WO2024021131A1 - Drx周期确定方法、装置 - Google Patents

Drx周期确定方法、装置 Download PDF

Info

Publication number
WO2024021131A1
WO2024021131A1 PCT/CN2022/109260 CN2022109260W WO2024021131A1 WO 2024021131 A1 WO2024021131 A1 WO 2024021131A1 CN 2022109260 W CN2022109260 W CN 2022109260W WO 2024021131 A1 WO2024021131 A1 WO 2024021131A1
Authority
WO
WIPO (PCT)
Prior art keywords
drx cycle
model
terminal device
service
network side
Prior art date
Application number
PCT/CN2022/109260
Other languages
English (en)
French (fr)
Inventor
牟勤
乔雪梅
李松
Original Assignee
北京小米移动软件有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京小米移动软件有限公司 filed Critical 北京小米移动软件有限公司
Priority to PCT/CN2022/109260 priority Critical patent/WO2024021131A1/zh
Priority to CN202280002609.5A priority patent/CN117796045A/zh
Publication of WO2024021131A1 publication Critical patent/WO2024021131A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W52/00—Power management, e.g. TPC [Transmission Power Control], power saving or power classes
    • H04W52/02—Power saving arrangements
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W8/00—Network data management
    • H04W8/22—Processing or transfer of terminal data, e.g. status or physical capabilities
    • H04W8/24—Transfer of terminal data

Definitions

  • the present disclosure relates to the field of communication technology, and in particular to a discontinuous reception (Discontinuous Reception, DRX) cycle determination method, device, equipment and storage medium.
  • DRX discontinuous Reception
  • the fifth generation mobile communication technology (5G) network can use the DRX discontinuous reception mechanism to reduce the energy consumption of terminal equipment. Reduce the energy consumption of terminal equipment by configuring long and short sleep cycles for the terminal equipment. For situations where the fixed sleep time length set by the traditional discontinuous reception mechanism results in a large data transmission delay, artificial intelligence methods can be used to predict the arrival time of data packets at the terminal device to reduce the energy consumption of the terminal device. For example, the Long Short-Term Memory (LSTM) network can be used to configure the DRX cycle of the terminal device. However, only using the same AI model to predict the arrival time of terminal device data packets makes the DRX cycle prediction inaccurate.
  • LSTM Long Short-Term Memory
  • the present disclosure proposes a DRX cycle determination method, device, equipment and storage medium to receive the DRX cycle determined based on the AI model corresponding to the set of business types running on the terminal equipment, and reduce the use of the same AI model for DRX cycle prediction by different businesses, so that In the case of inaccurate DRX cycle determination, the accuracy of DRX cycle determination can be improved.
  • An embodiment of the present disclosure proposes a method for determining a discontinuous reception DRX cycle.
  • the method is executed by a terminal device.
  • the method includes:
  • the network side device Receives the first DRX cycle sent by the network side device, where the first DRX cycle is determined based on an artificial intelligence (Artificial Intelligence, AI) model, and the AI model corresponds to a set of service types run by the terminal device.
  • AI Artificial Intelligence
  • the receiving the first DRX cycle sent by the network side device includes:
  • the receiving the first DRX cycle sent by the network side device includes:
  • the AI model In response to the AI model being deployed on the terminal device, the AI model is used to predict the DRX cycle for the set of service types run by the terminal device and determine the second DRX cycle;
  • using the AI model to predict the DRX cycle for the set of service types run by the terminal device and determining the second DRX cycle includes:
  • the AI model corresponding to the service type set is used to predict the DRX cycle and determine the second DRX cycle.
  • using an AI model corresponding to the service type set to predict the DRX cycle and determine the second DRX cycle includes:
  • the AI model corresponding to the service type is used to perform DRX cycle prediction and determine the second DRX cycle.
  • using an AI model corresponding to the service type set to predict the DRX cycle and determine the second DRX cycle includes:
  • the AI model corresponding to the at least two service types is used to perform DRX cycle prediction and determine the second DRX cycle.
  • using an AI model corresponding to the service type set to predict the DRX cycle and determine the second DRX cycle includes:
  • the AI model corresponding to each of the at least two business types is used to determine the respective business types.
  • the fifth DRX cycle corresponding to each business type is described below;
  • the AI model is not used for DRX cycle prediction.
  • the method further includes:
  • the method further includes:
  • the AI model is a model trained based on the business type corresponding to the AI model.
  • Another aspect of the present disclosure provides a method for determining a DRX cycle, which is executed by a network side device.
  • the method includes:
  • the method before sending the first DRX cycle to the terminal device, the method further includes:
  • the AI model In response to the AI model being deployed on the network side device, the AI model is used to predict the DRX cycle for the set of service types run by the terminal device, and generate a third DRX cycle;
  • the first DRX cycle is determined based on the third DRX cycle.
  • using the AI model to predict the DRX cycle for the set of service types run by the terminal device and determining the third DRX cycle includes:
  • the AI model corresponding to the service type set is used to predict the DRX cycle and determine the third DRX cycle.
  • using an AI model corresponding to the service type set to predict the DRX cycle and determine the third DRX cycle includes:
  • the AI model corresponding to the service type is used to perform DRX cycle prediction and determine the third DRX cycle.
  • using an AI model corresponding to the service type set to predict the DRX cycle and determine the third DRX cycle includes:
  • the AI model corresponding to the at least two service types is used to perform DRX cycle prediction and determine the third DRX cycle.
  • using an AI model corresponding to the service type set to predict the DRX cycle and determine the third DRX cycle includes:
  • the AI model corresponding to each of the at least two business types is used to determine the respective business types.
  • the fourth DRX cycle corresponding to each business type is described below;
  • the AI model is not used for DRX cycle prediction.
  • the method before sending the first DRX cycle to the terminal device, the method further includes:
  • the first DRX cycle is determined based on the second DRX cycle.
  • the method further includes:
  • the method further includes:
  • the AI model is a model trained based on the business type corresponding to the AI model.
  • Another aspect of the present disclosure provides a method for determining a DRX cycle, which is executed by a terminal device.
  • the method includes:
  • using the AI model to predict the DRX cycle for the set of service types run by the terminal device and determining the second DRX cycle includes:
  • the AI model corresponding to the service type set is used to predict the DRX cycle and determine the second DRX cycle.
  • using an AI model corresponding to the service type set to predict the DRX cycle and determine the second DRX cycle includes:
  • the AI model corresponding to the service type is used to perform DRX cycle prediction and determine the second DRX cycle.
  • using an AI model corresponding to the service type set to predict the DRX cycle and determine the second DRX cycle includes:
  • the AI model corresponding to the at least two service types is used to perform DRX cycle prediction and determine the second DRX cycle.
  • using an AI model corresponding to the service type set to predict the DRX cycle and determine the second DRX cycle includes:
  • the AI model corresponding to each of the at least two business types is used to determine the respective business types.
  • the fifth DRX cycle corresponding to each business type is described below;
  • the AI model is not used for DRX cycle prediction.
  • the method further includes:
  • the method further includes:
  • Another aspect of the present disclosure provides a method for determining a DRX cycle, which is executed by a network side device.
  • the method includes:
  • a DRX cycle determination device which is provided on the terminal side and includes:
  • a receiving module configured to receive the first DRX cycle sent by the network side device, where the first DRX cycle is determined based on an artificial intelligence AI model, and the AI model corresponds to a set of service types run by the terminal device.
  • Another aspect of the present disclosure provides a DRX cycle determination device, which is provided on the network side and includes:
  • a sending module configured to send a first DRX cycle to the terminal device, where the first DRX cycle is determined based on an artificial intelligence AI model, and the AI model corresponds to a set of service types run by the terminal device.
  • a DRX cycle determination device which is provided on the terminal side and includes:
  • a determination module configured to respond to the AI model being deployed on the terminal device, using the AI model to predict the DRX cycle for the set of service types run by the terminal device, and determine the second DRX cycle;
  • a sending module configured to send the second DRX cycle to the network side device.
  • Another aspect of the present disclosure provides a DRX cycle determination device, which is provided on the network side and includes:
  • a receiving module configured to respond to the AI model being deployed on the terminal device and receive the second DRX cycle sent by the terminal device and determined by the terminal device using the AI model.
  • the device includes a processor and a memory.
  • a computer program is stored in the memory.
  • the processor executes the computer program stored in the memory, so that the The device performs the method proposed in the embodiment of the above aspect.
  • the device includes a processor and a memory.
  • a computer program is stored in the memory.
  • the processor executes the computer program stored in the memory so that the The device performs the method proposed in the above embodiment of another aspect.
  • a communication device provided by another embodiment of the present disclosure includes: a processor and an interface circuit
  • the interface circuit is used to receive code instructions and transmit them to the processor
  • the processor is configured to run the code instructions to perform the method proposed in the embodiment of one aspect.
  • a communication device provided by another embodiment of the present disclosure includes: a processor and an interface circuit
  • the interface circuit is used to receive code instructions and transmit them to the processor
  • the processor is configured to run the code instructions to perform the method proposed in another embodiment.
  • a computer-readable storage medium provided by an embodiment of another aspect of the present disclosure is used to store instructions. When the instructions are executed, the method proposed by the embodiment of the present disclosure is implemented.
  • a computer-readable storage medium provided by an embodiment of another aspect of the present disclosure is used to store instructions. When the instructions are executed, the method proposed by the embodiment of another aspect is implemented.
  • the first DRX cycle is determined based on the artificial intelligence AI model, and the AI model is consistent with the service type run by the terminal device.
  • the first DRX cycle is determined based on the AI model corresponding to the set of service types run by the terminal device, it reduces the situation where different services use the same AI model to predict the DRX cycle, resulting in inaccurate DRX cycle determination.
  • the accuracy of DRX cycle determination can be improved.
  • This disclosure provides a processing method for the situation of "DRX cycle determination" to receive the DRX cycle determined based on the AI model corresponding to the set of service types running on the terminal equipment, and reduce the use of the same AI model for DRX cycle prediction by different services. In situations where the DRX cycle determination is inaccurate, the accuracy of the DRX cycle determination can be improved.
  • Figure 1 is a schematic flowchart of a DRX cycle determination method provided by an embodiment of the present disclosure
  • Figure 2 is a schematic flowchart of a DRX cycle determination method provided by another embodiment of the present disclosure.
  • Figure 3 is a schematic flowchart of a DRX cycle determination method provided by yet another embodiment of the present disclosure.
  • Figure 4 is a schematic flowchart of a DRX cycle determination method provided by yet another embodiment of the present disclosure.
  • Figure 5 is a schematic flowchart of a DRX cycle determination method provided by yet another embodiment of the present disclosure.
  • Figure 6 is a schematic flowchart of a DRX cycle determination method provided by yet another embodiment of the present disclosure.
  • Figure 7 is a schematic flowchart of a DRX cycle determination method provided by yet another embodiment of the present disclosure.
  • Figure 8 is a schematic flowchart of a DRX cycle determination method provided by yet another embodiment of the present disclosure.
  • Figure 9 is a schematic flowchart of a DRX cycle determination method provided by yet another embodiment of the present disclosure.
  • Figure 10 is a schematic flowchart of a DRX cycle determination method provided by yet another embodiment of the present disclosure.
  • Figure 11 is a schematic flowchart of a DRX cycle determination method provided by another embodiment of the present disclosure.
  • Figure 12 is a schematic flowchart of a DRX cycle determination method provided by yet another embodiment of the present disclosure.
  • Figure 13 is a schematic flowchart of a DRX cycle determination method provided by yet another embodiment of the present disclosure.
  • Figure 14 is a schematic flowchart of a DRX cycle determination method provided by yet another embodiment of the present disclosure.
  • Figure 15 is a schematic flowchart of a DRX cycle determination method provided by another embodiment of the present disclosure.
  • Figure 16 is a schematic flowchart of a DRX cycle determination method provided by yet another embodiment of the present disclosure.
  • Figure 17 is a schematic flowchart of a DRX cycle determination method provided by yet another embodiment of the present disclosure.
  • Figure 18 is a schematic flowchart of a DRX cycle determination method provided by yet another embodiment of the present disclosure.
  • Figure 19 is a schematic flowchart of a DRX cycle determination method provided by yet another embodiment of the present disclosure.
  • Figure 20 is a schematic flowchart of a DRX cycle determination method provided by yet another embodiment of the present disclosure.
  • Figure 21 is a schematic structural diagram of a DRX cycle determination device provided by an embodiment of the present disclosure.
  • Figure 22 is a schematic structural diagram of a DRX cycle determination device provided by another embodiment of the present disclosure.
  • Figure 23 is a schematic structural diagram of a DRX cycle determination device provided by another embodiment of the present disclosure.
  • Figure 24 is a schematic structural diagram of a DRX cycle determination device provided by another embodiment of the present disclosure.
  • Figure 25 is a schematic structural diagram of a DRX cycle determination device provided by another embodiment of the present disclosure.
  • Figure 26 is a schematic structural diagram of a DRX cycle determination device provided by another embodiment of the present disclosure.
  • Figure 27 is a block diagram of a terminal device provided by an embodiment of the present disclosure.
  • Figure 28 is a block diagram of a network side device provided by an embodiment of the present disclosure.
  • first, second, third, etc. may be used to describe various information in the embodiments of the present disclosure, the information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other.
  • first information may also be called second information, and similarly, the second information may also be called first information.
  • the words "if” and “if” as used herein may be interpreted as “when” or “when” or “in response to determining.”
  • the fifth generation mobile communication technology (5G) network can use the DRX discontinuous reception mechanism to reduce the energy consumption of terminals, and achieve power saving by configuring long and short sleep cycles for the terminal.
  • the traditional discontinuous reception mechanism usually sets a fixed sleep time length. This method cannot adapt to changes in data packet arrival time and may cause large delays.
  • the service type includes, for example, an online game service type, a video service type, a web browsing service type, etc.
  • different business types correspond to different data packet reaching rules.
  • Recurrent Neural Network in artificial intelligence has shown enormous results in predicting future values of a given sequence.
  • LSTM is a popular RNN, which is specially used to learn the long-term dependence of a sequence to predict the future value of the sequence.
  • Long-term dependencies refer to sequences where the predicted output value depends on a long sequence of previous input values, rather than a single previous input value.
  • the jitter delay sequence of historical data packet arrivals can be used as training data to train an LSTM model, and then the trained model can be used to predict the next data packet when each data packet arrives. Arrival jitter delay value. This method can achieve better performance in most cases, making the average prediction error smaller.
  • the base station can use the LSTM network to predict the arrival time of the next data packet of the terminal device when each data packet arrives, and then configure the DRX sleep cycle of the terminal device based on the prediction result. Ensure that the terminal device wakes up before the data packet arrives and sleeps when no data packet arrives.
  • Figure 1 is a schematic flowchart of a DRX cycle determination method provided by an embodiment of the present disclosure. The method is executed by a terminal device. As shown in Figure 1, the method may include the following steps:
  • Step 101 Receive the first DRX cycle sent by the network side device, where the first DRX cycle is determined based on the artificial intelligence AI model, and the AI model corresponds to the set of service types run by the terminal device.
  • the terminal device may be a device that provides voice and/or data connectivity to the user.
  • Terminal devices can communicate with one or more core networks via RAN (Radio Access Network).
  • Terminal devices can be IoT terminals, such as sensor devices, mobile phones (or "cellular" phones) and devices with The computer of the Internet of Things terminal, for example, can be a fixed, portable, pocket-sized, handheld, computer-built-in or vehicle-mounted device.
  • station STA
  • subscriber unit subscriber unit
  • subscriber station subscriber station
  • mobile station mobile station
  • remote station remote station
  • access terminal access terminal
  • user device user terminal
  • user agent useragent
  • the terminal device may also be a device of an unmanned aerial vehicle.
  • the terminal device may also be a vehicle-mounted device, for example, it may be a driving computer with wireless communication function, or a wireless terminal connected to an external driving computer.
  • the terminal device may also be a roadside device, for example, it may be a street light, a signal light or other roadside device with wireless communication function.
  • the first DRX cycle is a cycle determined by the network side and sent to the terminal device.
  • the first of the first DRX cycles is only used to distinguish it from other DRX cycles and does not specifically refer to a fixed cycle.
  • the terminal device when the terminal device receives the first DRX cycle sent by the network side device, the terminal device can receive the data packet based on the first DRX cycle to ensure data transmission delay. , reduce the energy consumption of terminal equipment.
  • receiving the first DRX cycle sent by the network side device includes:
  • the network side device In response to the AI model being deployed on the network side device, the network side device that receives the transmission from the network side device adopts the first DRX cycle determined by the AI model.
  • receiving the first DRX cycle sent by the network side device includes:
  • the AI model In response to the AI model being deployed on the terminal device, the AI model is used to predict the DRX cycle for the set of service types run by the terminal device and determine the second DRX cycle;
  • the second DRX cycle refers to a cycle determined in response to the AI model being deployed on the terminal device and the terminal device using the AI model to predict the DRX cycle for the set of service types run by the terminal device.
  • the second of the second DRX cycles is only used to distinguish it from other DRX cycles and does not specifically refer to a fixed cycle.
  • the terminal device may send the second DRX cycle to the network side device, the network side device may determine the first DRX cycle according to the second DRX cycle, and the network side device may send the first DRX cycle to Terminal Equipment.
  • the terminal device may send a second DRX cycle to the network side device, and the network side device may receive the second DRX cycle.
  • an AI model is used to predict the DRX cycle for the set of service types run by the terminal device and determine the second DRX cycle, including:
  • Classify the service sets run by the terminal equipment and determine the service type set of the service set;
  • the AI model corresponding to the set of business types is used to predict the DRX cycle and determine the second DRX cycle.
  • the AI model corresponding to the service type set is used to predict the DRX cycle and determine the second DRX cycle, including:
  • the AI model corresponding to the service type is used to predict the DRX cycle and determine the second DRX cycle.
  • the AI model corresponding to the service type set is used to predict the DRX cycle and determine the second DRX cycle, including:
  • the AI model corresponding to the at least two service types is used to predict the DRX cycle and determine the second DRX cycle.
  • the AI model corresponding to the service type set is used to predict the DRX cycle and determine the second DRX cycle, including:
  • the AI model corresponding to each of the at least two business types is used to determine the fifth corresponding to each business type respectively.
  • the AI model is not used for DRX cycle prediction.
  • the fifth DRX cycle is used to indicate that when the AI model is deployed on the terminal device, the response service type set includes at least two service types, and there is no corresponding service type corresponding to the at least two service types.
  • AI model the terminal device uses an AI model corresponding to each of the at least two service types to determine the cycle corresponding to each service type.
