Sensing and communication method, sensing and communication system, electronic device and storage medium

Abstract

The present disclosure provides a sensing and communication method, a sensing and communication system, an electronic device and a storage medium. The method is applied to a core network, and the core network comprises a sensing function entity and a sensing server. The method comprises: receiving first sensing data sent by a sensing node; and on the basis of a first artificial intelligence model trained by the sensing server, and by means of the sensing function entity, processing the first sensing data to obtain a first sensing result.

Description

Perception communication method, perception communication system, electronic device and storage medium

[0001] This disclosure claims priority to Chinese patent application No. 202311869832.2, filed on December 29, 2023, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present disclosure relates to the field of communication technology, and in particular to a perception communication method, a perception communication system, an electronic device, and a storage medium. Background Art

[0003] With the widespread application of fifth-generation (5G) communication systems, 5G is gradually penetrating into various industries and fields of society while meeting the needs of individual users, thus achieving an upgrade from consumer to industrial applications. Among them, artificial intelligence-based perception communication systems, based on existing network architectures and communication waveforms, use existing communication equipment to implement perception applications, promote the development of innovative application services, and are an important research direction of 5G. Summary of the Invention

[0004] In a first aspect, a perception communication method is provided, which is applied to a core network, wherein the core network includes a perception function entity and a perception server. The method includes:

[0005] receiving first sensing data sent by the sensing node;

[0006] Based on the first artificial intelligence model trained by the perception server, the first perception data is processed by the perception function entity to obtain a first perception result.

[0007] In a second aspect, a perception communication method is provided, which is applied to a perception node. The method includes:

[0008] receiving a first perception control instruction sent by a perception function entity in a core network, where the first perception control instruction is used to instruct a perception node to perform perception detection;

[0009] In response to the first perception control instruction, sending a first perception signal and acquiring first perception data;

[0010] The first perception data is sent to a perception function entity in the core network.

[0011] In a third aspect, a perception communication method is provided for use with an intelligent agent in an edge network. The method includes:

[0012] Acquiring second sensing data from the sensing node;

[0013] The second perception data is processed based on the second artificial intelligence model to obtain a second perception result.

[0014] In a fourth aspect, a perception communication system is provided, the perception communication system comprising: a perception node and a core network, the core network comprising a perception function entity and a perception server;

[0015] A perception node, configured to provide first perception data to a core network;

[0016] The core network is used to process the first perception data through the perception function entity based on the first artificial intelligence model trained by the perception server to obtain a first perception result.

[0017] In a fifth aspect, a communication device is provided, comprising: a memory and a processor; the memory and the processor are coupled; the memory is used to store a computer program; and when the processor executes the computer program, the perceptual communication method described in any one of the above aspects or embodiments is implemented.

[0018] In a sixth aspect, a computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the perceptual communication method described in any one of the above aspects or embodiments is implemented.

[0019] In a seventh aspect, a computer program product is provided, which includes computer program instructions, and when the computer program instructions are executed by a processor, the perceptual communication method described in any one of the above aspects or embodiments is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the present disclosure, the following briefly introduces the drawings required for use in some embodiments of the present disclosure. Obviously, the drawings described below are only drawings of some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0021] FIG1 is a schematic diagram of a perception scenario provided by some embodiments of the present disclosure.

[0022] FIG2 is a schematic diagram of the architecture of a perception communication system provided by some embodiments of the present disclosure.

[0023] FIG3 is a flow chart of a model training method provided in some embodiments of the present disclosure.

[0024] FIG4 is a flow chart of a perceptual communication method provided in some embodiments of the present disclosure.

[0025] FIG5 is a schematic diagram of a range Doppler map provided by some embodiments of the present disclosure.

[0026] FIG6 is a schematic diagram of a corresponding relationship of feature data provided by some embodiments of the present disclosure.

[0027] FIG7 is a schematic diagram of the architecture of a convolutional neural network provided in some embodiments of the present disclosure.

[0028] FIG8 is a schematic diagram of the structure of a long short-term memory neural network model provided by some embodiments of the present disclosure.

[0029] FIG9 is a schematic diagram of the structure of another long short-term memory neural network model provided by some embodiments of the present disclosure.

[0030] FIG10 is a flow chart of another perceptual communication method provided in some embodiments of the present disclosure.

[0031] FIG11 is a flow chart of another perceptual communication method provided in some embodiments of the present disclosure.

[0032] FIG12 is a flow chart of another perceptual communication method provided in some embodiments of the present disclosure.

[0033] FIG13 is a flow chart of another perceptual communication method provided in some embodiments of the present disclosure.

[0034] FIG14 is a flow chart of another perceptual communication method provided in some embodiments of the present disclosure.

[0035] FIG15 is a flow chart of another perceptual communication method provided in some embodiments of the present disclosure.

[0036] FIG16 is a schematic structural diagram of a perception communication device provided in some embodiments of the present disclosure.

[0037] FIG17 is a schematic structural diagram of another perception communication device provided in some embodiments of the present disclosure.

[0038] FIG18 is a schematic structural diagram of another perception communication device provided in some embodiments of the present disclosure.

[0039] FIG19 is a schematic structural diagram of a communication device provided in some embodiments of the present disclosure. DETAILED DESCRIPTION

[0040] The following will clearly and completely describe the technical solutions of this disclosure in conjunction with the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of this disclosure, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of this disclosure without making any creative efforts shall fall within the scope of protection of this disclosure.

[0041] It should be noted that in this disclosure, words such as "exemplarily" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described in this disclosure as "exemplary" or "for example" should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplarily" or "for example" is intended to present the relevant concepts by way of example.

[0042] In the following, the terms "first," "second," etc. are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the quantity of the technical features indicated. Therefore, a feature specified as "first," "second," etc. may explicitly or implicitly include one or more of the features.

[0043] In the description of this disclosure, unless otherwise specified, " / " means "or." For example, A / B can mean A or B. "And / or" herein is simply a description of an association between related objects, indicating that three possible relationships exist. For example, "A and / or B" can mean: only A, only B, and A and B. Furthermore, "at least one" means one or more, and "a plurality" means two or more.

[0044] The methods provided in the embodiments of the present disclosure can be applied to various communication systems. For example, the communication system can be a 5G communication system, a Wi-Fi (wireless fidelity) system, a 3GPP (the 3rd Generation Partnership Project)-related communication system, a future evolved communication system (such as 6G), or a system integrating multiple systems, and the embodiments of the present disclosure are not limited thereto.

[0045] With the widespread application of 5G, 5G is gradually penetrating into various industries and fields of society while meeting the needs of individual users, thus realizing the upgrade from consumer to industrial application. Synaesthesia integration is based on the existing network architecture and communication waveform, and uses existing communication equipment to realize perception applications, which promotes the development of innovative application services and is an important research direction of 5G. As shown in Figure 1, a schematic diagram of a perception scenario provided by an embodiment of the present disclosure is provided. The perception system in the perception base station 1 can perform base station perception of the drone 2, the human body 3, the vehicle 4 and the building 5. The perception system in the satellite 6 can perform satellite perception of the aircraft 7 (illustrated as an airplane). The perception system in the drone 2 can perform drone perception of the human body, and the perception terminal in the vehicle 4 can perform terminal perception of the human body 3.

[0046] In some embodiments, the terminal for terminal perception may also be a device with full-duplex transmission capability. The terminal may be a mobile phone, a tablet computer, a computer with wireless transceiver function, a virtual reality (VR) terminal, an augmented reality (AR) terminal, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home, etc. The embodiments of the present disclosure do not limit the application scenarios. The terminal may sometimes also be referred to as a user, user equipment (UE), an access terminal, a UE unit, a UE station, a mobile station, a mobile station, a remote station, a remote terminal, a mobile device, a UE terminal, a wireless communication device, a UE agent or a UE device, etc., and the embodiments of the present disclosure do not limit this.

