COMMUNICATION METHOD, APPARATUS, COMMUNICATION DEVICE, AND READABLE STORAGE MEDIUM

Abstract

The present disclosure discloses a communication method, an apparatus, a communication device, and a readable storage medium, which belong to the field of communication technology, and a communication method of an embodiment of the present disclosure includes: a second end receiving first instruction information for instructing a processing method at a reference point of a target object; and the second end processing the target object at the reference point according to the processing method.

Description

[Technical field]

[0001] (CROSS REFERENCE TO RELATED APPLICATIONS) This disclosure claims priority to Chinese Patent Application No. 202111673083.7, filed in China on December 31, 2021, the entire contents of which are incorporated herein by reference.

[0002] The present disclosure relates to the field of communication technology, and specifically to a communication method, apparatus, communication device, and readable storage medium. [Background technology]

[0003] In wireless communication systems in the related art, communication devices generally process signals, data, etc., according to a configured processing method, for example, performing channel coding based on a method agreed upon by a protocol, and such a method makes the communication devices relatively inflexible in the processing method for signals, data, etc. Summary of the Invention [Problem to be solved by the invention]

[0004] The embodiments of the present disclosure provide a communication method, an apparatus, a communication device, and a readable storage medium that can solve a problem in the related art that a communication device has relatively poor flexibility in processing signals, data, and the like. [Means for solving the problem]

[0005] A first aspect provides a method of communication, the method comprising: A second end receives first instruction information for instructing a processing manner at a reference point of a target object; The second end includes processing the target object at the reference point according to the processing scheme.

[0006] A second aspect provides a method of communication, the method comprising: The first end includes interacting with at least one second end first instruction information corresponding to a reference point, the first instruction information being used to instruct a processing manner of a target object at the reference point.

[0007] A third aspect provides a communications device, the communications device comprising: a receiving module for receiving first instruction information for instructing a processing method at a reference point of a target object; and a processing module for processing the target object at the reference point according to the processing scheme.

[0008] A fourth aspect provides a communications device, the communications device comprising: A transmitting module for interacting with at least one second end first instruction information corresponding to a reference point, the first instruction information being used to instruct a processing manner at the reference point of a target object.

[0009] A fifth aspect provides a communications device, the communications device comprising a processor and a memory, the memory storing a program or instructions operable to run on the processor, the program or instructions, when executed by the processor, implementing the steps of the communications method according to the first aspect, or implementing the steps of the communications method according to the second aspect.

[0010] A sixth aspect provides a readable storage medium storing a program or instructions which, when executed by a processor, performs the steps of the communication method according to the first aspect or performs the steps of the communication method according to the second aspect.

[0011] A seventh aspect provides a chip, the chip comprising a processor and a communication interface, the communication interface coupled to the processor, the processor running a program or instructions to implement steps of the communication method described in the first aspect or used to implement steps of the communication method described in the second aspect.

[0012] An eighth aspect provides a computer program product, the computer program product being stored on a non-transitory storage medium, the computer program product being executed by at least one processor to implement the steps of the communication method according to the first aspect or to implement the steps of the communication method according to the second aspect. Effect of the Invention

[0013] In the embodiment of the present disclosure, the first end interacts with at least one second end through the first instruction information to inform the second end of a processing manner at the reference point of the target object through the first instruction information, and the second end can process the target object according to the processing manner at the reference point of the target object based on the first instruction information. In this way, the first end can instruct the second end to process the target object at the reference point, making the processing manner of the communication device for signals, data, tasks, etc. more flexible. [Brief description of the drawings]

[0014] [Figure 1] 1 is a block diagram of a wireless communication system to which an embodiment of the present disclosure can be applied. [Diagram 2] 1 is a flowchart of a communication method according to an embodiment of the present disclosure. [Diagram 3] 1 is a flowchart of another communication method according to an embodiment of the present disclosure. [Figure 4] FIG. 2 is a structural diagram of a communication device according to an embodiment of the present disclosure. [Diagram 5] FIG. 2 is a structural diagram of another communication device according to an embodiment of the present disclosure. [Figure 6] FIG. 2 is a structural diagram of a communication device according to an embodiment of the present disclosure. [Figure 7] FIG. 2 is a structural diagram of a terminal according to an embodiment of the present disclosure. [Figure 8] FIG. 2 is a structural diagram of a network side device according to an embodiment of the present disclosure. [Figure 9]FIG. 2 is a structural diagram of another network side device according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] The following clearly describes the technical solutions in the embodiments of the present disclosure in conjunction with the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are only some of the embodiments of the present disclosure, and not all of the embodiments. All other embodiments obtained by those skilled in the art based on the embodiments in the present disclosure are all within the scope of protection of the present disclosure.

[0016] The terms "first," "second," etc. in the specification and claims of the present disclosure are intended to distinguish between similar objects and are not intended to describe a particular order or sequence. It is to be understood that the terms so used are interchangeable where appropriate, such that the embodiments of the present disclosure may be performed in other orders than those shown or described herein, and that the objects distinguished by "first" and "second" are generally of the same type and do not limit the number of objects, e.g., the first object may be one or more. Note that "and / or" in the specification and claims refers to at least one of the objects connected, and the character " / " generally refers to an "or" relationship between the related objects.

[0017] It should be noted that the techniques described in the embodiments of the present disclosure are not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, but can also be applied to other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency Division Multiple Access (SC-FDMA), and other systems. The terms "system" and "network" in the embodiments of the present disclosure are always used interchangeably, and the techniques described may be used in the systems and radio technologies mentioned above, or in other systems and radio technologies. Although the following description describes a New Radio (NR) system for illustrative purposes, and NR terminology is used in most of the following description, these techniques may also be used in applications other than NR system applications, such as sixth generation (6G) and 7G (8G) systems. th The present invention may be applied to a 6G (6th Generation) communication system.

[0018] 1 shows a block diagram of a wireless communication system to which an embodiment of the present disclosure can be applied. The wireless communication system includes a terminal 11 and a network side device 12. Here, the terminal 11 may be a mobile phone, a tablet personal computer, a laptop computer (also called a notebook computer), a personal digital assistant (PDA), a palmtop computer, a netbook, an ultra-mobile personal computer (UMPC), a mobile internet device (MID), an augmented reality (AR) / virtual reality (VR) device, a robot, a wearable device, a vehicle user equipment (VUE), a pedestrian user equipment (PUE), a smart home (home equipment having a wireless communication function, such as a refrigerator, a television, a washing machine, or furniture), a game machine, a personal computer, a mobile phone, a mobile terminal (Mobile Internet Device), a mobile user equipment (MID), a mobile terminal (Mobile User Equipment ... The network side equipment 12 may be a terminal side equipment such as a mobile computer (PC), a deposit and withdrawal machine or a self-service machine, and the wearable device includes a smart watch, a smart bracelet, a smart earphone, a smart glasses, a smart accessory (smart bracelet, smart hand chain, smart finger ring, smart necklace, smart ankle bracelet, smart anklet, etc.), a smart band, a smart clothing, etc. It should be noted that the embodiments of the present disclosure do not limit the specific type of the terminal 11. The network side equipment 12 may include an access network equipment or a core network equipment, where the access network equipment may be referred to as a radio access network equipment, a radio access network (Radio Access Network, RAN), a radio access network function, or a radio access network unit.The access network equipment may include a base station, a Wireless Local Area Network (WLAN) access point, or a WiFi node, and the base station may be called a Node B, an evolved Node B (eNB), an access point, a Base Transceiver Station (BTS), a radio base station, a radio transceiver, a Basic Service Set (BSS), an Extended Service Set (ESS), a home B node, a home evolved B node, a Transmission Reception Point (TRP), or any other suitable term in the art. As long as the same technical effect is achieved, the base station is not limited to a specific technical term, and it should be explained that the embodiments of the present disclosure take a base station in an NR system as an example, and do not limit the specific type of the base station.The core network devices are: Core Network Node, Core Network Function, Mobility Management Entity (MME), Access and Mobility Management Function (AMF), Session Management Function (SMF), User Plane Function (UPF), Policy Control Function (PCF), Policy and Charging Rules Function (PCRF), Edge Application Server Discovery Function (EASDF), Unified Data Management (UDM), Unified Data Repository (UDR), Home Subscriber Server (HSS), Centralized network configuration (CNC), Network Repository Function (NRF), Network Exposure Function (NEF), Local NEF (Local NEF or L-NEF), Binding Support Function (BSF), Application Function (Application Node Function (ADN)), and Application Node Function (ADN). It should be noted that the embodiments of the present disclosure take the core network device in the NR system as an example, and do not limit the specific type of the core network device.

[0019] In the following, in conjunction with the drawings, a communication method according to an embodiment of the present disclosure will be described in detail through several embodiments and application scenarios thereof.

[0020] Referring to FIG. 2, FIG. 2 is a flowchart of a communication method according to an embodiment of the present disclosure. As shown in FIG. 2, the method includes: Step 201, in which a second end receives first instruction information for instructing a processing method at a reference point of a target object; The second end includes processing 202 the target object at the reference point according to the processing strategy.

[0021] In an embodiment of the present disclosure, the first end and the second end are communication devices having a transmitting function and a receiving function. For example, the first end is one of a network side device and a terminal, and the second end is the other of a network side device and a terminal, or the first end and the second end are different nodes of a terminal, or the first end and the second end are different nodes of a network side device.

[0022] It should be explained that the network side equipment may include an access network equipment (e.g., a base station) and a core network equipment. Optionally, the first end is an access network equipment, and the second end is a core network equipment, or the first end is a terminal, and the second end is a core network equipment or an access network equipment, or the first end and the second end may be different nodes of the access network equipment, or the first end and the second end may be different nodes of the core network equipment, etc., which are not listed one by one in the embodiments of the present disclosure. In addition, the first end and the second end are not specifically referred to, and the first end may be the second end in some scenarios, and the third end, fourth end, fifth end, etc. mentioned in the subsequent embodiments, and similarly, the second end may be the first end in some scenarios, and the third end, fourth end, fifth end, etc. mentioned in the subsequent embodiments.

[0023] In an embodiment of the present disclosure, the second end may receive the first instruction information, and the first instruction information may be transmitted by the first end. Optionally, the first end may interact with the first instruction information to at least one second end, for example, the first end may broadcast the first instruction information to at least one second end, or the first end may directly transmit the first instruction information to the second end, or the first end may transmit the first instruction information to the second end via another device, for example, the core network may transmit the first instruction information to a base station, and the base station may transmit the first instruction information to the terminal.

[0024] Illustratively, the reference point may be a reference point predetermined by a first end and a second end. Optionally, the reference point is: Predefined and Contract by protocol, and second indication information for indicating the reference point transmitted by the third end.

[0025] For example, the location of the reference point may be agreed upon by the protocol, and the first end and the second end may determine the location of the reference point based on the agreement by the protocol, or the third end may send second instruction information to the first end and / or the second end to indicate the location of the reference point, and if only the first end receives the second instruction information, the first end may send the second instruction information to the second end, and if only the second end receives the second instruction information, the second end may send the second instruction information to the first end, or the reference point may be pre-defined.

[0026] It should be explained that the reference point may be regarded as a processing position agreed upon between two communication devices or two function modules, or may be called a processing interface or an interaction interface, etc., or may be regarded as a protocol mapping relationship between two communication devices or two function modules. Hereinafter, several reference points applicable in a communication system are listed.

