Communication method, related device and system

Abstract

A communication method, a related device and a system, which can achieve establishment of a communication connection of a communication management service on the basis of first configuration information sent by an artificial intelligence (AI) training unit. Subsequently, the communication connection can be used for transmitting service data of the communication management service, such that management of a wireless access communication service is achieved by means of the communication management service, so as to improve the quality of service (QoS) of the wireless access communication service. In the method, the AI training unit determines first configuration information, wherein the first configuration information is used for configuring a communication connection for data transmission, the data transmission is transmission of service data of a communication management service performed between the AI training unit and an AI inference unit, the communication management service is used for managing a wireless access communication service between a terminal device and a wireless access device, and the first configuration information comprises an identifier of the communication connection and identifiers of one or more QoS flows in the communication connection; and the AI training unit sends the first configuration information.

Description

A communication method, related equipment and system

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office on October 26, 2023, with application number 202311405682.X and invention name “A communication method, related equipment and system”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of communication technology, and in particular to a communication method, related equipment and system. Background Art

[0003] Wireless communication can be a transmission communication between two or more communication nodes without propagating through conductors or cables. The communication nodes generally include terminal devices and wireless access devices.

[0004] Currently, in wireless communication systems, wireless access devices can calculate and determine signal transmission resources. For example, these transmission resources may include time domain resources and frequency domain resources used to carry signals. Accordingly, terminal devices can transmit and receive signals using these transmission resources. In this way, the wireless access device can provide network access wireless communication services for at least one terminal device.

[0005] With the advancement of communication technology, the concept of communication management services has emerged in wireless communication systems, used to manage wireless access communication services. However, currently available literature lacks information on how to establish communication connections for these services. Therefore, establishing communication connections for these services in wireless communication systems remains a pressing technical challenge.

[0006] Summary of the Invention

[0007] The present application provides a communication method, related equipment and system, which can realize the establishment and / or parameter configuration of a communication connection of a communication management service based on the first configuration information sent by an artificial intelligence (AI) training unit. The communication connection can subsequently be used to realize the transmission of service data of the communication management service, and then realize the management of the wireless access communication service through the communication management service to improve the service quality of the wireless access communication service.

[0008] The first aspect of the present application provides a communication method, which is performed by an artificial intelligence (AI) training unit. The AI ​​training unit can be a communication device, or the AI ​​training unit can be a partial component of the communication device (such as a processor, chip or chip system, etc.), or the AI ​​training unit can be a logic module or software that implements all or part of the functions of the communication device. In the first aspect and its possible implementation, the method is described as being performed by an AI training unit. In the method, the AI ​​training unit determines first configuration information, and the first configuration information is used to configure a communication connection for data transmission. The data transmission is the transmission of business data of a communication management service between the AI ​​training unit and the AI ​​reasoning unit. The communication management service is used to manage the wireless access communication service between the terminal device and the wireless access device; the first configuration information includes an identifier of the communication connection, and an identifier of one or more quality of service flows (QoS flows) in the communication connection; the AI ​​training unit sends the first configuration information.

[0009] Based on the above technical solution, the communication management service is used to manage the wireless access communication service between the terminal device and the wireless access device. Among them, the first configuration information sent by the AI ​​training unit is used to configure the communication connection for data transmission, and the data transmission is the transmission of business data of the communication management service between the AI ​​training unit and the AI ​​reasoning unit. In other words, after the AI ​​reasoning unit receives the first configuration information, the AI ​​reasoning unit can transmit the business data of the communication management service based on the first configuration information. Thus, the first configuration information sent by the AI ​​training unit can realize the establishment of the communication connection of the communication management service, and subsequently the communication connection can be used to realize the transmission of business data of the communication management service, and then realize the management of the wireless access communication service through the communication management service to improve the service quality of the wireless access communication service.

[0010] It should be understood that the AI ​​training unit may be a functional entity responsible for the training of the AI ​​model. Alternatively, the AI ​​training unit may also be a functional entity responsible for the control and management of the communication management service, and the functions of the functional entity include but are not limited to the training of the AI ​​model, AI model deployment, management of AI connections, and quality of service (QoS) management of service transmission in the communication management service. Accordingly, the AI ​​training unit may have other names, such as AI management unit, AI connection management unit, AI model training unit, etc. Exemplarily, the AI ​​training unit may be a wireless access device or a module involved in AI processing in the wireless access device (such as a software module, hardware module, chip, etc.), or the AI ​​training unit may be a module external to the wireless access device.

[0011] Optionally, the AI ​​training unit may not be responsible for other functions in the control and management of the communication management service, except for the training of the AI ​​model. For example, these other functions may include the management of AI connections, QoS management of service transmission in the communication management service, etc. Accordingly, these other functions may be implemented by other devices / other units, such as the AI ​​management unit.

[0012] It should be understood that the AI ​​reasoning unit can be a functional entity for business processing based on the AI ​​model, including functions of the functional entity including but not limited to reasoning of AI models, processing of AI business data, etc. Accordingly, the AI ​​reasoning unit can have other names, such as AI model reasoning unit, AI data processing unit, etc. Exemplarily, the AI ​​reasoning unit can be a communication device in a wireless access communication service or a module of a communication device (such as a software module, hardware module, chip, etc.). The communication device can be a terminal device or a wireless access device, and the wireless access device can include a wireless access network device, a centralized unit (CU) or a distributed unit (DU), etc.

[0013] It should be understood that the communication management service is used to manage the wireless access communication service. It can be understood that the communication management service is used to manage the communication parameters involved in the wireless access communication service in an intelligent manner (including at least one of configuration, update, and optimization). The intelligent manner may include a manner enabled by technologies such as AI, neural networks, and machine learning. Optionally, the terms AI, intelligence, neural networks, and machine learning in this application can be used interchangeably.

[0014] In other words, the communication management service can be a service that improves the service quality of wireless access communication services in an intelligent manner, or a service that intelligently manages the service quality of wireless access communications. Accordingly, the communication management service can also be replaced by a communication configuration service, a communication optimization service, etc.

[0015] For example, the communication parameters involved in the wireless access communication service may include channel state information (CSI). Accordingly, the communication management service may include intelligent management of CSI, which is also called AI-enabled CSI feedback service or AI model-based CSI feedback service.

[0016] For example, the communication parameters involved in the wireless access communication service may include communication beams. Accordingly, the communication management service may include intelligent management of communication beams, which is also called AI-enabled beam management service or AI model-based beam management service.

[0017] Optionally, the service data of the communication management service includes an AI model corresponding to at least one of the aforementioned services to implement management of communication parameters corresponding to the at least one of the aforementioned services. For example, the AI ​​model included in the service data of the communication management service may include an AI model for an AI-based CSI feedback service to implement intelligent management of CSI through the AI ​​model; for another example, the AI ​​model included in the service data of the communication management service may include an AI model for an AI-based beam management service to implement intelligent management of communication beams through the AI ​​model.

[0018] For example, the communication parameters involved in the wireless access communication service may include positioning information. Accordingly, the communication management service may include intelligent management of positioning information, which is also called an AI-enabled location positioning service or an AI model-based location positioning service.

[0019] Optionally, the service data involved in the data transmission of the communication management service may include at least one of the AI ​​model information and the data required for AI model training. The AI ​​model information may include at least one of the parameter scale information of the AI ​​model, the structural information of the AI ​​model, and the intermediate results of the AI ​​model training (such as training hyperparameters). The AI ​​model can be used to calculate the communication parameters involved in the wireless access communication service (including at least one of CSI, communication beam, and positioning information) in an AI manner to obtain a calculation result, which can be used for the management of the wireless access communication service (including at least one of configuration, update, and optimization).

[0020] Further optionally, the AI ​​model can be replaced by a neural network model, a machine learning model, a deep learning model, an AI learning model, a machine learning model, a neural network, an AI algorithm, an AI algorithm model, etc.

[0021] It should be understood that the first configuration information includes the identifiers of one or more QoS flows in the communication connection. That is, the one or more QoS flows belong to the communication connection. Among them, the one or more QoS flows can be default QoS flows, and the configuration information of the one or more QoS flows can be included in the first configuration information, or the configuration information of the one or more QoS flows can be pre-configured, or the configuration information of the one or more QoS flows can be sent to the AI ​​reasoning unit through other configuration information by the AI ​​training unit, which is not limited here.

[0022] Optionally, in the configuration information of a QoS flow (such as one or more QoS flows mentioned above, or the N QoS flows appearing later, etc.), the configuration information of the QoS flow includes at least one of the following: the priority of the data transmission of the QoS flow, the data scale of the data transmission of the QoS flow, the packet loss rate requirement of the data transmission of the QoS flow, or the delay requirement of the data transmission of the QoS flow.

[0023] Optionally, the first configuration information also includes an identifier of the AI ​​training unit, so that the recipient of the first configuration information can clearly identify that the first configuration information comes from the AI ​​training unit based on the identifier.

[0024] In a possible implementation manner of the first aspect, the method further includes: the AI ​​training unit receiving first request information, where the first request information is used to request the first configuration information.

[0025] Based on the above technical solution, the AI ​​training unit can also receive first request information for requesting first configuration information, so that the AI ​​training unit triggers determination or sending of the first configuration information based on the request, so that the solution can be applicable to scenarios where other devices (such as AI inference units) request first configuration information.

[0026] Optionally, the first request information includes at least one of the following: an identifier of the AI ​​application scenario supported by the AI ​​reasoning unit, an identifier of the requested AI service type, a model identifier corresponding to the requested AI model, and an identifier of the AI ​​reasoning unit.

[0027] Optionally, the AI ​​scenario supported by the AI ​​reasoning unit satisfies any of the following:

[0028] The AI ​​inference unit is a DU or a module in the DU. The AI ​​scenarios supported by the AI ​​inference unit include at least one of a single user medium access control (SU MAC) dictionary, a multi-user (MU) pairing dictionary, a multi-cell coordinated scheduling dictionary, and a low-speed channel map.

[0029] The AI ​​inference unit is a terminal device or a module in the terminal device. The AI ​​scenarios supported by the AI ​​inference unit include at least one of interference spectrum, beam spectrum, and smart channel state information (CSI);

[0030] The AI ​​reasoning unit is a CU or a module in the CU. The AI ​​scenarios supported by the AI ​​reasoning unit include at least one of smart grid, smart load balancing, and smart energy saving.

[0031] In a possible implementation of the first aspect, the AI ​​training unit determines the first configuration information, including: the AI ​​training unit determines the first configuration information based on at least one of the following items, including: an identifier of the AI ​​application scenario corresponding to the business data, and an identifier of the AI ​​service type corresponding to the communication management business.

[0032] Optionally, in addition to at least one of the above items, the basis for the AI ​​training unit to determine the first configuration information may also include a model identifier of the AI ​​model corresponding to the AI ​​model information contained in the business data.

[0033] Based on the above technical solution, the basis for the AI ​​training unit to determine the first configuration information may include at least one of the above items to improve the flexibility of the solution implementation.

[0034] In a possible implementation of the first aspect, after the AI ​​training unit sends the first configuration information, the method further includes: the AI ​​training unit sends second configuration information, the second configuration information including configuration information of N QoS flows established in the communication connection, where N is a positive integer; wherein the second configuration information includes at least one of the following: an identifier of the communication connection, N identifiers corresponding to the N QoS flows, QoS information of the N QoS flows, and an identifier of the AI ​​inference unit.

[0035] Based on the above technical solution, after the AI ​​training unit configures the communication connection between the AI ​​training unit and the AI ​​reasoning unit through the first configuration information, the AI ​​training unit can also send second configuration information including N QoS flows established in the communication connection, so that the recipient of the second configuration information can implement the configuration of the N QoS flows based on the second configuration information.

[0036] In addition, the N QoS flows may be different from one or more QoS flows in the first configuration information, so as to implement update or addition of QoS flows in the communication connection.

[0037] In a possible implementation of the first aspect, the method further includes: the AI ​​training unit receives second request information, where the second request information is used to request the second configuration information; wherein the second request information includes an identifier of the communication connection.

[0038] Based on the above technical solution, the AI ​​training unit can also receive second request information for requesting second configuration information, so that the AI ​​training unit triggers determination or sending of second configuration information based on the request, so that the solution can be applicable to scenarios where other devices (such as AI inference units) request second configuration information.

[0039] In a possible implementation manner of the first aspect, the method further includes: the AI ​​training unit sending first indication information, where the first indication information is used to indicate deletion of at least one QoS flow among the N QoS flows.

[0040] Based on the above technical solution, the AI ​​training unit can also send a first indication message, so that the recipient of the first indication message can delete at least one of the N QoS flows based on the indication of the first indication message to release the resources of the at least one QoS flow, avoid resource waste caused by no business transmission on the at least one QoS flow, or use the resources of the at least one QoS flow to transmit other high-priority services.

[0041] In the present application, deleting a QoS flow (for example, deleting at least one QoS flow among N QoS flows) can be replaced by releasing the QoS flow, or releasing the resources corresponding to the QoS flow, or terminating the resources corresponding to the QoS flow.

[0042] In a possible implementation manner of the first aspect, before the AI ​​training unit sends the first indication information, the method further includes: the AI ​​training unit receiving third request information, where the third request information is used to request deletion of the at least one QoS flow.

[0043] Based on the above technical solution, the AI ​​training unit can also receive a third request information for requesting the deletion of at least one QoS flow, so that the AI ​​training unit triggers the determination or sending of the first indication information based on the request, so that the solution can be applicable to scenarios where other devices (such as AI inference units) request the deletion of QoS flows.

[0044] In a possible implementation manner of the first aspect, the method further includes: the AI ​​training unit sending second indication information, where the second indication information is used to instruct to release the communication connection.

[0045] Based on the above technical solution, the AI ​​training unit can also send a second indication information so that the recipient of the second indication information can release the communication connection based on the indication of the second indication information to release the resources of the communication connection and avoid waste of resources caused by no business transmission on the communication connection, or the resources of the communication connection can be used to transmit other high-priority businesses.

[0046] It can be understood that the AI ​​training unit or AI reasoning unit releases the communication connection, which can be understood as the AI ​​training unit or AI reasoning unit deleting (or releasing) the QoS flow of the communication connection.

[0047] In a possible implementation manner of the first aspect, the method further includes: the AI ​​training unit receiving fourth request information, where the fourth request information is used to request to release the communication connection.

[0048] Based on the above technical solution, the AI ​​training unit can also receive a fourth request information for requesting the release of the communication connection, so that the AI ​​training unit triggers determination or sending of a second indication information based on the request, so that the solution can be applicable to scenarios where other devices (such as AI inference units) request the release of the communication connection.

[0049] The second aspect of the present application provides a communication method, which is performed by an AI reasoning unit. The AI ​​reasoning unit can be a communication device, or the AI ​​reasoning unit can be a partial component of the communication device (such as a processor, a chip or a chip system, etc.), or the AI ​​reasoning unit can be a logic module or software that implements all or part of the functions of the communication device. In the second aspect and its possible implementation, the method is described as being performed by an AI reasoning unit. In the method, the AI ​​reasoning unit receives first configuration information, and the first configuration information is used to configure a communication connection for data transmission. The data transmission is the transmission of business data of a communication management service between an AI training unit and an AI reasoning unit, and the communication management service is used to manage the wireless access communication service between a terminal device and a wireless access device; the first configuration information includes an identifier of the communication connection, and an identifier of one or more QoS flows in the communication connection; the AI ​​reasoning unit transmits the business data in the communication connection based on the first configuration information.

[0050] Based on the above technical solution, the communication management service is used to manage the wireless access communication service between the terminal device and the wireless access device. Among them, the first configuration information received by the AI ​​reasoning unit is used to configure the communication connection for data transmission, and the data transmission is the transmission of business data of the communication management service between the AI ​​training unit and the AI ​​reasoning unit. In other words, after the AI ​​reasoning unit receives the first configuration information, the AI ​​reasoning unit can transmit the business data of the communication management service based on the first configuration information. Thus, the first configuration information sent by the AI ​​training unit can realize the establishment of the communication connection of the communication management service, and subsequently the communication connection can be used to realize the transmission of business data of the communication management service, thereby realizing the management of the wireless access communication service through the communication management service to improve the service quality of the wireless access communication service.

[0051] Optionally, the first configuration information also includes at least one of the following: quality of service (QoS) information of one or more QoS flows in the communication connection, and an identifier of the AI ​​training unit.