[0047] Among currently used perception functions, future mobile communication systems, such as the sixth generation (6G) communication system, will feature increasingly complex and diverse network scales, service types, and terminal devices. This will increase communication range, complex connections, and increased information exchange, placing high demands on perception. Therefore, intelligent management of perception is an inevitable trend. However, existing perception communication systems still largely separate communication and perception, relying heavily on expert communication experience and perception optimization algorithms. As the number of parameters increases, network maintenance and optimization become increasingly difficult.

[0048] In response to the above technical problems, the embodiments of the present disclosure provide a perception communication method, the idea of ​​which is to add perception function entities and perception servers to the existing core network architecture, so that the core network itself also has the ability of intelligent computing, and through the interaction between the core network, the intelligent body located in the edge network and the perception nodes, the sharing of perception data and the integration of artificial intelligence models are realized, thereby reducing the complexity of artificial model training. At the same time, the perception data is processed based on the trained artificial intelligence model to obtain the perception results, so that the method of obtaining the perception results is more accurate and less prone to errors, and it is convenient to open data to other modules in the system or third parties to realize real-time communication between each module in the perception communication system and complete the perception task.

[0049] Referring to Figure 2, which is a schematic diagram of the architecture of a perception communication system provided by an embodiment of the present disclosure, the system includes: perception nodes and a core network.

[0050] In some embodiments, the perception node is configured to provide first perception data to the core network.

[0051] In some embodiments, the core network includes a sensing function entity (SF) and a sensing server (SS), which is used to process the first perception data through the sensing function entity based on the first artificial intelligence model trained by the sensing server to obtain a first perception result.

[0052] In some embodiments, the perceptual communication system further includes an intelligent agent located in the edge network.

[0053] In some embodiments, the sensing node is configured to provide second sensing data to the agent.

[0054] In some embodiments, the intelligent agent includes a perception function entity and a perception server, which is used to process the second perception data based on a second artificial intelligence model to obtain a second perception result.

[0055] For example, the perception server in the intelligent agent is used to train the second artificial intelligence model, and the perception functional entity in the intelligent agent is used to process the second perception data based on the second artificial intelligence model to obtain a second perception result.

[0056] In some embodiments, the intelligent agent is further used to send at least one of the following to the core network: a perception service request message, a perception service response message, second perception data, a second perception result, and a second artificial intelligence model.

[0057] In some embodiments, the core network is also used to send at least one of the following to the intelligent agent: a perception service request message, a perception service response message, first perception data, a first perception result, and a first artificial intelligence model.

[0058] In some embodiments, the core network is further configured to send a first perception control instruction to the perception node in response to the perception service request message.

[0059] The perception service request message is sent by an intelligent agent located in the edge network to the core network; or, the perception service request message is generated by an application function network element in the core network, and the first perception control instruction is used to instruct the perception node to perform perception detection.

[0060] For example, the core network is further configured to send a first perception control instruction to the perception node through the perception function entity in the core network in response to the perception service request message.

[0061] In some embodiments, the core network is also used to receive at least one of the following contents sent by an intelligent agent located in the edge network: a perception service request message, a perception service response message, a second perception data, a second perception result, and a second artificial intelligence model.

[0062] The second perception result is obtained by the perception function entity in the intelligent body based on the perception server in the intelligent body training the second artificial intelligence model to process the second perception data.

[0063] In some embodiments, the perception function entity is configured with at least one of the following functions: perception control function, perception management function, artificial intelligence function, perception processing function, and data preprocessing function.

[0064] In some embodiments, the perception control function includes at least one of the following: selection of perception nodes, management of perception resources, management of perception time, management of artificial intelligence applications, and management of information transmission.

[0065] In some embodiments, the perception management function includes at least one of the following: obtaining perception business needs, authenticating perception business needs, determining perception tasks based on perception business needs, artificial intelligence model fusion, perception data fusion, and perception result fusion.

[0066] For example, when the perception management function obtains the first artificial intelligence model sent by the perception server of the core network and the second artificial intelligence model sent by the intelligent agent located in the edge network, the first artificial intelligence model and the second artificial intelligence model are integrated to obtain a more complete and accurate artificial intelligence model.

[0067] For example, when the perception management function obtains the first perception data sent by the perception node and the second perception data sent by the intelligent agent located in the edge network, the first perception data and the second perception data are fused to obtain more complete and accurate perception data.

[0068] For example, after the perception management function obtains a first perception result and a second perception result sent by an intelligent agent located in the edge network, the first perception result and the second perception result are fused to obtain a more complete and accurate perception result.

[0069] In some embodiments, the artificial intelligence function includes at least one of the following: training an artificial intelligence model and using an artificial intelligence model.

[0070] In some embodiments, the perception processing function is used to perform target detection, false alarm suppression, target association, trajectory tracking, target identification, and trajectory correction of perception data.

[0071] In some embodiments, the data preprocessing function is used to extract feature data or normalize the perception data.

[0072] In some embodiments, the perception functional entity is also used to obtain a trained artificial intelligence model from a perception server.

[0073] In some embodiments, the perception functional entity is also used to process perception data based on an artificial intelligence model to obtain perception results.

[0074] The perception results are used for at least one of the following: target detection, trajectory tracking, trajectory correction, target association, and target recognition.

[0075] In some embodiments, the perception function entity may also send a perception control instruction to the perception node, where the perception control instruction is used to select the perception node to perform the perception task.

[0076] In some embodiments, the perception function entity may also send at least one of the following contents to the perception server: first indication information for indicating whether the perception server performs model training, and second indication information for indicating a training cycle.

[0077] For example, the perception control function in the perception function entity sends at least one of the following contents to the perception server: first indication information for indicating whether the perception server performs model training, and second indication information for indicating a training cycle.

[0078] In some embodiments, the core network also fuses the acquired artificial intelligence models to reduce the training complexity of large models.

[0079] In some embodiments, the core network further includes at least one of the following network elements: network slice selection function (NSSF), network exposure function (NEF), network repository function (NRF), policy control function (PCF), unified data management (UDM), application function (AF), authentication server function (AUSF), access and mobility management function (AMF), session management function (SMF), user plane function (UPF) or other possible network functions (NF).

[0080] In some embodiments, NSSF uses slicing technology to virtualize multiple end-to-end networks on a common hardware basis. Each network has different NFs to adapt to different types of service requirements.

[0081] In some embodiments, the NEF is located between the 5G core network and external third-party application functions, responsible for managing externally exposed network data. All external applications that want to access data within the 5G core network must go through the NEF.

[0082] In some embodiments, NRF is used to register, manage and detect the status of NFs to achieve automated management of all NFs. When each NF is started, it must register with NRF before it can provide services. The registration information includes the NF type, address and service list.

[0083] In some embodiments, the PCF is used to manage network behavior using a unified policy framework and to execute relevant policies in conjunction with user information in a unified data repository (UDR).

[0084] In some embodiments, the UDM is used to manage user identification, subscription data, and authentication data, and is also used to manage the user's service network element registration.

[0085] In some embodiments, AF refers to various services at the application layer, which can be an application within the operator or a third-party AF (such as a video server or a game server). If it is an AF within the operator, it is in the same trusted domain as other NFs and can directly interact with other NFs. However, a third-party AF is not in the trusted domain and needs to access other NFs through NEF.

[0086] In some embodiments, AUSF is used to receive a request from AMF to authenticate the user equipment (UE), request a key from UDM, and then forward the key issued by UDM to AMF for authentication processing.

[0087] In some embodiments, AMF is used to provide a session management message transmission channel for UE and SMF, and to provide authentication, authorization functions, terminals and wireless core network control plane access points for user access.

[0088] In some embodiments, SMF is used together with AMF to support customized mobility management solutions, such as mobile initiated connection only (MICO) or radio access network (RAN) enhancements.

[0089] In some embodiments, the UPF is mainly used to send UE service data to the data network (DN), identify data and services, execute actions and policies, etc.

[0090] In some embodiments, the perception server is used to train an artificial intelligence model, and the artificial intelligence model is used to process perception data to obtain perception results.

[0091] In some embodiments, the training of the artificial intelligence model can be carried out by offline training and online prediction, or by online training and online prediction.

