information sent by the target AMF network element, the target SF network element can determine whether to obtain the perception result corresponding to the service awareness request information through the model based on the service awareness request information.

[0135] In some embodiments, when the target SF network element determines that the perception result is obtained through the model, the target SF network element can check whether there is an available model in the target SF network element's local environment that matches the service perception request information. If there is no available model in the target SF network element's local environment that matches the service perception request information, the operation of determining the target NWDAF network element is performed (i.e., step 230 is performed).

[0136] In some embodiments, if there is an available model in the local environment that matches the service-aware request information, the target SF network element determines the available model in the local environment that matches the service-aware request information as the target model.

[0137] In step 230, the target SF network element determines the target NWDAF network element based on the service awareness request information.

[0138] In some embodiments, the target SF network element determines the target NWDAF network element based on service awareness request information, first registration information of multiple NWDAF network elements, and second registration information of the target SF network element.

[0139] In some embodiments, it should be noted that the target SF network element determines the target NWDAF network element based on the service awareness request information, the first registration information of multiple NWDAF network elements, and the second registration information of the target SF network element. The first registration information includes the NWDAF network element's analysis information, service area information, awareness support information, model filtering information, and first model interoperability information. The first model interoperability information includes a list of vendors of shareable models, model formats, and model operating environments. And / or the second registration information includes the SF network element's analysis information, service area information, awareness support information, and second model interoperability information. The second model interoperability information includes vendor information, supported model formats, and supported model operating environments.

[0140] In some embodiments, the target SF network element may select an NWDAF network element that matches the service awareness request information and the second registration information of the target SF network element based on the service awareness request information, the first registration information, and the second registration information of the target SF network element; the target SF network element shall determine the NWDAF network element that matches the service awareness request information and the second registration information of the target SF network element as the target NWDAF network element.

[0141] In some embodiments, the target SF network element can determine the target NWDAF network element from multiple NWDAF network elements registered to the storage network element based on service-aware request information.

[0142] In step 240, the target SF network element sends a model subscription request to the target NWDAF network element.

[0143] In some embodiments, the model subscription request includes model filtering information and second model interoperability information.

[0144] In step 250, the target NWDAF network element receives the model subscription request and sends the trained target model to the target SF network element.

[0145] In step 260, the target SF network element receives the target model.

[0146] In step 270, the target SF network element obtains the perception results corresponding to the service perception request information based on the perception measurement data and the target model.

[0147] In some embodiments, the target SF network element can obtain sensing results by collecting sensing measurement data and then inputting the sensing measurement data into the target model.

[0148] In some embodiments, after the target SF network element obtains the perception result corresponding to the service perception request information, the target SF network element can send the perception result to the target AMF network element, then the target AMF network element forwards the perception result to the NEF network element, and finally the NEF network element forwards the perception result to the AF network element.

[0149] In the above embodiments, the target SF determines the target NWDAF network element based on the service perception request information, the target NWDAF network element obtains the trained target model, and finally, based on the perception measurement data and the target model, the perception result corresponding to the service perception request information is obtained, thus improving the performance and intelligence level of integrated communication and perception. Specifically, the target SF network element can collect and process perception measurement data in real time, and the SF network element helps optimize network resource allocation, improving the overall network efficiency. Furthermore, through the collaboration between the SF network element and the NWDAF network element (i.e., the target SF network element determines the target NWDAF network element, and the target NWDAF network element provides the trained target model to the target SF network element), the data fusion and intelligent analysis capabilities of the integrated communication and perception technology are improved, making it possible to obtain more accurate perception results.

[0150] Figure 3 shows a schematic diagram of some embodiments of the network device disclosed herein.

[0151] As shown in Figure 3, the network device 30 includes a first receiving unit 31, a determining unit 32, a sending unit 33, a second receiving unit 34, and an acquiring unit 35.

[0152] The first receiving unit is configured to receive service awareness request information sent by the AMF network element.

[0153] In some embodiments, the service-aware request information includes service type information, service requirement information, and target awareness node information.