  • the number of fifth DRX cycles is at least two.
  • the terminal device may determine the second DRX cycle based on at least two fifth DRX cycles.
  • the method further includes:
  • the method further includes:
  • the AI model is a model trained based on a business type corresponding to the AI model.
  • the first DRX cycle is determined based on the artificial intelligence AI model, and the AI model is consistent with the service type run by the terminal device.
  • the first DRX cycle is determined based on the AI model corresponding to the set of service types run by the terminal device, it reduces the situation where different services use the same AI model to predict the DRX cycle, resulting in inaccurate DRX cycle determination.
  • the accuracy of DRX cycle determination can be improved.
  • This disclosure provides a processing method for the situation of "DRX cycle determination" to receive the DRX cycle determined based on the AI model corresponding to the set of service types running on the terminal equipment, and reduce the use of the same AI model for DRX cycle prediction by different services. In situations where the DRX cycle determination is inaccurate, the accuracy of the DRX cycle determination can be improved.
  • FIG. 2 is a schematic flowchart of a DRX cycle determination method provided by an embodiment of the present disclosure. The method is executed by a terminal device. As shown in Figure 2, the method may include the following steps:
  • Step 201 In response to the AI model being deployed on the network side device, the network side device receives the first DRX cycle sent by the network side device and adopts the first DRX cycle determined by the AI model.
  • the first DRX cycle is determined based on an artificial intelligence AI model, and the AI model corresponds to a set of service types run by the terminal device.
  • the AI model is a model trained based on the business type corresponding to the AI model.
  • business types can be classified and different AI models can be used to predict DRX cycles for different business types.
  • the AI model corresponding to the video type is different from the AI model corresponding to the text download type.
  • the same AI model can correspond to only one business type, and the same AI model can correspond to at least two business types.
  • an AI model corresponding to the video type can be trained, and the AI model can be used to predict the DRX cycle for video type services.
  • the AI model corresponding to the video type and text download type can be trained, and the AI model can be used to predict the DRX cycle for the video type and text download type business.
  • the AI model can be deployed on the network side device.
  • the terminal device may receive the first DRX cycle sent by the network side device and determined by the network side device using the AI model. For example, when the network side device uses an AI model to determine the first DRX cycle, the network side device can send the first DRX cycle to the terminal device.
  • the network side device that receives the transmission from the network side device adopts the first DRX cycle determined by the AI model.
  • the first DRX cycle is determined based on the AI model corresponding to the set of service types run by the terminal device, it reduces the situation where different services use the same AI model to predict the DRX cycle, resulting in inaccurate DRX cycle determination.
  • the accuracy of DRX cycle determination can be improved.
  • the terminal device does not need to set an AI model, which can reduce the complexity of model deployment on the terminal device side.
  • This disclosure provides a processing method for the situation of "DRX cycle determination" to receive the DRX cycle determined based on the AI model corresponding to the set of service types running on the terminal equipment, and reduce the use of the same AI model for DRX cycle prediction by different services. In situations where the DRX cycle determination is inaccurate, the accuracy of the DRX cycle determination can be improved.
  • FIG 3 is a schematic flowchart of a DRX cycle determination method provided by an embodiment of the present disclosure. The method is executed by a terminal device. As shown in Figure 3, the method may include the following steps:
  • Step 301 In response to the AI model being deployed on the terminal device, use the AI model to predict the DRX cycle for the set of service types run by the terminal device and determine the second DRX cycle;
  • Step 302 Send the second DRX cycle to the network side device
  • Step 303 Receive the first DRX cycle determined by the network side device based on the second DRX cycle.
  • the AI model is a model trained based on the business type corresponding to the AI model.
  • the first DRX cycle is determined based on an artificial intelligence AI model, and the AI model corresponds to a set of service types run by the terminal device.
  • the terminal device in response to the AI model being deployed on the terminal device, can use the AI model to predict the DRX cycle for the set of service types run by the terminal device and determine the second DRX cycle.
  • the terminal device may send the second DRX cycle to the network side device.
  • the network side device may receive the second DRX cycle and determine the first DRX cycle based on the second DRX cycle.
  • the network side device may send the first DRX cycle determined according to the second DRX cycle to the terminal device.
  • the terminal device may receive the first DRX cycle determined by the network side device according to the second DRX cycle.
  • the second DRX cycle determined by the terminal device may also be a DRX cycle determined by the terminal device based on its own power and the service set run by the terminal device.
  • the first DRX cycle may be, for example, a DRX cycle obtained by adjusting the second DRX cycle by the network side device.
  • the network side device may use downlink control information (DCI) or high-level information to adjust the second DRX cycle to obtain the first DRX cycle.
  • DCI downlink control information
  • high-level information to adjust the second DRX cycle to obtain the first DRX cycle.
  • the AI model is deployed on the terminal device in response to the AI model, and the AI model is used to predict the DRX cycle for the set of service types run by the terminal device, determine the second DRX cycle, and send the second DRX cycle. to the network side device; receiving the first DRX cycle determined by the network side device according to the second DRX cycle.
  • the first DRX cycle is determined based on the AI model corresponding to the set of service types run by the terminal device, it reduces the situation where different services use the same AI model to predict the DRX cycle, resulting in inaccurate DRX cycle determination. The accuracy of DRX cycle determination can be improved.
  • the embodiment of the present disclosure specifically discloses a solution in which the first DRX cycle is determined based on the second DRX cycle.
  • This disclosure provides a processing method for the situation of "DRX cycle determination" to receive the DRX cycle determined based on the AI model corresponding to the set of service types running on the terminal equipment, and reduce the use of the same AI model for DRX cycle prediction by different services. In situations where the DRX cycle determination is inaccurate, the accuracy of the DRX cycle determination can be improved.
  • Figure 4 is a schematic flowchart of a DRX cycle determination method provided by an embodiment of the present disclosure. The method is executed by a terminal device. As shown in Figure 4, the method may include the following steps:
  • Step 401 Classify the service sets run by the terminal device and determine the service type set of the service set;
  • Step 402 Use the AI model corresponding to the service type set to predict the DRX cycle and determine the second DRX cycle.
  • the AI model is a model trained based on the business type corresponding to the AI model.
  • the service set may refer to a set including at least one running service.
  • This business set does not specifically refer to a fixed set.
  • the service set can also change accordingly.
  • the service set can also change accordingly.
  • the business type set refers to a type set corresponding to the business set.
  • the service type set may, for example, refer to a set including at least one service type.
  • the terminal device in response to the AI model being deployed on the terminal device, may determine a service set run by the terminal device.
  • the terminal device can classify the service set and determine the service type set of the service set.
  • the terminal device can use the AI model corresponding to the service type set to predict the DRX cycle and determine the second DRX cycle.
  • the number of services corresponding to the service set is not necessarily equal to the number of service types corresponding to the service type set. For example, when a service set contains two services with the same service type, the number of services corresponding to the service set is not equal to the number of service types corresponding to the service type set.
  • the service type set of the service set is determined by classifying the service set run by the terminal device; the AI model corresponding to the service type set is used to predict the DRX cycle and determine the second DRX cycle.
  • the second DRX cycle is determined based on the AI model corresponding to the set of service types run by the terminal device, it reduces the possibility of inaccurate DRX cycle determination due to different service terminal devices using the same AI model to predict the DRX cycle. situation, which can improve the accuracy of DRX cycle determination.
  • the embodiment of the present disclosure specifically discloses a scheme for determining the second DRX cycle.
  • This disclosure provides a processing method for the situation of "DRX cycle determination" to determine the DRX cycle based on the AI model corresponding to the set of service types running on the terminal equipment, reducing the use of the same AI model for DRX cycle prediction by different services, so that DRX In the case of inaccurate cycle determination, the accuracy of DRX cycle determination can be improved.
  • Figure 5 is a schematic flowchart of a DRX cycle determination method provided by an embodiment of the present disclosure. The method is executed by a terminal device. As shown in Figure 5, the method may include the following steps:
  • Step 501 In response to the service type set including one service type, use the AI model corresponding to the service type to predict the DRX cycle and determine the second DRX cycle.
  • the AI model is a model trained based on the business type corresponding to the AI model.
  • the terminal device in response to the service type set including one service type, uses an AI model corresponding to the service type to perform DRX cycle prediction and determine the second DRX cycle.
  • the response service type set includes one service type, and the one service type may be a video type, for example.
  • the terminal device uses the AI model corresponding to the video type to predict the DRX cycle and determine the second DRX cycle.
  • the AI model corresponding to the service type in response to the service type set including one service type, is used to predict the DRX cycle and determine the second DRX cycle.
  • the second DRX cycle is determined according to the AI model corresponding to the set of service types run by the terminal device, it reduces the situation where different services use the same AI model to predict the DRX cycle, resulting in inaccurate DRX cycle determination.
  • the accuracy of DRX cycle determination can be improved.
  • the embodiments of the present disclosure specifically disclose a solution for determining the second DRX cycle when the service type set includes one service type.
  • This disclosure provides a processing method for the situation of "DRX cycle determination" to determine the DRX cycle based on the AI model corresponding to the set of service types running on the terminal equipment, reducing the use of the same AI model for DRX cycle prediction by different services, so that DRX In the case of inaccurate cycle determination, the accuracy of DRX cycle determination can be improved.
  • Figure 6 is a schematic flowchart of a DRX cycle determination method provided by an embodiment of the present disclosure. The method is executed by a terminal device. As shown in Figure 6, the method may include the following steps:
  • Step 601 In response to the service type set including at least two service types, use the AI model corresponding to the at least two service types to perform DRX cycle prediction and determine the second DRX cycle.
  • the AI model is a model trained based on the business type corresponding to the AI model.
  • the AI model in the embodiment of the present disclosure is a model trained based on at least two business types corresponding to the AI model.
  • the terminal device in response to the service type set including at least two service types, can use an AI model corresponding to the at least two service types to perform DRX cycle prediction and determine the second DRX cycle.
  • the AI model corresponds to at least two business types at the same time.
  • the AI model is a model trained based on at least two business types corresponding to the AI model.
  • the terminal device in response to the service type set including two service types, the two service types are, for example, a video type and a text download type, the terminal device may adopt a method corresponding to the video type and the text download type.
  • the AI model predicts the DRX cycle and determines the second DRX cycle.
  • the AI model corresponding to the at least two service types is used to perform DRX cycle prediction, and the second DRX cycle is determined.
  • the second DRX cycle is determined according to the AI model corresponding to the set of service types run by the terminal device, it reduces the situation where different services use the same AI model to predict the DRX cycle, resulting in inaccurate DRX cycle determination.
  • the accuracy of DRX cycle determination can be improved.
  • the embodiments of the present disclosure specifically disclose a solution for determining the second DRX cycle when the service type set includes at least two service types.
  • This disclosure provides a processing method for the situation of "DRX cycle determination" to determine the DRX cycle based on the AI model corresponding to the set of service types running on the terminal equipment, reducing the use of the same AI model for DRX cycle prediction by different services, so that DRX In the case of inaccurate cycle determination, the accuracy of DRX cycle determination can be improved.
  • Figure 7 is a schematic flowchart of a DRX cycle determination method provided by an embodiment of the present disclosure. The method is executed by a terminal device. As shown in Figure 7, the method may include the following steps:
  • Step 701 In response to the fact that the business type set includes at least two business types and there is no AI model corresponding to the at least two business types, use the AI model corresponding to each of the at least two business types to determine the corresponding business type respectively.
  • Step 702 Determine the second DRX cycle based on at least two fifth DRX cycles
  • Step 703 In response to the service type set including at least two service types, and there is no AI model corresponding to at least two service types, do not use the AI model to predict the DRX cycle.
  • steps 701-702 and step 703 are executed alternatively, that is, when steps 701-702 are executed, step 703 is not executed, and when step 703 is executed, steps 701-702 are not executed.
  • the AI model is a model trained based on the business type corresponding to the AI model.
  • the terminal device in response to the service type set including at least two service types, and there is no AI model corresponding to the at least two service types, the terminal device may adopt an AI model corresponding to each of the at least two service types.
  • the AI model corresponding to the service type determines the fifth DRX cycle corresponding to each service type respectively, and the terminal device can determine the second DRX cycle based on at least two fifth DRX cycles.
  • the two service types are, for example, a video type and a text download type, and there is no terminal device corresponding to the video type and the text download type.
  • the terminal device can use the AI model corresponding to the video type to determine the fifth DRX cycle corresponding to the video type, and the terminal device can use the AI model corresponding to the text download type to determine the fifth DRX cycle corresponding to the text download type.
  • the terminal device may determine the second DRX cycle based on the fifth DRX cycle corresponding to the video type and the fifth DRX cycle corresponding to the text download type.
  • the terminal device in response to the service type set including at least two service types, and there is no AI model corresponding to the at least two service types, the terminal device may not use the AI model to perform DRX cycle prediction.
  • the two service types are, for example, a video type and a text download type, and there are no video types and text download types in the terminal device.
  • the terminal device may not use the AI model to predict the DRX cycle.
  • an AI model corresponding to each of the at least two service types is adopted.
  • the AI model corresponding to the type determines the fifth DRX cycle corresponding to each service type respectively; determines the second DRX cycle based on at least two fifth DRX cycles; or in response to the service type set including at least two service types, and does not exist with at least The AI models corresponding to the two business types do not use AI models for DRX cycle prediction.
  • the second DRX cycle is determined according to the AI model corresponding to the set of service types run by the terminal device, it reduces the situation where different services use the same AI model to predict the DRX cycle, resulting in inaccurate DRX cycle determination.
  • the accuracy of DRX cycle determination can be improved.
  • the embodiments of the present disclosure specifically disclose a solution for determining the second DRX cycle when the service type set includes at least two service types and there is no AI model corresponding to at least two service types.
  • This disclosure provides a processing method for the situation of "DRX cycle determination" to determine the DRX cycle based on the AI model corresponding to the set of service types running on the terminal equipment, reducing the use of the same AI model for DRX cycle prediction by different services, so that DRX In the case of inaccurate cycle determination, the accuracy of DRX cycle determination can be improved.
  • Figure 8 is a schematic flowchart of a DRX cycle determination method provided by an embodiment of the present disclosure. The method is executed by a terminal device. As shown in Figure 8, the method may include the following steps:
  • Step 801 Based on the service set run by the terminal device, send a first model download request for the service set to the network side device;
  • Step 802 Receive the AI model sent by the network side device in response to the first model download request, where the AI model corresponds to the service type set of the service set.
  • the AI model is a model trained based on the business type corresponding to the AI model.
  • the first model download request refers to a request sent by the terminal device based on a service set run by the terminal device.
  • the first in the first model download request is only used to distinguish it from other model download requests, and does not specifically refer to a fixed model download request.
  • the terminal device may send a first model download request for the service set to the network side device.
  • the terminal device may receive the AI model sent by the network side device in response to the first model download request, where the AI model corresponds to the service type set of the service set.
  • the service set run by the terminal device may include a video playback service.
  • the terminal device may send a first model download request for the video playback service to Network side equipment.
  • the terminal device may receive the AI model sent by the network side device in response to the first model download request, where the AI model corresponds to the video type of the video playback service.
  • a first model download request for the service set is sent to the network side device; and the AI model sent by the network side device in response to the first model download request is received.
  • the AI model corresponds to the business type set of the business set.
  • the terminal device can send a model download request to the network side device, and can send different model download requests to the network side device for different download situations, which can improve the convenience of AI model downloading, and at the same time, receive network
  • the side device responds to the AI model sent by the first model download request. Since the AI model corresponds to the service type set of the service set, the matching between the AI model and the service set can be improved.
  • Figure 9 is a schematic flowchart of a DRX cycle determination method provided by an embodiment of the present disclosure. The method is executed by a terminal device. As shown in Figure 9, the method may include the following steps:
  • Step 901 In response to the model download instruction for the AI model, send a second model download request to the network side device;
  • Step 902 Receive the AI model sent by the network side device in response to the second model download request.
  • the AI model is a model trained based on the business type corresponding to the AI model.
  • the terminal device can monitor the service run by the terminal device. , based on the monitoring results, send the first model download request to the network side device.
  • the second model download request refers to a request sent by the terminal device for a model download instruction of the AI model.
  • the second in the second model download request is only used to distinguish it from other model download requests, and does not specifically refer to a fixed model download request.
  • the service set run by the terminal device may include a game service.
  • the terminal device may send a first model download request for the game service to the network side device.
  • the terminal device may receive the AI model sent by the network side device in response to the first model download request, where the AI model corresponds to the video type of the game service.
  • the terminal device in response to the model download instruction for the AI model, may send a second model download request to the network side device.
  • the terminal device may receive the AI model sent by the network side device in response to the second model download request.
  • a second model download request is sent to the network side device; and the AI model sent by the network side device in response to the second model download request is received.
  • the terminal device can respond to the model download instruction for the AI model and send a model download request to the network side device, which can improve the convenience of AI model download and reduce the mismatch between the AI model and the business set. It can improve the matching between AI models and business sets.
  • Figure 10 is a schematic flowchart of a DRX cycle determination method provided by an embodiment of the present disclosure. The method is executed by a network side device. As shown in Figure 10, the method may include the following steps:
  • Step 1001 Send the first DRX cycle to the terminal device, where the first DRX cycle is determined based on the artificial intelligence AI model, and the AI model corresponds to the set of service types run by the terminal device.
  • the method before sending the first DRX cycle to the terminal device, the method further includes:
  • the AI model In response to the AI model being deployed on the network side equipment, the AI model is used to predict the DRX cycle for the set of service types run by the terminal equipment and generate the third DRX cycle;
  • the first DRX cycle is determined.
  • the AI model is used to predict the DRX cycle for the set of service types run by the terminal equipment, and determine the third DRX cycle, including:
  • Classify the service sets run by the terminal equipment and determine the service type set of the service set;
  • the AI model corresponding to the set of business types is used to predict the DRX cycle and determine the third DRX cycle.
  • an AI model corresponding to a set of service types is used to predict the DRX cycle and determine the third DRX cycle, including:
  • the AI model corresponding to the service type is used to predict the DRX cycle and determine the third DRX cycle.
  • the AI model corresponding to the service type set is used to predict the DRX cycle and determine the third DRX cycle, including:
  • the AI model corresponding to the at least two service types is used to predict the DRX cycle and determine the third DRX cycle.
  • an AI model corresponding to a set of service types is used to predict the DRX cycle and determine the third DRX cycle, including:
  • the AI model corresponding to each of the at least two business types is used to determine the fourth corresponding to each business type respectively.
  • the AI model is not used for DRX cycle prediction.