[0092] See Figure 3, which is a flow chart of a model training method provided by an embodiment of the present disclosure. As shown in Figure 3, taking the offline training and online prediction method of the artificial intelligence model as an example, the training of the artificial intelligence model includes four stages: the initial stage, the training stage, the prediction stage, and the collection stage.

[0093] In the initial stage of artificial intelligence model training, the perception server can store an initial data set using simulation data or actual scene measured data, and use the initial data set for initial training to obtain an initial training model. In the training stage of artificial intelligence model training, when the training data accumulates to a certain amount, periodic artificial intelligence model training is carried out. In the prediction stage of artificial intelligence model training, the perception function entity makes real-time online predictions and passes the pre-processed data with high confidence and the corresponding perception results to the perception server for training sample collection. In the collection stage of artificial intelligence model training, the perception server continuously collects data for periodic training of the artificial intelligence model.

[0094] In some embodiments, the online training and online prediction methods of the artificial intelligence model may refer to the artificial intelligence function in the perception function entity, which may perform some lightweight online training and online prediction, and pass the high-confidence pre-processed data and corresponding perception results to the perception server for training sample collection.

[0095] In some embodiments, the perception server is also used to send the trained artificial intelligence model to the perception function entity.

[0096] In some embodiments, the perception server is further configured with at least one of the following functions: service control function, data preprocessing function, data storage function, and data opening function.

[0097] The service control functions include at least one of the following: management of artificial intelligence applications, management of model training time, management of data openness, and management of information transmission; data preprocessing function, used to extract feature data or normalize perception data; data storage function, used to store perception data with higher confidence as a data set for subsequent periodic training of artificial intelligence models; data openness function, used to provide at least one of perception data, perception results, and artificial intelligence models to the outside world.

[0098] In some embodiments, the management of artificial intelligence applications is used to determine whether the perception server performs training of the artificial intelligence model; the management of model training time is used to determine the training cycle of the artificial intelligence model; the management of data openness function is used to determine whether the perception data and perception results are open and shared; and the management of information transmission is used to determine whether the open and shared perception data and perception results are transmitted.

[0099] In some embodiments, the perception server is further used to send at least one of the following contents to the core network: perception data, artificial intelligence model.

[0100] In some embodiments, the perception node is further used to receive a first perception control instruction sent by a perception function entity in the core network.

[0101] The first perception control instruction is used to instruct the perception node to perform perception detection.

[0102] In some embodiments, the perception node is further configured to send a first perception signal and obtain first perception data in response to a first perception control instruction.

[0103] For example, after the perception node receives the first perception control instruction sent by the perception function entity, the perception node sends a first perception signal according to the perception method indicated by the first perception control instruction, performs the first perception task, and obtains the first perception data.

[0104] It should be noted that the first perception data may be measurement data of the physical layer or perception result data.

[0105] In some embodiments, the perception node is further configured to send first perception data to a perception function entity in the core network.

[0106] For example, after the perception node obtains the perception data, it sends the perception data to the perception function entity.

[0107] In some embodiments, the perception node is further used to receive a second perception control instruction sent by an intelligent agent located in the edge network.

[0108] The second perception control instruction is used to instruct the perception node to perform perception detection.

[0109] In some embodiments, the sensing node is further configured to send a second sensing signal and obtain second sensing data in response to a second sensing control instruction.

[0110] For example, after the perception node receives the second perception control instruction sent by the intelligent agent located in the edge network, the perception node sends a second perception signal according to the perception method indicated by the second perception control instruction, performs the second perception task, and obtains second perception data.

[0111] In some embodiments, the sensing node is further configured to send second sensing data to the agent.

[0112] In some embodiments, referring to FIG2 , there may be multiple sensing nodes, and communication between the sensing nodes is achieved through a Uu interface (U stands for user to network interface, and u stands for Universal). Each sensing node may be a generation node B (gNB) base station or a UE.

[0113] In some embodiments, the perception data or perception results processed by the UE are transmitted to the perception function entity or intelligent agent through the Uu interface and the gNB base station.

[0114] In some embodiments, the perception node is also used for perception signal processing, communication signal processing, and manual training and prediction of artificial intelligence models.

[0115] It should be noted that the system architecture and application scenarios described in the embodiments of the present disclosure are intended to more clearly illustrate the technical solutions of the embodiments of the present disclosure, and do not constitute a limitation on the technical solutions provided by the embodiments of the present disclosure. Ordinary technicians in this field can know that with the evolution of the system architecture and the emergence of new business scenarios, the technical solutions provided by the embodiments of the present disclosure are also applicable to similar technical problems.

[0116] A perception communication method provided by an embodiment of the present disclosure is described below with reference to the accompanying drawings.

[0117] 4 is a flow chart of a perception communication method provided in an embodiment of the present disclosure, which is applied to a core network. The core network includes a perception function entity and a perception server. As shown in FIG4 , the method includes the following steps:

[0118] S101. The core network receives first perception data sent by a perception node.

[0119] In some embodiments, after the core network receives a perception service request message generated by an application function network element in the core network, in response to the perception service request message, the perception function entity in the core network sends a first perception control instruction to the perception node.

[0120] The first perception control instruction is used to instruct the perception node to perform perception detection.

[0121] Furthermore, after the perception node receives the first perception control instruction sent by the perception function entity in the core network, it sends a first perception signal in response to the first perception control instruction and obtains first perception data.

[0122] In some embodiments, after the sensing node obtains the first sensing data, the sensing node sends the first sensing data to the core network, and the core network receives the first sensing data sent by the sensing node.

[0123] S102. The core network processes the first perception data through the perception function entity based on the first artificial intelligence model trained by the perception server to obtain a first perception result.

[0124] In some embodiments, after the core network obtains the first perception data sent by the perception node, the perception function entity in the core network can obtain the trained first artificial intelligence model from the perception server, and process the first perception data through the first artificial intelligence model to obtain a first perception result.

[0125] For example, when the core network sends a perception service request message to the perception function entity, the perception function entity receives the perception service request message sent by the core network and obtains the trained artificial intelligence model from the perception server.

[0126] In some embodiments, the awareness service request message may carry the awareness service type, awareness area, awareness reporting content, and awareness reporting type.

[0127] The perception service type can be drone perception, vehicle perception, or perception of other targets. The perception area can be within a radius of 1,000 meters centered on the perception node or other ranges. The perception reporting content can include the position and speed of the target. The perception reporting type can be perception result reporting.

[0128] It should be noted that the target may also be a person, a car or other object with a moving track or a state change, and the present disclosure does not limit the type of the target.

[0129] In some embodiments, the perception function entity selects a perception node to perform perception detection in response to a perception service request message, and obtains first perception data obtained by the perception node during the perception detection process.

[0130] In some embodiments, the sensing function entity selects a sensing node for sensing detection in response to the sensing service request message, and obtains first sensing data obtained by the sensing node during the sensing detection process, which can be implemented as follows:

[0131] A1. The perception function entity determines the perception task based on the perception service request message.

[0132] For example, the perception function entity responds to the perception service request message, authenticates the perception service request message through the perception management function in the perception function entity, and after the perception service request message is authenticated, the perception management function determines the perception task based on the perception service request message (such as perceiving the drones within the perception area, mainly perceiving the position and speed of the drones).

[0133] A2. The perception function entity selects a perception node that performs a perception task and sends a first perception control instruction to the perception node.

[0134] The first perception control instruction is used to instruct the perception node to perform a perception task. The first perception control instruction includes perception configuration information, and the perception configuration information is used to configure at least one of perception resources, perception time, and perception signals.

[0135] For example, after the perception task is determined, the perception management function in the perception function entity sends a perception service request message to the perception control function. The perception control function in the perception function entity selects the perception node and perception method to perform the perception task according to the perception service request message, and sends a first perception control instruction to the perception node.

[0136] In some embodiments, the sensing node may be a base station, and the sensing mode may be A-transmit-A-receive or A-transmit-B-receive.

