Search

CN-122002630-A - Data transmission method, device, terminal, storage medium and program product

CN122002630ACN 122002630 ACN122002630 ACN 122002630ACN-122002630-A

Abstract

The application discloses a data transmission method, which comprises the steps that first equipment sends first information to a first terminal, wherein the first information is used for establishing one or more first sessions, the first sessions comprise one or more wireless carriers used for transmitting artificial intelligence or machine learning data with any size, the wireless carriers of the first sessions are marked by adopting marks of an artificial intelligence or machine learning model, and the first terminal directly accesses the artificial intelligence or machine learning data corresponding to the first marks in a first equipment side through the wireless carriers corresponding to the first marks for training or reasoning. The first terminal receives a first message and sends a second message to the first device, wherein the second message is used for representing that the first session establishment is completed, and the first device receives the second message. The application also discloses a first device, a first terminal, a second device, a fourth device, a computer readable storage medium and a computer program product.

Inventors

  • LI XIANG
  • SUN QI
  • LI NAN

Assignees

  • 中国移动通信有限公司研究院
  • 中国移动通信集团有限公司

Dates

Publication Date
20260508
Application Date
20241106

Claims (20)

  1. 1. A method of data transmission, for use with a first device, the method comprising: the method comprises the steps of sending a first message to a first terminal, wherein the first message is used for establishing one or more first sessions, the first session comprises one or more wireless carriers used for transmitting artificial intelligence or machine learning data with any size, the wireless carriers of the first session are marked by adopting marks of an artificial intelligence or machine learning model, and the first terminal directly accesses the artificial intelligence or machine learning data training or reasoning corresponding to the first mark in the first equipment side through the wireless carriers corresponding to the first mark; and receiving a second message sent by the first terminal, wherein the second message is used for representing that the first session establishment is completed.
  2. 2. The method according to claim 1, wherein the method further comprises: Establishing a first session for artificial intelligence or machine learning life cycle management for the first terminal, wherein the first session comprises first information, and the first information comprises quality requirements of artificial intelligence or machine learning training/reasoning, wireless connection service quality requirements, artificial intelligence or machine learning model information, base station identification where the artificial intelligence or machine learning model is located and wireless bearing information of artificial intelligence or machine learning data; Recording first information into a context, wherein the context comprises a context of a first terminal at a first equipment side and a first session context established for a first session; And allocating data radio bearer resources based on the first information.
  3. 3. The method according to claim 2, wherein the method further comprises: and sending the context to the second device so that the second device establishes an artificial intelligence or machine learning data transmission session for the first terminal based on the context.
  4. 4. The method according to claim 2, wherein the method further comprises: Based on the context, a transmission channel for artificial intelligence or machine learning data between the first device and the second device is established.
  5. 5. The method according to claim 1, wherein the method further comprises: Sensing artificial intelligence or machine learning capability of a terminal, wherein the terminal comprises a first terminal; a transmission session and radio bearer for artificial intelligence or machine learning data is established for a second terminal having artificial intelligence or machine learning capabilities.
  6. 6. The method of claim 1, wherein the first session comprises one or more of: A session identifier; an identification of the first terminal; identification of artificial intelligence or machine learning models; The processing mode of the model; Whether the artificial intelligence or machine learning data to be transmitted requires integrity protection or encryption; an integrity protection or encryption algorithm that can be employed by artificial intelligence or machine learning data requiring integrity protection or encryption; whether the artificial intelligence or machine learning data to be transmitted needs to be compressed or encoded; an artificial intelligence or machine learning data requiring compression or encoding can employ an encoding or compression method; Radio bearer information; Artificial intelligence or machine learning data.
  7. 7. The method according to claim 1, wherein the method further comprises: Updating the first session if the first session satisfies a first condition, wherein the first session satisfies the first condition includes one or more of: The session identification is adjusted; the identification of the first terminal is adjusted; The identification of the artificial intelligence or machine learning model is adjusted; adjusting artificial intelligence or machine learning data requiring integrity protection or encryption to be free of integrity protection or encryption; adjusting the artificial intelligence or machine learning data without integrity protection or encryption to require integrity protection or encryption; Adjusting artificial intelligence or machine learning data to be compressed or encoded to be free of compression or encoding; adjusting artificial intelligence or machine learning data that does not require compression or encoding to require compression or encoding; the integrity protection or encryption algorithm adopted by the artificial intelligence or machine learning data which needs the integrity protection or encryption is adjusted; The artificial intelligence or machine learning data to be compressed or encoded is adjusted by the adopted encoding or compression method; adjustment of radio bearer resources.