  • the method before sending the first DRX cycle to the terminal device, the method further includes:
  • the terminal device In response to the AI model being deployed on the terminal device, the terminal device receiving the transmission from the terminal device adopts the second DRX cycle determined by the AI model;
  • the first DRX cycle is determined.
  • the method further includes:
  • the method further includes:
  • the AI model is a model trained based on the business type corresponding to the AI model.
  • the input data of the AI model may be, for example, the arrival intervals of the first N data packets
  • the output of the AI model may be, for example, the arrival intervals of the next M data packets.
  • N and M are positive integers.
  • the values of N and M may be different for different business types or for different AI models.
  • the trained AI models will be different for different business types.
  • the first DRX cycle is determined based on the artificial intelligence AI model, and the AI model corresponds to the set of service types run by the terminal device. .
  • the first DRX cycle is determined based on the AI model corresponding to the set of service types run by the terminal device, it reduces the situation where different services use the same AI model to predict the DRX cycle, resulting in inaccurate DRX cycle determination. The accuracy of DRX cycle determination can be improved.
  • This disclosure provides a processing method for the situation of "DRX cycle determination" to send the DRX cycle determined based on the AI model corresponding to the set of service types running on the terminal device to the terminal device, reducing the use of the same AI model for DRX by different services.
  • Cycle prediction can improve the accuracy of DRX cycle determination in cases where the DRX cycle determination is inaccurate.
  • Figure 11 is a schematic flowchart of a DRX cycle determination method provided by an embodiment of the present disclosure. The method is executed by a network side device. As shown in Figure 11, the method may include the following steps:
  • Step 1101. In response to the AI model being deployed on the network side device, use the AI model to predict the DRX cycle for the set of service types run by the terminal device, and generate the third DRX cycle;
  • Step 1102 Determine the first DRX cycle based on the third DRX cycle.
  • the AI model is a model trained based on the business type corresponding to the AI model.
  • the third DRX cycle is a DRX cycle generated by deploying an AI model on the network side device.
  • the network side device uses the AI model to predict the DRX cycle for the set of service types run by the terminal device.
  • the third in the third DRX cycle is only used to distinguish other DRX cycles and does not specifically refer to a fixed DRX cycle.
  • the network side device in response to the AI model being deployed on the network side device, can use the AI model to predict the DRX cycle for the set of service types run by the terminal device, and generate the third DRX cycle.
  • the side device may determine the first DRX cycle based on the third DRX cycle.
  • the network side device may send the first DRX cycle to the terminal device.
  • the network side device when the network side device determines the first DRX cycle based on the third DRX cycle, the network side device may use DCI information or high-layer information to adjust the third DRX cycle and determine the third DRX cycle.
  • DCI information or high-layer information may be used to adjust the third DRX cycle and determine the third DRX cycle.
  • the network side can use different AI models to predict the DRX cycle for the set of service types run by the terminal devices.
  • the AI model used by the network side device can be determined based on the usage behavior of the terminal device, for example.
  • the number of AI models deployed by the network side device may be one or more.
  • the AI model is used to predict the DRX cycle for the set of service types run by the terminal device, and the third DRX cycle is generated; according to the third DRX period to determine the first DRX period.
  • the first DRX cycle is determined based on the AI model corresponding to the set of service types run by the terminal device, it reduces the situation where different services use the same AI model to predict the DRX cycle, resulting in inaccurate DRX cycle determination.
  • the accuracy of DRX cycle determination can be improved.
  • the embodiment of the present disclosure specifically discloses a solution in which the first DRX cycle is determined based on the third DRX cycle.
  • This disclosure provides a processing method for the situation of "DRX cycle determination" to determine the DRX cycle based on the AI model corresponding to the set of service types running on the terminal equipment, reducing the use of the same AI model for DRX cycle prediction by different services, so that DRX In the case of inaccurate cycle determination, the accuracy of DRX cycle determination can be improved.
  • Figure 12 is a schematic flowchart of a DRX cycle determination method provided by an embodiment of the present disclosure. The method is executed by a network side device. As shown in Figure 12, the method may include the following steps:
  • Step 1201 Classify the service sets run by the terminal device and determine the service type set of the service set;
  • Step 1202 Use the AI model corresponding to the service type set to predict the DRX cycle and determine the third DRX cycle.
  • the AI model is a model trained based on the business type corresponding to the AI model.
  • the service set may refer to a set including at least one running service.
  • This business set does not specifically refer to a fixed set.
  • the service set can also change accordingly.
  • the service set can also change accordingly.
  • the business type set refers to a type set corresponding to the business set.
  • the service type set may, for example, refer to a set including at least one service type.
  • the network side device in response to the AI model being deployed on the network side device, can determine the service set run by the terminal device. For example, the network side device may receive the service set sent by the terminal device, and the network side device may also determine the service set run by the terminal device based on the communication data with the terminal device.
  • the network side device may classify the service set and determine the service type set of the service set.
  • the network side device can use the AI model corresponding to the service type set to predict the DRX cycle and determine the third DRX cycle.
  • the number of services corresponding to the service set is not necessarily equal to the number of service types corresponding to the service type set. For example, when a service set contains two services with the same service type, the number of services corresponding to the service set is not equal to the number of service types corresponding to the service type set.
  • the service type set of the service set is determined by classifying the service set run by the terminal device; the AI model corresponding to the service type set is used to predict the DRX cycle and determine the third DRX cycle.
  • the third DRX cycle is determined based on the AI model corresponding to the set of service types run by the terminal device, it is reduced that different service network side devices use the same AI model to predict the DRX cycle, making the DRX cycle determination inaccurate. situation, the accuracy of DRX cycle determination can be improved.
  • the embodiment of the present disclosure specifically discloses a solution for determining the third DRX cycle.
  • This disclosure provides a processing method for the situation of "DRX cycle determination" to determine the DRX cycle based on the AI model corresponding to the set of service types running on the terminal equipment, reducing the use of the same AI model for DRX cycle prediction by different services, so that DRX In the case of inaccurate cycle determination, the accuracy of DRX cycle determination can be improved.
  • Figure 13 is a schematic flowchart of a DRX cycle determination method provided by an embodiment of the present disclosure. The method is executed by a network side device. As shown in Figure 13, the method may include the following steps:
  • Step 1301 In response to the service type set including one service type, use the AI model corresponding to the service type to predict the DRX cycle and determine the third DRX cycle.
  • the AI model is a model trained based on the business type corresponding to the AI model.
  • the network side device in response to the service type set including one service type, can use the AI model corresponding to the service type to perform DRX cycle prediction and determine the third DRX cycle.
  • the response service type set includes one service type, and the one service type may be a video type, for example.
  • the network side device can use the AI model corresponding to the video type to predict the DRX cycle and determine the third DRX cycle.
  • the AI model corresponding to the service type in response to the service type set including one service type, is used to perform DRX cycle prediction, and the third DRX cycle is determined.
  • the third DRX cycle is determined based on the AI model corresponding to the set of service types run by the terminal device, it is reduced that different service network side devices use the same AI model to predict the DRX cycle, making the DRX cycle determination inaccurate. situation, the accuracy of DRX cycle determination can be improved.
  • the embodiments of the present disclosure specifically disclose a solution for determining the third DRX cycle when the service type set includes one service type.
  • This disclosure provides a processing method for the situation of "DRX cycle determination" to determine the DRX cycle based on the AI model corresponding to the set of service types running on the terminal equipment, reducing the use of the same AI model for DRX cycle prediction by different services, so that DRX In the case of inaccurate cycle determination, the accuracy of DRX cycle determination can be improved.
  • Figure 14 is a schematic flowchart of a DRX cycle determination method provided by an embodiment of the present disclosure. The method is executed by a network side device. As shown in Figure 14, the method may include the following steps:
  • Step 1401 In response to the service type set including at least two service types, use the AI model corresponding to the at least two service types to perform DRX cycle prediction and determine the third DRX cycle.
  • the AI model is a model trained based on the business type corresponding to the AI model.
  • the network side device in response to the service type set including at least two service types, can use an AI model corresponding to at least two service types to perform DRX cycle prediction and determine the third DRX cycle.
  • the AI model corresponds to at least two business types at the same time.
  • the AI model is a model trained based on at least two business types corresponding to the AI model.
  • the network side device in response to the service type set including two service types, the two service types are, for example, a video type and a text download type, the network side device may adopt a method related to the video type and the text download type.
  • the corresponding AI model predicts the DRX cycle and determines the third DRX cycle.
  • the AI model corresponding to the at least two service types is used to perform DRX cycle prediction, and the third DRX cycle is determined.
  • the third DRX cycle is determined based on the AI model corresponding to the set of service types run by the terminal device, it is reduced that different service network side devices use the same AI model to predict the DRX cycle, making the DRX cycle determination inaccurate. situation, the accuracy of DRX cycle determination can be improved.
  • the embodiments of the present disclosure specifically disclose a solution for determining the third DRX cycle when the service type set includes at least two service types.
  • This disclosure provides a processing method for the situation of "DRX cycle determination" to determine the DRX cycle based on the AI model corresponding to the set of service types running on the terminal equipment, reducing the use of the same AI model for DRX cycle prediction by different services, so that DRX In the case of inaccurate cycle determination, the accuracy of DRX cycle determination can be improved.
  • Figure 15 is a schematic flowchart of a DRX cycle determination method provided by an embodiment of the present disclosure. The method is executed by a network side device. As shown in Figure 15, the method may include the following steps:
  • Step 1501 In response to the fact that the business type set includes at least two business types and there is no AI model corresponding to the at least two business types, use the AI model corresponding to each of the at least two business types to determine the corresponding business type respectively.
  • Step 1502 Determine the third DRX cycle based on at least two fourth DRX cycles
  • Step 1503 In response to the service type set including at least two service types, and there is no AI model corresponding to at least two service types, do not use the AI model to predict the DRX cycle.
  • the AI model is a model trained based on the business type corresponding to the AI model.
  • steps 1501-1502 and step 1503 are executed alternatively, that is, when steps 1501-1502 are executed, step 1503 is not executed, and when step 1503 is executed, steps 1501-1502 are not executed.
  • the fourth DRX cycle is used to indicate that when the AI model is deployed on the network side device, the response service type set includes at least two service types, and there is no corresponding service type corresponding to at least two service types.
  • the network side device uses an AI model corresponding to each of at least two service types to determine the cycle corresponding to each service type.
  • the number of fourth DRX cycles is at least two.
  • the network side device in response to the service type set including at least two service types, and there is no AI model corresponding to the at least two service types, the network side device may adopt an AI model corresponding to the at least two service types.
  • the AI model corresponding to each service type determines the fourth DRX cycle corresponding to each service type, and the terminal device can determine the third DRX cycle based on at least two fourth DRX cycles.
  • the response service type set includes two service types, such as a video type and a text download type.
  • the network side device can use the AI model corresponding to the video type to determine the fourth DRX cycle corresponding to the video type, and the terminal device
  • the AI model corresponding to the text download type can be used to determine the fourth DRX cycle corresponding to the text download type.
  • the terminal device may determine the third DRX cycle based on the fourth DRX cycle corresponding to the video type and the fourth DRX cycle corresponding to the text download type.
  • the network side device in response to the service type set including at least two service types, and there is no AI model corresponding to the at least two service types, the network side device may not use the AI model to predict the DRX cycle. .
  • the two service types are, for example, a video type and a text download type, and there is no service type related to the video type and text download type in the network side device.
  • the network side device does not need to use the AI model to predict the DRX cycle.
  • an AI model corresponding to each of the at least two service types is adopted.
  • the AI model corresponding to the type determines the fourth DRX cycle corresponding to each service type respectively; determines the third DRX cycle based on at least two fourth DRX cycles; or, in response to the service type set including at least two service types, and there is no corresponding AI models corresponding to at least two business types, AI models are not used for DRX cycle prediction.
  • the third DRX cycle is determined based on the AI model corresponding to the set of service types run by the terminal device, it is reduced that different service network side devices use the same AI model to predict the DRX cycle, making the DRX cycle determination inaccurate. situation, the accuracy of DRX cycle determination can be improved.
  • the embodiments of the present disclosure specifically disclose a solution for determining the third DRX cycle when the service type set includes at least two service types.
  • This disclosure provides a processing method for the situation of "DRX cycle determination" to determine the DRX cycle based on the AI model corresponding to the set of service types running on the terminal equipment, reducing the use of the same AI model for DRX cycle prediction by different services, so that DRX In the case of inaccurate cycle determination, the accuracy of DRX cycle determination can be improved.
  • Figure 16 is a schematic flowchart of a DRX cycle determination method provided by an embodiment of the present disclosure. The method is executed by a network side device. As shown in Figure 16, the method may include the following steps:
  • Step 1601. In response to the AI model being deployed on the terminal device, the terminal device receiving the message sent by the terminal device adopts the second DRX cycle determined by the AI model;
  • Step 1602 Determine the first DRX cycle based on the second DRX cycle.
  • the AI model is a model trained based on the business type corresponding to the AI model.
  • the network side device when the network side device determines the first DRX cycle based on the second DRX cycle, the network side device may send the first DRX cycle to the terminal device.
  • the terminal device receiving the transmission from the terminal device adopts the second DRX cycle determined by the AI model; according to the second DRX cycle, the first DRX cycle is determined cycle.
  • the first DRX cycle is determined based on the AI model corresponding to the set of service types run by the terminal device, it is reduced that different service network side devices use the same AI model to predict the DRX cycle, making the DRX cycle determination inaccurate. situation, the accuracy of DRX cycle determination can be improved.
  • the embodiments of the present disclosure specifically disclose a solution in which the first DRX cycle is determined based on the second DRX cycle sent by the terminal device.
  • This disclosure provides a processing method for the situation of "DRX cycle determination" to determine the DRX cycle based on the AI model corresponding to the set of service types running on the terminal equipment, reducing the use of the same AI model for DRX cycle prediction by different services, so that DRX In the case of inaccurate cycle determination, the accuracy of DRX cycle determination can be improved.
  • Figure 17 is a schematic flowchart of a DRX cycle determination method provided by an embodiment of the present disclosure. The method is executed by a network side device. As shown in Figure 17, the method may include the following steps:
  • Step 1701 Receive a first model download request sent by the terminal device, where the first model download request is a request for a service set run by the terminal device;
  • Step 1702 Send the AI model for the first model download request to the terminal device, where the AI model corresponds to the service type set of the service set.
  • the AI model is a model trained based on the business type corresponding to the AI model.
  • the network side device can receive the model download request sent by the terminal device. Since different download situations correspond to different model download requests, the convenience of AI model download can be improved.
  • the first model download request is sent.
  • the requested AI model is sent to the terminal device. Since the AI model corresponds to the service type set of the service set, the matching between the AI model and the service set can be improved.
  • Figure 18 is a schematic flowchart of a DRX cycle determination method provided by an embodiment of the present disclosure. The method is executed by a network side device. As shown in Figure 18, the method may include the following steps:
  • Step 1801 Receive the second model download request sent by the terminal device for the model download instruction of the AI model
  • Step 1802 Send the AI model for the second model download request to the terminal device.
  • the AI model is a model trained based on the business type corresponding to the AI model.
  • the network side device can receive the model download request sent by the terminal device for the model download instruction of the AI model, which can improve the convenience of downloading the AI model, reduce the mismatch between the AI model and the business set, and can improve the Matching of AI model and business set.
  • Figure 19 is a schematic flowchart of a DRX cycle determination method provided by an embodiment of the present disclosure. The method is executed by a terminal device. As shown in Figure 19, the method may include the following steps:
  • Step 1901 In response to the AI model being deployed on the terminal device, use the AI model to predict the DRX cycle for the set of service types run by the terminal device and determine the second DRX cycle;
  • Step 1902 Send the second DRX cycle to the network side device.
  • an AI model is used to predict the DRX cycle for the set of service types run by the terminal device and determine the second DRX cycle, including:
  • Classify the service sets run by the terminal equipment and determine the service type set of the service set;
  • the AI model corresponding to the set of business types is used to predict the DRX cycle and determine the second DRX cycle.
  • the AI model corresponding to the service type set is used to predict the DRX cycle and determine the second DRX cycle, including:
  • the AI model corresponding to the service type is used to predict the DRX cycle and determine the second DRX cycle.
  • the AI model corresponding to the service type set is used to predict the DRX cycle and determine the second DRX cycle, including:
  • the AI model corresponding to the at least two service types is used to predict the DRX cycle and determine the second DRX cycle.
  • the AI model corresponding to the service type set is used to predict the DRX cycle and determine the second DRX cycle, including:
  • the AI model corresponding to each of the at least two business types is used to determine the fifth corresponding to each business type respectively.
  • the AI model is not used for DRX cycle prediction.
  • the method further includes:
  • the method further includes:
  • step 1901 For a detailed introduction to step 1901, reference may be made to the description of the above embodiments, and the embodiments of the present disclosure will not be described in detail here.
  • the second DRX cycle refers to a cycle determined in response to the AI model being deployed on the terminal device and the terminal device using the AI model to predict the DRX cycle for the set of service types run by the terminal device.
  • the second of the second DRX cycles is only used to distinguish it from other DRX cycles and does not specifically refer to a fixed cycle.
  • the AI model can be deployed on the terminal device.
  • the terminal device can use the AI model to predict the DRX cycle for the set of service types run by the terminal device, determine the second DRX cycle, and send the second DRX cycle to the network side device.
  • the network side device may receive the second DRX cycle sent by the terminal device.
  • the network side device may determine the first DRX cycle based on the second DRX cycle, or may not determine the first DRX cycle based on the second DRX cycle.
  • the AI model is a model trained based on the business type corresponding to the AI model.
  • the AI model is deployed on the terminal device in response to the AI model, and the AI model is used to predict the DRX cycle for the set of service types run by the terminal device, determine the second DRX cycle, and send the second DRX cycle. to the network side device.
  • the second DRX cycle is determined according to the AI model corresponding to the set of service types run by the terminal device, the accuracy of determining the second DRX cycle can be improved.
  • This disclosure provides a processing method for the situation of "DRX cycle determination" to provide the DRX cycle determined based on the AI model corresponding to the set of service types run by the terminal device to the network side device, which can improve the accuracy of DRX cycle determination. .
  • Figure 20 is a schematic flowchart of a DRX cycle determination method provided by an embodiment of the present disclosure. The method is executed by a network side device. As shown in Figure 20, the method may include the following steps:
  • Step 2001 In response to the AI model being deployed on the terminal device, the terminal device that receives the message sent by the terminal device adopts the second DRX cycle determined by the AI model.