[0052] In a possible implementation manner of the second aspect, the method further includes: the AI ​​reasoning unit sending first request information, where the first request information is used to request the first configuration information.

[0053] Based on the above technical solution, the AI ​​reasoning unit can also send a first request information for requesting the first configuration information, so that the AI ​​training unit triggers the determination or sending of the first configuration information based on the request, so that the solution can be applicable to the scenario where the AI ​​reasoning unit requests the first configuration information.

[0054] Optionally, the first request information includes at least one of the following: an identifier of the AI ​​application scenario supported by the AI ​​reasoning unit, an identifier of the requested AI service type, a model identifier corresponding to the requested AI model, and an identifier of the AI ​​reasoning unit.

[0055] Optionally, the AI ​​scenario supported by the AI ​​reasoning unit satisfies any of the following:

[0056] The AI ​​inference unit is a distributed unit DU or a module in the DU. The AI ​​scenarios supported by the AI ​​inference unit include at least one of a single-user medium access control SU MAC dictionary, a multi-user MU pairing dictionary, a multi-cell coordinated scheduling dictionary, and a low-speed channel map.

[0057] The AI ​​inference unit is a terminal device or a module in the terminal device. The AI ​​scenarios supported by the AI ​​inference unit include at least one of interference spectrum, beam spectrum, and smart channel state information CSI;

[0058] The AI ​​inference unit is a centralized unit CU or a module in the CU. The AI ​​scenarios supported by the AI ​​inference unit include at least one of smart grid, smart load balancing, and smart energy saving.

[0059] In a possible implementation of the second aspect, after the AI ​​reasoning unit receives the first configuration information, the method further includes: the AI ​​reasoning unit receives second configuration information, the second configuration information including configuration information of N QoS flows established in the communication connection, where N is a positive integer; wherein the second configuration information includes at least one of the following: an identifier of the communication connection, N identifiers corresponding to the N QoS flows, quality of service QoS information of the N QoS flows, and an identifier of the AI ​​reasoning unit.

[0060] Based on the above technical solution, after the AI ​​training unit configures the communication connection between the AI ​​training unit and the AI ​​reasoning unit through the first configuration information, the AI ​​reasoning unit can also receive second configuration information including N QoS flows established in the communication connection, so that the AI ​​reasoning unit can implement the configuration of the N QoS flows based on the second configuration information.

[0061] In addition, the N QoS flows may be different from one or more QoS flows in the first configuration information, so as to implement update or addition of QoS flows in the communication connection.

[0062] In a possible implementation of the second aspect, the method further includes: the AI ​​reasoning unit sends a second request message, where the second request message is used to request the second configuration information; wherein the second request message includes an identifier of the communication connection.

[0063] Based on the above technical solution, the AI ​​reasoning unit can also send a second request information for requesting the second configuration information, so that the AI ​​training unit triggers the determination or sending of the second configuration information based on the request, so that the solution can be applicable to the scenario where the AI ​​reasoning unit requests the second configuration information.

[0064] In a possible implementation manner of the second aspect, the method further includes: the AI ​​reasoning unit receiving first indication information, where the first indication information is used to indicate deletion of at least one QoS flow among the N QoS flows.

[0065] Based on the above technical solution, the AI ​​reasoning unit can also receive a first indication information, so that the AI ​​reasoning unit can delete at least one of the N QoS flows based on the indication of the first indication information to release the resources of the at least one QoS flow, avoid resource waste caused by no business transmission on the at least one QoS flow, or use the resources of the at least one QoS flow to transmit other high-priority businesses.

[0066] In a possible implementation manner of the second aspect, before the AI ​​reasoning unit receives the first indication information, the method further includes: the AI ​​reasoning unit sending third request information, where the third request information is used to request deletion of the at least one QoS flow.

[0067] Based on the above technical solution, the AI ​​reasoning unit can also send a third request information for requesting to delete the at least one QoS flow, so that the AI ​​training unit triggers determination or sends the first indication information based on the request, so that the solution can be applicable to the scenario where the AI ​​reasoning unit requests to delete the QoS flow.

[0068] In a possible implementation manner of the second aspect, the method further includes: the AI ​​reasoning unit receiving second indication information, where the second indication information is used to indicate the release of the communication connection.

[0069] Based on the above technical solution, the AI ​​reasoning unit can also receive a second indication information, so that the AI ​​reasoning unit can release the communication connection based on the indication of the second indication information to release the resources of the communication connection, avoid the waste of resources caused by no business transmission on the communication connection, or use the resources of the communication connection to transmit other high-priority businesses.

[0070] It can be understood that the AI ​​training unit or AI reasoning unit releases the communication connection, which can be understood as the AI ​​training unit or AI reasoning unit deleting (or releasing) the QoS flow of the communication connection.

[0071] In a possible implementation manner of the second aspect, the method further includes: the AI ​​reasoning unit sending fourth request information, where the fourth request information is used to request to release the communication connection.

[0072] Based on the above technical solution, the AI ​​reasoning unit can also send a fourth request information for requesting the release of the communication connection, so that the AI ​​training unit triggers determination or sends a second indication information based on the request, so that the solution can be applicable to the scenario where the AI ​​reasoning unit requests the release of the communication connection.

[0073] The third aspect of the present application provides a communication device (e.g., a first communication device), which can implement the method in the above-mentioned first aspect and any possible implementation thereof, that is, the device can be an AI training unit in the first aspect and any possible implementation thereof. The device includes a processing module and a transceiver module; the processing module is used to determine first configuration information, the first configuration information is used to configure a communication connection for data transmission, the data transmission is the transmission of business data of a communication management service between the AI ​​training unit and the AI ​​reasoning unit, and the communication management service is used to manage the wireless access communication service between the terminal device and the wireless access device; the first configuration information includes an identifier of the communication connection, and an identifier of one or more quality of service flows QoS flow in the communication connection; the transceiver module is used to send the first configuration information.

[0074] In a possible implementation manner of the third aspect, the transceiver module is further configured to receive first request information, where the first request information is used to request the first configuration information.

[0075] In a possible implementation of the third aspect, the first request information includes at least one of the following: an identifier of the AI ​​application scenario supported by the AI ​​reasoning unit, an identifier of the requested AI service type, a model identifier corresponding to the requested AI model, and an identifier of the AI ​​reasoning unit.

[0076] In a possible implementation of the third aspect, the AI ​​scenario supported by the AI ​​reasoning unit satisfies any of the following:

[0077] The AI ​​inference unit is a distributed unit DU or a module in the DU. The AI ​​scenarios supported by the AI ​​inference unit include at least one of a single-user medium access control SU MAC dictionary, a multi-user MU pairing dictionary, a multi-cell coordinated scheduling dictionary, and a low-speed channel map.

[0078] The AI ​​inference unit is a terminal device or a module in the terminal device. The AI ​​scenarios supported by the AI ​​inference unit include at least one of interference spectrum, beam spectrum, and smart channel state information CSI;

[0079] The AI ​​inference unit is a centralized unit CU or a module in the CU. The AI ​​scenarios supported by the AI ​​inference unit include at least one of smart grid, smart load balancing, and smart energy saving.

[0080] In a possible implementation of the third aspect, the first configuration information also includes at least one of the following: quality of service (QoS) information of one or more QoS flows in the communication connection, and an identifier of the AI ​​training unit.

[0081] In a possible implementation of the third aspect, the processing module is used to determine the first configuration information, including: the processing module is specifically used to determine the first configuration information based on at least one of the following items, including: an identifier of the AI ​​application scenario corresponding to the business data, an identifier of the AI ​​service type corresponding to the communication management business, and a model identifier of the AI ​​model corresponding to the AI ​​model information contained in the business data.

[0082] In a possible implementation of the third aspect, the transceiver module is also used to send second configuration information, wherein the second configuration information includes configuration information of N QoS flows established in the communication connection, where N is a positive integer; wherein the second configuration information includes at least one of the following: an identifier of the communication connection, N identifiers corresponding to the N QoS flows, quality of service QoS information of the N QoS flows, and an identifier of the AI ​​inference unit.

[0083] In a possible implementation manner of the third aspect, the method further includes: the transceiver module is further used to receive second request information, and the second request information is used to request the second configuration information; wherein the second request information includes an identifier of the communication connection.

[0084] In a possible implementation manner of the third aspect, the method further includes: the transceiver module is further configured to send first indication information, where the first indication information is configured to indicate deletion of at least one QoS flow among the N QoS flows.

[0085] In a possible implementation manner of the third aspect, the transceiver module is further configured to receive third request information, where the third request information is used to request deletion of the at least one QoS flow.

[0086] In a possible implementation manner of the third aspect, the transceiver module is further configured to send second indication information, where the second indication information is used to instruct to release the communication connection.

[0087] In a possible implementation manner of the third aspect, the transceiver module is further configured to receive fourth request information, where the fourth request information is used to request to release the communication connection.

[0088] The fourth aspect of the present application provides a communication device (e.g., a second communication device), which can implement the method in the above-mentioned second aspect and any possible implementation thereof, that is, the device can be an AI reasoning unit in the second aspect and any possible implementation thereof. The device includes a processing module and a transceiver module; the transceiver module is used to receive first configuration information, and the first configuration information is used to configure a communication connection for data transmission, and the data transmission is the transmission of business data of a communication management service between an artificial intelligence AI training unit and an AI reasoning unit, and the communication management service is used to manage the wireless access communication service between a terminal device and a wireless access device; the first configuration information includes an identifier of the communication connection, and an identifier of one or more quality of service flows QoS flow in the communication connection; the processing module is used to transmit the business data in the communication connection based on the first configuration information.

[0089] In a possible implementation manner of the fourth aspect, the transceiver module is further used to send first request information, where the first request information is used to request the first configuration information.

[0090] In a possible implementation of the fourth aspect, the first request information includes at least one of the following: an identifier of the AI ​​application scenario supported by the AI ​​reasoning unit, an identifier of the requested AI service type, a model identifier corresponding to the requested AI model, and an identifier of the AI ​​reasoning unit.

[0091] In a possible implementation of the fourth aspect, the AI ​​scenario supported by the AI ​​reasoning unit satisfies any of the following:

[0092] The AI ​​inference unit is a distributed unit DU or a module in the DU. The AI ​​scenarios supported by the AI ​​inference unit include at least one of a single-user medium access control SU MAC dictionary, a multi-user MU pairing dictionary, a multi-cell coordinated scheduling dictionary, and a low-speed channel map.

[0093] The AI ​​inference unit is a terminal device or a module in the terminal device. The AI ​​scenarios supported by the AI ​​inference unit include at least one of interference spectrum, beam spectrum, and smart channel state information (CSI).

[0094] The AI ​​inference unit is a centralized unit CU or a module in the CU. The AI ​​scenarios supported by the AI ​​inference unit include at least one of smart grid, smart load balancing, and smart energy saving.

[0095] In a possible implementation of the fourth aspect, the first configuration information also includes at least one of the following: quality of service (QoS) information of one or more QoS flows in the communication connection, and an identifier of the AI ​​training unit.

[0096] In a possible implementation of the fourth aspect, the transceiver module is also used to receive second configuration information, the second configuration information including configuration information of N QoS flows established in the communication connection, where N is a positive integer; wherein the second configuration information includes at least one of the following: an identifier of the communication connection, N identifiers corresponding to the N QoS flows, quality of service QoS information of the N QoS flows, and an identifier of the AI ​​inference unit.

[0097] In a possible implementation manner of the fourth aspect, the transceiver module is further used to send second request information, where the second request information is used to request the second configuration information; wherein the second request information includes an identifier of the communication connection.

[0098] In a possible implementation manner of the fourth aspect, the transceiver module is further configured to receive first indication information, where the first indication information is used to instruct deletion of at least one QoS flow among the N QoS flows.

[0099] In a possible implementation manner of the fourth aspect, the transceiver module is further configured to send third request information, where the third request information is used to request deletion of the at least one QoS flow.

[0100] In a possible implementation manner of the fourth aspect, the transceiver module is further configured to receive second indication information, where the second indication information is used to instruct to release the communication connection.

[0101] In a possible implementation manner of the fourth aspect, the transceiver module is further configured to send fourth request information, where the fourth request information is used to request the release of the communication connection.

[0102] In a fifth aspect, the present application provides a communication device, comprising at least one processor, which is used to execute programs or instructions in a memory so that the device implements the method described in the first aspect or any possible implementation of the first aspect, or enables the device to implement the method described in the second aspect or any possible implementation of the second aspect.

[0103] In a sixth aspect, the present application provides a communication device comprising at least one logic circuit and an input / output interface; the logic circuit is used to execute the method described in the first aspect or any possible implementation of the first aspect, or to execute the method described in the second aspect or any possible implementation of the second aspect.

[0104] In a seventh aspect, the present application provides a computer-readable storage medium for storing one or more computer-executable instructions. When the computer-executable instructions are executed by a processor, the processor executes the method described in any possible implementation of any one of the first to second aspects above.

[0105] In an eighth aspect, the present application provides a computer program product. When a computer program in the computer program product is executed by a processor, the processor executes the method described in any possible implementation of any one of the first to second aspects above.

[0106] In a ninth aspect, the present application provides a chip system comprising at least one processor for supporting a communication device to implement functions involved in any possible implementation of any one of the first to second aspects.

[0107] In one possible design, the chip system may further include a memory for storing program instructions and data necessary for the communication device. The chip system may be composed of a chip or may include a chip and other discrete components. Optionally, the chip system may further include an interface circuit for providing program instructions and / or data to the at least one processor.

[0108] The tenth aspect of the present application provides a communication system, which includes the AI ​​training unit and AI reasoning unit in any of the above aspects and any of its implementation methods.

[0109] Optionally, the AI ​​reasoning unit is a terminal device, or the communication system also includes a terminal device.

[0110] Among them, the technical effects brought about by any design method in the third to tenth aspects can refer to the technical effects brought about by the different design methods in the above-mentioned first to second aspects, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0111] FIG1 is a schematic diagram of a communication system provided by the present application;

[0112] FIG2 is a schematic diagram of a PDU session involved in this application;

[0113] FIG3a is a schematic diagram of the network architecture provided by this application;

[0114] FIG3 b is another schematic diagram of the network architecture provided by this application;

[0115] FIG3c is another schematic diagram of the network architecture provided by this application;

[0116] Figure 3d is another schematic diagram of the network architecture provided by this application;

[0117] Figure 3e is another schematic diagram of the network architecture provided by this application;

[0118] FIG4 is a schematic diagram of a communication method provided by the present application;

[0119] FIG5 is another schematic diagram of the communication method provided by the present application;

[0120] FIG6 is another schematic diagram of the communication method provided by the present application;

[0121] FIG7 is another schematic diagram of the communication method provided by the present application;

[0122] FIG8 is another schematic diagram of the communication method provided by the present application;

[0123] FIG9 is another schematic diagram of the communication method provided by the present application;

[0124] FIG10 is another schematic diagram of the communication method provided by the present application;

[0125] FIG11 is a schematic diagram of a communication device provided by the present application;

[0126] FIG12 is another schematic diagram of a communication device provided by the present application;

[0127] FIG13 is another schematic diagram of the communication device provided by the present application;

[0128] FIG14 is another schematic diagram of a communication device provided by the present application;

[0129] FIG15 is another schematic diagram of the communication device provided in this application. DETAILED DESCRIPTION

[0130] First, some of the terms used in the embodiments of the present application are explained to facilitate understanding by those skilled in the art.

[0131] (1) Configuration and pre-configuration: In this application, configuration and pre-configuration will be used at the same time. Configuration refers to the network equipment such as base stations or servers sending some configuration parameter information or parameter values ​​to the terminal through messages or signaling, so that the terminal can determine the communication parameters or resources during transmission based on these values ​​or information. Pre-configuration is similar to configuration. It can be a way for network equipment such as base stations or servers to send parameter information or values ​​to the terminal through a communication link or carrier; it can also be a way to give the definition of corresponding parameters or parameter values ​​in the standard, or by setting the relevant parameters or values ​​in the terminal device in advance. This application does not limit this. Furthermore, these values ​​and parameters can be changed or updated.

[0132] (2) In this application, “used for indication” can include direct indication and indirect indication. When describing that a certain indication information is used to indicate A, it can be understood that the indication information carries A, directly indicates A, or indirectly indicates A.