  8. 8. The method of claim 7, wherein the updating the first session comprises: the method comprises the steps of sending a first indication message to the first terminal, wherein the first indication message is used for indicating a first device to update a first bearing resource of artificial intelligence or machine learning data; And receiving a third message sent by the first terminal, wherein the third message is used for notifying the completion of the updating of the first bearing resource.
  9. 9. The method according to claim 1, wherein the method further comprises: the method comprises the steps of sending second indication information to the first terminal, wherein the second indication information is used for indicating to release the first session and release a second bearing resource of artificial intelligence or machine learning data; and receiving a fourth message sent by the first terminal, wherein the fourth message is used for notifying the first session and the second bearer resource release completion.
  10. 10. The method of claim 2, wherein the first session context comprises one or more of: Artificial intelligence or machine learning model identification; Artificial intelligence or machine learning model suppliers; artificial intelligence or machine learning model versions; artificial intelligence or machine learning model types; artificial intelligence or machine learning model size; Algorithm complexity of artificial intelligence or machine learning models; an artificial intelligence or machine learning model calculates resource requirements; An artificial intelligence or machine learning model training data volume; Training the parameter entering information by using an artificial intelligence or machine learning model; an artificial intelligence or machine learning model infers the amount of data; The artificial intelligence or machine learning model reasoning parameter information; terminal information associated with the first session; base station information associated with the first session.
  11. 11. The method according to claim 1, wherein the method further comprises: starting an artificial intelligence or machine learning model training life cycle management process, and executing artificial intelligence or machine learning model selection and model deployment; Collecting training data for the selected or to-be-deployed artificial intelligence or machine learning model; Receiving artificial intelligence or machine learning data sent by a terminal directly through a session or sent by a third device, wherein the session comprises the first session; Based on the artificial intelligence or machine learning data, artificial intelligence or machine learning model training is performed.
  12. 12. The method according to claim 1, wherein the method further comprises: Receiving a third indication message sent by fourth equipment, wherein the third indication message is used for indicating the establishment of an artificial intelligence or machine learning model life cycle task, and the third indication message comprises model identification, model size, model training or reasoning, artificial intelligence or machine learning model life cycle task performance requirements, model data acquisition configuration information and acquired terminal information; Sending a fifth message to the fourth device, wherein the fifth message is used for notifying completion of the establishment of the life cycle task of the artificial intelligence or machine learning model; Receiving artificial intelligence or machine learning data sent by a terminal directly through a session or sent by a third device, wherein the session comprises the first session; And sending the collected artificial intelligence or machine learning data to the fourth equipment so that the fourth equipment can perform artificial intelligence or machine learning model training based on the collected artificial intelligence or machine learning data.
  13. 13. A data transmission method, applied to a first terminal, the method comprising: The method comprises the steps of receiving a first message sent by a first device, wherein the first message is used for establishing one or more first sessions, the first session comprises one or more wireless carriers used for transmitting artificial intelligence or machine learning data with any size, the wireless carriers of the first session are marked by adopting marks of an artificial intelligence or machine learning model, and the first terminal directly accesses the artificial intelligence or machine learning data training or reasoning corresponding to the first mark in the first device side through the wireless carriers corresponding to the first mark; and a second message sent to the first device, wherein the second message is used for characterizing that the first session establishment is completed.
  14. 14. The method of claim 13, wherein the method further comprises: Receiving a first indication message sent by the first device, wherein the first indication message is used for indicating the first device to update a first bearing resource of artificial intelligence or machine learning data; And sending a third message to the first terminal, wherein the third message is used for notifying the first bearing resource to finish updating.
  15. 15. The method of claim 13, wherein the method further comprises: Receiving second indication information sent by the first device, wherein the second indication information is used for indicating to release the first session and release a second bearing resource of artificial intelligence or machine learning data; And sending a fourth message to the first device, wherein the fourth message is used for notifying the first session and the second bearer resource release is completed.