  • the AI model is a model trained based on the business type corresponding to the AI model.
  • step 2001 For a detailed introduction to step 2001, reference may be made to the description of the above embodiments, and the embodiments of the present disclosure will not be described again here.
  • the terminal device that receives the transmission from the terminal device adopts the second DRX cycle determined by the AI model.
  • the accuracy of determining the second DRX cycle can be improved.
  • This disclosure provides a processing method for the situation of "DRX cycle determination" to receive the DRX cycle determined by the terminal device based on the AI model corresponding to the set of service types run by the terminal device, which can improve the accuracy of DRX cycle determination. accuracy.
  • Figure 21 is a schematic structural diagram of a DRX cycle determination device provided by an embodiment of the present disclosure. As shown in Figure 21, the device is provided on the terminal side.
  • the device 2100 may include:
  • the receiving module 2101 is configured to receive the first DRX cycle sent by the network side device, where the first DRX cycle is determined based on the artificial intelligence AI model, and the AI model corresponds to the set of service types run by the terminal device.
  • the receiving module receives the first DRX cycle sent by the network side device, where the first DRX cycle is determined based on the artificial intelligence AI model, and the AI model is consistent with Corresponds to the set of service types run by the terminal device.
  • the first DRX cycle is determined based on the AI model corresponding to the set of service types run by the terminal device, it reduces the situation where different services use the same AI model to predict the DRX cycle, resulting in inaccurate DRX cycle determination. The accuracy of DRX cycle determination can be improved.
  • This disclosure provides a processing method for the situation of "DRX cycle determination" to receive the DRX cycle determined based on the AI model corresponding to the set of service types running on the terminal equipment, and reduce the use of the same AI model for DRX cycle prediction by different services. In situations where the DRX cycle determination is inaccurate, the accuracy of the DRX cycle determination can be improved.
  • the receiving module 2101 is configured to receive the first DRX cycle sent by the network side device, specifically for:
  • the network side device In response to the AI model being deployed on the network side device, the network side device that receives the transmission from the network side device adopts the first DRX cycle determined by the AI model.
  • the receiving module 2101 is configured to receive the first DRX cycle sent by the network side device, specifically for:
  • the AI model In response to the AI model being deployed on the terminal device, the AI model is used to predict the DRX cycle for the set of service types run by the terminal device and determine the second DRX cycle;
  • the determination module 2102 is configured to use an AI model to predict the DRX cycle for the set of service types run by the terminal device, and when determining the second DRX cycle, is specifically used to:
  • Classify the service sets run by the terminal equipment and determine the service type set of the service set;
  • the AI model corresponding to the set of business types is used to predict the DRX cycle and determine the second DRX cycle.
  • the determination module 2102 is configured to use an AI model corresponding to the service type set to predict the DRX cycle, and when determining the second DRX cycle, is specifically used to:
  • the AI model corresponding to the service type is used to predict the DRX cycle and determine the second DRX cycle.
  • the determination module 2102 is configured to use an AI model corresponding to the service type set to predict the DRX cycle, and when determining the second DRX cycle, is specifically used to:
  • the AI model corresponding to the at least two service types is used to predict the DRX cycle and determine the second DRX cycle.
  • the determination module 2102 is configured to use an AI model corresponding to the service type set to predict the DRX cycle, and when determining the second DRX cycle, is specifically used to:
  • the AI model corresponding to each of the at least two business types is used to determine the fifth corresponding to each business type respectively.
  • the AI model is not used for DRX cycle prediction.
  • the receiving module 2101 is also used to:
  • the receiving module 2101 is also used to:
  • the AI model is a model trained based on the business type corresponding to the AI model.
  • Figure 22 is a schematic structural diagram of a DRX cycle determination device provided by an embodiment of the present disclosure. As shown in Figure 22, the device is provided on the network side.
  • the device 2200 may include:
  • the sending module 2201 is configured to send the first DRX cycle to the terminal device, where the first DRX cycle is determined based on the artificial intelligence AI model, and the AI model corresponds to the set of service types run by the terminal device.
  • the sending module sends the first DRX cycle to the terminal device, where the first DRX cycle is determined based on the artificial intelligence AI model, and the AI model is consistent with the terminal device Corresponds to the set of running business types.
  • the first DRX cycle is determined based on the AI model corresponding to the set of service types run by the terminal device, it reduces the situation where different services use the same AI model to predict the DRX cycle, resulting in inaccurate DRX cycle determination. The accuracy of DRX cycle determination can be improved.
  • This disclosure provides a processing method for the situation of "DRX cycle determination" to send the DRX cycle determined based on the AI model corresponding to the set of service types running on the terminal device to the terminal device, reducing the use of the same AI model for DRX by different services.
  • Cycle prediction can improve the accuracy of DRX cycle determination in cases where the DRX cycle determination is inaccurate.
  • Figure 23 is a schematic structural diagram of a DRX cycle determination device provided by an embodiment of the present disclosure. As shown in Figure 23, the device is provided on the network side, and the device 2200 A determining module 2202 may also be included, for before sending the first DRX cycle to the terminal device:
  • the AI model In response to the AI model being deployed on the network side equipment, the AI model is used to predict the DRX cycle for the set of service types run by the terminal equipment and generate the third DRX cycle;
  • the first DRX cycle is determined.
  • the determination module 2202 is configured to use an AI model to predict the DRX cycle for the set of service types run by the terminal device, and when determining the third DRX cycle, is specifically used to:
  • Classify the service sets run by the terminal equipment and determine the service type set of the service set;
  • the AI model corresponding to the set of business types is used to predict the DRX cycle and determine the third DRX cycle.
  • the determination module 2202 is configured to use an AI model corresponding to the service type set to predict the DRX cycle, and when determining the third DRX cycle, is specifically used to:
  • the AI model corresponding to the service type is used to predict the DRX cycle and determine the third DRX cycle.
  • the determination module 2202 is configured to use an AI model corresponding to the service type set to predict the DRX cycle, and when determining the third DRX cycle, is specifically used to:
  • the AI model corresponding to the at least two service types is used to predict the DRX cycle and determine the third DRX cycle.
  • the determination module 2202 is configured to use an AI model corresponding to the service type set to predict the DRX cycle, and when determining the third DRX cycle, is specifically used to:
  • the AI model corresponding to each of the at least two business types is used to determine the fourth corresponding to each business type respectively.
  • the AI model is not used for DRX cycle prediction.
  • Figure 24 is a schematic structural diagram of a DRX cycle determination device provided by an embodiment of the present disclosure. As shown in Figure 24, the device is provided on the network side, and the device 2200 A receiving module 2203 may also be included, configured to: before sending the first DRX cycle to the terminal device:
  • the terminal device In response to the AI model being deployed on the terminal device, the terminal device receiving the transmission from the terminal device adopts the second DRX cycle determined by the AI model.
  • the first DRX cycle is determined.
  • the sending module 2201 is also used to:
  • the sending module 2201 is also used to:
  • the AI model is a model trained based on the business type corresponding to the AI model.
  • Figure 25 is a schematic structural diagram of a DRX cycle determination device provided by an embodiment of the present disclosure. As shown in Figure 25, the device is provided on the terminal side.
  • the device 2500 may also include a determination module 2501 and a sending module 2502, where:
  • the determination module 2501 is configured to respond to the AI model being deployed on the terminal device, use the AI model to predict the DRX cycle for the set of service types run by the terminal device, and determine the second DRX cycle;
  • the sending module 2502 is used to send the second DRX cycle to the network side device.
  • the determination module is deployed on the terminal device in response to the AI model, uses the AI model to predict the DRX cycle for the set of service types run by the terminal device, and determines the second DRX cycle. ;
  • the sending module sends the second DRX cycle to the network side device.
  • the accuracy of determining the second DRX cycle can be improved.
  • This disclosure provides a processing method for the situation of "DRX cycle determination" to provide the DRX cycle determined based on the AI model corresponding to the set of service types run by the terminal device to the network side device, which can improve the accuracy of DRX cycle determination. .
  • the determination module 2501 is configured to use an AI model to predict the DRX cycle for the set of service types run by the terminal device, and when determining the second DRX cycle, is specifically used to:
  • Classify the service sets run by the terminal equipment and determine the service type set of the service set;
  • the AI model corresponding to the set of business types is used to predict the DRX cycle and determine the second DRX cycle.
  • the determination module 2501 is configured to use an AI model corresponding to the service type set to predict the DRX cycle, and when determining the second DRX cycle, is specifically used to:
  • the AI model corresponding to the service type is used to predict the DRX cycle and determine the second DRX cycle.
  • the determination module 2501 is configured to use an AI model corresponding to a set of service types to predict the DRX cycle, and when determining the second DRX cycle, is specifically used to:
  • the AI model corresponding to the at least two service types is used to predict the DRX cycle and determine the second DRX cycle.
  • the determination module 2501 is configured to use an AI model corresponding to a set of service types to predict the DRX cycle, and when determining the second DRX cycle, is specifically used to:
  • the AI model corresponding to each of the at least two business types is used to determine the fifth value corresponding to each business type respectively.
  • the AI model is not used for DRX cycle prediction.
  • the sending module 2502 is also used to:
  • the sending module 2502 is also used to:
  • Figure 26 is a schematic structural diagram of a DRX cycle determination device provided by an embodiment of the present disclosure. As shown in Figure 26, the device is provided on the terminal side.
  • the device 2600 may also include a receiving module 2601, wherein:
  • the receiving module 2601 is configured to respond to the AI model being deployed on the terminal device and receive the second DRX cycle sent by the terminal device and determined by the terminal device using the AI model.
  • the receiving module is deployed on the terminal device in response to the AI model, and receives the second DRX determined by the terminal device using the AI model and sent by the terminal device. cycle.
  • the second DRX cycle is determined according to the AI model corresponding to the set of service types run by the terminal device, the accuracy of determining the second DRX cycle can be improved.
  • This disclosure provides a processing method for the situation of "DRX cycle determination" to receive the DRX cycle determined by the terminal device based on the AI model corresponding to the set of service types run by the terminal device, which can improve the accuracy of DRX cycle determination. accuracy.
  • FIG. 27 is a block diagram of a terminal device UE2700 provided by an embodiment of the present disclosure.
  • UE2700 can be a mobile phone, computer, digital broadcast terminal device, messaging device, game console, tablet device, medical device, fitness device, personal digital assistant, etc.
  • the UE 2700 may include at least one of the following components: a processing component 2702 , a memory 2704 , a power supply component 2706 , a multimedia component 2708 , an audio component 2710 , an input/output (I/O) interface 2712 , a sensor component 2714 , and a communication component. 2716.
  • Processing component 2702 generally controls the overall operations of UE 2700, such as operations associated with display, phone calls, data communications, camera operations, and recording operations.
  • the processing component 2702 may include at least one processor 2720 to execute instructions to complete all or part of the steps of the above method. Additionally, processing component 2702 may include at least one module to facilitate interaction between processing component 2702 and other components. For example, processing component 2702 may include a multimedia module to facilitate interaction between multimedia component 2708 and processing component 2702.
  • Memory 2704 is configured to store various types of data to support operations at UE 2700. Examples of this data include instructions for any application or method operating on the UE2700, contact data, phonebook data, messages, pictures, videos, etc.
  • Memory 2704 may be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EEPROM), Programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.
  • SRAM static random access memory
  • EEPROM electrically erasable programmable read-only memory
  • EEPROM erasable programmable read-only memory
  • EPROM Programmable read-only memory
  • PROM programmable read-only memory
  • ROM read-only memory
  • magnetic memory flash memory, magnetic or optical disk.
  • Power supply component 2706 provides power to various components of UE 2700.
  • Power component 2706 may include a power management system, at least one power supply, and other components associated with generating, managing, and distributing power to UE 2700.
  • Multimedia component 2708 includes a screen that provides an output interface between the UE 2700 and the user.
  • the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user.
  • the touch panel includes at least one touch sensor to sense touches, slides, and gestures on the touch panel. The touch sensor may not only sense the boundary of the touch or sliding operation, but also detect the wake-up time and pressure related to the touch or sliding operation.
  • multimedia component 2708 includes a front-facing camera and/or a rear-facing camera. When the UE2700 is in an operating mode, such as shooting mode or video mode, the front camera and/or rear camera can receive external multimedia data.
  • Each front-facing camera and rear-facing camera can be a fixed optical lens system or have a focal length and optical zoom capabilities.
  • Audio component 2710 is configured to output and/or input audio signals.
  • audio component 2710 includes a microphone (MIC) configured to receive external audio signals when UE 2700 is in operating modes, such as call mode, recording mode, and voice recognition mode. The received audio signal may be further stored in memory 2704 or sent via communication component 2716.
  • audio component 2710 also includes a speaker for outputting audio signals.
  • the I/O interface 2712 provides an interface between the processing component 2702 and a peripheral interface module.
  • the peripheral interface module may be a keyboard, a click wheel, a button, etc. These buttons may include, but are not limited to: Home button, Volume buttons, Start button, and Lock button.
  • Sensor component 2714 includes at least one sensor for providing various aspects of status assessment for UE 2700 .
  • the sensor component 2714 can detect the open/closed state of the device 1600, the relative positioning of components, such as the display and keypad of the UE2700, the sensor component 2714 can also detect the position change of the UE2700 or a component of the UE2700, the user Presence or absence of contact with UE2700, UE2700 orientation or acceleration/deceleration and temperature changes of UE2700.
  • Sensor assembly 2714 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact.
  • Sensor assembly 2714 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications.
  • the sensor component 2714 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
  • Communication component 2716 is configured to facilitate wired or wireless communication between UE 2700 and other devices.
  • UE2700 can access wireless networks based on communication standards, such as WiFi, 2G or 3G, or a combination thereof.
  • the communication component 2716 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel.
  • the communications component 2716 also includes a near field communications (NFC) module to facilitate short-range communications.
  • NFC near field communications
  • the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.
  • RFID radio frequency identification
  • IrDA infrared data association
  • UWB ultra-wideband
  • Bluetooth Bluetooth
  • the UE 2700 may be configured by at least one Application Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array ( FPGA), controller, microcontroller, microprocessor or other electronic component implementation for executing the above method.
  • ASIC Application Specific Integrated Circuit
  • DSP Digital Signal Processor
  • DSPD Digital Signal Processing Device
  • PLD Programmable Logic Device
  • FPGA Field Programmable Gate Array
  • controller microcontroller, microprocessor or other electronic component implementation for executing the above method.
  • Figure 28 is a block diagram of a network side device 2800 provided by an embodiment of the present disclosure.
  • the network side device 2800 may be provided as a network side device.
  • the network side device 2800 includes a processing component 2822 , which further includes at least one processor, and a memory resource represented by a memory 2832 for storing instructions, such as application programs, that can be executed by the processing component 2822 .
  • the application program stored in memory 2832 may include one or more modules, each corresponding to a set of instructions.
  • the processing component 2822 is configured to execute instructions to perform any of the foregoing methods applied to the network side device, for example, the method shown in FIG. 10 .
  • the network side device 2800 may also include a power supply component 2826 configured to perform power management of the network side device 2800, a wired or wireless network interface 2850 configured to connect the network side device 2800 to the network, and an input/output (I/O). O)Interface 2858.
  • the network side device 2800 can operate based on an operating system stored in the memory 2832, such as Windows Server TM, Mac OS X TM, Unix TM, Linux TM, Free BSD TM or similar.
  • the methods provided by the embodiments of the present disclosure are introduced from the perspectives of network side equipment and UE respectively.
  • the network side device and the UE may include a hardware structure and a software module to implement the above functions in the form of a hardware structure, a software module, or a hardware structure plus a software module.
  • a certain function among the above functions can be executed by a hardware structure, a software module, or a hardware structure plus a software module.
  • the methods provided by the embodiments of the present disclosure are introduced from the perspectives of network side equipment and UE respectively.
  • the network side device and the UE may include a hardware structure and a software module to implement the above functions in the form of a hardware structure, a software module, or a hardware structure plus a software module.
  • a certain function among the above functions can be executed by a hardware structure, a software module, or a hardware structure plus a software module.
  • the communication device may include a transceiver module and a processing module.
  • the transceiver module may include a sending module and/or a receiving module.
  • the sending module is used to implement the sending function
  • the receiving module is used to implement the receiving function.
  • the transceiving module may implement the sending function and/or the receiving function.
  • the communication device may be a terminal device (such as the terminal device in the foregoing method embodiment), a device in the terminal device, or a device that can be used in conjunction with the terminal device.
  • the communication device may be a network device, a device in a network device, or a device that can be used in conjunction with the network device.
  • the communication device may be a network device, or may be a terminal device (such as the terminal device in the foregoing method embodiment), or may be a chip, chip system, or processor that supports the network device to implement the above method, or may be a terminal device that supports A chip, chip system, or processor that implements the above method.
  • the device can be used to implement the method described in the above method embodiment. For details, please refer to the description in the above method embodiment.
  • a communications device may include one or more processors.
  • the processor may be a general-purpose processor or a special-purpose processor, etc.
  • it can be a baseband processor or a central processing unit.
  • the baseband processor can be used to process communication protocols and communication data
  • the central processor can be used to control and execute communication devices (such as network side equipment, baseband chips, terminal equipment, terminal equipment chips, DU or CU, etc.)
  • a computer program processes data for a computer program.
  • the communication device may also include one or more memories, on which a computer program may be stored, and the processor executes the computer program, so that the communication device performs the method described in the above method embodiment.
  • data may also be stored in the memory.
  • the communication device and the memory can be provided separately or integrated together.
  • the communication device may also include a transceiver and an antenna.
  • the transceiver can be called a transceiver unit, a transceiver, or a transceiver circuit, etc., and is used to implement transceiver functions.
  • the transceiver can include a receiver and a transmitter.
  • the receiver can be called a receiver or a receiving circuit, etc., and is used to implement the receiving function;
  • the transmitter can be called a transmitter or a transmitting circuit, etc., and is used to implement the transmitting function.
  • one or more interface circuits may also be included in the communication device.
  • Interface circuitry is used to receive code instructions and transmit them to the processor.
  • the processor executes the code instructions to cause the communication device to perform the method described in the above method embodiment.
  • the communication device is a terminal device (such as the terminal device in the foregoing method embodiment): the processor is configured to execute the method shown in any one of Figures 1 to 9 or 19.
  • the communication device is a network-side device: the processor is used to execute the method shown in any one of Figures 10 to 18 or 20.
  • a transceiver for implementing receiving and transmitting functions may be included in the processor.
  • the transceiver may be a transceiver circuit, an interface, or an interface circuit.