[0027] Optionally, a baseband received signal after analog-to-digital (AD) and / or digital-to-analog (DA) conversion is defined as a reference point ReP.0.0.0; The signal after the Inverse Fast Fourier Transform (IFFT) is defined as the reference point ReP.0.0.1. The signal (soft information) that extracts the useful reference signal (RE) and then demaps the resource is defined as reference point ReP.0.0.2. The signal corresponding to the decoded bit sequence is defined as reference point ReP.0.0.3. The bit sequence inspection and decoding information is defined as the reference point ReP.0.0.4. The reference point corresponding to the delivery point of bit information to the Medium Access Control (MAC) layer is defined as ReP.0.0.5. The reference points corresponding to the above-mentioned receiving links of the physical downlink shared channel (PDSCH) are defined as ReP.0.1.1 to ReP.0.1.3, The bit sequence of acknowledgement (ACK) and / or non-acknowledgement (NACK) after PDSCH decoding is defined as reference point ReP.0.1.4, The reference point corresponding to the delivery point of the transport block (TB) received by the PDSCH to the MAC layer is defined as ReP.0.1.5. The reference point (REP) corresponding to the TB block received from the MAC layer by the transmission link of the Physical Uplink Shared Channel (PUSCH) is defined as ReP.0.2.0. The reference point after coding of the channel corresponding to PUSCH is defined as ReP.0.2.1. The reference point after PUSCH coding and modulation is defined as ReP.0.2.2. The reference point after multi-antenna processing of PUSCH is defined as ReP.0.2.3. The reference point after PUSCH Fast Fourier Transform (FFT) is defined as ReP.0.2.4.

[0028] In an embodiment of the present disclosure, the target object includes at least one of data, signals, and tasks. For example, the first instruction information may be used to instruct to process a signal after IFFT transformation at a reference point ReP.0.0.1, to process a signal corresponding to a decoded bit sequence at a reference point ReP.0.0.3, etc.

[0029] In an embodiment of the present disclosure, the second end receives first instruction information, determines a processing manner at the reference point of the target object according to the first instruction information, and the second end can process the target object according to the processing manner at the reference point of the target object based on the first instruction information. In this way, the processing manner at the reference point of the target object by the second end can be determined by the first instruction information, making the processing manner of signals, data, tasks, etc. by the communication devices more flexible, and thereby establishing corresponding capability interaction flow between the communication devices, and effectively coordinating the processing manner of signals, data, tasks, etc. between the communication devices.

[0030] Optionally, the processing method comprises: A processing method based on an artificial intelligence (AI) model, Non-defined processing methods and and a processing method determined by a target end including the second end.

[0031] Alternatively, the first instruction information may not include a processing method at the reference point of the target object, in which case the processing method may be considered to be a non-defined processing method that the second end determines by itself.

[0032] Alternatively, the target end may be a first end, and the first end may decide the processing method by itself and notify the second end by first instruction information, or the first end may instruct the second end to decide the processing method by itself by first instruction information.

[0033] It should be noted that, when the processing manner is a processing manner based on an AI model, the first instruction information may include information such as the type of the AI ​​model, input / output, weight parameters, etc. Here, the processing manner based on an AI model may be called a processing manner based on a neural network. Optionally, the processing manner may be other AI or machine learning processing manners, such as Gaussian process, Bayesian network, reinforcement learning, etc.

[0034] Optionally, the processing method based on the AI ​​model comprises: A model connection relationship of the AI ​​model; A startup method of the AI ​​model; and associated information of a processing domain corresponding to the AI ​​model, including the reference point.

[0035] For example, the first instruction information may include a connection relationship of the AI ​​model to indicate that the processing method at the reference point of the target object is a processing method based on an AI model, and in such a case, the target object may be processed by at least two AI models, and the first instruction information includes a model connection relationship of the at least two AI models.

[0036] Optionally, the model connection relationships of the AI ​​models include at least one of a processing order of the AI ​​models and input / output relationships between the AI ​​models.

[0037] For example, when the first instruction information instructs to process the target object based on at least two AI models at a reference point, the first instruction information may include a processing order of the at least two AI models, for example, which AI model to process first from the contracted reference point, and which AI model to process. As can be understood, the second end can process the target object at a pre-contracted reference point based on the first instruction information and according to the processing order of the AI ​​models instructed by the first instruction information.

[0038] Alternatively, the first instruction information may include an input / output relationship between AI models, for example using some inputs of one AI model as some outputs of another AI model or models.

[0039] Alternatively, the first instruction information may include the processing order of the AI ​​models and the input / output relationships between the AI ​​models, which are not further listed here.

[0040] Optionally, the second end processes the target object at the reference point according to the processing scheme. When the model connection relationship of the AI ​​model includes a processing order of the AI ​​model, the second end determines a first applied AI model according to the processing order of the AI ​​model, and launches the first applied AI model according to the processing order of the AI ​​model to process the target object; When the model connection relationship of the AI ​​models includes an input-output relationship between the AI ​​models, the second end determines a second applied AI model according to the input-output relationship between the AI ​​models, and processes the target object by the second applied AI model.

[0041] Here, the number of the first applied AI models and the second applied AI models may be multiple.

[0042] Optionally, the first instruction information includes first target information, and the first target information is used to indicate a model connection relationship of the AI ​​model, and the first target information is: a model identifier for indicating an AI model to be used by the target end including the second end; and a model connection identifier for indicating a connection relationship between different AI models.

[0043] For example, in the first instruction information, the first target information may be defined as a "model add list" ("modelAddModList"), which is used to indicate the model identifier of the AI ​​model used by the second end by referring to a model identifier (modelID) corresponding to the model configuration information (modelConfiguration). Or, in the first instruction information, the first target information may be defined as a "model topology add list" ("modelTopologyAddModList"), which is used to indicate the connection relationship between different AI models by referring to a model connection identifier (modTopID) corresponding to the model topology configuration information (modelTopologyConfiguration).

[0044] For example, using the reference points defined above, modelAddModList is configured to include the following modelIDs, model.0.0.0 to model.0.0.3, model.0.1.0 to model.0.1.4, model.0.2.0 to model.0.2.3, and the processing method of the model (non-defined, or processing based on an AI model, or other machine learning processing method) is configured in the modelConfiguration corresponding to each modelID, and the structure of the AI ​​model, corresponding parameters, etc. may be further configured as modelConfiguration, and the input reference point and output reference point of the model are further configured in modelConfiguration. For example, the input reference point of model.0.0.0 is defined as ReP.0.0.0, and the output reference point is defined as ReP.0.0.1, and the corresponding connection relationship is established based on the above model definition and the relationship between the corresponding input reference point and output reference point.

[0045] For example, modelTopologyAddModList may be configured to indicate the model connection relationships of an AI model. The connection relationships of model information processing are configured in modelTopologyAddModList. For example, the connection relationship corresponding to topologyID1 includes topology.0.0=sequential(model.0.0.0, model.0.0.1, model.0.0.2, model.0.0.3). In this case, it is sufficient to define only the input reference point of model.0.0.0 and the output reference point corresponding to model.0.0.3 without defining the connection reference points between models.

[0046] Optionally, the first target information includes model configuration information including the model identifier, and the model configuration information is further used to configure an input of an AI model to reference a first object, the first object including at least one of a pre-defined reference point and an output of another AI model.

[0047] For example, a modelConfiguration may include one input information element (input IE) that references a predefined reference point as an input of an AI model, e.g., referencePonitX.datapointY as one input of the AI ​​model, and subsequently references another predefined reference point as another input of the AI ​​model, e.g., referencePonitX.datapointZ, if the AI ​​model has multiple inputs.

[0048] Alternatively, an input IE in the model configuration information may be defined as an input to an AI model by referencing the output of another AI model.

[0049] It should be noted that when the reference for configuring the input of the AI ​​model in the model configuration information includes a preset reference point, the number of the preset reference points needs to be taken into consideration. Optionally, when the number of the preset reference points is more than one, the preset reference points are arranged in a preset order to form the input of one AI model.

[0050] In an embodiment of the present disclosure, the first instruction information may further include an activation method of an AI model, so as to indicate that the processing method at the pre-agreed reference point of the target object is a processing method based on an AI model.

[0051] Optionally, the activation manner of the AI ​​model is: Starting up based on a preset start-up time; triggering when data of at least one reference point corresponding to the AI ​​model arrives; Activating when at least one reference point data among at least one reference point data corresponding to the AI ​​model is updated; activating said AI model when all required inputs have arrived; Triggering at least one pre-configured AI model when the model completes processing; Triggering when an output of at least one pre-configured AI model is updated; activating said AI model when it receives an input from a previous AI model; and activating the AI ​​model when the AI ​​model receives a preset output value of another AI model.

[0052] It should be noted that the first end may configure an activation manner of the AI ​​model in the first instruction information, or also referred to as an activation condition, an activation condition, etc., thereby informing the second end when and / or how to activate the AI ​​model to realize processing on the target object.

[0053] For example, when the model connection relationships of multiple AI models have already been determined, the first instruction information may be configured to start each AI model based on a preset startup time, and the second end can know, based on the first instruction information, how long the wait time is required to start the corresponding AI model and begin processing.

[0054] Alternatively, the first instruction information may be configured to start the AI ​​model when data of at least one reference point corresponding to the AI ​​model reaches the corresponding reference point. For example, if the AI ​​model corresponds to three reference points, the AI ​​model is started after all inputs of the three reference points reach their respective reference points.

[0055] Alternatively, the first instruction information may further be configured to start the AI ​​model when at least one of the data of at least one reference point corresponding to the AI ​​model is updated. For example, when the AI ​​model corresponds to three reference points, the AI ​​model is started when data of one of the reference points is updated.

[0056] Alternatively, the first instruction information may be configured to activate the AI ​​model when all required inputs for the AI ​​model have arrived.

[0057] Alternatively, the activation of a certain AI model may be realized depending on the input, output, or processing of a specific AI model. For example, the first instruction information may be configured to activate a certain AI model when one or more other preset AI models have completed processing, or may be configured to activate a certain AI model when the output of one or more other preset AI models has been updated, or may be configured to activate a certain AI model when one or more other preset AI models have completed processing and have updated their output. Here, the completion of processing by an AI model may be obtaining the output of the AI ​​model.

[0058] Alternatively, the activation of an AI model may be realized depending on an input or output value of a specific AI model. For example, when a model connection relationship between a plurality of AI models is determined, the first instruction information may be configured to activate one of the AI ​​models when the AI ​​model receives an input of the previous AI model, or the first instruction information may be configured to activate one of the AI ​​models when the AI ​​model receives a specific output value of another AI model.

[0059] Of course, the activation manner of the AI ​​model may include at least one of the above several manners, which will not be further listed here.

[0060] As an example, some AI model activation methods or activation conditions are listed below.