[0137] It should be noted that A sends and A receives refers to sending perception signals through perception node A (or base station A) and receiving perception data through perception node A (or base station A), and A sends and B receives refers to sending perception signals through perception node A (or base station A) and receiving perception data through perception node B (or base station B).

[0138] Furthermore, the sensing node starts to perform the sensing task, performs sensing detection on the sensing area, obtains first sensing data obtained during the sensing detection process, and sends the first sensing data to the core network.

[0139] In some embodiments, the perception node receives a perception signal reflected from the target according to the synaesthesia-integrated perception time-frequency resource indicated by the first perception control function, performs baseband processing on the perception signal, and obtains first perception data of the target.

[0140] In some embodiments, the first sensing data may be range-doppler (RD) map data of the target.

[0141] A3. The core network receives the first perception data sent by the perception node.

[0142] In some embodiments, after the perception node obtains the first perception data obtained during the perception detection process, it sends the first perception data (such as RD graph data) to the core network, and the core network receives the first perception data.

[0143] Furthermore, after the core network receives the first perception data sent by the perception node, the perception function entity in the core network processes the first perception data based on the first artificial intelligence model to obtain a first perception result.

[0144] It can be understood that based on the perception communication method provided by the embodiment of the present disclosure, by adding perception function entities and perception servers to the existing core network architecture, the core network itself also has the ability of model training and intelligent computing. At the same time, the first artificial intelligence model trained based on the perception server processes the perception data to obtain the first perception result, making the method of obtaining the first perception result more accurate and less prone to errors.

[0145] In some embodiments, the first artificial intelligence model can be trained through a perception server. After the perception function entity obtains the first perception data sent by the perception node, the perception processing function in the perception function entity preprocesses the first perception data and sends the first perception data to the perception server. The perception server trains the first artificial intelligence model based on the preprocessed first perception data.

[0146] In some embodiments, the perception server trains the first artificial intelligence model in response to first indication information sent by the perception control function in the perception function entity to instruct the perception server to perform model training.

[0147] 5, FIG5 is a schematic diagram of a range Doppler map provided by an embodiment of the present disclosure, as shown in FIG5, P (m，n) Indicates the power of the grid at the mth row and nth column in the RD diagram.

[0148] In some embodiments, in the initial stage of training the first artificial intelligence model, the perception server uses the initial test data to perform model training on the first artificial intelligence model. After the RD graph of the perception signal is determined, the test unit and the protection unit of the RD data are extracted from the RD graph according to the reference unit in the RD graph. The figure shows the power data of 9 grids, which constitute the feature data of [P0, P1, P2, P3, P4, P5, P6, P7, P8]. This group of feature data is used as a sample data, and its corresponding label is 0 or 1, where 0 represents no target and 1 represents a target. The corresponding relationship is shown in Figure 6, which is a schematic diagram of the corresponding relationship of feature data provided in an embodiment of the present disclosure.

[0149] In some embodiments, the present disclosure adopts a convolutional neural network (CNN) network for training the model. FIG7 is a schematic diagram of the architecture of a convolutional neural network provided by an embodiment of the present disclosure. As shown in FIG7 , Conv L j L in (P1,P1) j is the number of convolution kernels, and (P1,P1) represents the size of the convolution kernel.

[0150] It should be noted that network training is not limited to CNN networks, and other networks can also be used, such as residual neural networks (ResNet).

[0151] In some embodiments, in addition to the input layer and the fully connected layer, the CNN network structure may also have J layers of networks in the middle, and each layer of the network includes convolution, activation, and pooling operations.

[0152] It should be noted that the CNN network model is a type of feedforward neural network that includes convolution calculations and has a deep structure. The CNN network model has representation learning capabilities and can perform translation-invariant classification of input information according to its hierarchical structure.

[0153] In some embodiments, the activation function of the CNN network adopts a linear rectification function (ReLU), as shown in formula (1): x =max (0，x) Formula (1).

[0154] It should be noted that the ReLU function, also known as the rectified linear unit, is an activation function commonly used in artificial neural networks, usually referring to nonlinear functions represented by ramp functions and their variants.

[0155] In some embodiments, the activation function of the fully connected layer uses the Sigmoid function, as shown in formula (2):

[0156] It should be noted that the Sigmoid function is a common S-shaped function in biology, also known as the S-shaped growth curve. In information science, due to its monotonic increasing properties and the monotonic increasing properties of its inverse function, the Sigmoid function is often used as the activation function of neural networks to map variables to between (0,1).

[0157] In some embodiments, the loss function used by the fully connected layer is a cross entropy function, as shown in formula (3):

[0158] O s is the size of the output, y i is the true value of the sample, The predicted value output by the model.

[0159] It should be noted that the cross entropy function is mainly used to measure the difference information between two probability distributions. The meaning of cross entropy is the difficulty of using the model to recognize text, or from the perspective of compression, how many bits are used to encode each word on average.

[0160] In some embodiments, the initial test data can be divided into 80% of the data as a training set and 20% of the data as a test set. The training set is used to train the first artificial intelligence model, and the test set is used to test the first artificial intelligence model.

[0161] In some embodiments, the perception server sends the trained first artificial intelligence model to the perception function entity, and the perception function entity processes the first perception data based on the first artificial intelligence model, extracts the data of the RD graph, and extracts the feature data [P0, P1, P2, P3, P4, P5, P6, P7, P8] as shown in Figure 5 above, and uses this feature data as the input of the first artificial intelligence model, and the online prediction output is no target (0) or target (1).

[0162] In some embodiments, for characteristic data of a target, other sensing detection is performed on the target, such as direction of arrival (DOA) estimation, signal-noise ratio (SNR) estimation, speed estimation, power calculation, etc.

[0163] It should be noted that DOA estimation is a positioning technology that obtains the distance and direction information of the target by processing the received echo signal. The SNR refers to the ratio of the strength of the received useful signal to the strength of the received interference signal (noise and interference).

[0164] Furthermore, based on the first perception data of the above-mentioned perception detection, target detection, trajectory tracking, trajectory correction, target association, and target identification are performed on the target.

[0165] It should be noted that if it is multi-sensory node perception, data fusion between the multiple sensing nodes is performed to obtain a more complete and accurate first perception result of target detection, trajectory tracking, trajectory correction, target association, and target recognition.

[0166] In some embodiments, the fusion of the first perception results among multiple perception nodes can be achieved by merging, optimizing, etc., or by using video.

[0167] In some embodiments, the perception function entity transmits the first perception result with a higher confidence level and the corresponding label to the perception server for data collection, and the perception server performs periodic model training on the first artificial intelligence model according to the second indication information sent by the perception control function.

[0168] In some embodiments, the perception server sends at least one of the first perception data, the first perception result, or the first artificial intelligence model to the core network.

[0169] In some embodiments, the perception processing function in the perception function entity sends a perception service response message to the perception management function, and the perception management function sends a perception service response message to the core network, and reports the first perception result according to the perception service request message.

[0170] In some embodiments, the perception function entity performs target detection, trajectory tracking, trajectory correction, target association, and target identification based on the DOA estimation, SNR estimation, speed estimation, power calculation and other information reported by the perception node to obtain the target's movement trajectory.

[0171] In some embodiments, since wireless signals are easily blocked in wireless communications, especially in high-frequency wireless communications, signal blind spots may occur, resulting in the loss of the target's trajectory. In this case, the missing part can be predicted based on the known historical trajectory information of the target.

[0172] In some embodiments, in the initial stage of training the first artificial intelligence model, the perception server uses initial test data to perform model training on the first artificial intelligence model, and the initial test data is actual test trajectory data which may also be the target.

[0173] For example, the trajectory point sequence of the target can be expressed as [(Lo1, La1, H1, V1), (Lo2, La2, H2, V2), ..., (Lo n , La n , H n , V n )].

[0174] Lo t La represents the longitude of the target trajectory point at time t, t represents the latitude of the target trajectory point perceived at time t, H t represents the height of the target trajectory point perceived at time t, V t Indicates that the target is perceived at the trajectory point (Lo t , La t , H t ), t = 1, 2, ..., n.