  • the transceiver circuits, interfaces or interface circuits used to implement the receiving and transmitting functions can be separate or integrated together.
  • the above-mentioned transceiver circuit, interface or interface circuit can be used for reading and writing codes/data, or the above-mentioned transceiver circuit, interface or interface circuit can be used for signal transmission or transfer.
  • the processor may store a computer program, and the computer program runs on the processor, which can cause the communication device to perform the method described in the above method embodiment.
  • the computer program may be embedded in the processor, in which case the processor may be implemented in hardware.
  • the communication device may include a circuit, and the circuit may implement the functions of sending or receiving or communicating in the foregoing method embodiments.
  • the processors and transceivers described in this disclosure may be implemented on integrated circuits (ICs), analog ICs, radio frequency integrated circuits (RFICs), mixed signal ICs, application specific integrated circuits (ASICs), printed circuit boards ( printed circuit board (PCB), electronic equipment, etc.
  • the processor and transceiver can also be manufactured using various IC process technologies, such as complementary metal oxide semiconductor (CMOS), n-type metal oxide-semiconductor (NMOS), P-type Metal oxide semiconductor (positive channel metal oxide semiconductor, PMOS), bipolar junction transistor (BJT), bipolar CMOS (BiCMOS), silicon germanium (SiGe), gallium arsenide (GaAs), etc.
  • CMOS complementary metal oxide semiconductor
  • NMOS n-type metal oxide-semiconductor
  • PMOS P-type Metal oxide semiconductor
  • BJT bipolar junction transistor
  • BiCMOS bipolar CMOS
  • SiGe silicon germanium
  • GaAs gallium arsenide
  • the communication device described in the above embodiments may be a network device or a terminal device (such as the terminal device in the foregoing method embodiment), but the scope of the communication device described in the present disclosure is not limited thereto, and the structure of the communication device may not be limited to limits.
  • the communication device may be a stand-alone device or may be part of a larger device.
  • the communication device may be:
  • the IC collection may also include storage components for storing data and computer programs;
  • the communication device may be a chip or a system on a chip
  • the chip includes a processor and an interface.
  • the number of processors may be one or more, and the number of interfaces may be multiple.
  • the chip also includes a memory for storing necessary computer programs and data.
  • the present disclosure also provides a readable storage medium on which instructions are stored, and when the instructions are executed by a computer, the functions of any of the above method embodiments are implemented.
  • the present disclosure also provides a computer program product, which, when executed by a computer, implements the functions of any of the above method embodiments.
  • the above embodiments it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof.
  • software it may be implemented in whole or in part in the form of a computer program product.
  • the computer program product includes one or more computer programs.
  • the computer program When the computer program is loaded and executed on a computer, the processes or functions described in accordance with the embodiments of the present disclosure are generated in whole or in part.
  • the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.
  • the computer program may be stored in or transferred from one computer-readable storage medium to another, for example, the computer program may be transferred from a website, computer, server, or data center Transmission to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) means.
  • the computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more available media integrated.
  • the available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., high-density digital video discs (DVD)), or semiconductor media (e.g., solid state disks, SSD)) etc.
  • magnetic media e.g., floppy disks, hard disks, magnetic tapes
  • optical media e.g., high-density digital video discs (DVD)
  • DVD digital video discs
  • semiconductor media e.g., solid state disks, SSD
  • At least one in the present disclosure can also be described as one or more, and the plurality can be two, three, four or more, and the present disclosure is not limited.
  • the technical feature is distinguished by “first”, “second”, “third”, “A”, “B”, “C” and “D”, etc.
  • the technical features described in “first”, “second”, “third”, “A”, “B”, “C” and “D” are in no particular order or order.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Databases & Information Systems (AREA)
  • Mobile Radio Communication Systems (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

一种DRX周期确定方法、装置、设备及存储介质，属于通信技术领域。该方法包括接收网络侧设备发送的第一DRX周期，其中，所述第一DRX周期是基于人工智能AI模型确定的，且所述AI模型与所述终端设备运行的业务类型集合对应。本申请针对"DRX周期确定"这一情形提供了一种处理方法，以接收基于与终端设备运行的业务类型集合对应AI模型确定的DRX周期，减少不同业务采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。

Description

DRX周期确定方法、装置 技术领域
本公开涉及通信技术领域，尤其涉及一种非连续接收(Discontinuous Reception，DRX)周期确定方法、装置、设备及存储介质。
背景技术
在通信系统中，第五代移动通信技术(5th Generation Mobile Communication Technology，5G)网络可以利用DRX非连续接收机制降低终端设备的能耗。通过给终端设备配置长短睡眠周期的方式降低终端设备的能耗。针对传统的非连续接收机制设置的固定的睡眠时间长度，使得数据传输延时较大的情况，可以采用人工智能的方法对终端设备数据包的到达时间进行预测，以降低终端设备的能耗。例如，可以采用长短期记忆网络(Long Short-Term Memory，LSTM)对终端设备的DRX周期进行配置。但是，仅采用同一AI模型对终端设备数据包的到达时间进行预测，使得DRX周期预测不准确。
发明内容
本公开提出的一种DRX周期确定方法、装置、设备及存储介质，以接收基于与终端设备运行的业务类型集合对应AI模型确定的DRX周期，减少不同业务采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。
本公开一方面实施例提出的一种非连续接收DRX周期确定方法，所述方法由终端设备执行，所述方法包括：
接收网络侧设备发送的第一DRX周期，其中，所述第一DRX周期是基于人工智能(Artificial Intelligence，AI)模型确定的，且所述AI模型与所述终端设备运行的业务类型集合对应。
可选地，在本公开的一个实施例之中，所述接收网络侧设备发送的第一DRX周期，包括：
响应于AI模型部署于所述网络侧设备，接收所述网络侧设备发送的所述网络侧设备采用所述AI模型确定的所述第一DRX周期。
可选地，在本公开的一个实施例之中，所述接收网络侧设备发送的第一DRX周期，包括：
响应于所述AI模型部署于所述终端设备，采用所述AI模型对所述终端设备运行的业务类型集合进行DRX周期预测，确定第二DRX周期；
发送所述第二DRX周期至所述网络侧设备；
接收所述网络侧设备根据所述第二DRX周期确定的所述第一DRX周期。
可选地，在本公开的一个实施例之中，所述采用所述AI模型对所述终端设备运行的业务类型集合进行DRX周期预测，确定第二DRX周期，包括：
对所述终端设备运行的业务集合进行分类，确定所述业务集合的业务类型集合；
采用与所述业务类型集合对应的AI模型进行DRX周期预测，确定第二DRX周期。
可选地，在本公开的一个实施例之中，所述采用与所述业务类型集合对应的AI模型进行DRX周期预测，确定第二DRX周期，包括：
响应于所述业务类型集合包括一种业务类型，采用与所述业务类型对应的AI模型进行DRX周期预测，确定所述第二DRX周期。
可选地，在本公开的一个实施例之中，所述采用与所述业务类型集合对应的AI模型进行DRX周期预测，确定第二DRX周期，包括：
响应于所述业务类型集合包括至少两种业务类型，采用与所述至少两种业务类型对应的AI模型进行DRX周期预测，确定所述第二DRX周期。
可选地，在本公开的一个实施例之中，所述采用与所述业务类型集合对应的AI模型进行DRX周期预测，确定第二DRX周期，包括：
响应于所述业务类型集合包括至少两种业务类型，且未存在与所述至少两种业务类型对应的AI模型，采用与所述至少两种业务类型中各业务类型对应的AI模型分别确定所述各业务类型对应的第五DRX周期；
基于至少两个第五DRX周期，确定所述第二DRX周期；
或，
响应于所述业务类型集合包括至少两种业务类型，且未存在与所述至少两种业务类型对应的AI模型，不采用AI模型进行DRX周期预测。
可选地，在本公开的一个实施例之中，所述方法还包括：
基于所述终端设备运行的业务集合，发送针对所述业务集合的第一模型下载请求至所述网络侧设备；
接收所述网络侧设备针对所述第一模型下载请求发送的AI模型，其中，所述AI模型与所述业务集合的业务类型集合对应。
可选地，在本公开的一个实施例之中，所述方法还包括：
响应于针对AI模型的模型下载指令，发送所述第二模型下载请求至所述网络侧设备；
接收所述网络侧设备针对所述第二模型下载请求发送的AI模型。
可选地，在本公开的一个实施例之中，其中，所述AI模型为基于与所述AI模型对应的业务类型进行训练得到的模型。
本公开另一方面实施例提出的一种DRX周期确定方法，由网络侧设备执行，所述方法包括：
发送第一DRX周期至终端设备，其中，所述第一DRX周期是基于人工智能AI模型确定的，且所述AI模型与所述终端设备运行的业务类型集合对应。
可选地，在本公开的一个实施例之中，在所述发送第一DRX周期至终端设备之前，还包括：
响应于AI模型部署于所述网络侧设备，采用所述AI模型对所述终端设备运行的业务类型集合进行DRX周期预测，生成第三DRX周期；
根据所述第三DRX周期，确定所述第一DRX周期。
可选地，在本公开的一个实施例之中，所述采用所述AI模型对所述终端设备运行的业务类型集合进行DRX周期预测，确定第三DRX周期，包括：
对所述终端设备运行的业务集合进行分类，确定所述业务集合的业务类型集合；
采用与所述业务类型集合对应的AI模型进行DRX周期预测，确定第三DRX周期。
可选地，在本公开的一个实施例之中，所述采用与所述业务类型集合对应的AI模型进行DRX周期预测，确定第三DRX周期，包括：
响应于所述业务类型集合包括一种业务类型，采用与所述业务类型对应的AI模型进行DRX周期预测，确定所述第三DRX周期。
可选地，在本公开的一个实施例之中，所述采用与所述业务类型集合对应的AI模型进行DRX周期预测，确定第三DRX周期，包括：
响应于所述业务类型集合包括至少两种业务类型，采用与所述至少两种业务类型对应的AI模型进行DRX周期预测，确定所述第三DRX周期。
可选地，在本公开的一个实施例之中，所述采用与所述业务类型集合对应的AI模型进行DRX周期预测，确定第三DRX周期，包括：
响应于所述业务类型集合包括至少两种业务类型，且未存在与所述至少两种业务类型对应的AI模型，采用与所述至少两种业务类型中各业务类型对应的AI模型分别确定所述各业务类型对应的第四DRX周期；
基于至少两个第四DRX周期，确定所述第三DRX周期；
或，
响应于所述业务类型集合包括至少两种业务类型，且未存在与所述至少两种业务类型对应的AI模型，不采用AI模型进行DRX周期预测。
可选地，在本公开的一个实施例之中，在所述发送第一DRX周期至终端设备之前，还包括：
响应于所述AI模型部署于所述终端设备，接收所述终端设备发送的所述终端设备采用所述AI模型确定的第二DRX周期；
根据所述第二DRX周期，确定所述第一DRX周期。
可选地，在本公开的一个实施例之中，所述方法还包括：
接收所述终端设备发送的第一模型下载请求，其中，所述第一模型下载请求为针对所述终端设备运行的业务集合的请求；
发送针对所述第一模型下载请求的AI模型至所述终端设备，其中，所述AI模型与所述业务集合的业务类型集合对应。
可选地，在本公开的一个实施例之中，所述方法还包括：
接收所述终端设备针对AI模型的模型下载指令发送的第二模型下载请求；
发送针对所述第二模型下载请求的AI模型至所述终端设备。
可选地，在本公开的一个实施例之中，其中，所述AI模型为基于与所述AI模型对应的业务类型进行训练得到 的模型。
本公开另一方面实施例提出的一种DRX周期确定方法，由终端设备执行，所述方法包括：
响应于AI模型部署于终端设备，采用所述AI模型对所述终端设备运行的业务类型集合进行DRX周期预测，确定第二DRX周期；
发送所述第二DRX周期至网络侧设备。
可选地，在本公开的一个实施例之中，所述采用所述AI模型对所述终端设备运行的业务类型集合进行DRX周期预测，确定第二DRX周期，包括：
对所述终端设备运行的业务集合进行分类，确定所述业务集合的业务类型集合；
采用与所述业务类型集合对应的AI模型进行DRX周期预测，确定第二DRX周期。
可选地，在本公开的一个实施例之中，所述采用与所述业务类型集合对应的AI模型进行DRX周期预测，确定第二DRX周期，包括：
响应于所述业务类型集合包括一种业务类型，采用与所述业务类型对应的AI模型进行DRX周期预测，确定所述第二DRX周期。
可选地，在本公开的一个实施例之中，所述采用与所述业务类型集合对应的AI模型进行DRX周期预测，确定第二DRX周期，包括：
响应于所述业务类型集合包括至少两种业务类型，采用与所述至少两种业务类型对应的AI模型进行DRX周期预测，确定所述第二DRX周期。
可选地，在本公开的一个实施例之中，所述采用与所述业务类型集合对应的AI模型进行DRX周期预测，确定第二DRX周期，包括：