  16. 16. A data transmission method, applied to a second device, the method comprising: Receiving a context sent by a first device, wherein the context comprises a context of a first terminal at a first device side and a first session context established for a first session between the first device and the first terminal, the first session comprises one or more wireless bearers used for transmitting artificial intelligence or machine learning data with any size, the wireless bearers of the first session are marked by adopting marks of an artificial intelligence or machine learning model, and the first terminal directly accesses the artificial intelligence or machine learning data training or reasoning corresponding to the first mark in the first device side through the wireless bearers corresponding to the first mark; Based on the context, establishing an artificial intelligence or machine learning data transmission session for the first terminal, establishing a transmission channel between the first device and the second device for artificial intelligence or machine learning data, and deploying/activating an artificial intelligence or machine learning model used by the first device.
  17. 17. A data transmission method, applied to a fourth device, the method comprising: The method comprises the steps of sending a third indication message to first equipment, wherein the third indication message is used for indicating the establishment of an artificial intelligence or machine learning model life cycle task, and the third indication message comprises model identification, model size, model training or reasoning, artificial intelligence or machine learning model life cycle task performance requirements, model data acquisition configuration information and acquired terminal information; receiving a fifth message sent by the first device, wherein the fifth message is used for notifying completion of the establishment of the life cycle task of the artificial intelligence or machine learning model; Receiving artificial intelligence or machine learning data sent by the first device, wherein the artificial intelligence or machine learning data is directly sent by a terminal through a session or the artificial intelligence or machine learning data sent by a third device, and the session comprises the first session; based on the collected artificial intelligence or machine learning data, artificial intelligence or machine learning model training is performed.
  18. 18. A first device, the first device comprising: The system comprises a first terminal, a first sending module, a first receiving module, a second sending module and a second sending module, wherein the first message is used for establishing one or more first sessions, the first sessions comprise one or more wireless carriers for transmitting artificial intelligence or machine learning data with any size, the wireless carriers of the first sessions are marked by adopting marks of an artificial intelligence or machine learning model, and the first terminal directly accesses the artificial intelligence or machine learning data corresponding to the first marks in the first equipment side through the wireless carriers corresponding to the first marks for training or reasoning; And the first receiving module is used for receiving a second message sent by the first terminal, wherein the second message is used for representing that the first session establishment is completed.
  19. 19. A first terminal, the first terminal comprising: The system comprises a first device side, a second device side, a first receiving module, a second receiving module, a first terminal and a second terminal, wherein the first device side is used for receiving a first message sent by the first device, the first message is used for establishing one or more first sessions, the first session comprises one or more wireless carriers for transmitting artificial intelligence or machine learning data with any size, the wireless carriers of the first session are marked by adopting marks of an artificial intelligence or machine learning model, and the first terminal directly accesses the artificial intelligence or machine learning data corresponding to the first marks in the first device side through the wireless carriers corresponding to the first marks for training or reasoning; and the second sending module is used for sending a second message to the first equipment, wherein the second message is used for representing that the first session establishment is completed.
  20. 20. A second device, the second device comprising: The system comprises a first receiving module, a third receiving module, a first terminal and a second receiving module, wherein the first receiving module is used for receiving a context sent by a first device, the context comprises a context of a first terminal at the first device side and a first session context established for a first session between the first device and the first terminal, the first session comprises one or more wireless bearers used for transmitting artificial intelligence or machine learning data with any size, the wireless bearers of the first session are marked by an identification of an artificial intelligence or machine learning model, and the first terminal directly accesses the artificial intelligence or machine learning data corresponding to the first identification in the first device side through the wireless bearers corresponding to the first identification to train or infer; And the third processing module is used for establishing an artificial intelligence or machine learning data transmission session for the first terminal, establishing a transmission channel between the first device and the second device for the artificial intelligence or machine learning data and deploying/activating an artificial intelligence or machine learning model used by the first device based on the context.