[0061] model.0.0.1 startup: Data of the reference point ReP.0.0.0 arrives, or the previous model notifies startup processing. The previous model may be the model that is arranged before model.0.0.1 in the determined model connection relationship, and all subsequent previous models may be understood in this way. The following explanation will be omitted. model.0.0.2 startup: Data for reference point ReP.0.0.1 arrives, or the previous model notifies startup processing. model.0.0.3 startup: Data for reference point ReP.0.0.2 arrives, or the previous model notifies startup processing. model.0.1.1 start: The message of the reference point ReP.0.0.4 instructs to start based on the specific time of start in the message of the model.0.1.0, and the data of the reference point ReP.0.1.1 arrives. model.0.1.2 startup: Data for reference point ReP.0.1.2 arrives, or the previous model notifies startup processing. model.0.1.3 startup: Data for reference point ReP.0.1.3 arrives, or the previous model notifies startup processing. model.0.1.4 startup: Data for reference point ReP.0.1.4 arrives, or the previous model notifies startup processing. model.0.2.1 startup: model.0.2.1 is instructed in the message of reference point ReP.0.0.4, and is started based on the specific time of startup in the message of model.0.1.1, or based on instruction information in reference point ReP.0.2.0 (e.g., instructing the startup time and instructing whether to start) and whether data has arrived at the reference point; model.0.2.2 startup: Data for reference point ReP.0.2.2 arrives, or the previous model notifies startup processing. model.0.2.3 startup: Data for reference point ReP.0.2.3 arrives, or the previous model notifies startup processing. model.0.2.4 startup: Data for reference point ReP.0.2.4 arrives, or the previous model notifies startup processing.

[0062] In the embodiment of the present disclosure, the number of the AI ​​models to be activated may be at least 1. For example, when at least one pre-configured AI model completes processing, activation of multiple AI models may be triggered.

[0063] In the embodiment of the present disclosure, the first instruction information may further indicate that the processing manner at the predetermined reference point of the target object is a processing manner based on an AI model through the relevant information of the processing domain corresponding to the AI ​​model. Here, the processing domain may be regarded as a set of reference points, and assuming that the number of reference points is multiple, the processing domain may be divided according to different functions of different reference points, and the functions corresponding to the reference points in the same processing domain are the same, and may be divided into a channel codec processing domain, a multi-antenna processing domain, etc.

[0064] Optionally, the number of the processing domains is at least one, and the processing domain is determined by at least one of a function of the reference point, a relationship between the input / output of the AI ​​model and the reference point, and a model connection relationship between the AI ​​models.

[0065] For example, the processing domain may be divided based on the function of the reference point, and the processing domain may be determined by the function of the reference point. Or, a relationship between the input / output of the AI ​​model and the reference point is formed, and the reference point belongs to the processing domain, and the processing domain may be determined, and the relationship between the AI ​​model and the processing domain may be determined. Or, the corresponding processing domain may be determined according to the model connection relationship between multiple AI models, and for example, an AI model located between two AI models is the same as the processing domain in which the two AI models are located.

[0066] Optionally, the related information of the processing domain includes at least one of a processing time constraint corresponding to the processing domain and a processing method corresponding to the processing domain, where the processing time constraint may be a processing time length or a startup time in the processing domain corresponding to the AI ​​model, and the processing method may be a startup method or a processing time length in the processing domain corresponding to the AI ​​model.

[0067] Optionally, the processing method corresponding to the processing domain includes at least one of a startup method of the AI ​​model, a startup time of the AI ​​model, a termination time of the AI ​​model, and a processing time length of the AI ​​model.

[0068] Optionally, the processing time constraint corresponding to the processing domain includes at least one of a startup method of the AI ​​model, a startup time of the AI ​​model, a termination time of the AI ​​model, and a processing time length of the AI ​​model.

[0069] It should be noted that the content included in the processing time constraint corresponding to the processing domain may be different from the content included in the processing method corresponding to the processing domain, for example, the processing time constraint corresponding to the processing domain includes the start time of the AI ​​model and the end time of the AI ​​model, and the processing method corresponding to the processing domain includes the start method of the AI ​​model.

[0070] Optionally, different said processing domains correspond to respective said processing time constraints and different said processing domains correspond to respective said processing schemes.

[0071] In an embodiment of the present disclosure, the first instruction information is further used to indicate at least one of a test method and test requirements for the reference point, and the second end can further test the reference point based on the test method and test requirements for the reference point carried in the first instruction information, for example, to test processing stability, processing performance, etc. at the reference point of the target object.

[0072] Optionally, the method further comprises: The second end further includes testing the reference points based on at least one of the test strategy and test requirements.

[0073] As can be understood, the second end can test a reference point based on the test method and / or test requirements, for example, test the processing stability, processing performance, etc. of the reference point of the target object. The second end can also establish a corresponding test method and / or test requirements for a processing method based on an AI model, and the second end can also test the processing method based on the AI ​​model, for example, test the processing stability, processing performance, etc. of the AI ​​model.

[0074] In an embodiment of the present disclosure, the method comprises: the second end sending a first service request to a fourth end to request a first function; receiving, by the second end, description information of a first capability transmitted by the fourth end; The second end further includes processing the target object based on the description information of the first function; Here, the descriptive information of the first function includes at least one of the reference point corresponding to the first end, the processing method, the relationship between the reference point and the processing method, associated information of a processing domain, AI model information, a model connection relationship of an AI model, and an activation method of an AI model.

[0075] It should be explained that the first end may send a first request to a fourth end to request registration of a first function, where the descriptive information of the first function includes at least one of the reference point corresponding to the first end, the processing method, the relationship between the reference point and the processing method, associated information of a processing domain, AI model information, a model connection relationship of an AI model, and an activation method of an AI model.

[0076] Here, the fourth end may be a Network Repository Function (NRF), which is responsible for maintaining a description of available network function instances, the services each network function instance supports, and the services each network function depends on. Optionally, the fourth end may also be another communication device, and the embodiments of the present disclosure are not specifically limited thereto.

[0077] In an embodiment of the present disclosure, a first end sends a first request to a fourth end to request to register a first function at the fourth end, and the first request may carry descriptive information of the first function, which is used to describe the first function. For example, the descriptive information of the first function may include AI model information, such as an AI model or an AI model list, such as model.0.0.0, or an AI model list [model.0.0.0, model.0.0.1, model.0.0.3], and further, based on the AI ​​model information, it can be determined which AI model the first function is processed by.

[0078] For example, the description information of the first function includes a reference point corresponding to the first end, and further determines at which reference point the target object is to be processed. Or, the description information of the first function includes a processing method, for example, the processing method includes a processing method based on an AI model, an undefined processing method, a processing method determined by the target end itself, etc. Or, the description information of the first function includes a relationship between a reference point and a processing method, for example, reference point ReP.0.0.0 applies processing method 1, and reference point ReP.0.0.0 and reference point ReP.0.0.1 apply processing method 2.

[0079] It should be noted that the description information of the first function may further include related information of a processing domain, for example, the above-mentioned processing domain includes a reference point, and it can be determined at which reference point the target object is to be processed based on the processing domain. Also, based on the processing domain, it can determine the function of the reference point, the relationship between the input and output of the AI ​​model and the reference point, the model connection relationship between the AI ​​models, etc., and the related information of the processing domain includes a processing time constraint corresponding to the processing domain and / or a processing method corresponding to the processing domain. For the related information of the processing domain, please refer to the description in the above embodiment, and no further description will be given here.

[0080] In addition, the descriptive information of the first function may further include AI model information, a model connection relationship of the AI ​​model, and a startup method of the AI ​​model. The related concepts of the AI ​​model information, the model connection relationship of the AI ​​model, and the startup method of the AI ​​model can be specifically referred to the descriptions in the above embodiments, and will not be further described here.

[0081] It should be explained that the descriptive information of the first function includes at least one of the reference point corresponding to the first function, the processing method, the relationship between the reference point and the processing method, related information of the processing domain, AI model information, the model connection relationship of the AI ​​model, and the startup method of the AI ​​model. Furthermore, the information content specifically included in the descriptive information of the first function may be in various forms, and will not be listed one by one in the embodiments of the present disclosure.

[0082] In an embodiment of the present disclosure, the second end sends a first service request requesting a first function to the fourth end, and the fourth end can send description information corresponding to the registered first function to the second end, and the second end processes a target object according to the description information of the first function, where the target object can be the same as or different from the target object in the above embodiment, such as a processing manner at a reference point of a signal indicated by the first indication information, and where the second end processes a task according to the description information of the first function.

[0083] It should be noted that the fourth end may register a first function according to the first request sent by the first end, and the second end or other communication device other than the first end may send a first service request to the fourth end to request the first function, in this case, the first end processes the target object according to the description information of the first function, where the description information of the first function may specifically refer to the above, and will not be further described here.

[0084] It should also be noted that when the second end sends a first service request to the fourth end and requests a first function, the first end can further interact with a sixth end associated therewith via third instruction information, and the sixth end can also process a target object according to the description information of the first function, where the sixth end can be a communication device other than the first end and the fourth end.

[0085] Optionally, the second end processes the target object based on the description information of the first function. When the description information of the first function includes the reference point corresponding to the first end, the second end processes the target object at the reference point; When the description information of the first function includes a relationship between the reference point and the processing manner, the second end processes the target object according to a processing manner corresponding to the reference point; When the description information of the first function includes related information of the processing domain, obtaining a target reference point where the second end is included in the processing domain, and processing the target object at the target reference point; When the description information of the first function includes the processing method, the second end processes the target object according to the processing method; When the description information of the first function includes the AI ​​model information, the second end determines a target AI model according to the AI ​​model information, and processes the target object according to the target AI model; When the description information of the first function includes a model connection relationship of the AI ​​model, the second end determines a target AI model according to the connection relationship of the AI ​​model, and processes the target object according to the target AI model; When the description information of the first function includes the activation method of the AI ​​model, the second end determines a target AI model based on the activation method of the AI ​​model, and activates the target AI model according to the activation method of the AI ​​model to process the target object.

[0086] Furthermore, when the description information of the first function is updated, the method further comprises: The method may further include the second end receiving updated first feature description information transmitted by at least one of the first end and the fourth end.

[0087] For example, the description information of the first function includes an AI model startup method, and when the AI ​​model startup method is updated, the first end sends the updated AI model startup method to the fourth end and / or the second end. Also, for example, the description information of the first function includes a reference point corresponding to the first end, and when the reference point corresponding to the first end is updated, the first end sends the updated reference point to the fourth end and / or the second end. As can be understood, the information content included in the description information of the first function may be in other cases, and will not be further listed here.

[0088] Alternatively, the fourth end may transmit the received, updated descriptive information of the first function to the second end, and the second end may directly receive the updated descriptive information of the first function transmitted by the first end or receive the updated descriptive information of the first function transmitted by the fourth end.

[0089] In the embodiment of the present disclosure, the first end sending a second request to a fifth end requesting registration of the first scheme; In such a case, the method comprises: the second end sending a second service request to a fifth end to request the first scheme; The second end receives description information of a first scheme transmitted by the fifth end; The second end may further include processing the target object based on the description information of the first type; Here, the descriptive information of the first method includes at least one of the reference point corresponding to the first method, the processing method, the relationship between the reference point and the processing method, associated information of a processing domain, AI model information, a model connection relationship of an AI model, and an activation method of an AI model.

[0090] Illustratively, the fifth end may be a Network Repository Function (NRF). Optionally, the fifth end and the fourth end may be the same communication device or different communication devices.

[0091] In an embodiment of the present disclosure, the first end requests to register the first method at the fifth end by sending a second request to the fifth end, and the first request may carry description information of the first method, which is used to describe the first method. The description information of the first method includes at least one of the reference point corresponding to the first method, the processing method, the relationship between the reference point and the processing method, related information of the processing domain, AI model information, the model connection relationship of the AI ​​model, and the startup method of the AI ​​model. The specific contents included in the description information of the first method may be various, and this embodiment does not specifically list them.