[0154] In some embodiments, the network device 30 is further configured to determine whether to obtain a perception result corresponding to the service perception request information through a model based on the service perception request information; if it is determined that the perception result should be obtained through a model, check whether there is an available model in the local environment of the target SF network element that matches the service perception request information, wherein if there is no available model in the local environment of the target SF network element that matches the service perception request information, the operation of determining the target NWDAF network element is performed.

[0155] In some embodiments, the target SF network element is determined by the target AMF network element from among multiple SF network elements registered to the storage network element based on service awareness request information.

[0156] In some embodiments, the target NWDAF network element is determined from a plurality of NWDAF network elements registered to the storage network element by the target SF network element.

[0157] In some embodiments, the target AMF network element is determined by the Network Open Function (NEF) network element based on the service-aware request information.

[0158] In some embodiments, the network device 30 is further configured to identify the available model in the local environment that matches the service-aware request information as the target model if an available model in the local environment that matches the service-aware request information exists.

[0159] Unit 32 is configured to determine the target NWDAF network element based on the service-aware request information.

[0160] In some embodiments, the determining unit 32 is further configured to determine the target NWDAF network element based on the service-aware request information, the first registration information of a plurality of NWDAF network elements, and the second registration information of the target SF network element.

[0161] In some embodiments, the first registration information includes NWDAF network element analysis information, service area information, perception support information, model filtering information, and first model interoperability information, wherein the first model interoperability information includes a list of vendors of shareable models, model formats, and model operating environments.

[0162] In some embodiments, the second registration information includes analysis information of the SF network element, service area information, perception support information, and second model interoperability information, wherein the second model interoperability information includes vendor information, supported model formats, and supported model operating environments.

[0163] In some embodiments, the determining unit 32 is further configured to select an NWDAF network element that matches the service awareness request information and the second registration information of the target SF network element based on the service awareness request information, the first registration information and the second registration information of the target SF network element; and determine the NWDAF network element that matches the service awareness request information and the second registration information of the target SF network element as the target NWDAF network element.

[0164] Sending unit 33 is configured to send a model subscription request to the target NWDAF network element.

[0165] In some embodiments, the model subscription request includes model filtering information and second model interoperability information.

[0166] The second receiving unit 34 is configured to receive the target model trained by the target NWDAF network element.

[0167] The acquisition unit 35 is configured to acquire the perception result corresponding to the business perception request information based on the perception measurement data and the target model.

[0168] In some embodiments, the acquisition unit 35 is further configured to collect sensing measurement data; input the sensing measurement data into the target model; and acquire sensing results.

[0169] In some embodiments, network device 30 is further configured to send the sensing results to NEF network element so that the sensing results can be forwarded to application function AF network element via NEF network element, wherein the service sensing request information is sent by AF network element.

[0170] In the above embodiments, the target SF determines the target NWDAF network element based on the service perception request information, the target NWDAF network element obtains the trained target model, and finally, based on the perception measurement data and the target model, the perception result corresponding to the service perception request information is obtained, thus improving the performance and intelligence level of integrated communication and perception. Specifically, the target SF network element can collect and process perception measurement data in real time, and the SF network element helps optimize network resource allocation, improving the overall network efficiency. Furthermore, through the collaboration between the SF network element and the NWDAF network element (i.e., the target SF network element determines the target NWDAF network element, and the target NWDAF network element provides the trained target model to the target SF network element), the data fusion and intelligent analysis capabilities of the integrated communication and perception technology are improved, making it possible to obtain more accurate perception results.

[0171] Figure 4 shows schematic diagrams of some other embodiments of the network devices disclosed herein.

[0172] As shown in FIG4, the storage network element 40 of this embodiment includes: a memory 41 and a processor 42 coupled to the memory 41. The processor 42 is configured to execute the intelligent sensing method in any of the embodiments of the present disclosure based on the instructions stored in the memory 61.

[0173] The memory 41 may include, for example, system memory, fixed non-volatile storage media, etc. The system memory stores, for example, the operating system, application programs, boot loader, and other programs.