[0133] In this application, the information indicated by the indication information is referred to as the information to be indicated. In the specific implementation process, there are many ways to indicate the information to be indicated. For example, it can be implemented by direct indication, such as by indicating the information to be indicated itself or the index of the information to be indicated. It can also be implemented by indirectly indicating other information, wherein there is an association between the other information and the information to be indicated. It is also possible to indicate only a part of the information to be indicated, while the other parts of the information to be indicated are known or agreed in advance. For example, the indication of specific information can also be achieved with the help of the arrangement order of each information agreed in advance (for example, stipulated in the protocol), thereby reducing the indication overhead to a certain extent.

[0134] The information to be indicated can be sent as a whole, or divided into multiple sub-information and sent separately, and the sending period and / or sending timing of these sub-information can be the same or different. The specific sending method is not limited in this application. Among them, the sending period and / or sending timing of these sub-information can be pre-defined, for example, pre-defined according to a protocol, or can be configured by the transmitting device by sending configuration information to the receiving device. Among them, the configuration information can, for example, but not limited to, include one or a combination of at least two of RRC signaling, medium access control (MAC) layer signaling and physical layer signaling. Among them, MAC layer signaling, for example, includes a medium access control control element (MAC CE); physical layer signaling, for example, includes downlink control information (DCI).

[0135] (3) The terms "system" and "network" in the embodiments of the present application can be used interchangeably. "At least one" means one or more, and "more" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, "at least one of A, B and C" includes A, B, C, AB, AC, BC or ABC. In addition, unless otherwise specified, the ordinal numbers such as "first" and "second" mentioned in the embodiments of the present application are used to distinguish multiple objects, and are not used to limit the order, timing, priority or importance of multiple objects.

[0136] (4) "Sending" and "receiving" in the embodiments of the present application indicate the direction of signal transmission. In the present application, when entity A sends information to entity B, it can be that A sends it directly to B, or that A sends it indirectly to B through other entities. Similarly, when entity B receives information from entity A, it can be that entity B directly receives the information sent by entity A, or that entity B indirectly receives the information sent by entity A through other entities. Entities A and B here can be RAN nodes or terminals, or modules inside RAN nodes or terminals. The sending and receiving of information can be information interaction between a RAN node and a terminal, for example, information interaction between a base station and a terminal; the sending and receiving of information can also be information interaction between two RAN nodes, for example, information interaction between a CU and a DU; the sending and receiving of information can also be information interaction between different modules inside a device, for example, information interaction between a terminal chip and other modules of the terminal, or information interaction between a base station chip and other modules in the base station. "Sending" can also be understood as the "output" of the chip interface, and "receiving" can also be understood as the "input" of the chip interface.

[0137] Please refer to FIG1 , which is a schematic diagram of the architecture of a communication system 1000 used in an embodiment of the present application. As shown in FIG1 , the communication system includes a radio access network (RAN) 100 and a core network 200 .

[0138] Optionally, the communication system 1000 may further include the Internet 300 .

[0139] In Figure 1 , RAN 100 includes at least one RAN node (e.g., 110a and 110b in Figure 1 , collectively referred to as 110) and may also include at least one terminal (e.g., 120a-120j in Figure 1 , collectively referred to as 120). RAN nodes may also be referred to as wireless access devices, network devices, access network devices, etc.

[0140] In Figure 1 , RAN 100 may also include other RAN nodes, such as wireless relay equipment and / or wireless backhaul equipment (not shown in Figure 1 ). Terminal 120 is wirelessly connected to RAN node 110, and RAN node 110 is wirelessly or wiredly connected to core network 200. The core network equipment in core network 200 and RAN node 110 in RAN 100 may be separate, distinct physical devices, or they may be a single physical device that integrates the logical functions of a core network device with the logical functions of a RAN node. Terminals and RAN nodes may be connected to each other via wired or wireless means.

[0141] RAN100 may be an evolved universal terrestrial radio access (E-UTRA) system, a new radio (NR) system, or a future radio access system defined in the 3rd Generation Partnership Project (3GPP). RAN100 may also include two or more of the aforementioned different radio access systems. RAN100 may also be an open RAN (O-RAN).

[0142] A RAN node, also known as a radio access network device, RAN entity, or access node, facilitates wireless access to a communication system by a terminal. In one application scenario, a RAN node can be a base station, an evolved NodeB (eNodeB), a transmission reception point (TRP), a next-generation NodeB (gNB) in a fifth-generation (5G) mobile communication system, a next-generation base station in a sixth-generation (6G) mobile communication system, or a base station in a future mobile communication system. A RAN node can be a macro base station (such as 110a in Figure 1), a micro base station, an indoor station (such as 110b in Figure 1), a relay node, or a donor node.

[0143] In another application scenario, multiple RAN nodes can collaborate to help terminals achieve wireless access, with different RAN nodes implementing portions of the base station's functions. For example, a RAN node can be a centralized unit (CU), a distributed unit (DU), or a radio unit (RU). The CU implements the base station's radio resource control protocol and packet data convergence protocol (PDCP) functions, and can also implement the service data adaptation protocol (SDAP) functions; the DU implements the base station's radio link control layer and MAC layer functions, and can also implement some or all of the physical layer functions. For detailed descriptions of each of the above protocol layers, please refer to the relevant technical specifications of 3GPP. The RU can be used to implement the transmission and reception of radio frequency signals. The CU and DU can be two independent RAN nodes, or they can be integrated into the same RAN node, such as in a baseband unit (BBU). The RU can be included in radio frequency equipment, such as a remote radio unit (RRU) or an active antenna unit (AAU). The CU can be further divided into two types of RAN nodes: CU-control plane and CU-user plane.

[0144] In different systems, RAN nodes may have different names. For example, in an open radio access network (open RAN, O-RAN or ORAN) system, CU may also be called O-CU (open CU), DU may also be called O-DU, CU-CP may also be called O-CU-CP, CU-UP may also be called O-CU-UP, and RU may also be called O-RU. For the convenience of description, this application uses CU, CU-CP, CU-UP, DU and RU as examples for description. Any unit of CU (or CU-CP, CU-UP), DU and RU in this application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0145] The communication between the access network device and the terminal device follows a certain protocol layer structure. The protocol layer may include a control plane protocol layer and a user plane protocol layer. The control plane protocol layer may include at least one of the following: a radio resource control (RRC) layer, a packet data convergence protocol (PDCP) layer, a radio link control (RLC) layer, a media access control (MAC) layer, or a physical (PHY) layer. The user plane protocol layer may include at least one of the following: a service data adaptation protocol (SDAP) layer, a PDCP layer, an RLC layer, a MAC layer, or a physical layer.

[0146] For the correspondence between network elements in the ORAN system and their achievable protocol layer functions, please refer to Table 1 below.

[0147] Table 1

[0148] The embodiments of the present application do not limit the specific technology and specific device form used by the RAN node. For ease of description, the following description uses a base station as an example of a RAN node.

[0149] A terminal is a device with wireless transceiver capabilities that can send signals to a base station or receive signals from a base station. A terminal may also be referred to as a terminal device, user equipment (UE), mobile station, mobile terminal, etc. Terminals can be widely used in various scenarios, such as device-to-device (D2D), vehicle-to-everything (V2X) communication, machine-type communication (MTC), Internet of Things (IoT), virtual reality, augmented reality, industrial control, autonomous driving, telemedicine, smart grid, smart furniture, smart office, smart wearable, smart transportation, smart city, etc. A terminal can be a mobile phone, tablet computer, computer with wireless transceiver capabilities, wearable device, vehicle, airplane, ship, robot, robotic arm, smart home device, etc. The embodiments of this application do not limit the specific technology and specific device form adopted by the terminal.

[0150] Base stations and terminals can be fixed or mobile. They can be deployed on land, indoors or outdoors, handheld or vehicle-mounted; on water; or on aircraft, balloons, and satellites. The embodiments of this application do not limit the application scenarios of base stations and terminals.

[0151] The roles of base stations and terminals can be relative. For example, the helicopter or drone 120i in Figure 1 can be configured as a mobile base station. To terminals 120j accessing the wireless access network 100 via 120i, terminal 120i is a base station. However, to base station 110a, 120i is a terminal, meaning that communication between 110a and 120i occurs via a wireless air interface protocol. Of course, communication between 110a and 120i can also occur via a base station-to-base station interface protocol. In this case, 120i is also a base station relative to 110a. Therefore, base stations and terminals can be collectively referred to as communication devices. 110a and 110b in Figure 1 can be referred to as communication devices with base station functionality, while 120a-120j in Figure 1 can be referred to as communication devices with terminal functionality.

[0152] Communication between base stations and terminals, between base stations, and between terminals can be carried out through authorized spectrum, unauthorized spectrum, or both; communication can be carried out through spectrum below 6 gigahertz (GHz), spectrum above 6 GHz, or spectrum below 6 GHz and spectrum above 6 GHz. The embodiments of the present application do not limit the spectrum resources used for wireless communication.

[0153] In this application, the functions of the base station can also be performed by a module in the base station (such as a chip), or by a control subsystem that includes the base station function. The control subsystem that includes the base station function here can be the control center in the above-mentioned application scenarios such as smart grid, industrial control, smart transportation, and smart city. The functions of the terminal can also be performed by a module in the terminal (such as a chip or modem), or by a device that includes the terminal function.

[0154] In wireless communication network systems, a data transmission guarantee mechanism based on packet data unit (PDU) sessions is defined for the transmission of users' common application service data (such as video, voice, game and other service data).

[0155] Figure 2 shows a schematic diagram of a PDU session implementation. The establishment of a PDU session relies on the participation of core network devices. Generally, a PDU session includes a radio bearer between a terminal device and an access network device, and a next-generation user plane (NG-U) tunnel between the access network device and the core network device. Optionally, if the access network device includes a DU and a CU, the PDU session also includes an F1 bearer between the DU and the CU.

[0156] Exemplarily, the session management function (SMF) network element in the core network device can control and manage the life cycle of the PDU session (including the creation, deletion, modification, etc. of the PDU session) based on the user's service type (the service type identifier is the data network name (DNN)) and its corresponding data transmission requirement policy (the policy is stored in the service transmission QoS policy, billing policy, etc. of the core network network element policy control function (PCF)), and configure the parameters of the PDU session based on the service QoS policy. In addition, during the establishment of the PDU session, the terminal device can initiate the establishment of the PDU session to the SMF network element based on the non-access stratum (NAS) message; thereafter, the SMF network element can execute the creation of the PDU session and determine the relevant configuration information, and at the same time guide the access network device to perform the corresponding PDU session establishment and configuration; accordingly, the access network device performs PDU Session related processing, including creating or modifying the radio bearer of the wireless air interface (such as the data radio bearer (DRB)).

[0157] Furthermore, in wireless communication systems, wireless access devices can calculate and determine signal transmission resources. For example, these transmission resources may include time-domain resources and frequency-domain resources used to carry signals. Accordingly, terminal devices can transmit and receive signals on these transmission resources. In this way, the wireless access device can provide network access wireless access communication services for the terminal device. However, improving data transmission performance in communication networks is a pressing technical issue.

[0158] In one possible implementation, communication management services implemented through intelligent technologies can intelligently manage (including optimizing, configuring, and updating) wireless access communication services to improve data transmission performance. These intelligent technologies may include artificial intelligence, neural network technology, and machine learning technology.

[0159] It should be understood that the communication management service is used to manage the wireless access communication service. It can be understood that the communication management service is used to manage the communication parameters involved in the wireless access communication service in an intelligent manner (including at least one of configuration, update, and optimization). The intelligent manner may include a manner enabled by technologies such as AI, neural networks, and machine learning. Optionally, the terms AI, intelligence, neural networks, and machine learning in this application can be used interchangeably.

[0160] In other words, the communication management service can be a service that improves the service quality of wireless access communication services in an intelligent manner, or a service that intelligently manages the service quality of wireless access communications. Accordingly, the communication management service can also be replaced by a communication configuration service, a communication optimization service, etc.

[0161] For example, the communication parameters involved in the wireless access communication service may include channel state information (CSI). Accordingly, the communication management service may include intelligent management of CSI, which is also called AI-enabled CSI feedback service or AI model-based CSI feedback service.

[0162] For example, the communication parameters involved in the wireless access communication service may include communication beams. Accordingly, the communication management service may include intelligent management of communication beams, which is also called AI-enabled beam management service or AI model-based beam management service.

[0163] Optionally, the service data of the communication management service includes an AI model corresponding to at least one of the aforementioned services to implement management of communication parameters corresponding to the at least one of the aforementioned services. For example, the AI ​​model included in the service data of the communication management service may include an AI model for an AI-based CSI feedback service to implement intelligent management of CSI through the AI ​​model; for another example, the AI ​​model included in the service data of the communication management service may include an AI model for an AI-based beam management service to implement intelligent management of communication beams through the AI ​​model.

[0164] For example, the communication parameters involved in the wireless access communication service may include positioning information. Accordingly, the communication management service may include intelligent management of positioning information, which is also called an AI-enabled location positioning service or an AI model-based location positioning service.

[0165] Typically, the service data associated with communication management services terminates at the terminal device and access network equipment to enable intelligent management of wireless access communication services, such as improving wireless access network performance or efficiency. Using traditional data transmission methods, this service data could be transmitted via PDU sessions. However, because the service data associated with communication management services terminates at the terminal device and access network equipment, the PDU sessions established by the core network equipment to transmit service data result in excessive signaling loops and waste of network communication resources.

[0166] To address the above technical issues, the present application provides a communication method, related devices, and systems that can establish a communication connection for a communication management service based on first configuration information sent by an AI training unit. This communication connection can then be used to transmit service data for the communication management service, thereby managing wireless access communication services through the communication management service to improve the service quality of the wireless access communication service. This will be described in detail below with reference to the accompanying drawings.

[0167] The following will provide an exemplary description of the network architecture used in the communication method provided in this application in conjunction with the examples shown in Figures 3a / 3b / 3c / 3d / 3e.

[0168] In the following example, the AI ​​training unit may be a functional entity responsible for the training of the AI ​​model. Alternatively, the AI ​​training unit may also be a functional entity responsible for the control and management of the communication management service, and the functions of the functional entity include but are not limited to the training of the AI ​​model, AI model deployment, management of AI connections, and quality of service (QoS) management of service transmission in the communication management service. Accordingly, the AI ​​training unit may have other names, such as AI management unit, AI connection management unit, AI model training unit, etc. Exemplarily, the AI ​​training unit may be a wireless access device or a module involved in AI processing in the wireless access device (such as a software module, hardware module, chip, etc.), or the AI ​​training unit may be a module external to the wireless access device.

[0169] Optionally, the AI ​​training unit may not be responsible for other functions in the control and management of the communication management service, except for the training of the AI ​​model. For example, the other functions may include the management of AI connections, QoS management of service transmission in the communication management service, etc. Accordingly, the other functions can be implemented by other devices / other units, such as the AI ​​management unit. For ease of understanding, the following example takes the AI ​​training unit as the functional entity responsible for the control and management of the communication management service as an example.

[0170] In the following example, the AI ​​reasoning unit may be a functional entity for business processing based on an AI model, including functions of the functional entity including but not limited to reasoning of AI models, processing of AI business data, etc. Accordingly, the AI ​​reasoning unit may have other names, such as an AI model reasoning unit, an AI data processing unit, etc. Exemplarily, the AI ​​reasoning unit may be a communication device in a wireless access communication service or a module of a communication device (such as a software module, a hardware module, a chip, etc.). The communication device may be a terminal device or a wireless access device, and the wireless access device may include a wireless access network device, a centralized unit (CU) or a distributed unit (DU), etc.

[0171] In the following example, the CU is responsible for functions such as interface control and mobility management of the terminal device, and the DU is responsible for functions such as access link management, wireless channel management, and resource mapping of the terminal device.

[0172] Optionally, in the examples shown in Figures 3a / 3b / 3c / 3d / 3e, the AI ​​training unit (or wireless access device, or CU, or DU) can be an ORAN network element (or a module in an ORAN network element), including but not limited to one or more of O-CU-CP, O-CU-UP, O-DU, and O-RU.