[0092] Here, the specific concepts of the reference point, the processing method, the relationship between the reference point and the processing method, related information of the processing domain, AI model information, the model connection relationship of the AI ​​model, and the startup method of the AI ​​model can be referred to in the description of the above-mentioned embodiments, and will not be described further here.

[0093] Optionally, the second end processes the target object based on the description information of the first type. When the description information of the first type includes the reference point corresponding to the first type, the second end processes a target object at the reference point; When the description information of the first manner includes a relationship between the reference point and the processing manner, the second end processes the target object according to the processing manner corresponding to the reference point; When the description information of the first manner includes related information of the processing domain, obtaining a target reference point where the second end is included in the processing domain, and processing a target object at the target reference point; When the description information of the first method includes the processing method, the second end processes the target object according to the processing method; When the description information of the first manner includes the AI ​​model information, the second end determines a target AI model according to the AI ​​model information, and processes the target object according to the target AI model; When the description information of the first manner includes a model connection relationship of the AI ​​model, the second end determines a target AI model according to the connection relationship of the AI ​​model, and processes the target object according to the target AI model; When the descriptive information of the first function includes the activation method of the AI ​​model, the second end determines a target AI model based on the activation method of the AI ​​model, and activates the target AI model according to the activation method of the AI ​​model to process the target object.

[0094] Optionally, when the second end requests a first method from the fifth end, the first end processes a third target object based on a target method, which is a method of processing a fourth target object according to description information of the first method.

[0095] Optionally, the first end processes a fourth target object based on the description information of the first manner; When the description information of the first method includes the reference point corresponding to the first method, the first end processes a fourth target object at the reference point; When the description information of the first manner includes a relationship between the reference point and the processing manner, the first end processes a fourth target object according to a processing manner corresponding to the reference point; When the description information of the first manner includes related information of the processing domain, obtain a target reference point whose first end is included in the processing domain, and process a fourth target object at the target reference point; When the description information of the first manner includes the processing manner, the first end processes a fourth target object according to the processing manner; When the description information of the first manner includes the AI ​​model information, the first end determines a target AI model according to the AI ​​model information, and processes a fourth target object according to the target AI model; When the description information of the first manner includes a model connection relationship of the AI ​​model, the first end determines a target AI model according to the connection relationship of the AI ​​model, and processes a fourth target object according to the target AI model; When the descriptive information of the first function includes the activation method of the AI ​​model, the first end determines a target AI model based on the activation method of the AI ​​model, and activates the target AI model according to the activation method of the AI ​​model to process a fourth target object.

[0096] Optionally, when the description information of the first scheme is updated, the method further comprises: The method further includes the second end receiving updated first scheme description information transmitted by at least one of the first end and the fifth end.

[0097] For example, the description information of the first method includes an AI model startup method, and when the AI ​​model startup method is updated, the first end transmits the updated AI model startup method to the fifth end and / or the second end. Also, for example, the description information of the first method includes a reference point corresponding to the first method, and when the reference point corresponding to the first method is updated, the first end transmits the updated reference point to the fifth end and / or the second end. As can be understood, the information content included in the description information of the first method may be in other cases, and will not be further listed here.

[0098] Alternatively, the fifth end may transmit the received, updated descriptive information of the first scheme to the second end, and the second end may directly receive the updated descriptive information of the first scheme transmitted by the first end or receive the updated descriptive information of the first scheme transmitted by the fifth end.

[0099] For a better understanding, the above solutions of the embodiments of the present disclosure are illustrated below by specific examples.

[0100] Assume that the description information of network function A (ie, the first function above) includes at least one of the following:

[0101] (1) An AI model or AI model list included in network function A, for example, model.0.0.0 or [model.0.0.0, model.0.0.1, model.0.0.3].

[0102] (2) Service information generated by network function A, such as Packet Data Convergence Protocol (PDCP) service data units (SDUs), Radio Link Control (RLC) SDUs, Medium Access Control (MAC) SDUs, Transport Blocks (TBs), etc., and may optionally further include a mapping relationship between services and reference points, for example, service 1 may be used for reference point ReP.0.0.0, and service 2 may be used for reference points ReP.0.0.0 and ReP.0.0.1.

[0103] (3) Service information that network function A depends on or consumes, ie, activation relationships / activation conditions, such as timing information or time information, event information, or MAC SDU, TB block data, etc.

[0104] (4) The processing domain to which network function A belongs.

[0105] Similarly, it may further include description information of network function B, description information of network function C, etc., which are not listed here. The outline of the related interaction process is as follows:

[0106] A network function A, B or C first registers with a Network Repository Function (NRF) responsible for network function registration, which maintains a description of available network function instances, the services that each network function instance supports, and the services that each network function instance depends on; When the description information of network functions A, B, or C is updated by configuration or by itself, it is necessary to update the description information in the network repository function; When network function A needs to use a first service, network function A may send a network function / service discovery request to a network repository function, including therein its required service description information and performance requirements; The network repository function provides network function information that satisfies the requested function / service based on the network functions that it can discover; Network function A uses the service generated by this network function based on the received information.

[0107] If network function A needs to use this service continuously, it can subscribe to network function profile update information that provides this service to the network repository function. If the update information is not received, then the network function can directly use the service generated by this function. If the update information is received and the update information affects the service used by network function A, network function A can send the required function / service discovery request to the network repository function again.

[0108] Referring to FIG. 3, FIG. 3 is a flowchart of another communication method according to an embodiment of the present disclosure. As shown in FIG. 3, the communication method includes: The method includes step 301 in which a first end interacts with at least one second end with first instruction information corresponding to a reference point, the first instruction information being used to instruct a processing manner at the reference point of a target object.

[0109] Optionally, the reference point is: Predefined and Contract by protocol, and second indication information for indicating the reference point transmitted by the third end.

[0110] Optionally, the processing method comprises: A processing method based on AI models, and a processing method determined by a target end, which is the first end or the second end.

[0111] Optionally, the processing method based on the AI ​​model comprises: A model connection relationship of the AI ​​model; A startup method of the AI ​​model; and associated information of a processing domain corresponding to the AI ​​model, including the reference point.

[0112] Optionally, the model connection relationship of the AI ​​model is: A processing order of the AI ​​model; and and input / output relationships between the AI ​​models.

[0113] Optionally, the first instruction information includes first target information, and the first target information is used to indicate a model connection relationship of the AI ​​model, and the first target information is: a model identifier for indicating an AI model to be used by a target end including at least one of the first end and the second end; and a model connection identifier for indicating a connection relationship between different AI models.

[0114] Optionally, the first target information includes model configuration information including the model identifier; The model configuration information is further used to configure an input of an AI model to reference a first object, the first object including at least one of a pre-defined reference point and an output of another AI model.

[0115] Alternatively, when the number of the preset reference points is a plurality of points, the plurality of preset reference points are arranged in a predetermined order.

[0116] Optionally, the activation manner of the AI ​​model is: Starting up based on a preset start-up time; triggering when data of at least one reference point corresponding to the AI ​​model arrives; Activating when at least one reference point data among at least one reference point data corresponding to the AI ​​model is updated; activating said AI model when all required inputs have arrived; Triggering at least one pre-configured AI model when the model completes processing; Triggering when an output of at least one pre-configured AI model is updated; activating said AI model when it receives an input from a previous AI model; and activating the AI ​​model when the AI ​​model receives a preset output value of another AI model.

[0117] Optionally, the number of AI models that are activated is at least one.

[0118] Optionally, the number of processing domains is at least one, and the processing domain comprises: The function of the reference point; A relationship between the input and output of the AI ​​model and the reference point; and and a model connection relationship between the AI ​​models.

[0119] Optionally, the relevant information for the processing domain comprises: A processing time constraint corresponding to the processing domain.

[0120] and a processing method corresponding to the processing domain.

[0121] Optionally, the processing method corresponding to the processing domain includes at least one of a startup method of the AI ​​model, a startup time of the AI ​​model, a termination time of the AI ​​model, and a processing time length of the AI ​​model.

[0122] Optionally, the processing time constraint corresponding to the processing domain includes at least one of a startup method of the AI ​​model, a startup time of the AI ​​model, a termination time of the AI ​​model, and a processing time length of the AI ​​model.

[0123] Optionally, different said processing domains correspond to respective said processing time constraints.

[0124] Optionally, different said processing domains correspond to respective said processing schemes.

[0125] Optionally, the method further comprises: The method further includes the first end sending a first request to a fourth end to request registration of a first function; Here, the descriptive information of the first function includes at least one of the reference point corresponding to the first function, the processing method, the relationship between the reference point and the processing method, a processing domain, AI model information, a model connection relationship of the AI ​​model, and a startup method of the AI ​​model.

[0126] Optionally, the method further comprises: When the second end requests a first function from the fourth end, the first end processes a first target object based on the description information of the first function, or the first end interacts with a sixth end with third instruction information, the third instruction information being used to instruct the sixth end to process a second target object based on the description information of the first function, and the sixth end is an entity having an associated relationship with the first end; Here, the descriptive information of the first function includes at least one of the reference point corresponding to the first function, the processing method, the relationship between the reference point and the processing method, associated information of a processing domain, AI model information, a model connection relationship of an AI model, and an activation method of an AI model.

[0127] Optionally, the first end processes the first target object based on the description information of the first function, When the description information of the first function includes the reference point corresponding to the first end, the first end processes the third target object at the reference point; When the description information of the first function includes a relationship between the reference point and the processing manner, the first end processes the target object according to a processing manner corresponding to the reference point; When the description information of the first function includes the processing domain, obtaining a reference point where the first end is included in the processing domain, and processing the target object at the reference point; When the description information of the first function includes the processing method, the first end processes the target object according to the processing method; When the description information of the first function includes the AI ​​model information, the first end determines a target AI model according to the AI ​​model information, and processes the target object according to the target AI model; When the description information of the first function includes a model connection relationship of the AI ​​model, the first end determines a target AI model according to the connection relationship of the AI ​​model, and processes the target object according to the target AI model; When the description information of the first function includes the activation method of the AI ​​model, the first end determines a target AI model based on the activation method of the AI ​​model, and activates the target AI model according to the activation method of the AI ​​model to process the target object.

[0128] Optionally, the method further comprises: The method further includes, when the descriptive information of the first function is updated, the first end transmitting the updated descriptive information of the first function to at least one of the fourth end and the second end.

[0129] Optionally, the method further comprises: The method further includes the first end sending a second request to a fifth end to request registration of the first method; Here, the descriptive information of the first method includes at least one of the reference point corresponding to the first method, the processing method, the relationship between the reference point and the processing method, associated information of a processing domain, AI model information, a model connection relationship of an AI model, and an activation method of an AI model.

[0130] Optionally, the method further comprises: When the second end requests the first method from the fifth end, the first end further processes a third target object based on a target method, which is a method of processing a fourth target object according to description information of the first method; Here, the descriptive information of the first method includes at least one of the reference point corresponding to the first method, the processing method, the relationship between the reference point and the processing method, associated information of a processing domain, AI model information, a model connection relationship of an AI model, and an activation method of an AI model.

[0131] Optionally, the method further comprises: The method further includes, when the descriptive information of the first method is updated, transmitting the updated descriptive information of the first method to at least one of the fifth end and the second end from the first end.

[0132] Optionally, the first instruction information is further used to indicate at least one of a test methodology and a test requirement for the reference point.

[0133] Optionally, the method further comprises: The first end further includes testing the reference points based on at least one of the test strategy and test requirements.