[0174] The storage network element 40 may also include an input / output interface 43, a network interface 44, and a storage interface 45. These interfaces 43, 44, and 45, as well as the memory 41 and processor 42, can be connected via, for example, a bus 46. The input / output interface 43 provides a connection interface for input / output devices such as monitors, mice, keyboards, touchscreens, microphones, and speakers. The network interface 44 provides a connection interface for various networked devices. The storage interface 45 provides a connection interface for external storage devices such as SD cards and USB flash drives.

[0175] Figure 5 shows a schematic diagram of some embodiments of the intelligent sensing system of this disclosure.

[0176] As shown in Figure 5, the intelligent sensing system 50 includes SF network element 51, AMF network element 52 and NWDAF network element 53.

[0177] SF element 51 is configured as a network device as in any embodiment of this disclosure.

[0178] AMF network element 52 is configured to send service awareness request information to the target SF network element.

[0179] In some embodiments, the AMF network element 52 is further configured to receive service awareness request information and determine the target SF network element from among multiple SF network elements registered to the storage network element based on the service awareness request information.

[0180] In some embodiments, the intelligent sensing system 50 further includes: a NEF network element, configured to receive service perception request information sent by an AF network element, determine a target AMF network element based on the service perception request information, and send the service perception request information to the target AMF network element.

[0181] In some embodiments, the NEF network element is also configured to perform an authorization check on the received service awareness request information, and if the authorization check passes, send the service awareness request information to the target AMF network element.

[0182] In some embodiments, the intelligent sensing system 50 further includes an AF network element, configured to send service sensing request information to the NEF network element and receive sensing results forwarded by the NEF network element.

[0183] NWDAF element 53 is configured to receive model subscription requests from the target SF element and send the trained target model to the target SF element.

[0184] In some embodiments, the NWDAF network element 53 is further configured to: collect perceptual training data; train the model subscribed to by the model subscription request based on the perceptual training data to obtain the trained target model.

[0185] In some embodiments, the intelligent sensing system further includes: a storage network element configured to receive first registration information from a plurality of NWDAF network elements to register the plurality of NWDAF network elements to the storage network element, and to receive second registration information from a plurality of SF network elements to register the plurality of SF network elements to the storage network element.

[0186] In the above embodiments, the target SF determines the target NWDAF network element based on the service perception request information, the target NWDAF network element obtains the trained target model, and finally, based on the perception measurement data and the target model, the perception result corresponding to the service perception request information is obtained, thus improving the performance and intelligence level of integrated communication and perception. Specifically, the target SF network element can collect and process perception measurement data in real time, and the SF network element helps optimize network resource allocation, improving the overall network efficiency. Furthermore, through the collaboration between the SF network element and the NWDAF network element (i.e., the target SF network element determines the target NWDAF network element, and the target NWDAF network element provides the trained target model to the target SF network element), the data fusion and intelligent analysis capabilities of the integrated communication and perception technology are improved, making it possible to obtain more accurate perception results.

[0187] Figure 6 shows schematic diagrams of further embodiments of the intelligent sensing method of this disclosure.

[0188] As shown in Figure 6, the intelligent sensing method includes steps S611 to S624.

[0189] In step S611, the SF network element and the NWDAF network element are registered to the NRF network element through the Nnrf_NFManagement_NFRegister service. The NWDAF network element is an NWDAF network element containing the MTLF (Model Training Logical Function).

[0190] In some embodiments, when an NWDAF network element registers with an NRF network element, it needs to send the first registration information of the NWDAF network element to the NRF network element. The first registration information includes the NWDAF network element's analysis information, service area information, perception support information, model filtering information, and first model interoperability information. The first model interoperability information includes a list of vendors of shareable models, model formats, and model operating environments.

[0191] In some embodiments, when an SF network element registers with an NRF network element, it needs to send the NRF network element second registration information of the SF network element. The second registration information includes the SF network element's analysis information, service area information, perception support information, and second model interoperability information. The second model interoperability information includes vendor information, supported model formats, and supported model operating environments.