[0173] In Figure 3a, the wireless access device may include a CU and a DU, and the AI ​​training unit mentioned later may be a module in the wireless access device that is independent of the CU and the DU, wherein the AI ​​training unit may communicate with the CU via the G1 interface, and the AI ​​training unit may also communicate with the DU via the G2 interface. In addition, in the architecture shown in Figure 3a, the AI ​​training unit may be referred to as a mobile intelligent function (MIF) entity, an AI entity, a RAN AI entity, etc. The AI ​​training unit may be deployed independently as a new network element entity, or it may be deployed in combination with the CU, but it is independent of the CU in terms of logical function.

[0174] It should be understood that in Figure 3a, the CU, DU or terminal device can serve as an AI reasoning unit, that is, the AI ​​reasoning unit can be a CU, DU or terminal device, or the AI ​​reasoning unit can be a module in the CU, a module in the DU or a module in the terminal device.

[0175] In Figure 3b, the wireless access device may include a CU and a DU. The AI ​​training unit mentioned below may be a module independent of the wireless access device, wherein the AI ​​training unit may communicate with the wireless access device via an E2 interface. In addition, the architecture shown in Figure 3b may be applied to open RAN scenarios. For example, the AI ​​training unit may be a functional entity of a near-real-time rAN intelligent controller (Near-RT RIC) of a wireless access network, or the AI ​​training unit may be a platform function module of a Near-RT RIC.

[0176] It should be understood that in Figure 3b, the wireless access device, CU, DU or terminal device can serve as an AI reasoning unit, that is, the AI ​​reasoning unit can be a CU, DU or terminal device, or the AI ​​reasoning unit can be a module in the CU, a module in the DU or a module in the terminal device.

[0177] In Figure 3c, the wireless access device may include a CU and a DU. The AI ​​training unit mentioned later may be a module built into the CU, wherein the AI ​​training unit may communicate with the DU via the F1 interface. In other words, by enhancing the CU functionality, namely, adding an AI QoS management function module to support QoS management (including optimization / configuration / update) of service transmission for communication management services, and at the same time enhancing the F1 interface between the CU and DU, the interaction of transmission configuration information mentioned later is supported.

[0178] It should be understood that in Figure 3c, the DU or the terminal device can serve as the AI ​​reasoning unit, that is, the AI ​​reasoning unit can be the DU or the terminal device, or the AI ​​reasoning unit can be a module in the DU or a module in the terminal device.

[0179] Optionally, in the above FIG. 3a to FIG. 3c, a scenario in which the CU and DU are separated in the radio access network is taken as an example. However, in actual applications, the radio access network may also be implemented in other ways.

[0180] For example, in Figure 3d, compared to the architectures shown in Figures 3a and 3c, the wireless access device may not distinguish between scenarios where the CU and DU are separated, meaning the AI ​​training unit may be a logical module or physical module within the wireless access device. It should be understood that in Figure 3d, the terminal device may serve as the AI ​​inference unit, meaning the AI ​​inference unit may be the terminal device, or the AI ​​inference unit may be a module within the terminal device.

[0181] For another example, in Figure 3e, compared to the architecture shown in Figure 3b, the wireless access device may not distinguish between scenarios where the CU and DU are separated, i.e., the AI ​​training unit may be a logical module / physical module independent of the wireless access device. It should be understood that in Figure 3e, the wireless access device or the terminal device may serve as the AI ​​inference unit, i.e., the AI ​​inference unit may be the wireless access device or the terminal device, or the AI ​​inference unit may be a module in the wireless access device or a module in the terminal device.

[0182] It should be understood that the AI ​​reasoning unit mentioned later can be any one of the wireless access device, terminal device, CU or DU in the architecture shown in Figures 3a to 3e. The specific implementation process is detailed in the description of the embodiments below.

[0183] Please refer to FIG4 , which is a schematic diagram of the communication method provided in this application. The method includes the following steps.

[0184] It should be noted that FIG4 (and FIG8 to FIG10 later) uses the AI ​​training unit and the AI ​​reasoning unit as the execution subjects of the interaction diagram as an example to illustrate the method. The AI ​​training unit and the AI ​​reasoning unit can be the AI ​​training unit and the AI ​​reasoning unit in any of FIG3a to FIG3e. For example, the AI ​​training unit can be an internal module of the wireless access device, or a device / module independent of the wireless access device. For another example, the AI ​​reasoning unit can be a wireless access device, a CU, a DU or a terminal device, or a module in a wireless access device, a module in a CU, a module in a DU or a module in a terminal device.

[0185] It should be understood that in Figure 4 (and Figures 8 to 10 below), the AI ​​training unit can be a communication device, or the AI ​​training unit can be a component of a communication device (such as a processor, chip, or chip system, etc.), or the AI ​​training unit can be a logic module or software that implements all or part of the functions of the communication device. Similarly, the AI ​​reasoning unit can be a communication device, or the AI ​​reasoning unit can be a component of a communication device (such as a processor, chip, or chip system, etc.), or the AI ​​reasoning unit can be a logic module or software that implements all or part of the functions of the communication device.

[0186] Optionally, the AI ​​training unit (or wireless access device, or CU, or DU) that executes the method shown in Figure 4 (and Figures 8 to 10 below) can be an ORAN network element (or a module in an ORAN network element), including but not limited to one or more of O-CU-CP, O-CU-UP, O-DU, and O-RU.

[0187] S401. The AI ​​training unit sends first configuration information. The first configuration information is used to configure a communication connection for data transmission, wherein the data transmission is the transmission of service data of a communication management service between the AI ​​training unit and the AI ​​reasoning unit, and the communication management service is used to manage wireless access communication services between a terminal device and a wireless access device; the first configuration information includes an identifier of the communication connection and identifiers of one or more quality of service flows (QoS flows) in the communication connection.

[0188] S402. The AI ​​reasoning unit and the AI ​​training unit transmit the first configuration information based on the first configuration information to transmit business data in the communication connection.

[0189] Optionally, the service data involved in the data transmission of the communication management service may include at least one of the AI ​​model information and the data required for AI model training. The AI ​​model information may include at least one of the parameter scale information of the AI ​​model, the structural information of the AI ​​model, and the intermediate results of the AI ​​model training (such as training hyperparameters). The AI ​​model can be used to calculate the communication parameters involved in the wireless access communication service (including at least one of CSI, communication beam, and positioning information) in an AI manner to obtain a calculation result, which can be used for the management of the wireless access communication service (including at least one of configuration, update, and optimization).

[0190] Further optionally, the AI ​​model can be replaced by a neural network model, a machine learning model, a learning model, an AI learning model, a machine learning model, a neural network, an AI network, etc.

[0191] In one possible implementation, after the AI ​​training unit and the AI ​​reasoning unit establish a communication connection for the communication management service based on the first configuration information in step S401, in step S402, the AI ​​training unit and the AI ​​reasoning unit may perform data transmission of the service data of the communication management service in the communication connection. As an example, FIG5 shows an implementation example of the data format of this service data.

[0192] As shown in Figure 5, the service data may include a payload. Optionally, the service data may also include a common header for carrying relevant information of the payload, such as the size of the payload, the type of data carried by the payload, etc.

[0193] In addition, the encapsulation header corresponding to the service data can be used to carry the identifier of the communication connection and the identifier of the QoS flow.

[0194] Optionally, the service data may also be encapsulated through other headers of the transport layer, including but not limited to a layer 1 / layer 2 header (L1 / L2 header), an outer IP header (outer IP header), etc.

[0195] It should be understood that in step S401, the first configuration information sent by the AI ​​training unit includes the identifiers of one or more QoS flows in the communication connection. That is, the one or more QoS flows belong to the communication connection. Among them, the one or more QoS flows can be default QoS flows, and the configuration information of the one or more QoS flows can be included in the first configuration information, or the configuration information of the one or more QoS flows can be pre-configured, or the configuration information of the one or more QoS flows can be sent to the AI ​​reasoning unit through other configuration information by the AI ​​training unit, which is not limited here.

[0196] Optionally, in the configuration information of a QoS flow (such as one or more QoS flows mentioned above, or the N QoS flows appearing later, etc.), the configuration information of the QoS flow includes at least one of the following: the priority of the data transmission of the QoS flow, the data scale of the data transmission of the QoS flow, the packet loss rate requirement of the data transmission of the QoS flow, or the delay requirement of the data transmission of the QoS flow.

[0197] Optionally, the first configuration information also includes an identifier of the AI ​​training unit, so that the recipient of the first configuration information can clearly identify that the first configuration information comes from the AI ​​training unit based on the identifier.

[0198] In one possible implementation, in the method shown in FIG4 , before step S401, the method may further include: the AI ​​training unit receiving first request information, where the first request information is used to request the first configuration information. Specifically, the AI ​​training unit may also receive first request information for requesting the first configuration information, so that the AI ​​training unit triggers determination or transmission of the first configuration information based on the request, so that the solution can be applied to scenarios where other devices (e.g., AI inference units) request the first configuration information.

[0199] Optionally, the first request information includes at least one of the following information A to information D.

[0200] Information A. Identification of the AI ​​application scenarios supported by the AI ​​inference unit.

[0201] Information A is used to identify the wireless AI service feature scenarios supported by the AI ​​inference unit, such as the intelligent CSI feature. Based on this parameter and the capabilities of the AI ​​inference unit, the AI ​​training unit selects an AI model (such as a convolutional neural network (CNN), a recurrent neural network (RNN), or a deep neural network (DNN) with different layers) that can be used for the corresponding scenario.

[0202] Optionally, in information A, the AI ​​scenario supported by the AI ​​reasoning unit satisfies any of the following:

[0203] The AI ​​inference unit is a DU or a module in the DU. The AI ​​scenarios supported by the AI ​​inference unit include at least one of a single-user medium access control (SU) MAC dictionary, a multi-user (MU) pairing dictionary, a multi-cell coordinated scheduling dictionary, and a low-speed channel map.

[0204] The AI ​​inference unit is a terminal device or a module in the terminal device. The AI ​​scenarios supported by the AI ​​inference unit include at least one of interference spectrum, beam spectrum, and smart channel state information CSI;

[0205] The AI ​​reasoning unit is a CU or a module in the CU. The AI ​​scenarios supported by the AI ​​reasoning unit include at least one of smart grid, smart load balancing, and smart energy saving.

[0206] Information B. Identifier of the requested AI service type.

[0207] Among them, the information B is used to identify the transmission data type of the communication connection requested by the AI ​​inference unit, such as AI model, AI training data, AI training intermediate results, etc.

[0208] Information C. Model ID corresponding to the requested AI model.

[0209] Among them, the information C is an optional parameter. For example, when the AI ​​service type identifier requested by information B includes the identifier of the AI ​​model, information C can be used to request the model identifier corresponding to the AI ​​model, such as CNN model 1, CNN model 2, etc.

[0210] Information D. Identification of the AI ​​reasoning unit.

[0211] The information D is used to identify the AI ​​reasoning unit.

[0212] In an implementation example, taking the AI ​​reasoning unit as a terminal device or a module in a terminal device as an example, the information D can be a globally unique temporary identifier (GUTI), a radio network temporary identifier (RNTI), a temporary mobile subscriber identity (TMSI), or other identifiers that can identify the terminal device.

[0213] In another implementation example, taking the AI ​​inference unit as a DU or a module in a DU as an example, the information D may be the IP address of the DU, the DU name, etc.

[0214] In another implementation example, taking the AI ​​inference unit as a CU or a module in the CU as an example, the information D can be the IP address of the CU, the CU name, etc.

[0215] In one possible implementation, the AI ​​training unit determines the first configuration information, including: the AI ​​training unit determines the first configuration information based on at least one of the following items, including: an identifier of the AI ​​application scenario corresponding to the business data, and an identifier of the AI ​​service type corresponding to the communication management business.

[0216] Specifically, the basis for the AI ​​training unit to determine the first configuration information may include at least one of the above items to enhance the flexibility of the solution implementation.

[0217] Optionally, in addition to at least one of the above items, the basis for the AI ​​training unit to determine the first configuration information may also include a model identifier of the AI ​​model corresponding to the AI ​​model information contained in the business data.

[0218] Optionally, if the AI ​​reasoning unit is a terminal device or a module in the terminal device, if the terminal device is in an idle (IDLE) state, then before the AI ​​training unit sends the first configuration information in step S401, the AI ​​training unit can page the terminal device through the CU / DU, so that after the terminal device is restored to the network, it enters the connected state (Connected), so that the terminal device can receive the first configuration information when it is in the connected state. Exemplarily, the AI ​​training unit can page the terminal device through the G1 interface, G2 interface, E2 interface, etc. between the CU / DU. The implementation of these interfaces can refer to the description of Figures 3a to 3e above.

[0219] Based on the technical solution shown in Figure 4, the communication management service is used to manage the wireless access communication service between the terminal device and the wireless access device. Among them, the first configuration information sent by the AI ​​training unit in step S401 is used to configure the communication connection for data transmission, and the data transmission is the transmission of business data of the communication management service between the AI ​​training unit and the AI ​​reasoning unit. In other words, after the AI ​​reasoning unit receives the first configuration information, the AI ​​reasoning unit can transmit the business data of the communication management service based on the first configuration information. Thus, the first configuration information sent by the AI ​​training unit can realize the establishment of the communication connection of the communication management service, and subsequently the communication connection can be used to realize the transmission of business data of the communication management service, and then realize the management of the wireless access communication service through the communication management service to improve the service quality of the wireless access communication service.

[0220] In addition, since the service data involved in the communication management service is terminated in the terminal device and the access network device, the method of transmitting service data through the PDU session established by the core network device as shown in Figure 2 will cause too many signaling process detours and waste network communication resources. In the technical solution shown in Figure 4, the AI ​​training unit is a wireless access device or an external module of the wireless access device, and the AI ​​reasoning unit is a wireless access device or a terminal device. For this reason, the first configuration information sent by the AI ​​training unit can realize the transmission of service data of the communication management service, and the transmission of service data of the communication management service can be realized without the participation of the core network device, which can avoid excessive signaling process detours and save network communication resources.

[0221] In one possible implementation, in the technical solution shown in FIG4 , after the AI ​​training unit sends the first configuration information in step S401, the method further includes: the AI ​​training unit sends second configuration information, the second configuration information including the configuration information of the N QoS flows established in the communication connection, N being a positive integer; wherein the second configuration information includes at least one of the following: an identifier of the communication connection, N identifiers corresponding to the N QoS flows, QoS information of the N QoS flows, and an identifier of the AI ​​reasoning unit. Specifically, after the AI ​​training unit configures the communication connection between the AI ​​training unit and the AI ​​reasoning unit through the first configuration information, the AI ​​training unit may also send second configuration information including the N QoS flows established in the communication connection, so that the recipient of the second configuration information can implement the configuration of the N QoS flows based on the second configuration information.

[0222] In addition, the N QoS flows may be different from one or more QoS flows in the first configuration information, so as to implement update or addition of QoS flows in the communication connection.

[0223] Optionally, if the AI ​​reasoning unit is a terminal device or a module in the terminal device, if the terminal device is in an idle (IDLE) state, then before the AI ​​training unit sends the second configuration information, the AI ​​training unit can page the terminal device through the CU / DU, so that after the terminal device is restored to the network, it enters a connected state (Connected), so that the terminal device can receive the second configuration information when it is in a connected state. Exemplarily, the AI ​​training unit can page the terminal device through the G1 interface, G2 interface, E2 interface, etc. between the CU / DU. The implementation of these interfaces can refer to the description of Figures 3a to 3e above.

[0224] In one possible implementation, the method further includes: the AI ​​training unit receiving second request information, the second request information being used to request the second configuration information; wherein the second request information includes an identifier of the communication connection. Specifically, the AI ​​training unit may also receive second request information for requesting the second configuration information, so that the AI ​​training unit triggers determining or sending the second configuration information based on the request, making the solution applicable to scenarios where other devices (such as AI inference units) request the second configuration information.

[0225] In one possible implementation, the method further includes: the AI ​​training unit sends a first indication message, where the first indication message is used to indicate the deletion of at least one QoS flow among the N QoS flows. Specifically, the AI ​​training unit may also send a first indication message so that the recipient of the first indication message can delete at least one QoS flow among the N QoS flows based on the indication of the first indication message, so as to release the resources of the at least one QoS flow, avoid the waste of resources caused by no business transmission on the at least one QoS flow, or use the resources of the at least one QoS flow to transmit other high-priority businesses.