[0134] It should be noted that the communication method according to the embodiment of the present disclosure is applied to a first end and corresponds to the communication method applied to a second end according to the embodiment of FIG. 2 above, and the specific implementation process of the relevant concepts and related steps in the embodiment of the present disclosure may be referred to the description in the embodiment of the method described in FIG. 2 above, and will not be further described here in order to avoid repetition.

[0135] In the embodiment of the present disclosure, the first end can interact with the second end in a processing manner at a reference point for a target object, so that the processing manner of the communication devices for signals, data, tasks, etc. is more flexible, and corresponding capability interaction flow can be established between the communication devices, so that the processing manner of signals, data, tasks, etc. between the communication devices can be effectively coordinated.

[0136] The execution body of the communication method according to the embodiment of the present disclosure may be a communication device. In the embodiment of the present disclosure, the communication device according to the embodiment of the present disclosure will be described by taking the communication method executed by the communication device as an example.

[0137] Referring to FIG. 4, FIG. 4 is a structural diagram of another communication device according to an embodiment of the present disclosure. As shown in FIG. 4, the communication device 400 includes: A receiving module 401 for receiving first instruction information for instructing a processing manner at a reference point of a target object; and a processing module 402 for processing the target object at the reference point according to the processing scheme.

[0138] Optionally, the reference point is: Predefined and Contract by protocol, and second indication information for indicating the reference point transmitted by the third end.

[0139] Optionally, the processing method comprises: A processing method based on artificial intelligence (AI) model; and a processing method determined by a target end including the second end.

[0140] Optionally, the processing method based on the AI ​​model comprises: A model connection relationship of the AI ​​model; A startup method of the AI ​​model; and associated information of a processing domain corresponding to the AI ​​model, including the reference point.

[0141] Optionally, the model connection relationship of the AI ​​model is: A processing order of the AI ​​model; and and input / output relationships between the AI ​​models.

[0142] Optionally, the processing module 402 further comprises: When the model connection relationship of the AI ​​model includes a processing order of the AI ​​model, determining a first applied AI model according to the processing order of the AI ​​model, starting up the first applied AI model according to the processing order of the AI ​​model, and processing the target object; When the model connection relationship of the AI ​​models includes an input / output relationship between the AI ​​models, it is used to perform at least one of determining a second applied AI model according to the input / output relationship between the AI ​​models, and processing the target object using the second applied AI model.

[0143] Optionally, the first instruction information includes first target information, and the first target information is used to indicate a model connection relationship of the AI ​​model, and the first target information is: a model identifier for indicating an AI model to be used by a target end including the second end; and a model connection identifier for indicating a connection relationship between different AI models.

[0144] Optionally, the first target information includes model configuration information including the model identifier; The model configuration information is further used to configure an input of an AI model to reference a first object, the first object including at least one of a pre-defined reference point and an output of another AI model.

[0145] Alternatively, when the number of the preset reference points is a plurality of points, the plurality of preset reference points are arranged in a predetermined order.

[0146] Optionally, the activation manner of the AI ​​model is: Starting up based on a preset start-up time; triggering when data of at least one reference point corresponding to the AI ​​model arrives; Activating when at least one reference point data among at least one reference point data corresponding to the AI ​​model is updated; activating said AI model when all required inputs have arrived; Triggering at least one pre-configured AI model when the model completes processing; Triggering when an output of at least one pre-configured AI model is updated; activating said AI model when it receives an input from a previous AI model; and activating the AI ​​model when the AI ​​model receives a preset output value of another AI model.

[0147] Optionally, the number of AI models that are activated is at least one.

[0148] Optionally, the number of processing domains is at least one, and the processing domain comprises: The function of the reference point; A relationship between the input and output of the AI ​​model and the reference point; and and a model connection relationship between the AI ​​models.

[0149] Optionally, the relevant information for the processing domain comprises: A processing time constraint corresponding to the processing domain.

[0150] and a processing method corresponding to the processing domain.

[0151] Optionally, the processing method corresponding to the processing domain includes at least one of a startup method of the AI ​​model, a startup time of the AI ​​model, a termination time of the AI ​​model, and a processing time length of the AI ​​model.

[0152] Optionally, the processing time constraint corresponding to the processing domain includes at least one of a startup method of the AI ​​model, a startup time of the AI ​​model, a termination time of the AI ​​model, and a processing time length of the AI ​​model.

[0153] Optionally, different said processing domains correspond to respective said processing time constraints.

[0154] Optionally, different said processing domains correspond to respective said processing schemes.

[0155] Optionally, the apparatus further includes a transmission module; the sending module is adapted to send a first service request to a fourth end for requesting a first function; The receiving module 401 is further used for receiving the description information of the first capability sent by the fourth end; The processing module 402 is further used to process the target object based on the description information of the first function; Here, the descriptive information of the first function includes at least one of the reference point corresponding to the first end, the processing method, the relationship between the reference point and the processing method, associated information of a processing domain, AI model information, a model connection relationship of an AI model, and an activation method of an AI model.

[0156] Optionally, the processing module 402 may further include: if the description information of the first function includes the reference point corresponding to the first edge, processing the target object at the reference point; When the description information of the first function includes a relationship between the reference point and the processing manner, processing the target object according to the processing manner corresponding to the reference point; When the description information of the first function includes related information of the processing domain, acquiring a target reference point included in the processing domain, and processing the target object at the target reference point; When the description information of the first function includes the processing method, processing the target object according to the processing method; When the description information of the first function includes the AI ​​model information, determining a target AI model based on the AI ​​model information, and processing the target object based on the target AI model; When the description information of the first function includes a model connection relationship of the AI ​​model, determining a target AI model based on the connection relationship of the AI ​​model, and processing the target object based on the target AI model; When the descriptive information of the first function includes the activation method of the AI ​​model, it is used to perform at least one of determining a target AI model based on the activation method of the AI ​​model, and invoking the target AI model in accordance with the activation method of the AI ​​model to process the target object.

[0157] Optionally, the receiving module 401 further comprises: It is used to receive updated first feature description information transmitted by at least one of the first end and the fourth end.

[0158] Optionally, the sending module is further used for sending a second service request to the fifth end for requesting the first scheme; The receiving module 401 is further used for receiving description information of a first mode sent by the fifth end; The processing module 402 is further used to process the target object based on the description information of the first manner; Here, the descriptive information of the first method includes at least one of the reference point corresponding to the first method, the processing method, the relationship between the reference point and the processing method, associated information of a processing domain, AI model information, a model connection relationship of an AI model, and an activation method of an AI model.

[0159] Optionally, the receiving module 401 further comprises: It is used to receive updated first scheme description information transmitted by at least one of the first end and the fifth end.

[0160] Optionally, the first instruction information is further used to indicate at least one of a test methodology and a test requirement for the reference point.

[0161] Optionally, the apparatus further includes a test module, the test module comprising: The test method is used to test the reference point based on at least one of the test method and the test requirements.

[0162] In the solution according to the embodiment of the present disclosure, the device can perform processing of the target object according to a processing manner at the reference point of the target object based on the first instruction information, making the processing manner of signals, data, tasks, etc. by the communication devices more flexible, and thereby establishing corresponding capability interaction flows between the communication devices, and effectively coordinating the processing manners of signals, data, tasks, etc. between the communication devices.

[0163] The communication device 400 in the embodiment of the present disclosure may be an electronic device, for example, an electronic device having an operating system, or may be a component in an electronic device, for example, an integrated circuit or chip. The electronic device may be a terminal or other device other than a terminal. Exemplarily, the terminal may include, but is not limited to, the types of terminal 11 listed above, and the other device may be a server, a network attached storage (NAS), etc., and the embodiment of the present disclosure is not specifically limited thereto.

[0164] The communication device 400 according to the embodiment of the present disclosure can implement each process implemented by the embodiment of the method in FIG. 2 and achieve the same technical effect, and will not be further described here to avoid repetition of description.

[0165] Referring to FIG. 5, FIG. 5 is a structural diagram of a communication device according to an embodiment of the present disclosure. As shown in FIG. 5, the communication device 500 includes: The system further includes a transmitting module 501 for interacting with at least one second end first instruction information corresponding to a reference point, the first instruction information being used to instruct a processing manner at the reference point of a target object.

[0166] Optionally, the reference point is: Predefined and Contract by protocol, and second indication information for indicating the reference point transmitted by the third end.

[0167] Optionally, the processing method comprises: A processing method based on artificial intelligence (AI) model; and a processing method determined by a target end, which is the first end or the second end.

[0168] Optionally, the processing method based on the AI ​​model comprises: A model connection relationship of the AI ​​model; A method for starting the AI ​​model; and associated information of a processing domain corresponding to the AI ​​model, including the reference point.

[0169] Optionally, the model connection relationship of the AI ​​model is: A processing order of the AI ​​model; and and input / output relationships between the AI ​​models.

[0170] Optionally, the first instruction information includes first target information, and the first target information is used to indicate a model connection relationship of the AI ​​model, and the first target information is: a model identifier for indicating an AI model to be used by the second end; and a model connection identifier for indicating a connection relationship between different AI models.

[0171] Optionally, the first target information includes model configuration information including the model identifier; The model configuration information is further used to configure an input of an AI model to reference a first object, the first object including at least one of a pre-defined reference point and an output of another AI model.

[0172] Alternatively, when the number of the preset reference points is a plurality of points, the plurality of preset reference points are arranged in a predetermined order.

[0173] Optionally, the activation manner of the AI ​​model is: Starting up based on a preset start-up time; triggering when data of at least one reference point corresponding to the AI ​​model arrives; Activating when at least one reference point data among at least one reference point data corresponding to the AI ​​model is updated; activating said AI model when all required inputs have arrived; Triggering at least one pre-configured AI model when the model completes processing; Triggering when an output of at least one pre-configured AI model is updated; activating said AI model when it receives an input from a previous AI model; and activating the AI ​​model when the AI ​​model receives a preset output value of another AI model.

[0174] Optionally, the number of AI models that are activated is at least one.

[0175] Optionally, the number of processing domains is at least one, and the processing domain comprises: The function of the reference point; A relationship between the input and output of the AI ​​model and the reference point; and and a model connection relationship between the AI ​​models.

[0176] Optionally, the relevant information for the processing domain comprises: A processing time constraint corresponding to the processing domain; and and a processing method corresponding to the processing domain.

[0177] Optionally, the processing method corresponding to the processing domain includes at least one of a startup method of the AI ​​model, a startup time of the AI ​​model, a termination time of the AI ​​model, and a processing time length of the AI ​​model.

[0178] Optionally, the processing time constraint corresponding to the processing domain includes at least one of a startup method of the AI ​​model, a startup time of the AI ​​model, a termination time of the AI ​​model, and a processing time length of the AI ​​model.

[0179] Optionally, different said processing domains correspond to respective said processing time constraints.

[0180] Optionally, different said processing domains correspond to respective said processing schemes.

[0181] Optionally, the transmitting module 501 further comprises: for sending a first request to the fourth end to request registration of the first function; Here, the descriptive information of the first function includes at least one of the reference point corresponding to the first end, the processing method, the relationship between the reference point and the processing method, a processing domain, AI model information, a model connection relationship of the AI ​​model, and a startup method of the AI ​​model.

[0182] Optionally, the apparatus further includes a processing module, the processing module comprising: When the second end requests a first function from the fourth end, the fourth end processes a first target object based on the description information of the first function, or the third instruction information is used to interact with the sixth end, and the third instruction information is used to instruct the sixth end to process a second target object based on the description information of the first function, and the sixth end is an entity having an associated relationship with the first end; Here, the descriptive information of the first function includes at least one of the reference point corresponding to the first function, the processing method, the relationship between the reference point and the processing method, associated information of a processing domain, AI model information, a model connection relationship of an AI model, and an activation method of an AI model.