[0192] In step S612, the AF network element sends a service awareness request message to the NEF network element.

[0193] In some embodiments, the service awareness request information includes service type (such as dynamic map, vehicle tracking, etc.), service requirements (perception resolution, perception accuracy, duration, target area information, latency, etc.), and specified perception node information (such as UE information).

[0194] In step S613, the NEF network element forwards the service awareness request information to the target AMF network element.

[0195] In some embodiments, the NEF network element performs an authorization check on the service awareness request from the AF network element. If the NEF network element authorizes the request, it selects a suitable target AMF network element and sends a service awareness request message to the target AMF network element.

[0196] In some embodiments, the NEF network element can determine the appropriate target AMF network element based on the specified sensing node information in the service awareness request information.

[0197] In some embodiments, if it is area-oriented perception, the NEF network element will select the target AMF network element serving the area based on the area information in the service perception request information of the AF network element. If it is target-oriented perception, the NEF network element will select the target AMF network element serving the area based on the target location information in the service perception request information of the AF network element. If the target itself has a UE (User Equipment) communication module and has UE capabilities (e.g., a vehicle), then target-oriented perception can be considered as perception of the UE's surroundings. In this case, the serving AMF network element of the UE can be selected as the target AMF network element, and the NEF network element will obtain the AMF information serving the UE by querying the UDM (Unified Data Management) network element.

[0198] In step S614, the target AMF network element selects a suitable target SF network element based on the target area information or target location information in the service awareness request information.

[0199] In step S615, the target AMF network element forwards the service awareness request information to the target SF network element.

[0200] In step S616, the target SF network element pattern service perception request information is used to determine whether to obtain the perception result corresponding to the service perception request information through the model.

[0201] In some embodiments, when it is determined that the perception result is obtained through the model, it is checked whether there is an available model in the local environment of the target SF network element that matches the service perception request information.

[0202] In step S617, if no available model matching the service-aware request information exists in the local environment of the target SF network element, the target SF network element determines the target NWDAF network element in the NRF network element. The target NWDAF network element includes the MTLF.

[0203] In step S618, the NRF network element returns one or more target NWDAF network elements to the target SF network element.

[0204] In step S619, the target SF network element sends a model subscription request to the target NWDAF network element through the Nnwdaf_MLModelProvision_Subscribe service.

[0205] In some embodiments, if the NRF network element returns multiple target NWDAF network elements, the target SF network element may arbitrarily select one target NWDAF network element.

[0206] In some embodiments, the model subscription request includes model filtering information and second model interoperability information.

[0207] In step S620, after the target NWDAF network element receives the model subscription request, it collects perceptual training data and uses the perceptual training data to train and update the model requested in the model subscription request.

[0208] In step S621, the target NWDAF network element can return the trained target model to the target SF network element through the Nnwdaf_MLModelProvision_Notify service.

[0209] In step S622, after receiving the target model, the target SF network element collects perception measurement data (data used for perception result inference) and uses the target model to perform perception result inference, that is, inputs the perception measurement data into the target model to obtain the perception result corresponding to the service perception request information.

[0210] In some embodiments, if the sensing mode is base station self-sensing and self-receiving, the target SF network element will collect sensing measurement data at the base station side (RAN); if the sensing mode is base station-to-base station sensing, the target SF network element will collect sensing measurement data at multiple base station sides; if the sensing mode is UE-to-base station sensing, the target SF network element will collect sensing measurement data at both the UE side and the base station side; if the sensing mode is UE-self-sensing and self-receiving, the target SF network element will collect sensing measurement data at the UE side; if the sensing mode is UE-to-UE sensing, the target SF network element will collect sensing measurement data at multiple UE sides; if the sensing mode is base station-to-UE sensing, the target SF network element will collect sensing measurement data at both the UE side and the base station side.

[0211] In step S623, the target SF network element sends the sensing results to the target AMF network element.

[0212] In step S624, the target AMF network element forwards the sensing result to the NEF network element, and then the NEF network element forwards the sensing result to the AF network element.