[0226] In the present application, deleting a QoS flow (for example, deleting at least one QoS flow among N QoS flows) can be replaced by releasing the QoS flow, or releasing resources corresponding to the QoS flow.

[0227] In one possible implementation, before the AI ​​training unit sends the first indication information, the method further includes: the AI ​​training unit receiving third request information, where the third request information is used to request deletion of the at least one QoS flow. Specifically, the AI ​​training unit may also receive third request information for requesting deletion of the at least one QoS flow, so that the AI ​​training unit triggers determination or sending of the first indication information based on the request, so that the solution can be applied to scenarios where other devices (such as AI inference units) request deletion of QoS flows.

[0228] In one possible implementation, the method further includes: the AI ​​training unit sending second indication information, where the second indication information is used to instruct the release of the communication connection. Specifically, the AI ​​training unit may further send the second indication information so that the recipient of the second indication information can release the communication connection based on the instruction of the second indication information, thereby releasing the resources of the communication connection and avoiding the waste of resources caused by no business transmission on the communication connection, or the resources of the communication connection can be used to transmit other high-priority businesses.

[0229] It can be understood that the AI ​​training unit or AI reasoning unit releases the communication connection, which can be understood as the AI ​​training unit or AI reasoning unit deleting (or releasing) the QoS flow of the communication connection.

[0230] In one possible implementation, the method further includes: the AI ​​training unit receiving fourth request information, where the fourth request information is used to request the release of the communication connection. Specifically, the AI ​​training unit may also receive fourth request information for requesting the release of the communication connection, so that the AI ​​training unit triggers determination or transmission of second indication information based on the request, so that the solution can be applied to scenarios where other devices (such as AI reasoning units) request the release of the communication connection.

[0231] As an application example, as shown in Figure 6, the AI ​​training unit may be the MIF entity shown in Figure 3a above. The MIF entity may communicate with the CU via the G1 interface, and the MIF entity may communicate with the DU via the G2 interface.

[0232] In an implementation example of the technical solution shown in Figure 4, if the AI ​​reasoning unit is a CU, the communication connection established between the AI ​​training unit and the AI ​​reasoning unit can be the AI ​​connection (AI Connection) between the CU and the MIF shown in the figure, and the figure takes the AI ​​connection as an example including two AI QoS flows.

[0233] In another implementation example of the technical solution shown in Figure 4, if the AI ​​reasoning unit is a DU, the communication connection established between the AI ​​training unit and the AI ​​reasoning unit can be the AI ​​Connection between the DU and the MIF shown in the figure, and the figure takes the AI ​​connection as an example including two AI QoS flows.

[0234] In another implementation example of the technical solution shown in Figure 4, if the AI ​​reasoning unit is a terminal device (denoted as UE in the figure), the communication connection established between the AI ​​training unit and the AI ​​reasoning unit can be the AI ​​Connection between the UE and the MIF shown in the figure, and the figure takes the AI ​​connection as an example including two AI QoS flows. It can be understood that the AI ​​Connection between the UE and the MIF includes two sections, one of which is the communication connection between the UE and the DU through the Uu interface, and the other end is the communication connection between the DU and the MIF through the G2 interface.

[0235] Optionally, in the AI ​​Connection between the UE and the MIF, the communication connection between the UE and the DU through the Uu interface may include a radio bearer (RB). The RB may be a data radio bearer (DRB) for transmitting service data of a wireless access communication service, or the RB may be a bearer other than the DRB. In the figure, the RB is illustrated as a computing radio bearer (CRB) other than the DRB.

[0236] As an application example, as shown in Figure 7, the AI ​​training unit may be the Near-RT RIC entity shown in Figure 3a above. The Near-RT RIC entity may communicate with the CU or DU via the E2 interface.

[0237] In an implementation example of the technical solution shown in Figure 4, if the AI ​​reasoning unit is a CU, the communication connection established between the AI ​​training unit and the AI ​​reasoning unit can be the AI ​​connection (AI Connection) between the CU and the Near-RT RIC shown in the figure, and the figure takes the AI ​​connection as an example including two AI QoS flows.

[0238] In another implementation example of the technical solution shown in Figure 4, if the AI ​​reasoning unit is a DU, the communication connection established between the AI ​​training unit and the AI ​​reasoning unit can be the AI ​​Connection between the DU and the Near-RT RIC shown in the figure, and the figure takes the AI ​​connection as an example including two AI QoS flows.

[0239] In another implementation example of the technical solution shown in Figure 4, if the AI ​​reasoning unit is a terminal device (denoted as UE in the figure), the communication connection established between the AI ​​training unit and the AI ​​reasoning unit can be the AI ​​Connection between the UE and the Near-RT RIC shown in the figure, and the figure takes the AI ​​connection as an example including two AI QoS flows. It can be understood that the AI ​​Connection between the UE and the Near-RT RIC includes two sections, one of which is the communication connection between the UE and the DU through the Uu interface, and the other is the communication connection between the DU and the Near-RT RIC through the E2 interface.

[0240] Optionally, in the AI ​​Connection between the UE and the Near-RT RIC, the communication connection implemented between the UE and the DU through the Uu interface may include a radio bearer (RB). The RB may be a data radio bearer (DRB) for transmitting service data of a wireless access communication service, or the RB may be a bearer other than the DRB. In the figure, the RB is illustrated as a computing radio bearer (CRB) other than the DRB.

[0241] In the technical solution shown in Figure 4, the AI ​​training unit can implement the configuration of the communication connection through the first configuration information, implement the configuration of the QoS flow through the second configuration information, and also implement the deletion or release of the communication connection / QoS flow by deleting the indication information (such as the first indication information or the second indication information).

[0242] The following will use the implementation examples shown in Figures 8 to 10 to exemplify these implementation processes. It should be understood that in the examples shown in Figures 8 to 10 below, the AI ​​training unit can be the entities such as MIF, Near-RT RIC mentioned above, and the AI ​​reasoning unit can be CU, DU or terminal equipment (taking the terminal equipment as UE as an example for description), etc. In addition, as shown in the implementation examples shown in Figures 6 and 7, the communication connection established in the technical solution shown in Figure 4 above can be an AI Connection between the AI ​​training unit and the AI ​​reasoning unit. For this reason, in the examples shown in Figures 8 to 10 below, the communication connection is taken as an example for explanation.

[0243] Please refer to Figure 8, which is an implementation example of the technical solution shown in Figure 4. This implementation example involves configuring the AI ​​training unit to implement a communication connection through the first configuration information. As shown in Figure 8, this implementation example includes the following steps.

[0244] It should be noted that, in the example shown in FIG8 , the transmission of the first configuration information involved in step 5, step 7, and step 9 is an implementation example of the aforementioned step S402.

[0245] Step 1: The terminal device sends a request message requesting configuration of a communication connection.

[0246] Specifically, if the UE supports AI-enabled air interface intelligent features (such as intelligent CSI feedback), it may need to request that an AI model be trained for it and sent to the UE during the service process, or the UE itself has the need to report AI model training data. Therefore, the UE can request the AI ​​training unit to establish an AI connection through step 1.

[0247] Optionally, the request information in step 1 may carry information such as the AI ​​scenario identifier, the requested AI service type (Requested AI service) type, the AI ​​model ID, and the UE ID (these four items of information are an implementation example of information A to information D above). Specifically:

[0248] AI scenario identifier: This identifier identifies the wireless AI service feature scenarios supported by the UE, such as the Smart CSI feature. Based on this parameter and the UE's capabilities, the AI ​​training unit selects an AI model (such as CNN, RNN, or DNNs of different layers) that can be used for the corresponding scenario and determines the QoS parameter configuration for the corresponding AI connection.

[0249] Requested AI service type: used to identify the type of transmission data that the UE requests to establish an AI Connection, such as AI model, AI training data, and AI training intermediate results.

[0250] AI model id: Optional parameter. If Requested AI service Type = AI model, this parameter is included to identify the specific AI model requested for transmission (such as CNN model 1, CNN model 2, etc.).

[0251] UE id: an identifier used to identify the UE, such as GUTI (Globally Unique Temporary Identifier), RNTI (Radio Network Temporary Identifier), TMSI (Temporary Mobile Subscriber Identity), etc., which can identify the UE and are not limited in the present invention.

[0252] Step 2: The DU sends a request message to the CU requesting configuration of a communication connection.

[0253] Specifically, when the DU receives a request from the UE (i.e., step 1) or the DU itself has an AI service data transmission requirement, the DU can initiate an AI connection establishment to the AI ​​training unit through the CU.

[0254] Optionally, the F1 AI connection request message in step 2 carries information such as the AI ​​scenario identifier, requested AI service type, AI model id, UE id, and DU id. Specifically:

[0255] AI scenario identifier: used to identify the wireless AI service feature scenarios supported by the UE / DU side. Its functional description refers to step 1. For example, Table 2 provides an example of the correspondence between an AI scenario identifier and its DU / UE AI scenario.

[0256] Table 2

[0257] Requested AI service type: Refer to the description in step 1.

[0258] AI model id: Refer to the description in step 1.

[0259] UE id: Optional parameter. If the AI ​​connection establishment is triggered by the UE (step 1 occurs), this parameter is carried in step 2 and its value is the parameter value in step 1.

[0260] DU id: used to identify the DU, such as the DU's IP address, DU name, etc.

[0261] Step A1: The DU sends a request message to the AI ​​training unit requesting configuration of a communication connection.

[0262] Specifically, because there is a communication interface (such as G2 interface and E2 interface) between the DU and the AI ​​training unit, if the DU needs to initiate the AI ​​connection establishment process (whether it is triggered by the DU itself or the UE (step 1)), the DU can indirectly initiate a request to the AI ​​training unit through the CU (F1 interface) (ie, step 2), or it can directly initiate a request to the AI ​​training unit through step A1, that is, through the communication interface between the DU and the AI ​​training unit.

[0263] It should be noted that the request information in step A1 carries AI scenario identifier, requested AI service type, AI model id, UE id, DU id and other information. For parameter explanation, please refer to the relevant description of step 2.

[0264] Step 3: The CU sends a request message to the AI ​​training unit requesting configuration of the communication connection.

[0265] Specifically, when the CU receives a request from the DU (i.e., step 2) or the CU itself has an AI service data transmission request, the CU initiates AI connection establishment to the AI ​​training unit through the CU. (If the DU's AI connection establishment process directly requests the AI ​​training unit through the G2 interface (i.e., executing step A1), this step is triggered only by the CU's own AI service data transmission request.)

[0266] It should be noted that the G1 AI connection request message in step 3 carries information such as the AI ​​scenario identifier, requested AI service type, AI model id, UE id, DU id, and CU id. Specifically:

[0267] AI scenario identifier: used to identify the wireless AI service feature scenarios supported by the UE / DU / CU side. Its functional description can refer to the description of step 1. For example, Table 3 provides an example of the correspondence between an AI scenario identifier and its CU / DU / UE AI scenario.

[0268] Table 3

[0269] Requested AI service type: Refer to the description in step 1.

[0270] AI model id: Refer to the description in step 1.

[0271] UE id: Optional parameter. If the AI ​​connection establishment is triggered by the UE (step 1 occurs), this parameter is carried in step 2 and its value is the parameter value in step 1.

[0272] DU id: Optional parameter. If the AI ​​connection establishment is triggered by the UE / DU (step 2 occurs), this parameter is carried in step 1c and its value is the parameter value in step 2.

[0273] CU id: used to identify the CU, such as the CU's IP address, CU name, etc.

[0274] Step 4. The AI ​​training unit determines the first configuration information.

[0275] The implementation process of the first configuration information may refer to the description of FIG4 and related implementation methods above.

[0276] If the AI ​​training unit itself has AI business data transmission requirements (such as the AI ​​training unit has completed the training of an AI model used in a certain AI scenario or needs to collect data required for AI model training, etc.), the establishment of the AI ​​connection is triggered, that is, the AI ​​training unit is triggered to determine the first configuration information.

[0277] Optionally, if the AI ​​service data transmission object of the AI ​​training unit itself is the UE, then if the UE processes the IDLE state, the AI ​​training unit needs to page the UE through the CU / DU, so that after the UE is reconnected to the network, it enters the Connected state, and then the UE initiates step 1 to establish the corresponding AI connection. Therefore, it is necessary to add a new AI service-triggered Paging paging on the G1 interface (that is, the AI ​​training unit sends a Paging message to the CU through G1, and the message carries the UE id and the cause value cause (whose value is the AI ​​service data transmission). The Paging processing method of the CU / DU and F1 interface can reuse the existing RAN-triggered Paging process, which will not be repeated in this article).

[0278] Exemplarily, in step 4, the AI ​​training unit determines the first configuration information based on the request information received in the above step. For example, the Requested AI service type parameter and the AI ​​scenario identifier in the request information may correspond to the transmitted AI service data type and AI service scenario, respectively. The first configuration information determined by the AI ​​training unit includes attribute description information for the newly created Connection, the assigned AI connection ID, etc. In addition, if the Connection needs to simultaneously support the transmission of different types of AI service data in the corresponding AI scenario, it is also necessary to determine the AI ​​QoS flow ID and corresponding QoS parameters for each AI service data transmission.

[0279] Step 5. The AI ​​training unit sends the first configuration information to the CU.

[0280] Specifically, if step 3 occurs, the AI ​​training unit executes step 5. For example, the AI ​​training unit sends the first configuration information to the CU through the G1 interface or the E2 interface. For example, the first configuration information may carry parameters such as AI Connection ID, AI QoS flow ID, AI QoS, UE ID, DU ID, and CU ID.

[0281] Step A2: The AI ​​training unit sends first configuration information to the DU.

[0282] Specifically, if step A1 occurs, the AI ​​training unit executes step A2. For example, the AI ​​training unit sends first configuration information to the DU via the G2 interface or the E2 interface. For example, the first configuration information may carry parameters such as the AI ​​Connection ID, the AI ​​QoS flow ID, the AI ​​QoS, the UE ID, and the DU ID.

[0283] Step 6. The CU performs configuration based on the first configuration information.

[0284] Specifically, if step 5 occurs, the CU executes step 6. For example, the CU establishes a local AI connection context based on the first configuration information. Optionally, if the AI ​​connection in step 1 is triggered by a UE request, the CU establishes a CRB, configures AI QoS parameters, and completes the mapping between the AI ​​QoS flow and the CRB.

[0285] Step 7. The CU sends the first configuration information to the DU.

[0286] Specifically, if step 2 occurs, the CU executes step 7. For example, the CU sends an F1 AI connection establishment request message carrying the first configuration information to the DU through the F1 interface. Similarly, the first configuration information may carry parameters such as AI Connection ID, AI QoS flow ID, AI QoS, UE ID, and DU ID.

[0287] Step 8. The DU performs configuration based on the first configuration information.

[0288] Specifically, if step A2 or step 7 occurs, then execute step 8. The DU builds a local AI connection context.

[0289] Step 9. The DU sends the first configuration information to the UE.

[0290] Specifically, if step 1 occurs, execute step 9. For example, the DU feeds back the AI ​​connection-related parameters allocated by the AI ​​training unit to the UE. This step may use the RRC reconfiguration message of the Uu interface to send the first configuration information, which may carry parameters such as the AI ​​Connection ID, AI QoS flow ID, and AI QoS.

[0291] Step 10. The UE performs configuration based on the first configuration information, for example, the UE performs parameter configuration of the corresponding wireless communication protocol layer.

[0292] Step 11. The UE sends feedback information, which is used to feedback whether the configuration is successful.

[0293] Step 12. The DU sends feedback information to the CU, which is used to feedback whether the configuration is successful.

[0294] Specifically, if step 7 occurs, the DU can execute step 12. For example, after completing local AI connection processing or receiving the feedback information from the UE in step 11, the DU replies to the CU with feedback information (or AI connection establishment response message), carrying the corresponding AI connection ID, AI QoS flow ID, and creation execution result (which can be success, failure, partial success, etc.).

[0295] Step A3. The DU sends feedback information to the AI ​​training unit, which is used to feedback whether the configuration is successful.

[0296] Specifically, if step A2 occurs, the DU can execute step A3. For example, after the DU completes the local AI connection processing or receives the confirmation reply message from the UE, it directly replies to the AI ​​training unit through G2 with feedback information (or AI connection establishment response message), carrying the corresponding AI connection ID, AI QoS flow ID and creation execution result (its value is success, failure and partial success).