[0183] Optionally, the processing module comprises: If the description information of the first function includes the reference point corresponding to the first edge, processing the first target object at the reference point; When the description information of the first function includes a relationship between the reference point and the processing manner, processing the first target object according to the processing manner corresponding to the reference point; When the description information of the first function includes the processing domain, acquiring a target reference point included in the processing domain, and processing the first target object at the target reference point; When the description information of the first function includes the processing method, processing the first target object according to the processing method; When the description information of the first function includes the AI ​​model information, determining a target AI model based on the AI ​​model information, and processing the first target object based on the target AI model; When the description information of the first function includes a model connection relationship of the AI ​​model, determining a target AI model based on the connection relationship of the AI ​​model, and processing the first target object based on the target AI model; When the descriptive information of the first function includes the activation method of the AI ​​model, it is used to perform at least one of determining a target AI model based on the activation method of the AI ​​model, and invoking the target AI model in accordance with the activation method of the AI ​​model to process the first target object.

[0184] Optionally, the transmitting module 501 further comprises: When the description information of the first function is updated, the description information of the first function is used to transmit the updated description information of the first function to at least one of the fourth end and the second end.

[0185] Optionally, the transmitting module 501 further comprises: for sending a second request to the fifth end for registration of the first scheme; Here, the descriptive information of the first method includes at least one of the reference point corresponding to the first method, the processing method, the relationship between the reference point and the processing method, associated information of a processing domain, AI model information, a model connection relationship of an AI model, and an activation method of an AI model.

[0186] Optionally, the processing module further comprises: When the second end requests the fifth end to use the first method, the third target object is processed based on a target method, which is a method for processing a fourth target object according to the description information of the first method; Here, the descriptive information of the first method includes at least one of the reference point corresponding to the first method, the processing method, the relationship between the reference point and the processing method, associated information of a processing domain, AI model information, a model connection relationship of an AI model, and an activation method of an AI model.

[0187] Optionally, the transmitting module 501 further comprises: When the description information of the first method is updated, the description information of the first method is used to transmit the updated description information of the first method to at least one of the fifth end and the second end.

[0188] Optionally, the first instruction information is further used to indicate at least one of a test methodology and a test requirement for the reference point.

[0189] Optionally, the apparatus further includes a test module, the test module comprising: The first end is used to test the reference point based on at least one of the test strategy and the test requirements.

[0190] The solution according to the embodiment of the present disclosure enables the device to instruct a processing method at a reference point for a target object by the second end, making the processing methods of signals, data, tasks, etc. by the communication devices more flexible, and thereby establishing corresponding capability interaction flows between the communication devices, and effectively coordinating the processing methods of signals, data, tasks, etc. between the communication devices.

[0191] The communication device 500 according to the embodiment of the present disclosure can implement each process implemented by the embodiment of the method of FIG. 3 and achieve the same technical effect, and will not be further described here to avoid repetition of description.

[0192] Optionally, as shown in Fig. 6, an embodiment of the present disclosure further provides a communication device 600, including a processor 601 and a memory 602, the memory 602 stores a program or instruction that can run on the processor 601, and when the program or instruction is executed by the processor 601, each step of the embodiment of the communication method described in Fig. 2 or Fig. 3 above can be realized, and the same technical effect can be achieved. In order to avoid repetition, no further description will be given here.

[0193] The embodiment of the present disclosure further provides a terminal, and the implementation processes and realization methods of the method embodiments of Figure 2 or Figure 3 can all be applied to the embodiment of this terminal, and the same technical effects can be achieved. Specifically, Figure 7 is a schematic diagram of the hardware structure of the terminal of the embodiment of the present disclosure.

[0194] The terminal 700 includes at least some components such as, but not limited to, a radio frequency unit 701, a network module 702, an audio output unit 703, an input unit 704, a sensor 705, a display unit 706, a user input unit 707, an interface unit 708, a memory 709 and a processor 710.

[0195] As can be understood by those skilled in the art, the terminal 700 may further include a power source (e.g., a battery) for powering each component, and the power source may be logically connected to the processor 710 by a power management system, so that the power management system can realize functions such as charge / discharge management and power consumption management. The terminal structure shown in Figure 7 does not constitute a limitation on the terminal, and the terminal may include more or less components than the number of components shown, or a combination of some components, or a different arrangement of components, and will not be further described here.

[0196] It should be understood that in the embodiment of the present disclosure, the input unit 704 may include a graphics processing unit (GPU) 7041 and a microphone 7042, and the graphics processor 7041 processes image data of still or video images obtained by an image capture device (e.g., a camera) in a video capture mode or an image capture mode. The display unit 706 may include a display panel 7061, and the display panel 7061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 707 includes at least one of a touch panel 7071 and other input devices 7072. The touch panel 7071 is also called a touch screen. The touch panel 7071 may include two parts: a touch detection device and a touch controller. The other input devices 7072 may include, but are not limited to, a physical keyboard, function keys (e.g., volume control buttons, switch buttons, etc.), a trackball, a mouse, and a control lever, which will not be described further herein.

[0197] In the embodiment of the present disclosure, when the radio frequency unit 701 receives downlink data from the network side device, the radio frequency unit 701 can transmit the downlink data to the processor 710 for processing, and the radio frequency unit 701 can transmit uplink data to the network side device. In general, the radio frequency unit 701 includes, but is not limited to, an antenna, an amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc.

[0198] The memory 709 may be used to store software programs or instructions and various data. The memory 709 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, where the first storage area may store an operating system, an application program or instructions required for at least one function (e.g., a sound playback function, an image playback function, etc.), etc. The memory 709 may include a volatile memory or a non-volatile memory, or the memory 709 may include both a volatile and a non-volatile memory. Here, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be Random Access Memory (RAM), Static Random Access Memory (Static RAM, SRAM), Dynamic Random Access Memory (DRAM, DRAM), Synchronous Dynamic Random Access Memory (Synchronous DRAM, SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (Double Data Rate SDRAM, DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (Enhanced SDRAM, ESDRAM), Synch link Dynamic Random Access Memory (Synch link DRAM, SLDRAM), and Direct Rambus Random Access Memory (Direct Rambus RAM, DRRAM). Memory 709 in embodiments of the present disclosure may include, but is not limited to, these and any other suitable types of memory.

[0199] The processor 710 may include one or more processing units. Optionally, the processor 710 may be integrated with an application processor and a modem processor, where the application processor mainly processes operations related to the operating system, user interface, and application programs, and the modem processor mainly processes wireless communication signals, e.g., a baseband processor. As can be understood, the modem processor may not be integrated into the processor 710.

[0200] In one embodiment of the present disclosure, the terminal 700 is a first end.

[0201] Here, the radio frequency unit 701 is used to interact with at least one second end with first instruction information corresponding to a reference point, and the first instruction information is used to instruct a processing manner at the reference point of a target object.

[0202] Optionally, the reference point is: Predefined and Contract by protocol, and second indication information for indicating the reference point transmitted by the third end.

[0203] Optionally, the processing method comprises: A processing method based on artificial intelligence (AI) model; and a processing method determined by a target end including the second end.

[0204] Optionally, the processing method based on the AI ​​model comprises: A model connection relationship of the AI ​​model; A method for starting the AI ​​model; and related information of the processing domain containing the reference point.

[0205] Optionally, the model connection relationship of the AI ​​model is: A processing order of the AI ​​model; and and input / output relationships between the AI ​​models.

[0206] Optionally, the first instruction information includes first target information, and the first target information is used to indicate a model connection relationship of the AI ​​model, and the first target information is: a model identifier for indicating an AI model to be used by a target end including the second end; and a model connection identifier for indicating a connection relationship between different AI models.

[0207] Optionally, the first target information includes model configuration information including the model identifier; The model configuration information is further used to configure an input of an AI model to reference a first object, the first object including at least one of a pre-defined reference point and an output of another AI model.

[0208] Alternatively, when the number of the preset reference points is a plurality of points, the plurality of preset reference points are arranged in a predetermined order.

[0209] Optionally, the activation manner of the AI ​​model is: Starting up based on a preset start-up time; triggering when data of at least one reference point corresponding to the AI ​​model arrives; Activating when at least one reference point data among at least one reference point data corresponding to the AI ​​model is updated; activating said AI model when all required inputs have arrived; Triggering at least one pre-configured AI model when the model completes processing; Triggering when an output of at least one pre-configured AI model is updated; activating said AI model when it receives an input from a previous AI model; and activating the AI ​​model when the AI ​​model receives a preset output value of another AI model.

[0210] Optionally, the number of AI models that are activated is at least one.

[0211] Optionally, the number of processing domains is at least one, and the processing domain comprises: The function of the reference point; A relationship between the input and output of the AI ​​model and the reference point; and and a model connection relationship between the AI ​​models.

[0212] Optionally, the relevant information for the processing domain comprises: A processing time constraint corresponding to the processing domain; and and a processing method corresponding to the processing domain.

[0213] Optionally, the processing method corresponding to the processing domain includes at least one of a startup method of the AI ​​model, a startup time of the AI ​​model, a termination time of the AI ​​model, and a processing time length of the AI ​​model.

[0214] Optionally, the processing time constraint corresponding to the processing domain includes at least one of a startup method of the AI ​​model, a startup time of the AI ​​model, a termination time of the AI ​​model, and a processing time length of the AI ​​model.

[0215] Optionally, different said processing domains correspond to respective said processing time constraints.

[0216] Optionally, different said processing domains correspond to respective said processing schemes.

[0217] Optionally, the radio frequency unit 701 is further used for sending a first request to the fourth end to request registration of the first function; Here, the descriptive information of the first function includes at least one of the reference point corresponding to the first end, the processing method, the relationship between the reference point and the processing method, a processing domain, AI model information, a model connection relationship of the AI ​​model, and a startup method of the AI ​​model.

[0218] Optionally, the processor 710 is used to process a target object based on the description information of the first function when the second end requests the fourth end to perform a first function, or to interact with a sixth end based on the description information of the first function, and the third instruction information is used to instruct the sixth end to process a second target object based on the description information of the first function, and the sixth end is an entity having an associated relationship with the first end; Here, the descriptive information of the first function includes at least one of the reference point corresponding to the first function, the processing method, the relationship between the reference point and the processing method, associated information of a processing domain, AI model information, a model connection relationship of an AI model, and an activation method of an AI model.

[0219] Optionally, the processor 710 may further When the description information of the first function includes the reference point corresponding to the first end, the first end processes the third target object at the reference point; When the description information of the first function includes a relationship between the reference point and the processing manner, the first end processes the third target object according to a processing manner corresponding to the reference point; When the description information of the first function includes the processing domain, obtaining a target reference point whose first end is included in the processing domain, and processing the third target object at the target reference point; When the description information of the first function includes the processing method, the first end processes the third target object according to the processing method; When the description information of the first function includes the AI ​​model information, the first end determines a target AI model according to the AI ​​model information, and processes the third target object according to the target AI model; When the description information of the first function includes a model connection relationship of the AI ​​model, the first end determines a target AI model according to the connection relationship of the AI ​​model, and processes the third target object according to the target AI model; When the description information of the first function includes the activation method of the AI ​​model, the first end is used to perform at least one of determining a target AI model based on the activation method of the AI ​​model, and invoking the target AI model according to the activation method of the AI ​​model to process the third target object.