Description

Data transmission method, device, terminal, storage medium and program product Technical Field The present application relates to the field of communications, but is not limited to, and in particular to a data transmission method, a first device, a first terminal, a second device, a fourth device, a computer readable storage medium and a computer program product. Background At present, artificial intelligence (ARTIFICIAL INTELLIGENCE, AI) data between a terminal and a base station can be transmitted in two modes, namely, wireless connection control plane signaling transmission and wireless connection user plane signaling transmission. For wireless connection control plane signaling, 3GPP specifies that the control signaling protocol data unit (protocol data unit, PDU) session transmission upper limit is 9000b, the AI/machine learning (MACHINE LEARNING, ML) model transmission upper limit is 45KB, and AI/ML model transmission with a size of tens to hundreds of MB levels cannot be satisfied. For wireless connection user plane transmission, in mobile communication Network, the data transmission of terminal service is established by Core Network (CN) and radio access Network establishes radio bearer, and in the aspect of Session management mode, PDU Session is established and maintained by CN. For the AI for radio access network (Radio Access Network, RAN) scenario, AI calculation in the RAN domain is usually required to meet low latency requirements, for example, at MS level, therefore, the processing of RAN domain AI data by the CN will face real-time risks of data processing, resulting in increased latency of data processing, resulting in data buffering, data accumulation and overflow, reduced network reliability, and other problems. In summary, the manner of transmitting AI data provided in the related art cannot meet the requirements, and therefore, there is a need to provide a new transmission manner for transmitting AI data between a terminal and a base station. Disclosure of Invention The application provides a data transmission method, a first device, a first terminal, a second device, a fourth device, a computer readable storage medium and a computer program product, and provides a novel transmission mode for transmitting AI data between a terminal and a base station. The technical scheme of the embodiment of the application is realized as follows: In a first aspect, an embodiment of the present application provides a data transmission method, applied to a first device, where the method includes: the method comprises the steps of sending a first message to a first terminal, wherein the first message is used for establishing one or more first sessions, the first session comprises one or more wireless carriers used for transmitting artificial intelligence or machine learning data with any size, the wireless carriers of the first session are marked by adopting marks of an artificial intelligence or machine learning model, and the first terminal directly accesses the artificial intelligence or machine learning data training or reasoning corresponding to the first mark in the first equipment side through the wireless carriers corresponding to the first mark; and receiving a second message sent by the first terminal, wherein the second message is used for representing that the first session establishment is completed. In a second aspect, an embodiment of the present application provides a data transmission method, applied to a first terminal, where the method includes: The method comprises the steps of receiving a first message sent by a first device, wherein the first message is used for establishing one or more first sessions, the first session comprises one or more wireless carriers used for transmitting artificial intelligence or machine learning data with any size, the wireless carriers of the first session are marked by adopting marks of an artificial intelligence or machine learning model, and the first terminal directly accesses the artificial intelligence or machine learning data training or reasoning corresponding to the first mark in the first device side through the wireless carriers corresponding to the first mark; and a second message sent to the first device, wherein the second message is used for characterizing that the first session establishment is completed. In a third aspect, an embodiment of the present application provides a data transmission method, applied to a second device, where the method includes: Receiving a context sent by a first device, wherein the context comprises a context of a first terminal at a first device side and a first session context established for a first session between the first device and the first terminal, the first session comprises one or more wireless bearers used for transmitting artificial intelligence or machine learning data with any size, the wireless bearers of the first session are marked by adopting marks of an artificial intelligence or machine