[0297] Step 13. The CU sends feedback information to the AI ​​training unit, which is used to feedback whether the configuration is successful.

[0298] Specifically, if step 5 occurs, the CU can execute step 13. For example, after completing local AI connection processing or receiving a confirmation reply message from the DU, the CU sends feedback information (or AI connection establishment response message) to the AI ​​training unit, carrying the corresponding AI connection ID, AI QoS flow ID, and creation execution result (which can be success, failure, or partial success).

[0299] Thus, through the technical solution shown in Figure 8, when the UE, CU, DU, or AI training unit has an AI service data transmission request (the detailed triggering conditions are described above), the AI ​​connection establishment is triggered to execute the service process of Example 1. In addition, the AI ​​training unit can combine the transmission requirements of the AI ​​service to effectively manage the lifecycle of the connection for transmitting AI service data, reducing system signaling consumption.

[0300] Please refer to Figure 9, which is an implementation example of the technical solution shown in Figure 4. This implementation example involves the AI ​​training unit configuring the QoS flow through the second configuration information. As shown in Figure 9, this implementation example includes the following steps.

[0301] It should be understood that the business process of the implementation process shown in Figure 9 is generally similar to the process of the implementation process shown in Figure 8. The main difference is that the UE\CU\DU can request the AI ​​QoS flow of AI transmission from the AI ​​training unit based on the actual AI service data transmission requirements in the same AI scenario. The AI ​​training unit evaluates whether the QoS configuration of the current AI QoS flow in the AI ​​connection meets the new requirements. If not, a new AI QoS flow creation is executed, that is, the process of the implementation process shown in Figure 9 is executed.

[0302] Step 1. The UE sends a request message requesting the configuration of a QoS flow.

[0303] Specifically, in the same AI scenario, if the UE's AI service transmission requirements change, it is possible that the currently established AI QoS flow cannot meet the requirements. In this case, it is necessary to request the AI ​​training unit to create a corresponding AI QoS flow in the AI ​​connection through step 1.

[0304] Optionally, the request information in step 1 may carry information such as AI Connection ID, Requested AI service type, AI model ID, and UE ID. Specifically:

[0305] AI Connection ID: used to identify the AI ​​connection for business data transmission that supports AI business scenarios on the UE side.

[0306] Requested AI service type: Refer to Figure 8 for the description of the implementation process.

[0307] AI model id: Refer to the description of the implementation process shown in Figure 8.

[0308] UE id: Refer to the relevant description of the implementation process shown in Figure 8.

[0309] Step 2. DU sends a request message to CU requesting configuration of QoS flow.

[0310] Specifically, when the DU receives a request from the UE (i.e., step 1) or the DU itself has a new AI service data transmission request, the DU carries information such as the AI ​​Connection ID, Requested AI service type, AI model id, UE id, and DU id through the request information in step 2. For parameter explanation, refer to the previous description.

[0311] Step B1. The DU sends a request message to the AI ​​training unit requesting configuration of a QoS flow.

[0312] Specifically, because there is a G2 interface or E2 interface between the DU and the AI ​​training unit, if the DU needs to initiate the AI ​​connection modification process (whether it is triggered by the DU itself or the UE (step 1)), the DU can indirectly initiate a request to the AI ​​training unit through the CU (F1 interface) (ie, step 2), or it can directly send a request message carrying AI Connection ID, Requested AI service type, AI model id, UE id, DU id and other information to the AI ​​training unit through step B1, that is, through the G2 interface or E2 interface. For parameter explanation, please refer to the previous description.

[0313] Step 3. The CU sends a request message to the AI ​​training unit requesting the configuration of the QoS flow.

[0314] Specifically, when the CU receives a request from the DU (i.e., step 2) or the CU itself has a new AI service data transmission request, the CU initiates an AI connection modification to the AI ​​training unit. (If the DU's AI connection modification process is directly requested to the AI ​​training unit via the G2 interface (i.e., executing step B1), then step 3 can be triggered by the CU's own new AI service data transmission request.)

[0315] In addition, the request information sent by the CU in step 3 can carry information such as AI Connection ID, Requested AI service type, AI model id, UE id, DU id, and CU id. For parameter explanations, refer to the previous description.

[0316] Step 4. The AI ​​training unit determines the second configuration information.

[0317] The implementation of the second configuration information may refer to the description of FIG4 and the related implementation process.

[0318] Specifically, if the AI ​​training unit itself has new AI business data transmission requirements (such as the AI ​​training unit has completed the training of a new type of AI model used in a certain AI scenario, etc.), it can trigger the AI ​​connection modification, that is, trigger the AI ​​training unit to determine the second configuration information.

[0319] Optionally, if the AI ​​service data transmission object of the AI ​​training unit itself is the UE, then if the UE processes the IDLE state, the AI ​​training unit needs to page the UE through the CU / DU, so that after the UE restores the connection with the network, it enters the Connected state, and then the UE initiates step 1 to implement the corresponding AI connection modification. Therefore, it is necessary to add a new AI service triggered Paging paging on the G1 interface (that is, the AI ​​training unit sends a Paging message to the CU through G1, and the message carries the UE id and the cause value cause (whose value is the AI ​​service data transmission connection modification). The Paging processing method of the CU / DU and F1 interface can reuse the existing RAN triggered Paging process processing, which will not be repeated in this article).

[0320] In addition, the AI ​​training unit can determine the second configuration information based on the parameters in the request information obtained in the above steps. For example, the AI ​​training unit determines the QoS parameters of the requested AI service data transmission based on the Requested AI service type parameter, and evaluates that the existing AI QoS flows in the AI ​​connection identified by the AI ​​connection ID cannot meet the QoS requirements of the new AI service. It then decides to create a new AI QoS flow, allocate an AI QoS flow ID, update the Connection context, and perform other functional processing.

[0321] Step 5. The AI ​​training unit sends the second configuration information to the CU.

[0322] Specifically, if step 3 occurs, execute step 5. For example, the AI ​​training unit sends the second configuration information to the CU through the G1 interface or the E2 interface. The second configuration information may carry parameters such as the AI ​​Connection ID, the new AI QoS flow ID, AI QoS, UE ID, DU ID, and CU ID.

[0323] Step B2. The AI ​​training unit sends the second configuration information to the DU.

[0324] Specifically, if step B1 occurs, step B2 is executed. For example, the AI ​​training unit sends the second configuration information to the DU via the G2 interface or the E2 interface. The second configuration information may carry parameters such as the AI ​​Connection ID, the new AI QoS flow ID, AI QoS, UE ID, and DU ID.

[0325] Step 6. CU performs configuration.

[0326] Specifically, if step 5 occurs, the CU may execute step 6. For example, the CU may update the local AI connection context. Alternatively, if the AI ​​connection in step 1 is modified by a UE request, the CU may create or modify a CRB, configure AI QoS parameters, and complete the mapping between the AI ​​QoS flow and the CRB.

[0327] Step 7. The CU sends the second configuration information to the DU.

[0328] Specifically, if step 2 occurs, the CU can execute step 7. For example, the CU sends an add F1 AI QoS flow message to the DU through the F1 interface. The message carries parameters such as the AI ​​Connection ID, the new AI QoS flow ID, AI QoS, UE ID, and DU ID.

[0329] Step 8.DU performs configuration.

[0330] Specifically, if step B2 or step 7 occurs, then execute step 8. The DU updates the local AI connection context.

[0331] Step 9. The DU sends the second configuration information to the UE.

[0332] Specifically, if step 1 occurs, the DU can perform step 9. For example, the DU feeds back the AI ​​QoS flow-related parameters allocated by the AI ​​training unit to the UE. This step can use the RRC reconfiguration message of the Uu interface to send AI Connection ID, new AI QoS flow ID, AI QoS and other parameters.

[0333] Step 10. UE performs configuration.

[0334] Step 11. The UE sends feedback information to the DU to indicate whether the configuration is successful.

[0335] Step 12. The DU sends feedback information to the CU to indicate whether the configuration is successful.

[0336] Specifically, if step 7 occurs, the DU can execute step 12. For example, after completing the local AI connection modification process or receiving the confirmation reply message from the UE, the DU replies to the CU with an AI QoS flow addition response message, which carries the corresponding AI connection ID, AI QoS flow ID, and the creation execution result (the value can be success, failure, or partial success).

[0337] Step B3. The DU sends feedback information to the AI ​​training unit to indicate whether the configuration is successful.

[0338] Specifically, if step B2 occurs, the DU can execute step A3. For example, after the DU completes the local AI connection modification process or receives the confirmation reply message from the UE, it directly replies to the AI ​​training unit through G2 with an AI QoS flow add response message, carrying the corresponding AI connection ID, AI QoS flow ID, and the creation execution result (which can be success, failure, or partial success).

[0339] Step 13. The CU sends feedback information to the AI ​​training unit to indicate whether the configuration is successful.

[0340] Specifically, if step 5 occurs, the CU can execute step 13. For example, after completing the local AI connection modification process or receiving the confirmation reply message from the DU, the CU replies to the AI ​​training unit with an AI QoS flow addition response message, carrying the corresponding AI connection ID, AI QoS flow ID, and the creation execution result (which can be success, failure, or partial success).

[0341] Based on the implementation process shown in Figure 9, when a UE, CU, DU, or AI training unit requires AI service data transmission and the current AI QoS flow cannot meet the QoS requirements of the corresponding AI service, one or more new AI QoS flows can be created within the existing AI connection through the implementation process shown in Figure 9. Furthermore, the AI ​​training unit can promptly update the connection transmitting AI service data based on the latest transmission requirements of the AI ​​service to ensure appropriate resource allocation.

[0342] Please refer to Figure 10, which shows an implementation example of the technical solution shown in Figure 4. This implementation example involves the AI ​​training unit deleting a communication connection or a QoS flow by deleting indication information. As shown in Figure 10, this implementation example includes the following steps.

[0343] It should be understood that the business process of the implementation process shown in Figure 10 is generally similar to the process of the implementation process shown in Figure 8. The main difference is that the implementation process shown in Figure 10 describes that when the AI ​​characteristics supported by the UE / CU / DU change, or there is no AI business data transmission or no data transmission of a specific AI business type for a long time (such as 1 day, 7 days), the corresponding AI connection is released or the AI ​​QoS flow therein is released through the implementation process shown in Figure 10.

[0344] Step 1. The UE sends a request message requesting to delete the configuration.

[0345] Specifically, if the UE no longer needs to transmit AI services, or no longer needs to transmit data of one or more AI service types in the AI ​​scenario, the UE requests the AI ​​training unit to delete the complete AI connection through step 1, or only delete one or more AI QoS flows in the AI ​​connection.

[0346] Optionally, the request information in step 1 can carry information such as AI Connection ID, AI QoS flow ID, and UE ID. Specifically:

[0347] AI Connection ID: used to identify the AI ​​connection that the UE wants to delete.

[0348] AI QoS flow ID: Optional parameter. If the UE needs to terminate the entire AI connection ID, step 1 only includes the AI ​​connection ID and does not carry the AI ​​QoS flow ID parameter. If the UE only deletes the AI ​​QoS flow specified in the AI ​​connection, the AI ​​QoS flow ID parameter is required.

[0349] UE id: Refer to the previous description.

[0350] Step 2. DU sends a request message to CU requesting to delete the configuration.

[0351] Specifically, when the DU receives a request from the UE (i.e., step 1) or the DU itself no longer needs to transmit AI services, or no longer needs to transmit data of one or more AI service types in the AI ​​scenario, the DU carries the AI ​​Connection ID, AI QoS flow ID, UE ID, DU ID and other information through the F1 AI connection delete request message in step 2. For parameter explanation, refer to the previous description.

[0352] Step C1. The DU sends a request message to the AI ​​training unit requesting configuration deletion.

[0353] Specifically, because there is a G2 interface or E2 interface between the DU and the AI ​​training unit, if the DU needs to initiate the AI ​​connection deletion process (whether it is triggered by the DU itself or the UE (step 1)), the DU can indirectly initiate a request to the AI ​​training unit through the CU (F1 interface) (ie, step 2), or it can directly send a request message carrying AI Connection ID, AI QoS flow ID, UE id, DU id, etc. to the AI ​​training unit through step C1, that is, through the G2 interface or E2 interface. For parameter explanation, refer to the previous description.

[0354] Step 3. The CU sends a request to the AI ​​training unit to delete the configuration.

[0355] Specifically, when the CU receives a request from the DU (i.e., step 2) or the CU no longer needs to transmit AI services, or no longer needs to transmit data of one or more AI service types in the AI ​​scenario, the CU initiates AI connection termination to the AI ​​training unit through the CU. (If the DU's AI connection deletion process is directly requested to the AI ​​training unit through the G2 interface or E2 interface (i.e., step C1 is executed), this step is triggered only because the CU itself no longer has AI service data transmission requirements.)

[0356] Optionally, in the request information in step 3 that carries information such as AI Connection ID, AI QoS flow ID, UE ID, DU ID, and CU ID, the explanation of each parameter refers to the previous description.

[0357] Step 4. The AI ​​training unit determines the deletion instruction information.

[0358] The implementation process of deleting the indication information may refer to the implementation process of the first indication information or the second indication information mentioned above.

[0359] Specifically, if the AI ​​training unit has no AI business data transmission for a long time, the implicit AI connection deletion process is triggered.

[0360] Optionally, if the AI ​​service data transmission object of the AI ​​training unit itself is the UE, then if the UE processes the IDLE state, the AI ​​training unit needs to page the UE through the CU / DU, so that after the UE restores the connection with the network, it enters the Connected state, and then the UE initiates step 1 to implement the corresponding AI connection deletion. Therefore, it is necessary to add a new AI service triggered Paging paging on the G1 interface (that is, the AI ​​training unit sends a Paging message to the CU through G1, and the message carries the UE id and the cause value cause (whose value is the AI ​​service data transmission connection deletion). The Paging processing method of the CU / DU and F1 interface can reuse the existing RAN triggered Paging process processing, which will not be repeated in this article).

[0361] Exemplarily, when the AI ​​training unit determines the deletion instruction information, the AI ​​training unit may determine the corresponding processing based on the parameters carried in the request information received in the above steps. For example, if the message carries both the AI ​​connection ID and the AI ​​QoS flow ID, only the AI ​​QoS flow identified by the AI ​​QoS flow ID is deleted. If the message carries only the AI ​​connection ID, the entire AI connection is terminated.

[0362] Step 5. The AI ​​training unit sends a deletion instruction message to the CU.

[0363] Specifically, if step 3 occurs, the AI ​​training unit executes step 5.

[0364] For example, if the AI ​​training unit decides to terminate the entire AI connection in step 4, it sends a G1 AI connection termination request message carrying deletion indication information to the CU through the G1 interface or E2 interface. The message carries AI Connection ID, new AI QoS flow ID, UE id, DU id, CU id and other parameters.

[0365] For example, if the AI ​​training unit decides to delete the AI ​​QoS flow specified in the AI ​​connection in step 4, it sends a delete G1 AI QoS flow request message carrying deletion indication information to the CU through the G1 interface or E2 interface. The message carries parameters such as AI Connection ID, AI QoS flow ID, UE id, DU id, and CU id.

[0366] Step C2: The AI ​​training unit sends a deletion instruction message to the DU.

[0367] Specifically, if step C1 occurs, step C2 is executed.

[0368] For example, if the AI ​​training unit decides to terminate the entire AI connection in step 4, it sends a G2 AI connection termination request message carrying deletion indication information to the DU through the G2 interface or E2 interface. The message carries AI Connection ID, new AI QoS flow ID, UE ID, DU ID, CU ID and other parameters.

[0369] For example, if the AI ​​training unit decides to delete the AI ​​QoS flow specified in the AI ​​connection in step 4, it sends a delete G2 AI QoS flow request message carrying deletion indication information to the DU through the G2 interface or E2 interface. The message carries parameters such as AI Connection ID, AI QoS flow ID, UE ID, DU ID, and CU ID.

[0370] Step 6. CU performs deletion.

[0371] Specifically, if step 5 occurs, the CU executes step 6. For example, the CU deletes the AI ​​connection context identified by the AI ​​connection ID, or deletes the AI ​​QoS flow in the AI ​​connection identified by the AI ​​QoS flow ID, according to the deletion indication information in step 5, and releases the corresponding CRB and radio resources.

[0372] Step 7. CU sends deletion indication information to DU.