[0213] In the above embodiments, the target SF determines the target NWDAF network element based on the service perception request information, the target NWDAF network element obtains the trained target model, and finally, based on the perception measurement data and the target model, the perception result corresponding to the service perception request information is obtained, thus improving the performance and intelligence level of integrated communication and perception. Specifically, the target SF network element can collect and process perception measurement data in real time, and the SF network element helps optimize network resource allocation, improving the overall network efficiency. Furthermore, through the collaboration between the SF network element and the NWDAF network element (i.e., the target SF network element determines the target NWDAF network element, and the target NWDAF network element provides the trained target model to the target SF network element), the data fusion and intelligent analysis capabilities of the integrated communication and perception technology are improved, making it possible to obtain more accurate perception results.

[0214] In some embodiments, a computer program product is protected, comprising a computer program or instructions that, when executed by a processor, implement the intelligent sensing method of this disclosure. The computer program product includes a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device, or installed from a ROM. When the computer program is executed by a CPU, it performs the functions defined in the methods of embodiments of this disclosure.

[0215] Those skilled in the art will understand that embodiments of this disclosure can be provided as methods, systems, or computer program products. Therefore, this disclosure can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this disclosure can take the form of a computer program product embodied on one or more computer-usable non-transitory storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0216] This concludes the detailed description of the intelligent sensing method, network device, intelligent sensing system, computer-readable storage medium, and computer program product disclosed herein. To avoid obscuring the concept of this disclosure, some details known in the art have not been described. Those skilled in the art will fully understand how to implement the technical solutions disclosed herein based on the above description.

[0217] The methods and systems of this disclosure may be implemented in many ways. For example, they may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order of steps for the methods is for illustrative purposes only, and the steps of the methods of this disclosure are not limited to the order specifically described above unless otherwise specifically stated. Furthermore, in some embodiments, this disclosure may also be implemented as a program recorded on a recording medium, the program including machine-readable instructions for implementing the methods according to this disclosure. Thus, this disclosure also covers recording media storing programs for performing the methods according to this disclosure.

[0218] While specific embodiments of this disclosure have been described in detail by way of example, those skilled in the art should understand that the examples are for illustrative purposes only and not intended to limit the scope of this disclosure. Those skilled in the art should understand that modifications can be made to the above embodiments without departing from the scope and spirit of this disclosure. The scope of this disclosure is defined by the appended claims.

Claims

1. An intelligent sensing method, executed by a target sensing function SF network element, comprising: Receive service-aware request information sent by the target access and mobility management function (AMF) network element; Based on the service awareness request information, the target network element for network data analysis function (NWDAF) is determined; Send a model subscription request to the target NWDAF network element; Receive the target model trained by the target NWDAF network element; Based on the perception measurement data and the target model, obtain the perception result corresponding to the business perception request information.

2. The intelligent sensing method according to claim 1 further includes: Based on the business perception request information, determine whether to obtain the perception result corresponding to the business perception request information through the model; If it is determined that the perception result is obtained through the model, check whether there is an available model in the local environment of the target SF network element that matches the service perception request information. If there is no available model in the local environment of the target SF network element that matches the service perception request information, perform the operation of determining the target NWDAF network element.

3. The intelligent sensing method according to claim 2 further includes: If a usable model exists in the local environment that matches the business-aware request information, the usable model in the local environment that matches the business-aware request information is determined as the target model.

4. The intelligent sensing method according to claim 2 or 3, wherein, The step of determining the target network element for network data analysis (NWDAF) based on the service awareness request information includes: The target NWDAF network element is determined based on the service awareness request information, the first registration information of multiple NWDAF network elements, and the second registration information of the target SF network element.

5. The intelligent sensing method according to claim 4, wherein, The first registration information includes NWDAF network element analysis information, service area information, perception support information, model filtering information, and first model interoperability information. The first model interoperability information includes a list of vendors of shareable models, model formats, and model operating environments; and / or The second registration information includes the analysis information of the SF network element, service area information, perception support information, and second model interoperability information. The second model interoperability information includes vendor information, supported model formats, and supported model operating environments.