响应于所述业务类型集合包括至少两种业务类型，且未存在与所述至少两种业务类型对应的AI模型，采用与所述至少两种业务类型中各业务类型对应的AI模型分别确定所述各业务类型对应的第五DRX周期；
基于至少两个第五DRX周期，确定所述第二DRX周期；
或，
响应于所述业务类型集合包括至少两种业务类型，且未存在与所述至少两种业务类型对应的AI模型，不采用AI模型进行DRX周期预测。
可选地，在本公开的一个实施例之中，所述方法还包括：
基于所述终端设备运行的业务集合，发送针对所述业务集合的第一模型下载请求至所述网络侧设备；
接收所述网络侧设备针对所述第一模型下载请求发送的AI模型，其中，所述AI模型与所述业务集合的业务类型集合对应。
可选地，在本公开的一个实施例之中，所述方法还包括：
响应于针对AI模型的模型下载指令，发送所述第二模型下载请求至所述网络侧设备；
接收所述网络侧设备针对所述第二模型下载请求发送的AI模型。
本公开另一方面实施例提出的一种DRX周期确定方法，由网络侧设备执行，所述方法包括：
响应于AI模型部署于终端设备，接收所述终端设备发送的所述终端设备采用所述AI模型确定的第二DRX周期。
本公开又一方面实施例提出的一种DRX周期确定装置，所述装置设置于终端侧，包括：
接收模块，用于接收网络侧设备发送的第一DRX周期，其中，所述第一DRX周期是基于人工智能AI模型确定的，且所述AI模型与所述终端设备运行的业务类型集合对应。
本公开又一方面实施例提出的一种DRX周期确定装置，所述装置设置于网络侧，包括：
发送模块，用于发送第一DRX周期至终端设备，其中，所述第一DRX周期是基于人工智能AI模型确定的，且所述AI模型与所述终端设备运行的业务类型集合对应。
本公开又一方面实施例提出的一种DRX周期确定装置，所述装置设置于终端侧，包括：
确定模块，用于响应于AI模型部署于终端设备，采用所述AI模型对所述终端设备运行的业务类型集合进行DRX周期预测，确定第二DRX周期；
发送模块，用于发送所述第二DRX周期至网络侧设备。
本公开又一方面实施例提出的一种DRX周期确定装置，所述装置设置于网络侧，包括：
接收模块，用于响应于AI模型部署于终端设备，接收所述终端设备发送的所述终端设备采用所述AI模型确定的第二DRX周期。
本公开又一方面实施例提出的一种终端设备，所述设备包括处理器和存储器，所述存储器中存储有计算机程序， 所述处理器执行所述存储器中存储的计算机程序，以使所述装置执行如上一方面实施例提出的方法。
本公开又一方面实施例提出的一种网络侧设备，所述设备包括处理器和存储器，所述存储器中存储有计算机程序，所述处理器执行所述存储器中存储的计算机程序，以使所述装置执行如上另一方面实施例提出的方法。
本公开又一方面实施例提出的通信装置，包括：处理器和接口电路；
所述接口电路，用于接收代码指令并传输至所述处理器；
所述处理器，用于运行所述代码指令以执行如一方面实施例提出的方法。
本公开又一方面实施例提出的通信装置，包括：处理器和接口电路；
所述接口电路，用于接收代码指令并传输至所述处理器；
所述处理器，用于运行所述代码指令以执行如另一方面实施例提出的方法。
本公开又一方面实施例提出的计算机可读存储介质，用于存储有指令，当所述指令被执行时，使如一方面实施例提出的方法被实现。
本公开又一方面实施例提出的计算机可读存储介质，用于存储有指令，当所述指令被执行时，使如另一方面实施例提出的方法被实现。
综上所述，在本公开实施例之中，通过接收网络侧设备发送的第一DRX周期，其中，第一DRX周期是基于人工智能AI模型确定的，且AI模型与终端设备运行的业务类型集合对应。在本公开实施例之中，由于第一DRX周期为根据终端设备运行的业务类型集合对应的AI模型确定的，减少不同业务采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。本公开针对于“DRX周期确定”这一情形提供了一种处理方法，以接收基于与终端设备运行的业务类型集合对应AI模型确定的DRX周期，减少不同业务采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。
附图说明
本公开上述的和/或附加的方面和优点从下面结合附图对实施例的描述中将变得明显和容易理解，其中：
图1为本公开一个实施例所提供的一种DRX周期确定方法的流程示意图；
图2为本公开另一个实施例所提供的一种DRX周期确定方法的流程示意图；
图3为本公开再一个实施例所提供的一种DRX周期确定方法的流程示意图；
图4为本公开又一个实施例所提供的一种DRX周期确定方法的流程示意图；
图5为本公开又一个实施例所提供的一种DRX周期确定方法的流程示意图；
图6为本公开又一个实施例所提供的一种DRX周期确定方法的流程示意图；
图7为本公开又一个实施例所提供的一种DRX周期确定方法的流程示意图；
图8为本公开又一个实施例所提供的一种DRX周期确定方法的流程示意图；
图9为本公开又一个实施例所提供的一种DRX周期确定方法的流程示意图；
图10为本公开又一个实施例所提供的一种DRX周期确定方法的流程示意图；
图11为本公开另一个实施例所提供的一种DRX周期确定方法的流程示意图；
图12为本公开再一个实施例所提供的一种DRX周期确定方法的流程示意图；
图13为本公开又一个实施例所提供的一种DRX周期确定方法的流程示意图；
图14为本公开又一个实施例所提供的一种DRX周期确定方法的流程示意图；
图15为本公开另一个实施例所提供的一种DRX周期确定方法的流程示意图；
图16为本公开再一个实施例所提供的一种DRX周期确定方法的流程示意图；
图17为本公开又一个实施例所提供的一种DRX周期确定方法的流程示意图；
图18为本公开又一个实施例所提供的一种DRX周期确定方法的流程示意图；
图19为本公开又一个实施例所提供的一种DRX周期确定方法的流程示意图；
图20为本公开又一个实施例所提供的一种DRX周期确定方法的流程示意图；
图21为本公开一个实施例所提供的一种DRX周期确定装置的结构示意图；
图22为本公开另一个实施例所提供的一种DRX周期确定装置的结构示意图；
图23为本公开另一个实施例所提供的一种DRX周期确定装置的结构示意图；
图24为本公开另一个实施例所提供的一种DRX周期确定装置的结构示意图；
图25为本公开另一个实施例所提供的一种DRX周期确定装置的结构示意图；
图26为本公开另一个实施例所提供的一种DRX周期确定装置的结构示意图；
图27是本公开一个实施例所提供的一种终端设备的框图；
图28为本公开一个实施例所提供的一种网络侧设备的框图。
具体实施方式
这里将详细地对示例性实施例进行说明，其示例表示在附图中。下面的描述涉及附图时，除非另有表示，不同附图中的相同数字表示相同或相似的要素。以下示例性实施例中所描述的实施方式并不代表与本公开实施例相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本公开实施例的一些方面相一致的装置和方法的例子。
在本公开实施例使用的术语是仅仅出于描述特定实施例的目的，而非旨在限制本公开实施例。在本公开实施例和所附权利要求书中所使用的单数形式的“一种”和“该”也旨在包括多数形式，除非上下文清楚地表示其他含义。还应当理解，本文中使用的术语“和/或”是指并包含一个或多个相关联的列出项目的任何或所有可能组合。
应当理解，尽管在本公开实施例可能采用术语第一、第二、第三等来描述各种信息，但这些信息不应限于这些术语。这些术语仅用来将同一类型的信息彼此区分开。例如，在不脱离本公开实施例范围的情况下，第一信息也可以被称为第二信息，类似地，第二信息也可以被称为第一信息。取决于语境，如在此所使用的词语“如果”及“若”可以被解释成为“在……时”或“当……时”或“响应于确定”。
在通信系统中，第五代移动通信技术(5th Generation Mobile Communication Technology，5G)网络可以利用DRX非连续接收机制来降低终端的能耗，通过给终端配置长短睡眠周期的方式，来到达省电的目的。传统的非连续接收机制通常设置固定的睡眠时间长度，这种方式无法适应数据包到达时间的变化，可能会导致较大的时延。
因此，可以研究采用人工智能方法对终端数据包到达的时间进行预测，并依据预测结果来动态调整DRX睡眠周期，使得终端准确地在数据包到来之前醒来，在没有数据包到达的时候进入睡眠状态，从而在保证数据传输时延的情况下，尽量降低终端能耗。
其中，在本公开的一个实施例之中，终端设备中运行的业务类型很多。该业务类型例如包括在线游戏业务类型，视频业务类型，网页浏览业务类型等。其中，不同的业务类型对应不同的数据包达到规律。当使用一个AI模型确定DRX睡眠周期时，无法提取出每个业务的固有特征，影响周期推理的精度，使得DRX睡眠周期确定的准确性较低。
其中，在本公开的一个实施例之中，人工智能中的递归神经网络(Recurrent Neural Network，RNN)在预测给定序列的未来值方面已经显示出令人难以置信的结果。其中，LSTM是一种流行的RNN，它是专门用来学习序列的长期依赖关系，以预测序列的未来值的。长期依赖指的是序列，它的预测输出值依赖于以前输入值的长序列，而不是唯一的以前输入值。
示例地，在本公开的一个实施例之中，可以将历史数据包到达的抖动时延序列作为训练数据来训练LSTM模型，然后在每个数据包到达时采用训练好的模型预测下一个数据包到达的抖动时延值。该方法可以在大多数情况下能够获得比较好的性能，使得预测的平均误差较小。
示例地，在本公开的一个实施例之中，基站例如可以在每一个数据包到达时采用LSTM网络预测终端设备下一个数据包到达的时间，然后依据预测结果对终端设备DRX睡眠周期进行配置，保证终端设备在数据包到达之前醒来，在没有数据包到达时处于睡眠状态。
下面参考附图对本公开实施例所提供的一种DRX周期确定方法、装置、设备及存储介质进行详细描述。
图1为本公开实施例所提供的一种DRX周期确定方法的流程示意图，该方法由终端设备执行，如图1所示，该方法可以包括以下步骤：
步骤101、接收网络侧设备发送的第一DRX周期，其中，第一DRX周期是基于人工智能AI模型确定的，且AI模型与终端设备运行的业务类型集合对应。
需要说明的是，在本公开的一个实施例之中，终端设备可以是指向用户提供语音和/或数据连通性的设备。终端设备可以经RAN(Radio Access Network，无线接入网)与一个或多个核心网进行通信，终端设备可以是物联网终端，如传感器设备、移动电话(或称为“蜂窝”电话)和具有物联网终端的计算机，例如，可以是固定式、便携式、袖珍式、手持式、计算机内置的或者车载的装置。例如，站(Station，STA)、订户单元(subscriber unit)、订户站(subscriber station)，移动站(mobile station)、移动台(mobile)、远程站(remote station)、接入点、远程终端(remoteterminal)、接入终端(access terminal)、用户装置(user terminal)或用户代理(useragent)。或者，终端设备也可以是无人飞行器的设备。或者，终端设备也可以是车载设备，比如，可以是具有无线通信功能的行车电脑，或者是外接行车电脑的无线终端。或者，终端设备也可以是路边设备，比如，可以是具有无线通信功能的路灯、信号灯或者其它路边设备等。
其中，在本公开的一个实施例之中，第一DRX周期为网络侧确定的，发送至终端设备的周期。该第一DRX周期中的第一仅用于与其余DRX周期进行区分，并不特指某一固定周期。
示例地，在本公开的一个实施例之中，当终端设备接收网络侧设备发送的第一DRX周期时，终端设备可以基于该第一DRX周期接收数据包，以保证数据传输时延的情况下，降低终端设备的能耗。
其中，在本公开的一个实施例之中，接收网络侧设备发送的第一DRX周期，包括：
响应于AI模型部署于网络侧设备，接收网络侧设备发送的网络侧设备采用AI模型确定的第一DRX周期。
示例地，在本公开的一个实施例之中，接收网络侧设备发送的第一DRX周期，包括：
响应于AI模型部署于终端设备，采用AI模型对终端设备运行的业务类型集合进行DRX周期预测，确定第二DRX周期；
发送第二DRX周期至网络侧设备；
接收网络侧设备根据第二DRX周期确定的第一DRX周期。
其中，在本公开的一个实施例之中，第二DRX周期是指响应于AI模型部署于终端设备，终端设备采用AI模型对终端设备运行的业务类型集合进行DRX周期预测，确定的周期。其中，第二DRX周期中的第二仅用于与其余DRX周期进行区分，并不特指某一固定周期。
示例地，在本公开的一个实施例之中，终端设备可以发送第二DRX周期至网络侧设备，网络侧设备可以根据第二DRX周期确定第一DRX周期，网络侧设备可以发送第一DRX至终端设备。
示例地，在本公开的一个实施例之中，终端设备可以发送第二DRX周期至网络侧设备，网络侧设备可以接收该第二DRX周期。
其中，在本公开的一个实施例之中，采用AI模型对终端设备运行的业务类型集合进行DRX周期预测，确定第二DRX周期，包括：
对终端设备运行的业务集合进行分类，确定业务集合的业务类型集合；
采用与业务类型集合对应的AI模型进行DRX周期预测，确定第二DRX周期。
以及，在本公开的一个实施例之中，采用与业务类型集合对应的AI模型进行DRX周期预测，确定第二DRX周期，包括：
响应于业务类型集合包括一种业务类型，采用与业务类型对应的AI模型进行DRX周期预测，确定第二DRX周期。
以及，在本公开的一个实施例之中，采用与业务类型集合对应的AI模型进行DRX周期预测，确定第二DRX周期，包括：
响应于业务类型集合包括至少两种业务类型，采用与至少两种业务类型对应的AI模型进行DRX周期预测，确定第二DRX周期。
示例地，在本公开的一个实施例之中，采用与业务类型集合对应的AI模型进行DRX周期预测，确定第二DRX周期，包括：
响应于业务类型集合包括至少两种业务类型，且未存在与至少两种业务类型对应的AI模型，采用与至少两种业务类型中各业务类型对应的AI模型分别确定各业务类型对应的第五DRX周期；
基于至少两个第五DRX周期，确定第二DRX周期；
或，
响应于业务类型集合包括至少两种业务类型，且未存在与至少两种业务类型对应的AI模型，不采用AI模型进行DRX周期预测。
其中，在本公开的一个实施例之中，第五DRX周期用于指示AI模型部署在终端设备时，响应于业务类型集合包括至少两种业务类型，且未存在与至少两种业务类型对应的AI模型，终端设备采用与至少两种业务类型中各业务类型对应的AI模型分别确定各业务类型对应的周期。该第五DRX周期的个数为至少两个。终端设备可以基于至少两个第五DRX周期，确定第二DRX周期。
其中，在本公开的一个实施例之中，该方法还包括：
基于终端设备运行的业务集合，发送针对业务集合的第一模型下载请求至网络侧设备；
接收网络侧设备针对第一模型下载请求发送的AI模型，其中，AI模型与业务集合的业务类型集合对应。
其中，在本公开的一个实施例之中，该方法还包括：
响应于针对AI模型的模型下载指令，发送第二模型下载请求至网络侧设备；
接收网络侧设备针对第二模型下载请求发送的AI模型。
其中，在本公开的一个实施例之中，其中，AI模型为基于与AI模型对应的业务类型进行训练得到的模型。
综上所述，在本公开实施例之中，通过接收网络侧设备发送的第一DRX周期，其中，第一DRX周期是基于人工智能AI模型确定的，且AI模型与终端设备运行的业务类型集合对应。在本公开实施例之中，由于第一DRX周期为根据终端设备运行的业务类型集合对应的AI模型确定的，减少不同业务采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。本公开针对于“DRX周期确定”这一情形提供了一种处理方法，以接收基于与终端设备运行的业务类型集合对应AI模型确定的DRX周期，减少不同业务采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。
图2为本公开实施例所提供的一种DRX周期确定方法的流程示意图，该方法由终端设备执行，如图2所示，该方法可以包括以下步骤：
步骤201、响应于AI模型部署于网络侧设备，接收网络侧设备发送的网络侧设备采用AI模型确定的第一DRX周期。
其中，在本公开的一个实施例之中，第一DRX周期是基于人工智能AI模型确定的，且AI模型与终端设备运行的业务类型集合对应。
其中，在本公开的一个实施例之中，AI模型为基于与AI模型对应的业务类型进行训练得到的模型。例如，可以对业务类型进行分类，针对不同的业务类型使用不同的AI模型进行DRX周期预测。例如，视频类型对应的AI模型不同于文字下载类型对应的AI模型。其中，同一AI模型可以仅与一种业务类型对应，同一AI模型可以与至少两种业务类型对应。
示例地，在本公开的一个实施例之中，例如，当AI模型仅与视频类型对应时，可以训练得到与视频类型对应的AI模型，可以使用AI模型对视频类型的业务进行DRX周期预测。例如，当AI模型仅与视频类型和文字下载类型对应时，可以训练得到与视频类型和文字下载类型对应的AI模型，可以使用AI模型对视频类型和文字下载类型的业务进行DRX周期预测。
以及，在本公开的一个实施例之中，AI模型可以部署于网络侧设备。响应于AI模型部署于网络侧设备，终端设备可以接收网络侧设备发送的网络侧设备采用AI模型确定的第一DRX周期。例如，网络侧设备采用采用AI模型确定第一DRX周期时，网络侧设备可以发送该第一DRX周期至终端设备。
综上所述，在本公开实施例之中，通过响应于AI模型部署于网络侧设备，接收网络侧设备发送的网络侧设备采用AI模型确定的第一DRX周期。在本公开实施例之中，由于第一DRX周期为根据终端设备运行的业务类型集合对应的AI模型确定的，减少不同业务采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。本公开的实施例中，终端设备无需设置AI模型，可以降低终端设备侧模型部署的复杂度。本公开针对于“DRX周期确定”这一情形提供了一种处理方法，以接收基于与终端设备运行的业务类型集合对应AI模型确定的DRX周期，减少不同业务采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。
图3为本公开实施例所提供的一种DRX周期确定方法的流程示意图，该方法由终端设备执行，如图3所示，该方法可以包括以下步骤：
步骤301、响应于AI模型部署于终端设备，采用AI模型对终端设备运行的业务类型集合进行DRX周期预测，确定第二DRX周期；
步骤302、发送第二DRX周期至网络侧设备；
步骤303、接收网络侧设备根据第二DRX周期确定的第一DRX周期。
其中，在本公开的一个实施例之中，AI模型为基于与AI模型对应的业务类型进行训练得到的模型。
其中，在本公开的一个实施例之中，第一DRX周期是基于人工智能AI模型确定的，且AI模型与终端设备运行的业务类型集合对应。
其中，在本公开的一个实施例之中，响应于AI模型部署于终端设备，终端设备可以采用AI模型对终端设备运行的业务类型集合进行DRX周期预测，确定第二DRX周期。终端设备可以发送第二DRX周期至网络侧设备。网络侧设备可以接收该第二DRX周期，并根据该第二DRX周期确定第一DRX周期。网络侧设备可以发送根据第二DRX周期确定的第一DRX周期至终端设备。终端设备可以接收网络侧设备根据第二DRX周期确定的第一DRX周期。
示例地，在本公开的一个实施例之中，终端设备确定的第二DRX周期例如还可以是终端设备根据自身电量和终端设备运行的业务集合确定的DRX周期。
示例地，在本公开的一个实施例中，第一DRX周期例如可以是网络侧设备对第二DRX周期进行调整，得到的DRX周期。网络侧设备恩例如可以使用下行控制信息(Downlink control information，DCI)或者高层信息对第二DRX周期进行调整，得到第一DRX周期。
综上所述，在本公开实施例之中，通过响应于AI模型部署于终端设备，采用AI模型对终端设备运行的业务类型集合进行DRX周期预测，确定第二DRX周期；发送第二DRX周期至网络侧设备；接收网络侧设备根据第二DRX周期确定的第一DRX周期。在本公开实施例之中，由于第一DRX周期为根据终端设备运行的业务类型集合对应的AI模型确定的，减少不同业务采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。本公开的实施例中具体公开了第一DRX周期为根据第二DRX周期确定的方案。本公开针对于“DRX周期确定”这一情形提供了一种处理方法，以接收基于与终端设备运行的业务类型集合对应AI模型确定的DRX周期，减少不同业务采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。
图4为本公开实施例所提供的一种DRX周期确定方法的流程示意图，该方法由终端设备执行，如图4所示，该方法可以包括以下步骤：