[0373] Specifically, if step 2 occurs, then step 7 is executed.

[0374] Step 8. DU performs deletion.

[0375] Specifically, if step C2 or step 7 occurs, then execute step 8. For example, according to the request in step 8, the DU deletes the AI ​​connection context identified by the AI ​​connection ID, or deletes the AI ​​QoS flow in the AI ​​connection identified by the AI ​​QoS flow ID, and releases the corresponding CRB and radio resources.

[0376] Step 9. The DU sends a deletion indication message to the UE.

[0377] Specifically, if step 1 occurs, then execute step 9. For example, the DU feeds back the AI ​​connection or AI QoS flow information deleted by the AI ​​training unit to the UE. This step can use the RRC reconfiguration message of the Uu interface to send deletion indication information. The deletion indication information can carry parameters such as the AI ​​Connection ID and AI QoS flow ID.

[0378] Step 10. The UE performs deletion.

[0379] Step 11. The UE sends feedback information to the DU to indicate whether to delete the data.

[0380] Step 12: DU sends feedback information to CU to inform whether to delete.

[0381] Specifically, if step 7 occurs, then execute step 12. For example, after the DU completes the local AI connection deletion process, or after receiving the feedback information from the UE indicating that the connection has been deleted in step 11, the DU replies to the CU with an AI connection termination / AI QoS flow deletion response message, which carries the corresponding AI connection ID, AI QoS flow ID, and the deletion execution result (which can be success, failure, or partial success).

[0382] Step C3. DU sends feedback information to the AI ​​training unit to inform whether to delete.

[0383] Specifically, if step C2 occurs, the DU executes step C3. For example, after completing the local AI connection deletion process or receiving the confirmation reply message from the UE, the DU directly replies to the AI ​​training unit via the G2 interface or E2 interface with an AI connection termination / AI QoS flow deletion response message, carrying the corresponding AI connection ID, AI QoS flow ID, and the deletion execution result (which can be success, failure, or partial success).

[0384] Step 13. The CU sends feedback information to the AI ​​training unit to indicate whether to delete the data.

[0385] Specifically, if step 9 is completed, the CU executes step 13. For example, after the CU completes the local AI connection deletion process or receives a confirmation reply message from the DU, it replies to the AI ​​training unit with an AI connection termination / AI QoS flow deletion response message, carrying the corresponding AI connection ID, AI QoS flow ID, and the deletion execution result (which can be success, failure, or partial success).

[0386] Based on the implementation process shown in Figure 10, if the AI ​​features supported by the UE / CU / DU change, or if there is no AI service data transmission or no data transmission of a specific AI service type for a long period of time (e.g., 1 day or 7 days), the corresponding AI connection or the AI ​​QoS flow therein is released through the implementation process shown in Figure 10. In addition, the AI ​​training unit can timely reclaim resources for connections transmitting AI service data based on the status of the AI ​​service, improving resource utilization.

[0387] Referring to Figure 11 , an embodiment of the present application provides a communication device 1100 that can implement the functions of the communication device in the above method embodiment, thereby also achieving the beneficial effects of the above method embodiment. The communication device can be the AI ​​training unit or AI reasoning unit described in the above embodiment.

[0388] In addition, the communication device 1100 may be a communication device, or an integrated circuit or component inside the communication device, such as a chip.

[0389] In one possible implementation, when the device 1100 (for example, a first communication device) is used to execute the method executed by the AI ​​training unit in any of the aforementioned embodiments, the device 1100 includes a processing module 1101 and a transceiver module 1102; the processing module 1101 is used to determine first configuration information, and the first configuration information is used to configure a communication connection for data transmission, and the data transmission is the transmission of business data of a communication management service between the AI ​​training unit and the AI ​​reasoning unit, and the communication management service is used to manage the wireless access communication service between the terminal device and the wireless access device; the first configuration information includes an identifier of the communication connection, and an identifier of one or more quality of service flows QoS flow in the communication connection; the transceiver module 1102 is used to send the first configuration information.

[0390] In a possible implementation, the transceiver module 1102 is further configured to receive first request information, where the first request information is used to request the first configuration information.

[0391] In one possible implementation, the first request information includes at least one of the following: an identifier of the AI ​​application scenario supported by the AI ​​reasoning unit, an identifier of the requested AI service type, a model identifier corresponding to the requested AI model, and an identifier of the AI ​​reasoning unit.

[0392] In one possible implementation, the AI ​​scenario supported by the AI ​​reasoning unit satisfies any of the following:

[0393] The AI ​​inference unit is a distributed unit DU or a module in the DU. The AI ​​scenarios supported by the AI ​​inference unit include at least one of a single-user medium access control SU MAC dictionary, a multi-user MU pairing dictionary, a multi-cell coordinated scheduling dictionary, and a low-speed channel map.

[0394] The AI ​​inference unit is a terminal device or a module in the terminal device. The AI ​​scenarios supported by the AI ​​inference unit include at least one of interference spectrum, beam spectrum, and smart channel state information CSI;

[0395] The AI ​​inference unit is a centralized unit CU or a module in the CU. The AI ​​scenarios supported by the AI ​​inference unit include at least one of smart grid, smart load balancing, and smart energy saving.

[0396] In one possible implementation, the first configuration information also includes at least one of the following: quality of service (QoS) information of one or more QoS flows in the communication connection, and an identifier of the AI ​​training unit.

[0397] In one possible implementation, the processing module 1101 is used to determine the first configuration information, including: the processing module 1101 is specifically used to determine the first configuration information based on at least one of the following items, including: an identifier of the AI ​​application scenario corresponding to the business data, an identifier of the AI ​​service type corresponding to the communication management business, and a model identifier of the AI ​​model corresponding to the AI ​​model information contained in the business data.

[0398] In one possible implementation, the transceiver module 1102 is also used to send second configuration information, which includes configuration information of N QoS flows established in the communication connection, where N is a positive integer; wherein the second configuration information includes at least one of the following: an identifier of the communication connection, N identifiers corresponding to the N QoS flows, quality of service QoS information of the N QoS flows, and an identifier of the AI ​​inference unit.

[0399] In a possible implementation, the method further includes: the transceiver module 1102 is further configured to receive second request information, where the second request information is used to request the second configuration information; wherein the second request information includes an identifier of the communication connection.

[0400] In a possible implementation, the method further includes: the transceiver module 1102 is further configured to send first indication information, where the first indication information is configured to indicate deletion of at least one QoS flow among the N QoS flows.

[0401] In a possible implementation, the transceiver module 1102 is further configured to receive third request information, where the third request information is used to request deletion of the at least one QoS flow.

[0402] In a possible implementation, the transceiver module 1102 is further configured to send second indication information, where the second indication information is used to instruct to release the communication connection.

[0403] In a possible implementation, the transceiver module 1102 is further configured to receive fourth request information, where the fourth request information is used to request to release the communication connection.

[0404] In one possible implementation, when the device 1100 (for example, a second communication device) is used to execute the method executed by the AI ​​reasoning unit in any of the aforementioned embodiments, the device 1100 includes a processing module 1101 and a transceiver module 1102; the transceiver module 1102 is used to receive first configuration information, and the first configuration information is used to configure a communication connection for data transmission, and the data transmission is the transmission of business data of a communication management service between the artificial intelligence AI training unit and the AI ​​reasoning unit, and the communication management service is used to manage the wireless access communication service between the terminal device and the wireless access device; the first configuration information includes an identifier of the communication connection, and an identifier of one or more quality of service flows QoS flow in the communication connection; the processing module 1101 is used to transmit the business data in the communication connection based on the first configuration information.

[0405] In a possible implementation, the transceiver module 1102 is further configured to send first request information, where the first request information is used to request the first configuration information.

[0406] In one possible implementation, the first request information includes at least one of the following: an identifier of the AI ​​application scenario supported by the AI ​​reasoning unit, an identifier of the requested AI service type, a model identifier corresponding to the requested AI model, and an identifier of the AI ​​reasoning unit.

[0407] In one possible implementation, the AI ​​scenario supported by the AI ​​reasoning unit satisfies any of the following:

[0408] The AI ​​inference unit is a distributed unit DU or a module in the DU. The AI ​​scenarios supported by the AI ​​inference unit include at least one of a single-user medium access control SU MAC dictionary, a multi-user MU pairing dictionary, a multi-cell coordinated scheduling dictionary, and a low-speed channel map.

[0409] The AI ​​inference unit is a terminal device or a module in the terminal device. The AI ​​scenarios supported by the AI ​​inference unit include at least one of interference spectrum, beam spectrum, and smart channel state information CSI;

[0410] The AI ​​inference unit is a centralized unit CU or a module in the CU. The AI ​​scenarios supported by the AI ​​inference unit include at least one of smart grid, smart load balancing, and smart energy saving.

[0411] In one possible implementation, the first configuration information also includes at least one of the following: quality of service (QoS) information of one or more QoS flows in the communication connection, and an identifier of the AI ​​training unit.

[0412] In one possible implementation, the transceiver module 1102 is also used to receive second configuration information, which includes configuration information of N QoS flows established in the communication connection, where N is a positive integer; wherein the second configuration information includes at least one of the following: an identifier of the communication connection, N identifiers corresponding to the N QoS flows, quality of service QoS information of the N QoS flows, and an identifier of the AI ​​inference unit.

[0413] In a possible implementation, the transceiver module 1102 is further configured to send second request information, where the second request information is used to request the second configuration information; wherein the second request information includes an identifier of the communication connection.

[0414] In a possible implementation, the transceiver module 1102 is further configured to receive first indication information, where the first indication information is used to instruct deletion of at least one QoS flow among the N QoS flows.

[0415] In a possible implementation, the transceiver module 1102 is further configured to send third request information, where the third request information is used to request deletion of the at least one QoS flow.

[0416] In a possible implementation, the transceiver module 1102 is further configured to receive second indication information, where the second indication information is used to instruct to release the communication connection.

[0417] In a possible implementation, the transceiver module 1102 is further configured to send fourth request information, where the fourth request information is used to request to release the communication connection.

[0418] It should be noted that, for details of the information execution process of the units of the above-mentioned communication device 1100, please refer to the description in the method embodiment shown above in this application, and will not be repeated here.

[0419] Please refer to Figure 12, which is another schematic structural diagram of a communication device 1200 provided in this application. The communication device 1200 includes a logic circuit 1201 and an input / output interface 1202. The communication device 1200 may be a chip or an integrated circuit.

[0420] The transceiver module 1102 shown in FIG11 may be a communication interface, which may be the input / output interface 1202 in FIG12 , which may include an input interface and an output interface. Alternatively, the communication interface may be a transceiver circuit, which may include an input interface circuit and an output interface circuit.

[0421] Optionally, the logic circuit 1201 is used to determine first configuration information, which is used to configure a communication connection for data transmission, where the data transmission is the transmission of business data of a communication management service between an AI training unit and an AI reasoning unit, and the communication management service is used to manage a wireless access communication service between a terminal device and a wireless access device; the first configuration information includes an identifier of the communication connection, and an identifier of one or more quality of service flows QoS flows in the communication connection; the input and output interface 1202 is used to send the first configuration information.

[0422] Optionally, the input-output interface 1202 is used to receive first configuration information, which is used to configure a communication connection for data transmission, where the data transmission is the transmission of business data of a communication management service between an artificial intelligence AI training unit and an AI reasoning unit, and the communication management service is used to manage the wireless access communication service between a terminal device and a wireless access device; the first configuration information includes an identifier of the communication connection, and an identifier of one or more quality of service flows QoS flows in the communication connection; the logic circuit 1201 is used to transmit the business data in the communication connection based on the first configuration information.

[0423] Among them, the logic circuit 1201 and the input and output interface 1202 can also execute other steps performed by the AI ​​training unit or AI reasoning unit in any embodiment and achieve corresponding beneficial effects, which will not be repeated here.

[0424] In a possible implementation, the processing module 1101 shown in FIG. 11 may be the logic circuit 1201 in FIG. 12 .

[0425] Optionally, the logic circuit 1201 may be a processing device, and the functions of the processing device may be partially or entirely implemented by software. The functions of the processing device may be partially or entirely implemented by software.

[0426] Optionally, the processing device may include a memory and a processor, wherein the memory is used to store a computer program, and the processor reads and executes the computer program stored in the memory to perform corresponding processing and / or steps in any one of the method embodiments.

[0427] Alternatively, the processing device may include only a processor. A memory for storing the computer program is located outside the processing device, and the processor is connected to the memory via circuits / wires to read and execute the computer program stored in the memory. The memory and processor may be integrated or physically separate.

[0428] Optionally, the processing device may be one or more chips, or one or more integrated circuits. For example, the processing device may be one or more field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), system-on-chips (SoCs), central processor units (CPUs), network processors (NPs), digital signal processors (DSPs), microcontroller units (MCUs), programmable logic devices (PLDs), or other integrated chips, or any combination of the above chips or processors.

[0429] Please refer to FIG. 13 , which shows a communication device 1300 involved in the above embodiments provided in an embodiment of the present application. Specifically, the communication device 1300 may be a communication device serving as a terminal device in the above embodiments.

[0430] Herein, a possible logical structure diagram of the communication device 1300 is shown. The communication device 1300 may include but is not limited to at least one processor 1301 and a communication port 1302 .

[0431] The transceiver module 1102 shown in FIG11 may be a communication interface, which may be the communication port 1302 in FIG13 , which may include an input interface and an output interface. Alternatively, the communication port 1302 may be a transceiver circuit, which may include an input interface circuit and an output interface circuit.

[0432] Further optionally, the device may also include at least one of a memory 1303 and a bus 1304. In an embodiment of the present application, the at least one processor 1301 is used to control and process the actions of the communication device 1300.

[0433] In addition, the processor 1301 can be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field-programmable gate array, or other programmable logic device, a transistor logic device, a hardware component, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a digital signal processor and a microprocessor, and so on. Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0434] It should be noted that the communication device 1300 shown in Figure 13 can be specifically used to implement the steps implemented by the terminal device in the aforementioned method embodiment and achieve the corresponding technical effects of the terminal device. The specific implementation methods of the communication device shown in Figure 13 can refer to the description in the aforementioned method embodiment and will not be repeated here.

[0435] Please refer to Figure 14, which is a structural diagram of the communication device 1400 involved in the above-mentioned embodiments provided in an embodiment of the present application. The communication device 1400 can specifically be a communication device as the first communication device or wireless access device in the above-mentioned embodiments, wherein the structure of the communication device can refer to the structure shown in Figure 14.

[0436] The communication device 1400 includes at least one processor 1411 and at least one network interface 1414. Further optionally, the communication device also includes at least one memory 1412, at least one transceiver 1413 and one or more antennas 1415. The processor 1411, the memory 1412, the transceiver 1413 and the network interface 1414 are connected, for example, via a bus. In an embodiment of the present application, the connection may include various interfaces, transmission lines or buses, etc., which are not limited in this embodiment. The antenna 1415 is connected to the transceiver 1413. The network interface 1414 is used to enable the communication device to communicate with other communication devices through a communication link. For example, the network interface 1414 may include a network interface between the communication device and the core network device, such as an S1 interface, and the network interface may include a network interface between the communication device and other communication devices (such as other network devices or core network devices), such as an X2 or Xn interface.

[0437] The transceiver module 1102 shown in FIG11 may be a communication interface, which may be the network interface 1414 in FIG14 , which may include an input interface and an output interface. Alternatively, the network interface 1414 may be a transceiver circuit, which may include an input interface circuit and an output interface circuit.

[0438] Processor 1411 is primarily used to process communication protocols and communication data, control the entire communication device, execute software programs, and process software program data, for example, to support the communication device in performing the actions described in the embodiments. The communication device may include a baseband processor and a central processing unit. The baseband processor is primarily used to process communication protocols and communication data, while the central processing unit is primarily used to control the entire terminal device, execute software programs, and process software program data. Processor 1411 in Figure 14 may integrate the functions of both a baseband processor and a central processing unit. Those skilled in the art will appreciate that the baseband processor and the central processing unit may also be independent processors interconnected via a bus or other technology. Those skilled in the art will appreciate that a terminal device may include multiple baseband processors to accommodate different network standards, multiple central processing units to enhance its processing capabilities, and various components of the terminal device may be connected via various buses. The baseband processor may also be referred to as a baseband processing circuit or a baseband processing chip. The central processing unit may also be referred to as a central processing circuit or a central processing chip. The functionality for processing communication protocols and communication data may be built into the processor or stored in memory as a software program, which is executed by the processor to implement the baseband processing functionality.