[0175] In some embodiments, after the actual test trajectory data of the target is obtained, data preprocessing is required for the actual test trajectory data, and the actual test trajectory data is normalized between the minimum and maximum values ​​within a certain range to achieve standardization of the training data.

[0176] In some embodiments, the trajectory data of adjacent moments in the trajectory point sequence are differentiated, that is, x t =Lo t+1 -Lo t ,y t =La t+1 -La t , z t =H t+1 -H t , v t =V t+1-V t .

[0177] Furthermore, we get (n-1) trajectory sequences, namely [(x1, y1, z1, v1), (x2, y2, z2, v2), ..., (x n-1 ,y n-1 , z n-1 , v n-1 )].

[0178] In some embodiments, the sklearn tool in the machine learning library is used to normalize the differential trajectory sequence using the MinMaxScaler() function, scale it to the range of [-1, 1], and save the output parameter scaler of the function. The normalized data is used to construct a supervised sequence. Table 1 is a schematic diagram of a construction method of a supervised sequence provided in some embodiments of the present disclosure, taking n=13 as an example, as shown in Table 1:

[0179] Table 1

[0180] For example, if the constructed supervision sequence is [(x1, y1, z1, v1), (x2, y2, z2, v2), ..., (x 12 ,y 12 , z 12 , v 12 )], then the label of the supervised sequence is (x 13 ,y 13 , z 13 , v 13 ); If the constructed supervision sequence is [(x2, y2, z2, v2),

[0181] (x3, y3, z3, v3),..., (x 13 ,y 13 , z 13 , v 13 )], then the label of the supervised sequence is (x 14 ,y 14 , z 14 , v 14 ); If the constructed supervision sequence is [(x3, y3, z3, v3), (x4, y4, z4, v4), ..., (x 14 ,y 14 , z 14 , v 14 )], then the label of the supervised sequence is (x 15 ,y 15 , z 15 , v 15); If the constructed supervision sequence is [(x4, y4, z4, v4), (x5, y5, z5, v5), ..., (x 15 ,y 15 , z 15 , v 15 )], then the label of the supervised sequence is (x 16 ,y 16 , z 16 , v 16 ); If the constructed supervision sequence is [(x t-12 ,y t-12 , z t-12 , v t-12 ), (x t-11 ,y t-11 , z t-11 , v t-11 ),...,(x t-1 ,y t-1 , z t-1 , v t-1 )], then the label of the supervised sequence is (x t ,y t , z t , v t ).

[0182] In some embodiments, the processed data set is divided into a training data set and a test data set in a ratio of 80% and 20%, the training data set is used to train the first artificial intelligence model, and the test data set is used to evaluate the first artificial intelligence model.

[0183] In some embodiments, a long short term memory (LSTM) neural network model can be constructed, and the network model parameters can be configured to train the first artificial intelligence model.

[0184] In some embodiments, the LSTM network model includes three gate information, namely, a forget gate, an input gate, and an output gate. FIG8 is a structural diagram of a long short-term memory neural network model provided by an embodiment of the present disclosure. As shown in FIG8 , the forget gate mainly controls the proportion of data features of the previous layer of the network that are forgotten, that is, the input data features are weighted and summed with the previous sequence state, and the result is input to the forget gate to obtain the data feature output of the forget gate. The calculation method is shown in formula (4): f t =σ(W xf ·x t +W hf ·h t-1 +b f ) formula (4).

[0185] f t is the data feature output of the forget gate, Wxf is the weighted coefficient of the forget gate for the current moment data, x t is the input data feature, W hf Represents the weighted coefficient of the forget gate to the state of the previous moment, h t-1 is the previous sequence state, b f is the forget gate data bias constant, and σ(x) represents the sigmoid activation function.

[0186] Furthermore, the main memory data at the current moment is obtained by combining the memory system data at the previous moment. The calculation method is shown in formula (5): t1 =c t-1 ⊙f t Formula (5).

[0187] c t1 is the main memory data at the current moment, c t-1 It is the memory system data of the previous moment.

[0188] In some embodiments, the input gate mainly filters the effective features of the current input data and compensates and updates the control data features of the forget gate in combination with the current data. The data feature extraction method of the input gate is shown in formula (6): t =σ(W xi ·x t +W hi ·h t-1 +b i ) formula (6).

[0189] i t is the data feature output of the input gate, W xi is the weighted coefficient of the input gate for the current moment data, W hi is the weighted coefficient of the input gate to the state at the previous moment, b i is the input gate data bias constant.

[0190] Furthermore, the input data characteristics will compensate for the memory data characteristics to a certain extent, and the input gate characteristic parameters need to be screened. The calculation method of the screening control coefficient is shown in formula (7): c′ t =tan h(W xc ·x t +W hc ·h t-1 +b c ) formula (7).

[0191] c′ t is the characteristic screening control coefficient of the input gate, W xc Filter the control weight coefficient for the current input data, W hcInput the filter weight coefficient for the data state at the previous moment, b c To filter the control data bias constant, tan h(x) is the activation function.

[0192] Furthermore, the input gate data is filtered and controlled to obtain the memory system data at the next moment. The calculation method is shown in formula (8): t2 =c′ t ⊙i t Formula (8).

[0193] c t2 Memory system data for the next moment.

[0194] In some embodiments, the output value of the memory parameter at the current moment can be determined based on the main memory data at the current moment and the memory system data at the next moment. The calculation method is shown in formula (9): t =c t1 +c t2 Formula (9).

[0195] c t The output value of the memory parameter at the current moment.

[0196] In some embodiments, the output gate mainly learns the model and predicts the training set based on the forgotten data features and the current data features. The training method is shown in formula (10): t =σ(W xo ·x t +W ho ·h t-1 +b o ⊙tan h(c t )) Formula (10).

[0197] h t Output data for the output gate, W xo is the weight coefficient of the data at the current moment in the output gate, W ho is the weight coefficient of the state data at the previous moment in the output gate, b o is the data bias constant in the output gate.

[0198] In some embodiments, the present disclosure may adopt an architecture of two LSTM layers plus a fully connected layer. FIG9 is a schematic diagram of the architecture of a long short-term memory neural network model provided in an embodiment of the present disclosure. Table 2 shows a parameter configuration method of an architecture of two LSTM layers plus a fully connected layer, as shown in Table 2:

[0199] Table 2

[0200] Exemplarily, in combination with FIG9 and Table 2, the number of hidden layers of the LSTM may be 64, the activation function may be ReLU, and the loss function may be a mean square error (MSE) function.

[0201] In some embodiments, after the first artificial intelligence model is trained, the perception server sends the trained first artificial intelligence model to the core network.

[0202] In some embodiments, after the perception function entity receives the trained first artificial intelligence model, the perception function entity preprocesses the actual test trajectory data (the preprocessing method is consistent with the preprocessing method used when training the model), inputs the preprocessed data set into the first artificial intelligence model, and obtains the predicted value (x t ,y t , z t , v t ), according to the scaler saved during data preprocessing, perform denormalization, and then add (Lo n , La n , H n , V n ), and get the final predicted value (Lo n+1 , La n+1 , H n+1 , V n+1 ).

[0203] In some embodiments, the perception function entity transmits the actual test trajectory data with higher confidence and the corresponding labels to the perception server for data collection.

[0204] In some embodiments, the perception function entity transmits the perception results with higher confidence and the corresponding labels to the perception server for data collection, and the perception server performs periodic model training on the first artificial intelligence model according to the second indication information sent by the perception control function to indicate the training cycle.

[0205] In some embodiments, the perception processing function in the perception function entity sends response information of the perception service request message to the perception management function, and the perception management function sends response information of the perception service request message to the core network, and reports the perception results according to the perception service request message, thereby displaying a complete operation trajectory of the target.

[0206] Referring to FIG10 , FIG10 is a flow chart of another perception communication method provided in an embodiment of the present disclosure, which is applied to a perception node. As shown in FIG10 , the method includes the following steps:

[0207] S201. A perception node receives a first perception control instruction sent by a perception function entity in a core network.