步骤401、对终端设备运行的业务集合进行分类，确定业务集合的业务类型集合；
步骤402、采用与业务类型集合对应的AI模型进行DRX周期预测，确定第二DRX周期。
其中，在本公开的一个实施例之中，AI模型为基于与AI模型对应的业务类型进行训练得到的模型。
示例地，在本公开的一个实施例之中，业务集合例如可以指包括至少一个运行业务的集合。该业务集合并不特指某一固定集合。例如，当终端设备运行的业务数量发生变化时，该业务集合也可以相应变化。例如，当终端设备运行的具体业务发生变化时，该业务集合也可以相应变化。
示例地，在本公开的一个实施例之中，业务类型集合是指与业务集合对应的类型集合。该业务类型集合例如可以指包括至少一个业务类型的集合。
示例地，在本公开的一个实施例之中，响应于AI模型部署于终端设备，终端设备可以确定终端设备运行的业务集合。终端设备可以对业务集合进行分类，确定该业务集合的业务类型集合。终端设备可以采用与业务类型集合对应的AI模型进行DRX周期预测，确定第二DRX周期。其中，业务集合对应的业务数量不一定与业务类型集合对应的业务类型数量相等。例如，当业务集合存在业务类型相同的两个业务时，该业务集合对应的业务数量与业务类型集合对应的业务类型数量不相等。
综上所述，在本公开实施例之中，通过对终端设备运行的业务集合进行分类，确定业务集合的业务类型集合；采用与业务类型集合对应的AI模型进行DRX周期预测，确定第二DRX周期。在本公开实施例之中，由于第二DRX周期为根据终端设备运行的业务类型集合对应的AI模型确定的，减少不同业务终端设备采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。本公开的实施例中具体公开了第二DRX周期确定的方案。本公开针对于“DRX周期确定”这一情形提供了一种处理方法，以基于与终端设备运行的业务类型集合对应AI模型确定DRX周期，减少不同业务采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。
图5为本公开实施例所提供的一种DRX周期确定方法的流程示意图，该方法由终端设备执行，如图5所示，该方法可以包括以下步骤：
步骤501、响应于业务类型集合包括一种业务类型，采用与业务类型对应的AI模型进行DRX周期预测，确定第二DRX周期。
其中，在本公开的一个实施例之中，AI模型为基于与AI模型对应的业务类型进行训练得到的模型。
以及，在本公开的一个实施例之中，响应于业务类型集合包括一种业务类型，终端设备采用与该业务类型对应的AI模型进行DRX周期预测，确定第二DRX周期。
示例地，在本公开的一个实施例之中，响应于业务类型集合包括一种业务类型，该一种业务类型例如可以是视频类型。终端设备采用与该视频类型对应的AI模型进行DRX周期预测，确定第二DRX周期。
综上所述，在本公开实施例之中，通过响应于业务类型集合包括一种业务类型，采用与业务类型对应的AI模型进行DRX周期预测，确定第二DRX周期。在本公开实施例之中，由于第二DRX周期为根据终端设备运行的业务类型集合对应的AI模型确定的，减少不同业务采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。本公开的实施例中具体公开了业务类型集合包括一种业务类型时第二DRX周期确定的方案。本公开针对于“DRX周期确定”这一情形提供了一种处理方法，以基于与终端设备运行的业务类型集合对应AI模型确定DRX周期，减少不同业务采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。
图6为本公开实施例所提供的一种DRX周期确定方法的流程示意图，该方法由终端设备执行，如图6所示，该方法可以包括以下步骤：
步骤601、响应于业务类型集合包括至少两种业务类型，采用与至少两种业务类型对应的AI模型进行DRX周 期预测，确定第二DRX周期。
其中，在本公开的一个实施例之中，AI模型为基于与AI模型对应的业务类型进行训练得到的模型。本公开实施例的AI模型为基于与AI模型对应的至少两种业务类型进行训练得到的模型。
以及，在本公开的一个实施例之中，响应于业务类型集合包括至少两种业务类型，终端设备可以采用与至少两种业务类型对应的AI模型进行DRX周期预测，确定第二DRX周期。该AI模型同时与至少两种业务类型对应。例如，该AI模型为基于与AI模型对应的至少两种业务类型进行训练得到的模型。
示例地，在本公开的一个实施例之中，响应于业务类型集合包括两种业务类型，该两种业务类型例如是视频类型和文字下载类型，终端设备可以采用与视频类型和文字下载类型对应的AI模型进行DRX周期预测，确定第二DRX周期。
综上所述，在本公开实施例之中，通过响应于业务类型集合包括至少两种业务类型，采用与至少两种业务类型对应的AI模型进行DRX周期预测，确定第二DRX周期。在本公开实施例之中，由于第二DRX周期为根据终端设备运行的业务类型集合对应的AI模型确定的，减少不同业务采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。本公开的实施例中具体公开了业务类型集合包括至少两种业务类型时第二DRX周期确定的方案。本公开针对于“DRX周期确定”这一情形提供了一种处理方法，以基于与终端设备运行的业务类型集合对应AI模型确定DRX周期，减少不同业务采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。
图7为本公开实施例所提供的一种DRX周期确定方法的流程示意图，该方法由终端设备执行，如图7所示，该方法可以包括以下步骤：
步骤701、响应于业务类型集合包括至少两种业务类型，且未存在与至少两种业务类型对应的AI模型，采用与至少两种业务类型中各业务类型对应的AI模型分别确定各业务类型对应的第五DRX周期；
步骤702、基于至少两个第五DRX周期，确定第二DRX周期；
步骤703、响应于业务类型集合包括至少两种业务类型，且未存在与至少两种业务类型对应的AI模型，不采用AI模型进行DRX周期预测。
其中，在本公开的一个实施例之中，步骤701-702和步骤703择一执行，即，执行步骤701-702时，不执行步骤703，执行步骤703时不执行步骤701-702。
其中，在本公开的一个实施例之中，AI模型为基于与AI模型对应的业务类型进行训练得到的模型。
以及，在本公开的一个实施例之中，响应于业务类型集合包括至少两种业务类型，且未存在与至少两种业务类型对应的AI模型，终端设备可以采用与至少两种业务类型中各业务类型对应的AI模型分别确定各业务类型对应的第五DRX周期，终端设备基于至少两个第五DRX周期，可以确定第二DRX周期。
示例地，在本公开的一个实施例之中，响应于业务类型集合包括两种业务类型，该两种业务类型例如是视频类型和文字下载类型，终端设备未存在与视频类型和文字下载类型对应的AI模型时，终端设备可以采用视频类型对应的AI模型确定与视频类型对应的第五DRX周期，终端设备可以采用文字下载类型对应的AI模型确定与文字下载类型对应的第五DRX周期。终端设备可以基于视频类型对应的第五DRX周期和文字下载类型对应的第五DRX周期，确定第二DRX周期。
以及，在本公开的一个实施例之中，响应于业务类型集合包括至少两种业务类型，且未存在与至少两种业务类型对应的AI模型，终端设备可以不采用AI模型进行DRX周期预测。
示例地，在本公开的一个实施例之中，响应于业务类型集合包括两种业务类型，该两种业务类型例如是视频类型和文字下载类型，终端设备中未存在与视频类型和文字下载类型对应的AI模型时，终端设备可以不采用AI模型进行DRX周期预测。
综上所述，在本公开实施例之中，通过响应于业务类型集合包括至少两种业务类型，且未存在与至少两种业务类型对应的AI模型，采用与至少两种业务类型中各业务类型对应的AI模型分别确定各业务类型对应的第五DRX周期；基于至少两个第五DRX周期，确定第二DRX周期；或响应于业务类型集合包括至少两种业务类型，且未存在与至少两种业务类型对应的AI模型，不采用AI模型进行DRX周期预测。在本公开实施例之中，由于第二DRX周期为根据终端设备运行的业务类型集合对应的AI模型确定的，减少不同业务采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。本公开的实施例中具体公开了业务类型集合包括至少两种业务类型且未存在与至少两种业务类型对应的AI模型时第二DRX周期确定的方案。本公开针对于“DRX周期确定”这一情形提供了一种处理方法，以基于与终端设备运行的业务类型集合对应AI模型确定DRX周期，减少不同业务采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。
图8为本公开实施例所提供的一种DRX周期确定方法的流程示意图，该方法由终端设备执行，如图8所示，该方法可以包括以下步骤：
步骤801、基于终端设备运行的业务集合，发送针对业务集合的第一模型下载请求至网络侧设备；
步骤802、接收网络侧设备针对第一模型下载请求发送的AI模型，其中，AI模型与业务集合的业务类型集合对应。
其中，在本公开的一个实施例之中，AI模型为基于与AI模型对应的业务类型进行训练得到的模型。
以及，在本公开的一个实施例之中，第一模型下载请求是指终端设备基于终端设备运行的业务集合所发送的请求。第一模型下载请求中的第一仅用于与其余模型下载请求进行区分，并不特指某一固定的模型下载请求。
示例地，在本公开的一个实施例之中，基于终端设备运行的业务集合，终端设备可以发送针对业务集合的第一模型下载请求至网络侧设备。终端设备可以接收网络侧设备针对第一模型下载请求发送的AI模型，其中，AI模型与业务集合的业务类型集合对应。
示例地，在本公开的一个实施例之中，终端设备运行的业务集合例如可以包括视频播放业务，基于终端设备运行的视频播放业务，终端设备可以发送针对视频播放业务的第一模型下载请求至网络侧设备。终端设备可以接收网络侧设备针对第一模型下载请求发送的AI模型，其中，AI模型与视频播放业务的视频类型对应。
综上所述，在本公开实施例之中，基于终端设备运行的业务集合，发送针对业务集合的第一模型下载请求至网络侧设备；接收网络侧设备针对第一模型下载请求发送的AI模型，其中，AI模型与业务集合的业务类型集合对应。在本公开实施例之中，终端设备可以发送模型下载请求至网络侧设备，针对不同的下载情况可以发送不同的模型下载请求至网络侧设备，可以提高AI模型下载的便利性，同时，接收网络侧设备针对第一模型下载请求发送的AI模型，由于AI模型与业务集合的业务类型集合对应，可以提高AI模型与业务集合的匹配性。
图9为本公开实施例所提供的一种DRX周期确定方法的流程示意图，该方法由终端设备执行，如图9所示，该方法可以包括以下步骤：
步骤901、响应于针对AI模型的模型下载指令，发送第二模型下载请求至网络侧设备；
步骤902、接收网络侧设备针对第二模型下载请求发送的AI模型。
其中，在本公开的一个实施例之中，AI模型为基于与AI模型对应的业务类型进行训练得到的模型。
示例地，在本公开的一个实施例之中，基于终端设备运行的业务集合，终端设备发送针对业务集合的第一模型下载请求至网络侧设备时，终端设备可以对终端设备运行的业务进行监测，基于监测结果，发送第一模型下载请求至网络侧设备。
以及，在本公开的一个实施例之中，第二模型下载请求是指终端设备针对AI模型的模型下载指令所发送的请求。第二模型下载请求中的第二仅用于与其余模型下载请求进行区分，并不特指某一固定的模型下载请求。
示例地，在本公开的一个实施例之中，终端设备运行的业务集合例如可以包括游戏业务，基于终端设备运行的游戏业务，终端设备可以发送针对游戏业务的第一模型下载请求至网络侧设备。终端设备可以接收网络侧设备针对第一模型下载请求发送的AI模型，其中，AI模型与游戏业务的视频类型对应。
示例地，在本公开的一个实施例之中，响应于针对AI模型的模型下载指令，终端设备可以发送第二模型下载请求至网络侧设备。终端设备可以接收网络侧设备针对第二模型下载请求发送的AI模型。
综上所述，在本公开实施例之中，响应于针对AI模型的模型下载指令，发送第二模型下载请求至网络侧设备；、接收网络侧设备针对第二模型下载请求发送的AI模型。在本公开实施例之中，终端设备可以响应于针对AI模型的模型下载指令，发送模型下载请求至网络侧设备，可以提高AI模型下载的便利性，减少AI模型与业务集合不匹配的情况，可以提高AI模型与业务集合的匹配性。
图10为本公开实施例所提供的一种DRX周期确定方法的流程示意图，该方法由网络侧设备执行，如图10所示，该方法可以包括以下步骤：
步骤1001、发送第一DRX周期至终端设备，其中，第一DRX周期是基于人工智能AI模型确定的，且AI模型与终端设备运行的业务类型集合对应。
其中，在本公开的一个实施例之中，在发送第一DRX周期至终端设备之前，还包括：
响应于AI模型部署于网络侧设备，采用AI模型对终端设备运行的业务类型集合进行DRX周期预测，生成第三DRX周期；
根据第三DRX周期，确定第一DRX周期。
以及，在本公开的一个实施例之中，采用AI模型对终端设备运行的业务类型集合进行DRX周期预测，确定第三DRX周期，包括：
对终端设备运行的业务集合进行分类，确定业务集合的业务类型集合；
采用与业务类型集合对应的AI模型进行DRX周期预测，确定第三DRX周期。
示例地，在本公开的一个实施例之中，采用与业务类型集合对应的AI模型进行DRX周期预测，确定第三DRX周期，包括：
响应于业务类型集合包括一种业务类型，采用与业务类型对应的AI模型进行DRX周期预测，确定第三DRX周期。
以及，在本公开的一个实施例之中，采用与业务类型集合对应的AI模型进行DRX周期预测，确定第三DRX周期，包括：
响应于业务类型集合包括至少两种业务类型，采用与至少两种业务类型对应的AI模型进行DRX周期预测，确定第三DRX周期。
示例地，在本公开的一个实施例之中，采用与业务类型集合对应的AI模型进行DRX周期预测，确定第三DRX周期，包括：
响应于业务类型集合包括至少两种业务类型，且未存在与至少两种业务类型对应的AI模型，采用与至少两种业务类型中各业务类型对应的AI模型分别确定各业务类型对应的第四DRX周期；
基于至少两个第四DRX周期，确定第三DRX周期；
或，
响应于业务类型集合包括至少两种业务类型，且未存在与至少两种业务类型对应的AI模型，不采用AI模型进行DRX周期预测。
示例地，在本公开的一个实施例之中，在发送第一DRX周期至终端设备之前，还包括：
响应于AI模型部署于终端设备，接收终端设备发送的终端设备采用AI模型确定的第二DRX周期；
根据第二DRX周期，确定第一DRX周期。
进一步地，在本公开的一个实施例之中，该方法还包括：
接收终端设备发送的第一模型下载请求，其中，第一模型下载请求为针对终端设备运行的业务集合的请求；
发送针对第一模型下载请求的AI模型至终端设备，其中，AI模型与业务集合的业务类型集合对应。
进一步地，在本公开的一个实施例之中，该方法还包括：
接收终端设备针对AI模型的模型下载指令发送的第二模型下载请求；
发送针对第二模型下载请求的AI模型至终端设备。
示例地，在本公开的一个实施例之中，其中，AI模型为基于与AI模型对应的业务类型进行训练得到的模型。
示例地，在本公开的一个实施例之中，该AI模型的输入数据例如可以是前N个数据包的到达间隔，该AI模型的输出例如可以是后M个数据包的到达间隔。其中，N和M为正整数。
示例地，在本公开的一个实施例之中，针对不同的业务类型，或者针对不同的AI模型，N和M的取值可以不同。也就是说，针对不同的业务类型，所训练得到的AI模型也会不同。
综上所述，在本公开实施例之中，通过发送第一DRX周期至终端设备，其中，第一DRX周期是基于人工智能AI模型确定的，且AI模型与终端设备运行的业务类型集合对应。在本公开实施例之中，由于第一DRX周期为根据终端设备运行的业务类型集合对应的AI模型确定的，减少不同业务采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。本公开针对于“DRX周期确定”这一情形提供了一种处理方法，以发送基于与终端设备运行的业务类型集合对应AI模型确定的DRX周期至终端设备，减少不同业务采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。
图11为本公开实施例所提供的一种DRX周期确定方法的流程示意图，该方法由网络侧设备执行，如图11所示，该方法可以包括以下步骤：
步骤1101、响应于AI模型部署于网络侧设备，采用AI模型对终端设备运行的业务类型集合进行DRX周期预测，生成第三DRX周期；
步骤1102、根据第三DRX周期，确定第一DRX周期。
其中，在本公开的一个实施例之中，AI模型为基于与AI模型对应的业务类型进行训练得到的模型。
以及，在本公开的一个实施例之中，第三DRX周期为AI模型部署于网络侧设备，网络侧设备采用AI模型对终端设备运行的业务类型集合进行DRX周期预测，生成的DRX周期。该第三DRX周期中的第三仅用于其余DRX周期进行区分，并不特指某一固定DRX周期。
示例地，在本公开的一个实施例之中，响应于AI模型部署于网络侧设备，网络侧设备可以采用AI模型对终端设备运行的业务类型集合进行DRX周期预测，生成第三DRX周期，网络侧设备可以根据第三DRX周期，确定第一DRX周期。
以及，在本公开的一个实施例之中，网络侧设备可以发送第一DRX周期至终端设备。
示例地，在本公开的一个实施例之中，网络侧设备可以根据第三DRX周期，确定第一DRX周期时，网络侧设备可以使用DCI信息或者高层信息对第三DRX周期进行调整，确定第一DRX周期。
其中，在本公开的一个实施例之中，针对不同的终端设备，网络侧可以采用不同的AI模型对终端设备运行的业务类型集合进行DRX周期预测。网络侧设备所使用的AI模型例如可以根据终端设备的使用行为确定。
示例地，在本公开的一个实施例中，网络侧设备所部署的AI模型的数量可以是一个或者多个。
综上所述，在本公开实施例之中，通过响应于AI模型部署于网络侧设备，采用AI模型对终端设备运行的业务类型集合进行DRX周期预测，生成第三DRX周期；根据第三DRX周期，确定第一DRX周期。在本公开实施例之中，由于第一DRX周期为根据终端设备运行的业务类型集合对应的AI模型确定的，减少不同业务采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。本公开的实施例中具体公开了第一DRX周期为根据第三DRX周期确定的方案。本公开针对于“DRX周期确定”这一情形提供了一种处理方法，以基于与终端设备运行的业务类型集合对应AI模型确定DRX周期，减少不同业务采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。
图12为本公开实施例所提供的一种DRX周期确定方法的流程示意图，该方法由网络侧设备执行，如图12所示，该方法可以包括以下步骤：
步骤1201、对终端设备运行的业务集合进行分类，确定业务集合的业务类型集合；
步骤1202、采用与业务类型集合对应的AI模型进行DRX周期预测，确定第三DRX周期。
其中，在本公开的一个实施例之中，AI模型为基于与AI模型对应的业务类型进行训练得到的模型。
示例地，在本公开的一个实施例之中，业务集合例如可以指包括至少一个运行业务的集合。该业务集合并不特指某一固定集合。例如，当终端设备运行的业务数量发生变化时，该业务集合也可以相应变化。例如，当终端设备运行的具体业务发生变化时，该业务集合也可以相应变化。
示例地，在本公开的一个实施例之中，业务类型集合是指与业务集合对应的类型集合。该业务类型集合例如可以指包括至少一个业务类型的集合。
示例地，在本公开的一个实施例之中，响应于AI模型部署于网络侧设备，网络侧设备可以确定终端设备运行的业务集合。网络侧设备例如可以接收终端设备发送的业务集合，网络侧设备例如还可以根据与终端设备之间的通信数据确定终端设备运行的业务集合。
示例地，在本公开的一个实施例之中，网络侧设备可以对业务集合进行分类，确定该业务集合的业务类型集合。网络侧设备可以采用与业务类型集合对应的AI模型进行DRX周期预测，确定第三DRX周期。其中，业务集合对应的业务数量不一定与业务类型集合对应的业务类型数量相等。例如，当业务集合存在业务类型相同的两个业务时，该业务集合对应的业务数量与业务类型集合对应的业务类型数量不相等。
综上所述，在本公开实施例之中，通过对终端设备运行的业务集合进行分类，确定业务集合的业务类型集合；采用与业务类型集合对应的AI模型进行DRX周期预测，确定第三DRX周期。在本公开实施例之中，由于第三DRX周期为根据终端设备运行的业务类型集合对应的AI模型确定的，减少不同业务网络侧设备采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。本公开的实施例中具体公开了第三DRX周期确定的方案。本公开针对于“DRX周期确定”这一情形提供了一种处理方法，以基于与终端设备运行的业务类型集合对应AI模型确定DRX周期，减少不同业务采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。