[0439] The memory is primarily used to store software programs and data. Memory 1412 may exist independently and be connected to processor 1411. Alternatively, memory 1412 may be integrated with processor 1411, for example, within a single chip. Memory 1412 may store program code for executing the technical solutions of the embodiments of the present application, and execution is controlled by processor 1411. The various computer program codes executed may also be considered drivers for processor 1411.

[0440] Figure 14 shows only one memory and one processor. In an actual terminal device, there may be multiple processors and multiple memories. The memory may also be referred to as a storage medium or a storage device. The memory may be a storage element on the same chip as the processor, i.e., an on-chip storage element, or an independent storage element, which is not limited in the present embodiment.

[0441] The transceiver 1413 can be used to support the reception or transmission of radio frequency signals between the communication device and the terminal. The transceiver 1413 can be connected to the antenna 1415. The transceiver 1413 includes a transmitter Tx and a receiver Rx. Specifically, one or more antennas 1415 can receive radio frequency signals. The receiver Rx of the transceiver 1413 is used to receive the radio frequency signal from the antenna, convert the radio frequency signal into a digital baseband signal or a digital intermediate frequency signal, and provide the digital baseband signal or digital intermediate frequency signal to the processor 1411 so that the processor 1411 can further process the digital baseband signal or digital intermediate frequency signal, such as demodulation and decoding. In addition, the transmitter Tx in the transceiver 1413 is also used to receive a modulated digital baseband signal or digital intermediate frequency signal from the processor 1411, convert the modulated digital baseband signal or digital intermediate frequency signal into a radio frequency signal, and transmit the radio frequency signal through one or more antennas 1415. Specifically, the receiver Rx can selectively perform one or more stages of down-mixing and analog-to-digital conversion on the RF signal to obtain a digital baseband signal or a digital intermediate frequency signal. The order of the down-mixing and analog-to-digital conversion processes is adjustable. The transmitter Tx can selectively perform one or more stages of up-mixing and digital-to-analog conversion on the modulated digital baseband signal or digital intermediate frequency signal to obtain a RF signal. The order of the up-mixing and digital-to-analog conversion processes is adjustable. The digital baseband signal and the digital intermediate frequency signal may be collectively referred to as digital signals.

[0442] The transceiver 1413 may also be referred to as a transceiver module, a transceiver, a transceiver device, etc. Optionally, a device in the transceiver module that implements a receiving function may be referred to as a receiving unit, and a device in the transceiver module that implements a transmitting function may be referred to as a transmitting unit. That is, the transceiver module includes a receiving unit and a transmitting unit. The receiving unit may also be referred to as a receiver, an input port, a receiving circuit, etc., and the transmitting unit may be referred to as a transmitter, a transmitter, or a transmitting circuit, etc.

[0443] It should be noted that the communication device 1400 shown in Figure 14 can be specifically used to implement the steps implemented by the first communication device or wireless access device in the aforementioned method embodiment, and to achieve the corresponding technical effects of the network device. The specific implementation methods of the communication device 1400 shown in Figure 14 can refer to the description in the aforementioned method embodiment, and will not be repeated here.

[0444] Please refer to FIG15 , which is a schematic structural diagram of the communication device involved in the above-mentioned embodiment provided in an embodiment of the present application.

[0445] It can be understood that the communication device 150 includes, for example, modules, units, elements, circuits, or interfaces, which are appropriately configured together to perform the technical solutions provided in this application. The communication device 150 may be the AI ​​training unit or AI reasoning unit described above, or it may be a component (such as a chip) in these devices, used to implement the method described in the following method embodiment. The communication device 150 includes one or more processors 151. The processor 151 may be a general-purpose processor or a dedicated processor, etc. For example, it may be a baseband processor or a central processing unit. The baseband processor can be used to process communication protocols and communication data, and the central processing unit can be used to control the communication device (such as a RAN node, terminal, or chip, etc.), execute software programs, and process data of software programs.

[0446] Optionally, in one design, the processor 151 may include a program 153 (sometimes also referred to as code or instructions), which may be executed on the processor 151 to cause the communication device 150 to perform the methods described in the following embodiments. In yet another possible design, the communication device 150 includes circuitry (not shown in FIG15 ).

[0447] Optionally, the communication device 150 may include one or more memories 152 on which a program 154 (sometimes also referred to as code or instructions) is stored. The program 154 can be run on the processor 151 so that the communication device 150 executes the method described in the above method embodiment.

[0448] Optionally, the processor 151 and / or the memory 152 may include an AI module 157, 1511, which is used to implement AI-related functions. The AI ​​module can be implemented through software, hardware, or a combination of software and hardware. For example, the AI ​​module may include a wireless intelligent control (RIC) module. For example, the AI ​​module may be a near real-time RIC or a non-real-time RIC.

[0449] Optionally, data may be stored in the processor 151 and / or the memory 152. The processor and the memory may be provided separately or integrated together.

[0450] Optionally, the communication device 150 may further include a transceiver 155 and / or an antenna 156. The processor 151 may also be referred to as a processing module, which controls the communication device (e.g., a RAN node or terminal). The transceiver 155 may also be referred to as a transceiver module, a transceiver, a transceiver circuit, or a transceiver, and is configured to implement the transceiver functions of the communication device through the antenna 156.

[0451] The transceiver module 1102 shown in FIG11 may be a communication interface, which may be the transceiver 155 in FIG15 , which may include an input interface and an output interface. Alternatively, the transceiver 155 may be a transceiver circuit, which may include an input interface circuit and an output interface circuit.

[0452] An embodiment of the present application also provides a computer-readable storage medium, which is used to store one or more computer-executable instructions. When the computer-executable instructions are executed by a processor, the processor executes the method described in the possible implementation methods of the AI ​​training unit or AI reasoning unit in the aforementioned embodiments.

[0453] An embodiment of the present application also provides a computer program product (or computer program). When the computer program product is executed by the processor, the processor executes the method of possible implementation of the above-mentioned AI training unit or AI reasoning unit.

[0454] An embodiment of the present application also provides a chip system, which includes at least one processor for supporting a communication device to implement the functions involved in the above-mentioned implementation method. Optionally, the chip system also includes an interface circuit, which provides program instructions and / or data to the at least one processor. In one possible design, the chip system may also include a memory for storing program instructions and data necessary for the communication device. The chip system may be composed of a chip, or may include a chip and other discrete devices, wherein the communication device may specifically be an AI training unit or an AI reasoning unit in the aforementioned method embodiment.

[0455] An embodiment of the present application also provides a communication system, which includes the AI ​​training unit and AI reasoning unit in any of the above embodiments.

[0456] Optionally, the communication system further includes a terminal device, or the AI ​​reasoning unit may be a terminal device.

[0457] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0458] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0459] In addition, the functional units in the various embodiments of the present application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the contributing part or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present application. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

Claims

1. A communication method, characterized in that: include: Determine first configuration information, where the first configuration information is used to configure a communication connection for data transmission, where the data transmission is the transmission of service data of a communication management service between an artificial intelligence AI training unit and an AI reasoning unit, and the communication management service is used to manage a wireless access communication service between a terminal device and a wireless access device; the first configuration information includes an identifier of the communication connection, and identifiers of one or more quality of service flows QoS flow in the communication connection; Send the first configuration information.

2. The method according to claim 1, characterized in that: The method further comprises: First request information is received, where the first request information is used to request the first configuration information.

3. The method according to claim 2, characterized in that The first request information includes at least one of the following: The identifier of the AI ​​application scenario supported by the AI ​​reasoning unit, the requested AI service type identifier, the model identifier corresponding to the requested AI model, and the identifier of the AI ​​reasoning unit.

4. The method according to claim 3, characterized in that The AI ​​scenarios supported by the AI ​​inference unit meet any of the following conditions: The AI ​​reasoning unit is a distributed unit DU or a module in the DU, and the AI ​​scenarios supported by the AI ​​reasoning unit include at least one of a single-user medium access control SU MAC dictionary, a multi-user MU pairing dictionary, a multi-cell coordinated scheduling dictionary, and a low-speed channel map; The AI ​​inference unit is a terminal device or a module in the terminal device, and the AI ​​scenario supported by the AI ​​inference unit includes at least one of an interference spectrum, a beam spectrum, and a smart channel state information CSI; The AI ​​reasoning unit is a centralized unit CU or a module in the CU, and the AI ​​scenarios supported by the AI ​​reasoning unit include at least one of smart grid, smart load balancing, and smart energy saving.

5. The method according to any one of claims 1 to 4, characterized in that: The first configuration information also includes at least one of the following: Quality of service (QoS) information of one or more QoS flows in the communication connection, and an identifier of the AI ​​training unit.

6. The method according to any one of claims 1 to 5, characterized in that: The determining of the first configuration information comprises: The first configuration information is determined based on at least one of the following: The identifier of the AI ​​application scenario corresponding to the business data, the identifier of the AI ​​service type corresponding to the communication management business, and the model identifier of the AI ​​model corresponding to the AI ​​model information contained in the business data.

7. The method according to any one of claims 1 to 6, characterized in that: After sending the first configuration information, the method further includes: Sending second configuration information, wherein the second configuration information includes configuration information of N QoS flows established in the communication connection, where N is a positive integer; wherein the second configuration information includes at least one of the following: The identifier of the communication connection, the N identifiers corresponding to the N QoS flows, the quality of service QoS information of the N QoS flows, and the identifier of the AI ​​reasoning unit.

8. The method according to claim 7, characterized in that The method further comprises: Second request information is received, where the second request information is used to request the second configuration information; wherein the second request information includes an identifier of the communication connection.

9. The method according to claim 7 or 8, characterized in that: The method further comprises: Send first indication information, where the first indication information is used to indicate to delete at least one QoS flow among the N QoS flows.

10. The method according to claim 9, characterized in that Before sending the first indication information, the method further includes: A third request information is received, where the third request information is used to request deletion of the at least one QoS flow.

11. The method according to any one of claims 1 to 10, characterized in that: The method further comprises: Sending second indication information, where the second indication information is used to indicate releasing the communication connection.

12. The method according to claim 11, characterized in that The method further comprises: Fourth request information is received, where the fourth request information is used to request to release the communication connection.

13. A communication method, characterized in that: include: Receive first configuration information, wherein the first configuration information is used to configure a communication connection for data transmission, wherein the data transmission is the transmission of business data of a communication management service performed between an artificial intelligence AI training unit and an AI reasoning unit, wherein the communication management service is used to manage a terminal A wireless access communication service between a terminal device and a wireless access device; the first configuration information includes an identifier of the communication connection, and an identifier of one or more quality of service flows QoS flow in the communication connection; The service data is transmitted in the communication connection based on the first configuration information.

14. The method according to claim 13, characterized in that The method further comprises: Send first request information, where the first request information is used to request the first configuration information.

15. The method according to claim 14, characterized in that The first request information includes at least one of the following: The identifier of the AI ​​application scenario supported by the AI ​​reasoning unit, the requested AI service type identifier, the model identifier corresponding to the requested AI model, and the identifier of the AI ​​reasoning unit.

16. The method according to claim 15, characterized in that The AI ​​scenarios supported by the AI ​​inference unit meet any of the following conditions: The AI ​​reasoning unit is a distributed unit DU or a module in the DU, and the AI ​​scenarios supported by the AI ​​reasoning unit include at least one of a single-user medium access control SU MAC dictionary, a multi-user MU pairing dictionary, a multi-cell coordinated scheduling dictionary, and a low-speed channel map; The AI ​​inference unit is a terminal device or a module in the terminal device, and the AI ​​scenario supported by the AI ​​inference unit includes at least one of an interference spectrum, a beam spectrum, and a smart channel state information CSI; The AI ​​reasoning unit is a centralized unit CU or a module in the CU, and the AI ​​scenarios supported by the AI ​​reasoning unit include at least one of smart grid, smart load balancing, and smart energy saving.

17. The method according to any one of claims 13 to 16, characterized in that: The first configuration information also includes at least one of the following: Quality of service (QoS) information of one or more QoS flows in the communication connection, and an identifier of the AI ​​training unit.

18. The method according to any one of claims 13 to 17, characterized in that After receiving the first configuration information, the method further includes: Receive second configuration information, where the second configuration information includes configuration information of N QoS flows established in the communication connection, where N is a positive integer; wherein the second configuration information includes at least one of the following: The identifier of the communication connection, the N identifiers corresponding to the N QoS flows, the quality of service QoS information of the N QoS flows, and the identifier of the AI ​​reasoning unit.

19. The method according to claim 18, characterized in that The method further comprises: Sending second request information, where the second request information is used to request the second configuration information; wherein the second request information includes an identifier of the communication connection.

20. The method according to claim 18 or 19, characterized in that The method further comprises: First indication information is received, where the first indication information is used to indicate to delete at least one QoS flow among the N QoS flows.

21. The method according to claim 20, characterized in that Before receiving the first indication information, the method further includes: Sending third request information, where the third request information is used to request deletion of the at least one QoS flow.

22. The method according to any one of claims 13 to 21, characterized in that The method further comprises: Second indication information is received, where the second indication information is used to instruct to release the communication connection.

23. The method according to claim 22, characterized in that The method further comprises: Sending fourth request information, where the fourth request information is used to request to release the communication connection.

24. A communication method, characterized in that: include: The artificial intelligence AI training unit sends first configuration information, where the first configuration information is used to configure a communication connection for data transmission, where the data transmission is the transmission of service data of a communication management service between the AI ​​training unit and the AI ​​reasoning unit, and the communication management service is used to manage a wireless access communication service between a terminal device and a wireless access device; the first configuration information includes an identifier of the communication connection, and an identifier of one or more quality of service flows QoS flow in the communication connection; The AI ​​reasoning unit receives the first configuration information; The business data is transmitted between the AI ​​training unit and the AI ​​reasoning unit in the communication connection based on the first configuration information.

25. The method according to claim 24, characterized in that The method further comprises: The AI ​​reasoning unit sends a first request message to the AI ​​training unit, where the first request message is used to request the first configuration information; wherein the first request message includes at least one of the following: The identifier of the AI ​​application scenario supported by the AI ​​reasoning unit, the requested AI service type identifier, the model identifier corresponding to the requested AI model, and the identifier of the AI ​​reasoning unit.

26. The method according to claim 25, characterized in that The AI ​​scenarios supported by the AI ​​inference unit meet any of the following conditions: The AI ​​reasoning unit is a distributed unit DU or a module in the DU, and the AI ​​scenarios supported by the AI ​​reasoning unit include at least one of a single-user medium access control SU MAC dictionary, a multi-user MU pairing dictionary, a multi-cell coordinated scheduling dictionary, and a low-speed channel map; The AI ​​inference unit is a terminal device or a module in the terminal device, and the AI ​​scenario supported by the AI ​​inference unit includes at least one of an interference spectrum, a beam spectrum, and a smart channel state information CSI; The AI ​​reasoning unit is a centralized unit CU or a module in the CU, and the AI ​​scenarios supported by the AI ​​reasoning unit include at least one of smart grid, smart load balancing, and smart energy saving.

27. The method according to any one of claims 24 to 26, characterized in that The first configuration information also includes at least one of the following: Quality of service (QoS) information of one or more QoS flows in the communication connection, and an identifier of the AI ​​training unit.

28. A communication device, characterized in that: Comprising means for performing the method as claimed in any one of claims 1 to 23.

29. A communication device, characterized in that: The method comprises at least one processor coupled to a memory; the at least one processor is configured to execute the method according to any one of claims 1 to 23.

30. A communication system, characterized in that: including a first communication device and a second communication device; The first communication device is used to execute the method according to any one of claims 1 to 12, and the second communication device is used to execute the method according to any one of claims 13 to 23.

31. The communication system according to claim 30, characterized in that The second communication device is a terminal device, or the communication system also includes a terminal device.

32. A readable storage medium, characterized in that: The storage medium stores a computer program or an instruction. When the computer program or the instruction is executed by the communication device, the communication device implements the method according to any one of claims 1 to 27.

33. A computer program product, characterized in that When the computer program in the computer program product is executed by a communication device, the communication device is caused to implement the method according to any one of claims 1 to 27.

Images