[0208] In some embodiments, when the core network receives a perception service request message sent by an intelligent agent located in the edge network or a perception service request message generated by an application function network element in the core network, in response to the perception service request message, the perception function entity in the core network sends a first perception control instruction to the perception node.

[0209] The first perception control instruction is used to instruct the perception node to perform perception detection.

[0210] S202. The sensing node sends a first sensing signal in response to the first sensing control instruction and obtains first sensing data.

[0211] In some embodiments, after the perception node receives a first perception control instruction sent by a perception function entity in the core network, it sends a first perception signal in response to the first perception control instruction and obtains first perception data.

[0212] S203. The perception node sends first perception data to a perception function entity in the core network.

[0213] In some embodiments, after the perception node obtains the first perception data, it sends the first perception data to a perception function entity in the core network.

[0214] Referring to FIG11 , FIG11 is a flow chart of another perception communication method provided in an embodiment of the present disclosure, which is applied to a perception node. As shown in FIG11 , the method includes the following steps:

[0215] S301. A perception node receives a second perception control instruction sent by an agent in an edge network.

[0216] The second perception control instruction is used to instruct the perception node to perform perception detection.

[0217] In some embodiments, after the core network receives a perception service request message sent by an agent located in an edge network, the core network sends a second perception control instruction to the agent in response to the perception service request message.

[0218] S302. The sensing node sends a second sensing signal in response to the second sensing control instruction and obtains second sensing data.

[0219] In some embodiments, after the perception node receives the second perception control instruction from the core network, it sends a second perception signal in response to the second perception control instruction and obtains second perception data.

[0220] S303. The perception node sends second perception data to the agent.

[0221] In some embodiments, after the sensing node obtains the second sensing data, it sends the second sensing data to an intelligent agent located in the edge network.

[0222] It should be noted that based on the perception communication method provided in the embodiment of the present disclosure, the intelligent agent obtains the second perception data from the perception node through the communication interaction between the perception node and the intelligent agent. At the same time, the second perception data is processed by the second artificial intelligence model trained by the perception server in the intelligent agent, which diversifies the processing method of the perception data, improves the accuracy of the perception results, and makes the credibility of the second perception results higher.

[0223] Referring to FIG. 12 , FIG. 12 is a flow chart of another perception communication method provided in an embodiment of the present disclosure, which is applied to an intelligent agent in an edge network. As shown in FIG. 12 , the method includes the following steps:

[0224] S401. The intelligent agent obtains second perception data from the perception node.

[0225] In some embodiments, when the agent needs to obtain second perception data, the agent sends a second perception control instruction to the perception node.

[0226] The second perception control instruction is used to instruct the perception node to perform perception detection.

[0227] In some embodiments, when the perception node receives a second perception control instruction sent by the intelligent agent, it sends a second perception signal in response to the second perception control instruction, obtains second perception data, and sends the second perception data to the intelligent agent, and the intelligent agent receives the second perception data.

[0228] S402. The intelligent agent processes the second perception data based on the second artificial intelligence model to obtain a second perception result.

[0229] In some embodiments, after the intelligent agent receives the second perception data sent by the perception node, the intelligent agent can process the second perception data based on the second artificial intelligence model trained by the perception server in the intelligent agent to obtain a second perception result.

[0230] It should be noted that the training method for the second artificial intelligence model is consistent with the training method for the first artificial intelligence model in the above step S102, and will not be repeated here.

[0231] In some embodiments, the intelligent agent may also send at least one of the following to the core network: a perception service response message, second perception data, a second perception result, and a second artificial intelligence model.

[0232] In some embodiments, the intelligent agent may also receive at least one of the following contents sent by the core network: a perception service request message, first perception data, a first perception result, and a first artificial intelligence model.

[0233] The first perception result is obtained by processing the first perception data based on the first artificial intelligence model.

[0234] It should be noted that based on the perception communication method provided in the embodiment of the present disclosure, the intelligent agent obtains the second perception data from the perception node through the communication interaction between the perception node and the intelligent agent. At the same time, the second perception data is processed by the second artificial intelligence model trained by the perception server in the intelligent agent, which diversifies the processing method of the perception data, improves the accuracy of the perception results, and makes the credibility of the second perception results higher.

[0235] In some embodiments, the above steps S101 to S102 can also be implemented by the process shown in Figure 13. Referring to Figure 13, it is a flow chart of another sensing communication method provided by the embodiment of the present disclosure. As shown in Figure 13, taking the target as a drone as an example, the method includes the following steps:

[0236] S501. The core network sends a first perception control instruction of the drone to the perception management function in the perception function entity.

[0237] The first perception control instruction is used to indicate the perception service demand, and the first perception control instruction may carry the perception service type, the perception area, the perception reporting content, and the perception reporting type.

[0238] The perception service type is drone perception, the perception area can be within a radius of 1000 meters centered on the perception node or other ranges, the perception reporting content can include the position and speed of the drone, and the perception reporting type can be perception result reporting.

[0239] S502: After the perception management function obtains the first perception control instruction, it authenticates the first perception control instruction.

[0240] S503: The perception management function sends the first perception control instruction that has passed authentication to the perception control function in the perception function entity.

[0241] S504: After the perception control function obtains the first perception control instruction, it selects the perception method, perception node and perception data processing method for the drone according to the first perception control instruction.

[0242] S505. The perception control function sends a first perception control instruction to the perception node.

[0243] The first perception control instruction is used to instruct the perception node to perform a perception task. The perception control instruction includes perception configuration information. The perception configuration information is used to configure at least one of a perception resource, a perception time, and a perception signal.

[0244] S506. The perception control function sends first instruction information for model training to the perception server.

[0245] S507. After receiving the first perception control instruction, the perception node sends a first perception signal to the drone according to the first perception control instruction, performs the first perception task, and obtains the first perception data of the drone.

[0246] S508. The perception node sends the first perception data of the drone to the perception processing function of the perception function entity.

[0247] S509: The perception processing function performs perception data preprocessing on the first perception data.

[0248] The perception data preprocessing includes extracting feature data or normalizing the first perception data.

[0249] S510. After receiving the first instruction information for model training sent by the perception control function, the perception server trains the first artificial intelligence model and sends the trained first artificial intelligence model to the perception processing function.

[0250] It should be noted that, for the training of the first artificial intelligence model, please refer to the above step S102, which will not be repeated here.

[0251] S511. The perception processing function performs artificial intelligence prediction on the first artificial intelligence model to obtain a predicted first perception result.

[0252] S512. The perception processing function sends the first perception result to the perception server for storage.

[0253] S513. The perception server periodically trains the first artificial intelligence model based on the second indication information sent by the perception control function to indicate the training cycle and the perception result.

[0254] S514: After obtaining the first perception result, the perception processing function in the perception function entity sends a perception service response message to the perception management function.

[0255] S515. The perception management function sends the perception service response message to the core network, and the core network obtains the first perception result of the drone.

[0256] The first perception result may include the position and speed of the drone, showing a complete motion trajectory of the drone.

[0257] In some embodiments, the above steps S201 to S202 can also be implemented by the process shown in Figure 14. Referring to Figure 14, it is a flow chart of another sensing communication method provided by the embodiment of the present disclosure. As shown in Figure 14, taking the target as a drone as an example, the method includes the following steps:

[0258] S601. The application function of the core network sends a first perception control instruction of the drone to the perception management function in the perception function entity.

[0259] The first perception control instruction is used to indicate the perception service demand, and the first perception control instruction may carry the perception service type, the perception area, the perception reporting content, and the perception reporting type.

[0260] The perception service type is drone perception, the perception area can be within a radius of 1000 meters centered on the perception node or other ranges, the perception reporting content can include the position and speed of the drone, and the perception reporting type can be perception result reporting.

[0261] S602: After receiving the first perception control instruction, the perception management function authenticates the first perception control instruction.