[0220] Optionally, the radio frequency unit 701 is further used for transmitting updated first function description information to at least one of the fourth end and the second end when the first function description information is updated.

[0221] Optionally, the radio frequency unit 701 is further used for sending a second request to the fifth end to request registration of the first scheme; Here, the descriptive information of the first method includes at least one of the reference point corresponding to the first method, the processing method, the relationship between the reference point and the processing method, associated information of a processing domain, AI model information, a model connection relationship of an AI model, and an activation method of an AI model.

[0222] Optionally, the processor 710 is further used to process a third target object based on a target manner, which is a manner of processing a fourth target object according to description information of the first manner, when the second end requests the first manner from the fifth end; Here, the descriptive information of the first method includes at least one of the reference point corresponding to the first method, the processing method, the relationship between the reference point and the processing method, associated information of a processing domain, AI model information, a model connection relationship of an AI model, and an activation method of an AI model.

[0223] Optionally, the radio frequency unit 701 is further used for transmitting updated descriptive information of the first method to at least one of the fifth end and the second end when the descriptive information of the first method is updated.

[0224] Optionally, the first instruction information is further used to indicate at least one of a test methodology and a test requirement for the reference point.

[0225] Optionally, the processor 710 is further adapted to test the reference points based on at least one of the test strategy and the test requirements.

[0226] In another embodiment of the present disclosure, the terminal 700 is a second end.

[0227] Wherein, the radio frequency unit 701 is used for receiving first instruction information for instructing a processing manner at a reference point of a target object; A processor 710 is used to process the target object at the reference point according to the processing scheme.

[0228] Optionally, the reference point is: Predefined and Contract by protocol, and second indication information for indicating the reference point transmitted by the third end.

[0229] Optionally, the processing method comprises: A processing method based on artificial intelligence (AI) model; and a processing method determined by a target end, which is the first end or the second end.

[0230] Optionally, the processing method based on the AI ​​model comprises: A model connection relationship of the AI ​​model; A method for starting the AI ​​model; and related information of the processing domain containing the reference point.

[0231] Optionally, the model connection relationship of the AI ​​model is: A processing order of the AI ​​model; and and input / output relationships between the AI ​​models.

[0232] Optionally, the processor 710 may further When the model connection relationship of the AI ​​model includes a processing order of the AI ​​model, determining a first applied AI model according to the processing order of the AI ​​model, starting up the first applied AI model according to the processing order of the AI ​​model, and processing the target object; When the model connection relationship of the AI ​​models includes an input / output relationship between the AI ​​models, it is used to perform at least one of determining a second applied AI model according to the input / output relationship between the AI ​​models, and processing the target object using the second applied AI model.

[0233] Optionally, the first instruction information includes first target information, and the first target information is used to indicate a model connection relationship of the AI ​​model, and the first target information is: a model identifier for indicating an AI model to be used by a target end including at least one of the first end and the second end; and a model connection identifier for indicating a connection relationship between different AI models.

[0234] Optionally, the first target information includes model configuration information including the model identifier; The model configuration information is further used to configure an input of an AI model to reference a first object, the first object including at least one of a pre-defined reference point and an output of another AI model.

[0235] Alternatively, when the number of the preset reference points is a plurality of points, the plurality of preset reference points are arranged in a predetermined order.

[0236] Optionally, the activation manner of the AI ​​model is: Starting up based on a preset start-up time; triggering when data of at least one reference point corresponding to the AI ​​model arrives; Activating when at least one reference point data among at least one reference point data corresponding to the AI ​​model is updated; activating said AI model when all required inputs have arrived; Triggering at least one pre-configured AI model when the model completes processing; Triggering when an output of at least one pre-configured AI model is updated; activating said AI model when it receives an input from a previous AI model; and activating the AI ​​model when the AI ​​model receives a preset output value of another AI model.

[0237] Optionally, the number of AI models that are activated is at least one.

[0238] Optionally, the number of processing domains is at least one, and the processing domain comprises: The function of the reference point; A relationship between the input and output of the AI ​​model and the reference point; and and a model connection relationship between the AI ​​models.

[0239] Optionally, the relevant information for the processing domain comprises: A processing time constraint corresponding to the processing domain; and and a processing method corresponding to the processing domain.

[0240] Optionally, the processing method corresponding to the processing domain includes at least one of a startup method of the AI ​​model, a startup time of the AI ​​model, a termination time of the AI ​​model, and a processing time length of the AI ​​model.

[0241] Optionally, the processing time constraint corresponding to the processing domain includes at least one of a startup method of the AI ​​model, a startup time of the AI ​​model, a termination time of the AI ​​model, and a processing time length of the AI ​​model.

[0242] Optionally, different said processing domains correspond to respective said processing time constraints.

[0243] Optionally, different said processing domains correspond to respective said processing schemes.

[0244] Optionally, the radio frequency unit 701 further transmits a first service request to the fourth end to request the first function; and for receiving first capability description information transmitted by the fourth end; The processor 710 is further adapted to process the target object based on the description information of the first function; Here, the descriptive information of the first function includes at least one of the reference point corresponding to the first end, the processing method, the relationship between the reference point and the processing method, associated information of the processing domain, AI model information, a model connection relationship of the AI ​​model, and an activation method of the AI ​​model.

[0245] Optionally, the processor 710 may further if the description information of the first function includes the reference point corresponding to the first edge, processing the target object at the reference point; When the description information of the first function includes a relationship between the reference point and the processing manner, processing the target object according to the processing manner corresponding to the reference point; When the description information of the first function includes related information of the processing domain, acquiring a target reference point included in the processing domain, and processing the target object at the target reference point; When the description information of the first function includes the processing method, processing the target object according to the processing method; When the description information of the first function includes the AI ​​model information, determining a target AI model based on the AI ​​model information, and processing the target object based on the target AI model; When the description information of the first function includes a model connection relationship of the AI ​​model, determining a target AI model based on the connection relationship of the AI ​​model, and processing the target object based on the target AI model; When the descriptive information of the first function includes the activation method of the AI ​​model, it is used to perform at least one of determining a target AI model based on the activation method of the AI ​​model, and invoking the target AI model in accordance with the activation method of the AI ​​model to process the target object.

[0246] Optionally, the radio frequency unit 701 further comprises: It is used to receive updated first feature description information transmitted by at least one of the first end and the fourth end.

[0247] Optionally, the radio frequency unit 701 further transmits a second service request to the fifth end to request the first scheme; and used to receive description information of a first scheme transmitted by the fifth end; The processor 710 is further adapted to process the target object based on the description information of the first format; Here, the descriptive information of the first method includes at least one of the reference point corresponding to the first method, the processing method, the relationship between the reference point and the processing method, associated information of a processing domain, AI model information, a model connection relationship of an AI model, and an activation method of an AI model.

[0248] Optionally, the radio frequency unit 701 further comprises: It is used to receive updated first scheme description information transmitted by at least one of the first end and the fifth end.

[0249] Optionally, the first instruction information is further used to indicate at least one of a test methodology and a test requirement for the reference point.

[0250] Optionally, the processor 710 is further adapted to test the reference points based on at least one of the test strategy and the test requirements.

[0251] The terminal 700 according to an embodiment of the present disclosure can interact with other communication devices in a processing manner at a pre-agreed reference point of a target object, making the processing manner of signals, data, tasks, etc. by the communication devices more flexible.

[0252] The embodiments of the present disclosure further provide a network side device, and the implementation processes and realization methods of the embodiments of the methods described in Figures 2 and 3 above can all be applied to the embodiments of this network side device, and the same technical effects can be achieved.

[0253] Specifically, an embodiment of the present disclosure further provides a network side device. As shown in Fig. 8, the network side device 800 includes an antenna 81, a radio frequency device 82, a baseband device 83, a processor 84, and a memory 85. The antenna 81 and the radio frequency device 82 are connected. In the uplink direction, the radio frequency device 82 receives information through the antenna 81, and transmits the received information to the baseband device 83 for processing. In the downlink direction, the baseband device 83 processes the information to be transmitted and transmits it to the radio frequency device 82, and the radio frequency device 82 transmits the received information through the antenna 81 after processing it.

[0254] The methods performed by the network side equipment in the above embodiments may be implemented in a baseband device 83, which includes a baseband processor.

[0255] The baseband device 83 may include, for example, at least one baseband board, on which multiple chips are installed, and as shown in FIG. 8, one of the chips is, for example, a baseband processor, which is connected to a memory 85 via a bus interface, calls the program in the memory 85, and performs the network equipment operations shown in the above method embodiments.

[0256] The network side equipment may further include a network interface 86, which may be, for example, a common public radio interface (CPRI).

[0257] Specifically, the network side device 800 of the embodiment of the present disclosure further includes instructions or programs stored in the memory 85 and capable of running on the processor 84, and the processor 84 can call the instructions or programs in the memory 85 to execute the method performed by each module shown in FIG. 4 or FIG. 5, and achieve the same technical effect, which will not be described further here in order to avoid repetition of description.

[0258] Specifically, an embodiment of the present disclosure further provides another network side device. As shown in Fig. 9, the network side device 900 includes a processor 901, a network interface 902 and a memory 903. Here, the network interface 902 is, for example, a common public radio interface (CPRI).

[0259] Specifically, the network side device 900 of the embodiment of the present disclosure further includes instructions or programs stored in the memory 903 and capable of running on the processor 901, and the processor 901 can call the instructions or programs in the memory 903 to execute the method performed by each module shown in FIG. 4 or FIG. 5, and achieve the same technical effect, which will not be described further here in order to avoid repetition of description.

[0260] An embodiment of the present disclosure further provides a readable storage medium, in which a program or instruction is stored, which, when executed by a processor, can realize each process of the embodiment of the method described in FIG. 2 or FIG. 3 above, and achieve the same technical effect, which will not be described further here in order to avoid repetition.

[0261] Wherein, the processor is the processor in the terminal according to the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read only memory ROM, a random access memory RAM, a magnetic disk, or an optical disk.

[0262] An embodiment of the present disclosure further provides a chip, the chip including a processor and a communication interface, the communication interface is coupled to the processor, the processor is used to run a program or instruction to realize each process of the embodiment of the method described in the above FIG. 2 or FIG. 3, and can achieve the same technical effect, and will not be described further here to avoid repetition of description.

[0263] It should be understood that the chips referred to in the embodiments of the present disclosure may be referred to as system level chips, system chips, chip systems, or systems on chips.

[0264] An embodiment of the present disclosure further provides a computer program product, the computer program product being stored in a non-transitory storage medium, and the computer program product being executed by at least one processor to realize each process of the embodiment of the method described in FIG. 2 or FIG. 3 above, and to achieve the same technical effect, which will not be described further here in order to avoid repetition of description.

[0265] An embodiment of the present disclosure further provides a communication system including a terminal and a network side equipment, wherein the terminal may be used to perform steps of the method described in the above FIG. 2, and the network side equipment may be used to perform steps of the method described in the above FIG. 3, or the terminal may be used to perform steps of the method described in the above FIG. 3, and the network side equipment may be used to perform steps of the method described in the above FIG. 2.