6. The intelligent sensing method according to claim 4 or 5, wherein, The step of determining the target NWDAF network element based on the service awareness request information, the first registration information of multiple NWDAF network elements, and the second registration information of the target SF network element includes: Based on the service awareness request information, the first registration information, and the second registration information of the target SF network element, select an NWDAF network element that matches the service awareness request information and the second registration information of the target SF network element; The NWDAF network element that matches the service awareness request information and the second registration information of the target SF network element is identified as the target NWDAF network element.

7. The intelligent sensing method according to any one of claims 1 to 6, wherein, The business perception request information includes business type information, business requirement information, and target perception node information.

8. The intelligent sensing method according to claim 7, wherein, The target SF network element is determined by the target AMF network element from multiple SF network elements registered to the storage network element based on the service awareness request information.

9. The intelligent sensing method according to any one of claims 1 to 8, wherein, The target NWDAF network element is determined from multiple NWDAF network elements registered to the storage network element by the target SF network element.

10. The intelligent sensing method according to claims 7 to 9, wherein, The target AMF network element is determined by the Network Open Function (NEF) network element based on the service awareness request information.

11. The intelligent sensing method according to any one of claims 1 to 10, wherein, The model subscription request includes model filtering information and second model interoperability information.

12. The intelligent sensing method according to any one of claims 1 to 11, wherein, The step of obtaining the perception result corresponding to the business perception request information based on the perception measurement data and the target model includes: Collect the sensing measurement data; The perception measurement data is input into the target model to obtain the perception result.

13. The intelligent sensing method according to any one of claims 1 to 12, further comprising: The sensing results are sent to the NEF network element, which then forwards the sensing results to the application function AF network element, wherein the service sensing request information is sent by the AF network element.

14. An intelligent sensing method, executed by an intelligent sensing system, comprising: The target AMF network element sends a service awareness request message to the target SF network element; The target SF network element receives the service awareness request information sent by the target AMF network element; The target SF network element determines the target NWDAF network element based on the service awareness request information; The target SF network element sends a model subscription request to the target NWDAF network element; The target NWDAF network element receives the model subscription request and sends the trained target model to the target SF network element; The target SF network element receives the target model; The target SF network element obtains the perception result corresponding to the service perception request information based on the perception measurement data and the target model.

15. The intelligent sensing method according to claim 14, further comprising: The target SF network element determines whether to obtain the perception result corresponding to the service perception request information through the model based on the service perception request information. If it is determined that the perception result is obtained through the model, the target SF network element checks whether there is an available model in the local environment of the target SF network element that matches the service perception request information. If there is no available model in the local environment of the target SF network element that matches the service perception request information, the operation of determining the target NWDAF network element is performed.

16. The intelligent sensing method according to claim 15, further comprising: If a usable model matching the service awareness request information exists in the local environment, the target SF network element determines the usable model matching the service awareness request information in the local environment as the target model.

17. The intelligent sensing method according to claim 15 or 16, wherein, The target SF network element determines the target NWDAF network element based on the service awareness request information, including: The target SF network element determines the target NWDAF network element based on the service awareness request information, the first registration information of multiple NWDAF network elements, and the second registration information of the target SF network element.

18. The intelligent sensing method according to claim 17, wherein, The first registration information includes NWDAF network element analysis information, service area information, perception support information, model filtering information, and first model interoperability information. The first model interoperability information includes a list of vendors of shareable models, model formats, and model operating environments; and / or The second registration information includes the analysis information of the SF network element, service area information, perception support information, and second model interoperability information. The second model interoperability information includes vendor information, supported model formats, and supported model operating environments.

19. The intelligent sensing method according to claim 17 or 18, wherein, The target SF network element determines the target NWDAF network element based on the service awareness request information, the first registration information of multiple NWDAF network elements, and the second registration information of the target SF network element, including: The target SF network element selects an NWDAF network element that matches the service awareness request information and the second registration information of the target SF network element based on the service awareness request information, the first registration information, and the second registration information of the target SF network element. The target SF network element will identify the NWDAF network element that matches the service awareness request information and the second registration information of the target SF network element as the target NWDAF network element.