[0262] S603. The perception management function sends the first perception control instruction that has passed authentication to the perception control function in the perception function entity.

[0263] S604. The perception control function selects a perception method, a perception node, and a processing method for perception data according to the first perception control instruction.

[0264] S605. The perception control function sends the first perception control instruction to the perception node.

[0265] S606. The perception node performs the perception task according to the first perception control instruction.

[0266] For example, after the perception node receives the first perception control instruction, it sends a first perception signal to the drone according to the first perception control instruction, performs the first perception task, and obtains the first perception data of the drone.

[0267] S607. The perception node sends the first perception data to the perception management function.

[0268] S608. The perception node trains and predicts a first artificial intelligence model based on the first perception data to obtain a first perception result.

[0269] S609. The perception node sends the first artificial intelligence model and the first perception result to the perception management function.

[0270] S610: The perception management function integrates artificial intelligence models, perception results, and perception data.

[0271] S611. The perception management function sends a perception service response message to the application function of the core network.

[0272] In some embodiments, the above steps S301-S302 and S401-S402 can also be implemented by the process shown in Figure 15. Referring to Figure 15, it is a flow chart of another perception communication method provided by the embodiment of the present disclosure. As shown in Figure 15, taking the target as a drone as an example, the method includes the following steps:

[0273] S701. The application function of the core network sends a second perception control instruction to the intelligent agent.

[0274] The second perception control instruction is used to indicate the perception service demand, and the second perception control instruction may carry the perception service type, the perception area, the perception reporting content, and the perception reporting type.

[0275] The perception service type is drone perception, the perception area can be within a radius of 1000 meters centered on the perception node or other ranges, the perception reporting content can include the position and speed of the drone, and the perception reporting type can be perception result reporting.

[0276] S702: The intelligent agent receives the second perception control instruction and authenticates the second perception control instruction.

[0277] For example, the perception function entity in the intelligent agent authenticates the second perception control instruction.

[0278] S703. The intelligent agent sends the second perception control instruction that has passed authentication to the perception node.

[0279] S704. The perception node performs the perception task according to the second perception control instruction, obtains the second perception data, and sends the second perception data to the intelligent agent.

[0280] For example, when the perception node receives the second perception control instruction, it sends a second perception signal to the drone according to the second perception control instruction, performs the second perception task, and obtains the second perception data of the drone.

[0281] S705. The intelligent agent trains and predicts the second artificial intelligence model based on the second perception data.

[0282] For example, the intelligent agent trains the second artificial intelligence model through the perception server in the intelligent agent, and predicts the trained second artificial intelligence model through the perception function entity in the intelligent agent to obtain a second perception result.

[0283] S706. The intelligent agent sends the perception service response message, the second perception result and the second artificial intelligence model to the core network.

[0284] In some embodiments, after the core network receives the second perception result and the second artificial intelligence model, the perception management function in the core network performs fusion of the artificial intelligence model, fusion of the perception result, and fusion of the perception data.

[0285] The above mainly introduces the scheme of the embodiment of the present disclosure from the perspective of method. It can be understood that in order to realize the above functions, the perception communication device includes at least one of the hardware structure and software modules corresponding to the execution of each function. It should be easy for those skilled in the art to realize that, in combination with the units and algorithm steps of each example described in the embodiment disclosed herein, the embodiment of the present disclosure can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the embodiment of the present disclosure.

[0286] It is understandable that, in order to realize the above functions, the perception communication device includes hardware structures and / or software modules corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the algorithm steps of each example described in the embodiments of the present disclosure, the present disclosure can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present disclosure.

[0287] The embodiment of the present disclosure can divide the functional modules of the perception communication device according to the above-mentioned method embodiment. For example, each functional module can be divided corresponding to each function, or two or more functions can be integrated into one functional module. The above-mentioned integrated module can be implemented in the form of hardware or software. It should be noted that the division of modules in the embodiment of the present disclosure is schematic and is only a logical functional division. There may be other division methods in actual implementation. The following is an example of dividing each functional module corresponding to each function.

[0288] Figure 16 is a schematic diagram of the structure of a perceptual communication device provided in an embodiment of the present disclosure. The perceptual communication device is applied to a core network and can execute the perceptual communication method provided in the above method embodiment. As shown in Figure 16, the perceptual communication device 200 includes a receiving module 201, a processing module 202, and a sending module 203.

[0289] In some embodiments, the receiving module 201 is configured to receive first sensing data sent by a sensing node.

[0290] In some embodiments, the processing module 202 is used to process the first perception data through the perception function entity based on the first artificial intelligence model trained by the perception server to obtain a first perception result.

[0291] In some embodiments, the sending module 203 is used to send a first sensing control instruction to the sensing node in response to the sensing service request message, where the first sensing control instruction is used to instruct the sensing node to perform sensing detection.

[0292] In some embodiments, the awareness service request message is sent by an agent located in an edge network to a core network; or, the awareness service request message is generated by an application function network element in the core network.

[0293] In some embodiments, the sending module 203 is also used to send at least one of the following to the intelligent agent located in the edge network: a perception service request message, a perception service response message, a first perception data, a first perception result, and a first artificial intelligence model.

[0294] In some embodiments, the receiving module 201 is also used to receive at least one of the following contents sent by an intelligent agent located in the edge network: a perception service request message, a perception service response message, a second perception data, a second perception result, and a second artificial intelligence model.

[0295] In some embodiments, the second perception result is obtained by the intelligent agent processing the second perception data based on the second artificial intelligence model.

[0296] In some embodiments, the perception server is configured with at least one of the following functions: service control function, data preprocessing function, data storage function, and data opening function.

[0297] In some embodiments, the service control function includes at least one of the following: management of artificial intelligence applications, management of model training time, management of data openness functions, and management of information transmission.

[0298] In some embodiments, the data opening function is used to provide at least one of perception data, perception results, and artificial intelligence models to the outside world.

[0299] Figure 17 is a schematic diagram of the structure of a perception communication device provided by an embodiment of the present disclosure. The perception communication device is applied to a perception node and can execute the perception communication method provided by the above method embodiment. As shown in Figure 17, the perception communication device 300 includes: a receiving module 301 and a sending module 302.

[0300] In some embodiments, the receiving module 301 is used to receive a first perception control instruction sent by a perception function entity in the core network, where the first perception control instruction is used to instruct a perception node to perform perception detection.

[0301] In some embodiments, the sending module 302 is configured to send a first perception signal and obtain first perception data in response to a first perception control instruction.

[0302] In some embodiments, the sending module 302 is further configured to send the first perception data to a perception function entity in the core network.

[0303] In some embodiments, the receiving module 301 is further used to receive a second perception control instruction sent by an intelligent agent located in the edge network, where the second perception control instruction is used to instruct the perception node to perform perception detection.

[0304] In some embodiments, the sending module 302 is further configured to send a second perception signal in response to a second perception control instruction and obtain second perception data.

[0305] In some embodiments, the sending module 302 is further used to send second perception data to the agent.

[0306] Figure 18 is a schematic diagram of the structure of another sensory communication device provided in an embodiment of the present disclosure. This sensory communication device is applied to an intelligent agent in an edge network and can execute the sensory communication method provided in the above method embodiment. As shown in Figure 18, sensory communication device 400 includes an acquisition module 401, a processing module 402, and a sending module 403.

[0307] In some embodiments, the acquisition module 401 is used to acquire second perception data from a perception node.

[0308] In some embodiments, the processing module 402 is used to process the second perception data based on the second artificial intelligence model to obtain a second perception result.

[0309] In some embodiments, the sending module 403 is used to send a second sensing control instruction to the sensing node, where the second sensing control instruction is used to instruct the sensing node to perform sensing detection.

[0310] In some embodiments, the sending module 403 is further used to send at least one of the following contents to the core network: a perception service response message, second perception data, a second perception result, and a second artificial intelligence model.

[0311] In some embodiments, the acquisition module 401 is further used to receive at least one of the following contents sent by the core network: a perception service request message, first perception data, a first perception result, and a first artificial intelligence model.