[0266] It should be explained that in this specification, the terms "comprise", "include", or any other variants thereof are intended to cover the non-exclusive "comprise", whereby a process, method, article, or apparatus that includes a set of elements includes not only those elements, but also other elements not specifically listed or inherent to such process, method, article, or apparatus. Absent any further limitations, an element limited by the phrase "comprises a" does not preclude the presence of other identical elements in the process, method, article, or apparatus that includes the element. It should be noted that the scope of the methods and apparatuses in the embodiments of the present disclosure is not limited to performing functions in the order shown or discussed, but may include performing functions in an essentially simultaneous manner or in reverse order based on the functions involved, for example, the described methods can be performed in a different order than described, and various steps can be added, omitted, or combined. Also, features described with reference to some examples can be combined in other examples.

[0267] From the above description of the embodiments, it is clear to those skilled in the art that the methods of the above embodiments can be realized in the form of software and a necessary general-purpose hardware platform. Of course, they may also be realized in hardware, but in many cases the former is a more preferred embodiment. In light of this understanding, the technical solution of the present disclosure, in substance or in part contributing to the related art, may be embodied in the form of a computer software product, which is stored in a storage medium (e.g., ROM / RAM, magnetic disk, optical disk) and includes some instructions for causing a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the embodiments of the present disclosure.

[0268] The above describes the embodiments of the present disclosure in conjunction with the drawings, but the present disclosure is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not limiting. Those skilled in the art can take the teachings of the present disclosure and make many forms without departing from the spirit and scope of the present disclosure, all of which are within the scope of protection of the present disclosure.

Claims

1. 1. A communication method comprising: A second end receives first instruction information for instructing a processing manner at a reference point of a target object; and the second end processing the target object at the reference point according to the processing scheme.

2. The reference point is Predefined and Contract by protocol, and second indication information for indicating the reference point transmitted by a third end.

3. The processing method includes: A processing method based on an artificial intelligence (AI) model; and a processing strategy determined by a target edge including the second edge.

4. The processing method based on the AI ​​model is as follows: A model connection relationship of the AI ​​model; A startup method of the AI ​​model; and associated information of a processing domain corresponding to the AI ​​model, including the reference point.

5. The model connection relationship of the AI ​​model is as follows: A processing order of the AI ​​model; and and an input / output relationship between the AI ​​models.

6. The second end processes the target object at the reference point according to the processing scheme, When the model connection relationship of the AI ​​model includes a processing order of the AI ​​model, the second end determines a first applied AI model according to the processing order of the AI ​​model, and launches the first applied AI model according to the processing order of the AI ​​model to process the target object; The method of claim 5, further comprising at least one of: when the model connection relationship of the AI ​​models includes an input-output relationship between the AI ​​models, the second end determines a second applied AI model according to the input-output relationship between the AI ​​models; and processing the target object by the second applied AI model.

7. The first instruction information includes first target information for instructing a model connection relationship of the AI ​​model, and the first target information includes: a model identifier for indicating an AI model to be used by a target end including the second end; and a model connection identifier for indicating connection relationships between different AI models.

8. the first target information includes model configuration information including the model identifier; 8. The method of claim 7, wherein the model configuration information is further used to configure an input of an AI model to reference a first object, the first object including at least one of a predefined reference point and an output of another AI model.

9. The startup method of the AI ​​model is as follows: Starting up based on a preset start-up time; Triggering upon arrival of data of at least one reference point corresponding to the AI ​​model; Activating when at least one reference point data among at least one reference point data corresponding to the AI ​​model is updated; Triggering said AI model when all required inputs have arrived; Triggering at least one pre-configured AI model when the model completes processing; Triggering when an output of at least one pre-defined AI model is updated; Activating the AI ​​model when it receives an input from a previous AI model; and activating the AI ​​model when the AI ​​model receives a preset output value of another AI model.

10. The method of claim 9 , wherein the number of AI models that are activated is at least one.

11. The number of the processing domains is at least one, and the processing domain includes: The function of the reference point; A relationship between the input and output of the AI ​​model and the reference point; and model connection relationships between the AI ​​models.

12. The relevant information of the processing domain is: A processing time constraint corresponding to the processing domain; and and a processing scheme corresponding to the processing domain.

13. The method of claim 12, wherein the processing time constraint corresponding to the processing domain or the processing method corresponding to the processing domain includes at least one of a startup method of the AI ​​model, a startup time of the AI ​​model, a termination time of the AI ​​model, and a processing time length of the AI ​​model.

14. The method of claim 12 , wherein different said processing domains correspond to respective said processing time constraints.

15. The method of claim 12 , wherein different said processing domains correspond to respective said processing schemes.

16. The method comprises: the second end sending a first service request to a fourth end to request a first function; receiving, by the second end, description information of a first capability transmitted by the fourth end; The second end further includes processing the target object based on the description information of the first function; The method of claim 1, wherein the descriptive information of the first function includes at least one of the reference point corresponding to the first end, the processing method, the relationship between the reference point and the processing method, associated information of the processing domain, AI model information, a model connection relationship of the AI ​​model, and an activation method of the AI ​​model.

17. The second end processes the target object based on the description information of the first function, When the description information of the first function includes the reference point corresponding to the first end, the second end processes the target object at the reference point; When the description information of the first function includes a relationship between the reference point and the processing manner, the second end processes the target object according to a processing manner corresponding to the reference point; When the description information of the first function includes related information of the processing domain, obtaining a target reference point where the second end is included in the processing domain, and processing the target object at the target reference point; When the description information of the first function includes the processing method, the second end processes the target object according to the processing method; When the description information of the first function includes the AI ​​model information, the second end determines a target AI model according to the AI ​​model information, and processes the target object according to the target AI model; When the description information of the first function includes a model connection relationship of the AI ​​model, the second end determines a target AI model according to the connection relationship of the AI ​​model, and processes the target object according to the target AI model; The method of claim 16, further comprising at least one of: when the description information of the first function includes an activation manner of the AI ​​model, the second end determines a target AI model based on the activation manner of the AI ​​model; and invoking the target AI model according to the activation manner of the AI ​​model to process the target object.

18. The method comprises:

17. The method of claim 16, further comprising the second end receiving updated first capability description information sent by at least one of the first end and the fourth end.

19. The method comprises: the second end sending a second service request to a fifth end to request the first scheme; The second end receives description information of a first scheme transmitted by the fifth end; The second end further includes processing the target object based on the description information of the first type; The method of claim 1, wherein the descriptive information of the first method includes at least one of the reference point corresponding to the first method, the processing method, the relationship between the reference point and the processing method, associated information of the processing domain, AI model information, a model connection relationship of the AI ​​model, and an activation method of the AI ​​model.

20. The method comprises:

20. The method of claim 19, further comprising the second end receiving updated first scheme description information sent by at least one of the first end and the fifth end.

21. The method of claim 1 , wherein the first instruction information is further used to indicate at least one of a test methodology and a test requirement for the reference point.

22. The method comprises:

22. The method of claim 21, further comprising the second end testing the reference points based on at least one of the test strategy and test requirements.

23. 1. A communication method comprising: A communication method comprising a first end interacting with at least one second end first instruction information corresponding to a reference point, the first instruction information being used to instruct a processing method of a target object at the reference point.

24. The reference point is Predefined and Contract by protocol, and second indication information for indicating the reference point transmitted by a third end.

25. The processing method includes: A processing method based on an artificial intelligence (AI) model; and a processing strategy determined by a target edge being the first edge or the second edge.

26. The processing method based on the AI ​​model is as follows: A model connection relationship of the AI ​​model; A startup method of the AI ​​model; and associated information of a processing domain corresponding to the AI ​​model, including the reference point.

27. The method comprises: The method further includes the first end sending a first request to a fourth end to request registration of a first function; The method according to claim 23, wherein the descriptive information of the first function includes at least one of the reference point corresponding to the first function, the processing method, the relationship between the reference point and the processing method, a processing domain, AI model information, a model connection relationship of the AI ​​model, and an activation method of the AI ​​model.

28. The method comprises: When the second end requests a first function from the fourth end, the first end processes a first target object based on the description information of the first function, or the first end interacts with a sixth end with third instruction information, the third instruction information being used to instruct the sixth end to process a second target object based on the description information of the first function, and the sixth end is an entity having an associated relationship with the first end; The method according to claim 23, wherein the descriptive information of the first function includes at least one of the reference point corresponding to the first function, the processing method, the relationship between the reference point and the processing method, associated information of a processing domain, AI model information, a model connection relationship of an AI model, and an activation method of an AI model.

29. The first end processes a first target object based on the description information of the first function, When the description information of the first function includes the reference point corresponding to the first end, the first end processes the first target object at the reference point; When the description information of the first function includes a relationship between the reference point and the processing manner, the first end processes the first target object according to a processing manner corresponding to the reference point; When the description information of the first function includes the processing domain, obtaining a reference point where the first end is included in the processing domain, and processing the first target object at the reference point; When the description information of the first function includes the processing method, the first end processes the first target object according to the processing method; When the description information of the first function includes the AI ​​model information, the first end determines a target AI model according to the AI ​​model information, and processes the first target object according to the target AI model; When the description information of the first function includes a model connection relationship of the AI ​​model, the first end determines a target AI model according to the connection relationship of the AI ​​model, and processes the first target object according to the target AI model; The method of claim 28, further comprising at least one of: when the description information of the first function includes an activation method of the AI ​​model, the first end determines a target AI model based on the activation method of the AI ​​model; and invoking the target AI model according to the activation method of the AI ​​model to process the first target object.

30. The method comprises:

30. The method of claim 27, further comprising, when the descriptive information of the first function is updated, the first end sending updated descriptive information of the first function to at least one of the fourth end and the second end.

31. The method comprises: The method further includes the first end sending a second request to a fifth end to request registration of the first method; Here, the descriptive information of the first method includes at least one of the reference point corresponding to the first method, the processing method, the relationship between the reference point and the processing method, processing domain association information, AI model information, a model connection relationship of an AI model, and an activation method of an AI model.

32. The method comprises: When the second end requests the first method from the fifth end, the first end further processes a third target object based on a target method, which is a method for processing a fourth target object according to description information of the first method; Here, the descriptive information of the first method includes at least one of the reference point corresponding to the first method, the processing method, the relationship between the reference point and the processing method, processing domain association information, AI model information, a model connection relationship of an AI model, and an activation method of an AI model.

33. The method comprises:

33. The method of claim 31 or 32, further comprising, when the descriptive information of the first method is updated, the first end sending the updated descriptive information of the first method to at least one of the fifth end and the second end.

34. 24. The method of claim 23, wherein the first instructional information is further used to indicate at least one of a test strategy and a test requirement for the reference point.

35. The method comprises:

35. The method of claim 34, further comprising the first end testing the reference points based on at least one of the test strategy and test requirements.

36. A communication device, comprising: a receiving module for receiving first instruction information for instructing a processing method at a reference point of a target object; a processing module for processing the target object at the reference point according to the processing scheme.

37. A communication device, comprising: A communication device comprising: a transmitting module for interacting with at least one second end first instruction information corresponding to a reference point, the first instruction information being used to instruct a processing method at the reference point of a target object.

38. A communications device comprising a processor and a memory, the memory storing a program or instructions operable to run on the processor, the program or instructions, when executed by the processor, implementing the steps of a communications method as claimed in any one of claims 1 to 22, or implementing the steps of a communications method as claimed in any one of claims 23 to 35.

39. A readable storage medium storing a program or instructions, which, when executed by a processor, implements the steps of the communication method according to any one of claims 1 to 22 or implements the steps of the communication method according to any one of claims 23 to 35.

Images