20. The intelligent sensing method according to any one of claims 14 to 19, further comprising: The target AMF network element receives the service awareness request information sent by the NEF network element; The target AMF network element determines the target SF network element from multiple SF network elements registered to the storage network element based on the service awareness request information.

21. The intelligent sensing method according to any one of claims 14 to 20, wherein, The target SF network element determines the target NWDAF network element based on the service awareness request information, including: The target SF network element determines the target NWDAF network element from multiple NWDAF network elements registered to the storage network element based on the service awareness request information.

22. The intelligent sensing method according to any one of claims 14 to 21, further comprising: The NEF network element receives the service awareness request information sent by the AF network element; The NEF network element determines the target AMF network element based on the service awareness request information.

23. The intelligent sensing method according to any one of claims 14 to 22, wherein, The target SF network element obtains the perception result corresponding to the service perception request information based on the perception measurement data and the target model, including: The target SF network element collects the sensing measurement data; The target SF network element inputs the sensing measurement data into the target model to obtain the sensing results.

24. The intelligent sensing method according to any one of claims 14 to 23, further comprising: The target SF network element sends the sensing result to the target AMF network element; The target AMF network element forwards the sensing result to the NEF network element; The NEF network element forwards the sensing results to the AF network element.

25. The intelligent sensing method according to any one of claims 14 to 24, further comprising: The AF network element sends the service awareness request information to the NEF network element.

26. A network device, comprising: The first receiving unit is configured to receive service awareness request information sent by the AMF network element; The determining unit is configured to determine the target NWDAF network element based on the service awareness request information; The sending unit is configured to send a model subscription request to the target NWDAF network element; The second receiving unit is configured to receive the target model trained by the target NWDAF network element; The acquisition unit is configured to acquire the perception result corresponding to the business perception request information based on the perception measurement data and the target model.

27. A network device, comprising: Memory; and A processor coupled to the memory, the processor being configured to execute the intelligent sensing method of any one of claims 1 to 25 based on instructions stored in the memory.

28. An intelligent sensing system, comprising: The SF network element is configured as a network device as described in claim 26 or 27; The AMF network element is configured to send the service awareness request information to the target SF network element; The NWDAF network element is configured to receive the model subscription request from the target SF network element and send the trained target model to the target SF network element.

29. The intelligent sensing system according to claim 28, wherein, The NWDAF network element is also configured as follows: Collect perceptual training data; The model subscribed to by the model subscription request is trained based on the perception training data to obtain the trained target model.

30. The intelligent sensing system according to claim 28 or 29, further comprising: The storage network element is configured to receive first registration information from multiple NWDAF network elements to register the multiple NWDAF network elements to the storage network element, and to receive second registration information from multiple SF network elements to register the multiple SF network elements to the storage network element.

31. The intelligent sensing system according to any one of claims 28 to 30, wherein, The AMF network element is also configured to receive the service awareness request information and determine the target SF network element from multiple SF network elements registered in the storage network element based on the service awareness request information.

32. The intelligent sensing system according to any one of claims 28 to 31, further comprising: The NEF network element is configured to receive the service awareness request information sent by the AF network element, determine the target AMF network element based on the service awareness request information, and send the service awareness request information to the target AMF network element.

33. The intelligent sensing system according to claim 32, wherein, The NEF network element is also configured to perform an authorization check on the received service awareness request information, and if the authorization check passes, send the service awareness request information to the target AMF network element.

34. The intelligent sensing system according to any one of claims 28 to 33, further comprising: The AF network element is configured to send the service awareness request information to the NEF network element and receive the awareness result forwarded by the NEF network element.

35. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the intelligent sensing method according to any one of claims 1 to 25.

36. A computer program product comprising a computer program that, when executed by a processor, implements the intelligent sensing method according to any one of claims 1 to 25.

37. A computer program comprising: An instruction, when executed by the processor, causes the processor to perform the intelligent sensing method as described in any one of claims 1 to 25.

Images