[0312] In some embodiments, the first perception result is obtained by processing the first perception data based on the first artificial intelligence model.

[0313] In the case of implementing the functions of the above-mentioned integrated modules in hardware, the embodiments of the present disclosure provide a possible structure of the communication device involved in the above-mentioned embodiments. As shown in Figure 19, the communication device 500 includes: a processor 502 and a bus 504. In some embodiments, the communication device 500 may also include a memory 501; in some embodiments, the communication device 500 may also include a communication interface 503.

[0314] In some embodiments, the processor 502 can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the embodiments of the present disclosure. The processor 502 can be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a transistor logic device, a hardware component, or any combination thereof, and can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the embodiments of the present disclosure. The processor 502 can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0315] In some embodiments, the communication interface 503 is used to connect to other devices via a communication network, which may be Ethernet, wireless access network, wireless local area network (WLAN), etc.

[0316] In some embodiments, the memory 501 can be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to these.

[0317] As a possible implementation, the memory 501 can exist independently of the processor 502. The memory 501 can be connected to the processor 502 via a bus 504 to store instructions or program codes. When the processor 502 calls and executes the instructions or program codes stored in the memory 501, the perceptual communication method provided in the embodiment of the present disclosure can be implemented.

[0318] In another possible implementation, the memory 501 may also be integrated with the processor 502 .

[0319] In some embodiments, bus 504 may be an Extended Industry Standard Architecture (EISA) bus, etc. Bus 504 may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, FIG19 shows only one thick line, but this does not mean that there is only one bus or only one type of bus.

[0320] Some embodiments of the present disclosure provide a computer-readable storage medium (e.g., a non-transitory computer-readable storage medium), which stores computer program instructions. When the computer program instructions are executed on a computer, the computer executes the perceptual communication method of any of the above embodiments.

[0321] Exemplarily, the above-mentioned computer-readable storage media may include, but are not limited to: magnetic storage devices (e.g., hard disks, floppy disks, or magnetic tapes, etc.), optical disks (e.g., compact disks (CDs), digital versatile disks (DVDs), etc.), smart cards, and flash memory devices (e.g., erasable programmable read-only memories (EPROMs), cards, sticks, or key drives, etc.). The various computer-readable storage media described in the present disclosure may represent one or more devices and / or other machine-readable storage media for storing information. The term "machine-readable storage medium" may include, but is not limited to, wireless channels and various other media capable of storing, containing, and / or carrying instructions and / or data.

[0322] An embodiment of the present disclosure provides a computer program product containing instructions. When the computer program product is run on a computer, the computer is enabled to execute the perceptual communication method of any one of the above embodiments.

[0323] The above are only specific embodiments of the present disclosure, but the scope of protection of the present disclosure is not limited thereto. Any changes or replacements within the technical scope disclosed in the present disclosure should be included in the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure should be based on the scope of protection of the claims.

Claims

1. A perception communication method is applied to a core network, and the core network includes a perception function entity and a perception server; the method includes: Receiving first perception data sent by a perception node; Based on a first artificial intelligence model completed by training of the perception server, processing the first perception data through the perception function entity to obtain a first perception result.

2. The method according to claim 1, wherein, Before receiving the first perception data sent by the perception node, the method further includes: Responding to a perception service request message, sending a first perception control instruction to the perception node, and the first perception control instruction is used to instruct the perception node to perform perception detection.

3. The method according to claim 2, wherein, The perception service request message is sent by an intelligent agent located in an edge network to the core network; or, the perception service request message is generated by an application function network element in the core network.

4. The method according to claim 1, further includes: Sending at least one of the following to an intelligent agent located in an edge network: a perception service request message, a perception service response message, the first perception data, the first perception result, the first artificial intelligence model.

5. The method according to claim 1, further includes: Receiving at least one of the following sent by an intelligent agent located in an edge network: a perception service request message, a perception service response message, second perception data, a second perception result, a second artificial intelligence model.

6. The method according to claim 5, wherein, The second perception result is obtained by the intelligent agent processing the second perception data based on the second artificial intelligence model.

7. The method according to claim 1, wherein The perception function entity is configured with at least one of the following functions: a perception control function, a perception management function, an artificial intelligence function, a perception processing function, a data preprocessing function.

8. The method according to claim 7, wherein The perception control function includes at least one of the following: selection of a perception node, management of perception resources, management of perception time, management of artificial intelligence applications, management of information transmission.

9. The method according to claim 7, wherein The perception management function includes at least one of the following: obtaining perception service requirements, authentication of the perception service requirements, determining perception tasks based on the perception service requirements, artificial intelligence model fusion, perception data fusion, perception result fusion.

10. The method according to claim 7, wherein, The artificial intelligence function includes at least one of the following: training an artificial intelligence model, using the artificial intelligence model.

11. The method according to claim 1, wherein, The perception server is configured with at least one of the following functions: a service control function, a data preprocessing function, a data storage function, a data opening function.

12. The method according to claim 11, wherein, The service control function includes at least one of the following: management of artificial intelligence applications, management of model training time, management of the data opening function, management of information transmission.

13. The method according to claim 11, wherein, The data opening function is used to externally provide at least one of perception data, perception results, and artificial intelligence models.

14. A perception communication method is applied to a perception node, and the method includes: Receiving a first perception control instruction sent by a perception function entity in a core network, and the first perception control instruction is used to instruct the perception node to perform perception detection; Responding to the first perception control instruction, sending a first perception signal, and obtaining first perception data; Sending the first perception data to the perception function entity in the core network.

15. The method according to claim 14 further includes: Receiving a second sensing control instruction sent by an agent in the edge network, where the second sensing control instruction is used to instruct the sensing node to perform sensing detection; In response to the second sensing control instruction, sending a second sensing signal and obtaining second sensing data; Sending the second sensing data to the agent.

16. A sensing communication method applied to an agent in an edge network, the method including: Obtaining second sensing data from a sensing node; Processing the second sensing data based on a second artificial intelligence model to obtain a second sensing result.

17. The method according to claim 16 further includes: Sending a second sensing control instruction to the sensing node, where the second sensing control instruction is used to instruct the sensing node to perform sensing detection.

18. The method according to claim 16 further includes: Sending at least one of the following to the core network: a sensing service response message, second sensing data, a second sensing result, a second artificial intelligence model.

19. The method according to claim 16 further includes: Receiving at least one of the following sent by the core network: a sensing service request message, first sensing data, a first sensing result, a first artificial intelligence model.

20. The method according to claim 19, wherein The first sensing result is obtained by processing the first sensing data based on the first artificial intelligence model.

21. A sensing communication system, wherein, The sensing communication system includes: a sensing node and a core network, and the core network includes a sensing function entity and a sensing server; The sensing node is used to provide first sensing data to the core network; The core network is used to process the first sensing data through the sensing function entity based on the first artificial intelligence model trained by the sensing server to obtain a first sensing result.

22. The system according to claim 21, wherein, The sensing communication system further includes an agent in the edge network; The sensing node is further used to provide second sensing data to the agent; The agent is used to process the second sensing data based on a second artificial intelligence model to obtain a second sensing result.

23. The system according to claim 22, wherein, The agent is further used to send at least one of the following to the core network: a sensing service request message, a sensing service response message, the second sensing data, the second sensing result, the second artificial intelligence model.

24. According to the system of claim 22, wherein The core network is further used to send at least one of the following to the agent: a sensing service request message, a sensing service response message, the first sensing data, the first sensing result, the first artificial intelligence model.

25. A communication device, comprising: A memory and a processor; The memory and the processor are coupled; The memory is used to store instructions executable by the processor; When the processor executes the instructions, it executes the method according to any one of claims 1-13, or the method according to claim 14 or 15, or the method according to any one of claims 16-20.

26. A computer-readable storage medium, wherein, Computer instructions are stored on the computer-readable storage medium. When the computer instructions run on a computer, the computer is caused to execute the method according to any one of claims 1-13, or the method according to claim 14 or 15, or the method according to any one of claims 16-20.

Images