图13为本公开实施例所提供的一种DRX周期确定方法的流程示意图，该方法由网络侧设备执行，如图13所示，该方法可以包括以下步骤：
步骤1301、响应于业务类型集合包括一种业务类型，采用与业务类型对应的AI模型进行DRX周期预测，确定第三DRX周期。
其中，在本公开的一个实施例之中，AI模型为基于与AI模型对应的业务类型进行训练得到的模型。
以及，在本公开的一个实施例之中，响应于业务类型集合包括一种业务类型，网络侧设备可以采用与该业务类型对应的AI模型进行DRX周期预测，确定第三DRX周期。
示例地，在本公开的一个实施例之中，响应于业务类型集合包括一种业务类型，该一种业务类型例如可以是视频类型。网络侧设备可以采用与该视频类型对应的AI模型进行DRX周期预测，确定第三DRX周期。
综上所述，在本公开实施例之中，通过响应于业务类型集合包括一种业务类型，采用与业务类型对应的AI模型进行DRX周期预测，确定第三DRX周期。在本公开实施例之中，由于第三DRX周期为根据终端设备运行的业务类型集合对应的AI模型确定的，减少不同业务网络侧设备采用同一AI模型进行DRX周期预测，使得DRX周期 确定不准确的情况，可以提高DRX周期确定的准确性。本公开的实施例中具体公开了业务类型集合包括一种业务类型时第三DRX周期确定的方案。本公开针对于“DRX周期确定”这一情形提供了一种处理方法，以基于与终端设备运行的业务类型集合对应AI模型确定DRX周期，减少不同业务采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。
图14为本公开实施例所提供的一种DRX周期确定方法的流程示意图，该方法由网络侧设备执行，如图14所示，该方法可以包括以下步骤：
步骤1401、响应于业务类型集合包括至少两种业务类型，采用与至少两种业务类型对应的AI模型进行DRX周期预测，确定第三DRX周期。
其中，在本公开的一个实施例之中，AI模型为基于与AI模型对应的业务类型进行训练得到的模型。
以及，在本公开的一个实施例之中，响应于业务类型集合包括至少两种业务类型，网络侧设备可以采用与至少两种业务类型对应的AI模型进行DRX周期预测，确定第三DRX周期。该AI模型同时与至少两种业务类型对应。例如，该AI模型为基于与AI模型对应的至少两种业务类型进行训练得到的模型。
示例地，在本公开的一个实施例之中，响应于业务类型集合包括两种业务类型，该两种业务类型例如是视频类型和文字下载类型，网络侧设备可以采用与视频类型和文字下载类型对应的AI模型进行DRX周期预测，确定第三DRX周期。
综上所述，在本公开实施例之中，通过响应于业务类型集合包括至少两种业务类型，采用与至少两种业务类型对应的AI模型进行DRX周期预测，确定第三DRX周期。在本公开实施例之中，由于第三DRX周期为根据终端设备运行的业务类型集合对应的AI模型确定的，减少不同业务网络侧设备采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。本公开的实施例中具体公开了业务类型集合包括至少两种业务类型时第三DRX周期确定的方案。本公开针对于“DRX周期确定”这一情形提供了一种处理方法，以基于与终端设备运行的业务类型集合对应AI模型确定DRX周期，减少不同业务采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。
图15为本公开实施例所提供的一种DRX周期确定方法的流程示意图，该方法由网络侧设备执行，如图15所示，该方法可以包括以下步骤：
步骤1501、响应于业务类型集合包括至少两种业务类型，且未存在与至少两种业务类型对应的AI模型，采用与至少两种业务类型中各业务类型对应的AI模型分别确定各业务类型对应的第四DRX周期；
步骤1502、基于至少两个第四DRX周期，确定第三DRX周期；
或，
步骤1503、响应于业务类型集合包括至少两种业务类型，且未存在与至少两种业务类型对应的AI模型，不采用AI模型进行DRX周期预测。
其中，在本公开的一个实施例之中，AI模型为基于与AI模型对应的业务类型进行训练得到的模型。
其中，在本公开的一个实施例之中，步骤1501-1502和步骤1503择一执行，即，执行步骤1501-1502时，不执行步骤1503，执行步骤1503时不执行步骤1501-1502。
以及，在本公开的一个实施例之中，第四DRX周期用于指示AI模型部署在网络侧设备时，响应于业务类型集合包括至少两种业务类型，且未存在与至少两种业务类型对应的AI模型，网络侧设备采用与至少两种业务类型中各业务类型对应的AI模型分别确定各业务类型对应的周期。该第四DRX周期的个数为至少两个。
以及，在本公开的一个实施例之中，响应于业务类型集合包括至少两种业务类型，且未存在与至少两种业务类型对应的AI模型，网络侧设备可以采用与至少两种业务类型中各业务类型对应的AI模型分别确定各业务类型对应的第四DRX周期，终端设备基于至少两个第四DRX周期，可以确定第三DRX周期。
示例地，在本公开的一个实施例之中，响应于业务类型集合包括两种业务类型，该两种业务类型例如是视频类型和文字下载类型。响应于AI模型部署于网络侧设备，且未存在与视频类型和文字下载类型对应的AI模型时，网络侧设备可以采用视频类型对应的AI模型确定与视频类型对应的第四DRX周期，终端设备可以采用文字下载类型对应的AI模型确定与文字下载类型对应的第四DRX周期。终端设备可以基于视频类型对应的第四DRX周期和文字下载类型对应的第四DRX周期，确定第三DRX周期。
以及，在本公开的一个实施例之中，响应于业务类型集合包括至少两种业务类型，且未存在与至少两种业务类型对应的AI模型，网络侧设备可以不采用AI模型进行DRX周期预测。
示例地，在本公开的一个实施例之中，响应于业务类型集合包括两种业务类型，该两种业务类型例如是视频类型和文字下载类型，网络侧设备中未存在与视频类型和文字下载类型对应的AI模型时，网络侧设备可以不采用AI模型进行DRX周期预测。
综上所述，在本公开实施例之中，通过响应于业务类型集合包括至少两种业务类型，且未存在与至少两种业务类型对应的AI模型，采用与至少两种业务类型中各业务类型对应的AI模型分别确定各业务类型对应的第四DRX周期；基于至少两个第四DRX周期，确定第三DRX周期；或，响应于业务类型集合包括至少两种业务类型，且未存在与至少两种业务类型对应的AI模型，不采用AI模型进行DRX周期预测。在本公开实施例之中，由于第三DRX周期为根据终端设备运行的业务类型集合对应的AI模型确定的，减少不同业务网络侧设备采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。本公开的实施例中具体公开了业务类型集合包括至少两种业务类型时第三DRX周期确定的方案。本公开针对于“DRX周期确定”这一情形提供了一种处理方法，以基于与终端设备运行的业务类型集合对应AI模型确定DRX周期，减少不同业务采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。
图16为本公开实施例所提供的一种DRX周期确定方法的流程示意图，该方法由网络侧设备执行，如图16所示，该方法可以包括以下步骤：
步骤1601、响应于AI模型部署于终端设备，接收终端设备发送的终端设备采用AI模型确定的第二DRX周期；
步骤1602、根据第二DRX周期，确定第一DRX周期。
其中，在本公开的一个实施例之中，AI模型为基于与AI模型对应的业务类型进行训练得到的模型。
其中，关于步骤1601-1602的详细介绍可以参考上述实施例描述，本公开实施例在此不做赘述。
示例地，在本公开的一个实施例终端，网络侧设备根据第二DRX周期，确定第一DRX周期时，网络侧设备可以发送第一DRX周期至终端设备。
综上所述，在本公开实施例之中，通过响应于AI模型部署于终端设备，接收终端设备发送的终端设备采用AI模型确定的第二DRX周期；根据第二DRX周期，确定第一DRX周期。在本公开实施例之中，由于第一DRX周期为根据终端设备运行的业务类型集合对应的AI模型确定的，减少不同业务网络侧设备采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。本公开的实施例中具体公开了第一DRX周期为根据终端设备发送的第二DRX周期确定的方案。本公开针对于“DRX周期确定”这一情形提供了一种处理方法，以基于与终端设备运行的业务类型集合对应AI模型确定DRX周期，减少不同业务采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。
图17为本公开实施例所提供的一种DRX周期确定方法的流程示意图，该方法由网络侧设备执行，如图17所示，该方法可以包括以下步骤：
步骤1701、接收终端设备发送的第一模型下载请求，其中，第一模型下载请求为针对终端设备运行的业务集合的请求；
步骤1702、发送针对第一模型下载请求的AI模型至终端设备，其中，AI模型与业务集合的业务类型集合对应。
其中，在本公开的一个实施例之中，AI模型为基于与AI模型对应的业务类型进行训练得到的模型。
其中，关于步骤1701-1702的详细介绍可以参考上述实施例描述，本公开实施例在此不做赘述。
综上所述，在本公开实施例之中，通过接收终端设备发送的第一模型下载请求，其中，第一模型下载请求为针对终端设备运行的业务集合的请求；发送针对第一模型下载请求的AI模型至终端设备，其中，AI模型与业务集合的业务类型集合对应。在本公开实施例之中，网络侧设备可以接收终端设备发送的模型下载请求，由于不同的下载情况对应不同的模型下载请求，可以提高AI模型下载的便利性，同时，发送针对第一模型下载请求的AI模型至终端设备，由于AI模型与业务集合的业务类型集合对应，可以提高AI模型与业务集合的匹配性。
图18为本公开实施例所提供的一种DRX周期确定方法的流程示意图，该方法由网络侧设备执行，如图18所示，该方法可以包括以下步骤：
步骤1801、接收终端设备针对AI模型的模型下载指令发送的第二模型下载请求；
步骤1802、发送针对第二模型下载请求的AI模型至终端设备。
其中，在本公开的一个实施例之中，AI模型为基于与AI模型对应的业务类型进行训练得到的模型。
其中，关于步骤1801-1802的详细介绍可以参考上述实施例描述，本公开实施例在此不做赘述。
综上所述，在本公开实施例之中，通过接收终端设备针对AI模型的模型下载指令发送的第二模型下载请求；发送针对第二模型下载请求的AI模型至终端设备。在本公开实施例之中，网络侧设备可以接收终端设备针对AI模型的模型下载指令发送的模型下载请求，可以提高AI模型下载的便利性，减少AI模型与业务集合不匹配的情况，可以提高AI模型与业务集合的匹配性。
图19为本公开实施例所提供的一种DRX周期确定方法的流程示意图，该方法由终端设备执行，如图19所示，该方法可以包括以下步骤：
步骤1901、响应于AI模型部署于终端设备，采用AI模型对终端设备运行的业务类型集合进行DRX周期预测， 确定第二DRX周期；
步骤1902、发送第二DRX周期至网络侧设备。
其中，在本公开的一个实施例之中，采用AI模型对终端设备运行的业务类型集合进行DRX周期预测，确定第二DRX周期，包括：
对终端设备运行的业务集合进行分类，确定业务集合的业务类型集合；
采用与业务类型集合对应的AI模型进行DRX周期预测，确定第二DRX周期。
以及，在本公开的一个实施例之中，采用与业务类型集合对应的AI模型进行DRX周期预测，确定第二DRX周期，包括：
响应于业务类型集合包括一种业务类型，采用与业务类型对应的AI模型进行DRX周期预测，确定第二DRX周期。
以及，在本公开的一个实施例之中，采用与业务类型集合对应的AI模型进行DRX周期预测，确定第二DRX周期，包括：
响应于业务类型集合包括至少两种业务类型，采用与至少两种业务类型对应的AI模型进行DRX周期预测，确定第二DRX周期。
以及，在本公开的一个实施例之中，采用与业务类型集合对应的AI模型进行DRX周期预测，确定第二DRX周期，包括：
响应于业务类型集合包括至少两种业务类型，且未存在与至少两种业务类型对应的AI模型，采用与至少两种业务类型中各业务类型对应的AI模型分别确定各业务类型对应的第五DRX周期；
基于至少两个第五DRX周期，确定第二DRX周期；
或，
响应于业务类型集合包括至少两种业务类型，且未存在与至少两种业务类型对应的AI模型，不采用AI模型进行DRX周期预测。
以及，在本公开的一个实施例之中，该方法还包括：
基于终端设备运行的业务集合，发送针对业务集合的第一模型下载请求至网络侧设备；
接收网络侧设备针对第一模型下载请求发送的AI模型，其中，AI模型与业务集合的业务类型集合对应。
以及，在本公开的一个实施例之中，该方法还包括：
响应于针对AI模型的模型下载指令，发送第二模型下载请求至网络侧设备；
接收网络侧设备针对第二模型下载请求发送的AI模型。
其中，关于步骤1901的详细介绍可以参考上述实施例描述，本公开实施例在此不做赘述。
其中，在本公开的一个实施例之中，第二DRX周期是指响应于AI模型部署于终端设备，终端设备采用AI模型对终端设备运行的业务类型集合进行DRX周期预测，确定的周期。其中，第二DRX周期中的第二仅用于与其余DRX周期进行区分，并不特指某一固定周期。
以及，在本公开的一个实施例之中，AI模型可以部署于终端设备。响应于AI模型部署于终端设备，终端设备可以采用AI模型对终端设备运行的业务类型集合进行DRX周期预测，确定第二DRX周期，并发送第二DRX周期至网络侧设备。
示例地，在本公开的一个实施例之中，终端设备发送第二DRX周期至网络侧设备时，网络侧设备可以接收终端设备发送的第二DRX周期。网络侧设备可以根据该第二DRX周期确定第一DRX周期，也可以不根据该第二DRX周期确定第一DRX周期。
其中，在本公开的一个实施例之中，AI模型为基于与AI模型对应的业务类型进行训练得到的模型。
综上所述，在本公开实施例之中，通过响应于AI模型部署于终端设备，采用AI模型对终端设备运行的业务类型集合进行DRX周期预测，确定第二DRX周期；发送第二DRX周期至网络侧设备。在本公开实施例之中，由于第二DRX周期为根据终端设备运行的业务类型集合对应的AI模型确定的，可以提高第二DRX周期确定的准确性。本公开针对于“DRX周期确定”这一情形提供了一种处理方法，以提供基于与终端设备运行的业务类型集合对应AI模型确定的DRX周期至网络侧设备，可以提高DRX周期确定的准确性。
图20为本公开实施例所提供的一种DRX周期确定方法的流程示意图，该方法由网络侧设备执行，如图20所示，该方法可以包括以下步骤：
步骤2001、响应于AI模型部署于终端设备，接收终端设备发送的终端设备采用AI模型确定的第二DRX周期。
其中，在本公开的一个实施例之中，AI模型为基于与AI模型对应的业务类型进行训练得到的模型。
其中，关于步骤2001的详细介绍可以参考上述实施例描述，本公开实施例在此不做赘述。
综上所述，在本公开实施例之中，通过响应于AI模型部署于终端设备，接收终端设备发送的终端设备采用AI模型确定的第二DRX周期。在本公开实施例之中，由于第二DRX周期为根据终端设备运行的业务类型集合对应的AI模型确定的，可以提高第二DRX周期确定的准确性。本公开针对于“DRX周期确定”这一情形提供了一种处理方法，以接收终端设备发送的终端设备基于与终端设备运行的业务类型集合对应AI模型确定的DRX周期，可以提高DRX周期确定的准确性。
图21为本公开实施例所提供的一种DRX周期确定装置的结构示意图，如图21所示，该装置设置于终端侧，该装置2100可以包括：
接收模块2101，用于接收网络侧设备发送的第一DRX周期，其中，第一DRX周期是基于人工智能AI模型确定的，且AI模型与终端设备运行的业务类型集合对应。
综上所述，在本公开实施例的DRX周期确定装置之中，接收模块接收网络侧设备发送的第一DRX周期，其中，第一DRX周期是基于人工智能AI模型确定的，且AI模型与终端设备运行的业务类型集合对应。在本公开实施例之中，由于第一DRX周期为根据终端设备运行的业务类型集合对应的AI模型确定的，减少不同业务采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。本公开针对于“DRX周期确定”这一情形提供了一种处理方法，以接收基于与终端设备运行的业务类型集合对应AI模型确定的DRX周期，减少不同业务采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。
可选地，在本公开的一个实施例之中，接收模块2101，用于接收网络侧设备发送的第一DRX周期时，具体用于：
响应于AI模型部署于网络侧设备，接收网络侧设备发送的网络侧设备采用AI模型确定的第一DRX周期。
可选地，在本公开的一个实施例之中，接收模块2101，用于接收网络侧设备发送的第一DRX周期，具体用于：
响应于所述AI模型部署于所述终端设备，采用所述AI模型对所述终端设备运行的业务类型集合进行DRX周期预测，确定第二DRX周期；
发送所述第二DRX周期至所述网络侧设备。
接收所述网络侧设备根据所述第二DRX周期确定的所述第一DRX周期。
可选地，在本公开的一个实施例之中，确定模块2102，用于采用AI模型对终端设备运行的业务类型集合进行DRX周期预测，确定第二DRX周期时，具体用于：
对终端设备运行的业务集合进行分类，确定业务集合的业务类型集合；
采用与业务类型集合对应的AI模型进行DRX周期预测，确定第二DRX周期。
可选地，在本公开的一个实施例之中，确定模块2102，用于采用与业务类型集合对应的AI模型进行DRX周期预测，确定第二DRX周期时，具体用于：
响应于业务类型集合包括一种业务类型，采用与业务类型对应的AI模型进行DRX周期预测，确定第二DRX周期。
可选地，在本公开的一个实施例之中，确定模块2102，用于采用与业务类型集合对应的AI模型进行DRX周期预测，确定第二DRX周期时，具体用于：
响应于业务类型集合包括至少两种业务类型，采用与至少两种业务类型对应的AI模型进行DRX周期预测，确定第二DRX周期。
可选地，在本公开的一个实施例之中，确定模块2102，用于采用与业务类型集合对应的AI模型进行DRX周期预测，确定第二DRX周期时，具体用于：
响应于业务类型集合包括至少两种业务类型，且未存在与至少两种业务类型对应的AI模型，采用与至少两种业务类型中各业务类型对应的AI模型分别确定各业务类型对应的第五DRX周期；
基于至少两个第五DRX周期，确定第二DRX周期；
或，
响应于业务类型集合包括至少两种业务类型，且未存在与至少两种业务类型对应的AI模型，不采用AI模型进行DRX周期预测。
可选地，在本公开的一个实施例之中，接收模块2101，还用于：
基于终端设备运行的业务集合，发送针对业务集合的第一模型下载请求至网络侧设备；
接收网络侧设备针对第一模型下载请求发送的AI模型，其中，AI模型与业务集合的业务类型集合对应。
可选地，在本公开的一个实施例之中，接收模块2101，还用于：
响应于针对AI模型的模型下载指令，发送第二模型下载请求至网络侧设备；
接收网络侧设备针对第二模型下载请求发送的AI模型。
可选地，在本公开的一个实施例之中，其中，AI模型为基于与AI模型对应的业务类型进行训练得到的模型。
图22为本公开实施例所提供的一种DRX周期确定装置的结构示意图，如图22所示，该装置设置于网络侧，该装置2200可以包括：
发送模块2201，用于发送第一DRX周期至终端设备，其中，第一DRX周期是基于人工智能AI模型确定的，且AI模型与终端设备运行的业务类型集合对应。
综上所述，在本公开实施例的DRX周期确定装置之中，发送模块发送第一DRX周期至终端设备，其中，第一DRX周期是基于人工智能AI模型确定的，且AI模型与终端设备运行的业务类型集合对应。在本公开实施例之中，由于第一DRX周期为根据终端设备运行的业务类型集合对应的AI模型确定的，减少不同业务采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。本公开针对于“DRX周期确定”这一情形提供了一种处理方法，以发送基于与终端设备运行的业务类型集合对应AI模型确定的DRX周期至终端设备，减少不同业务采用同一AI模型进行DRX周期预测，使得DRX周期确定不准确的情况，可以提高DRX周期确定的准确性。
可选地，在本公开的一个实施例之中，图23为本公开实施例所提供的一种DRX周期确定装置的结构示意图，如图23所示，该装置设置于网络侧，该装置2200还可以包括确定模块2202，用于在发送第一DRX周期至终端设备之前：
响应于AI模型部署于网络侧设备，采用AI模型对终端设备运行的业务类型集合进行DRX周期预测，生成第三DRX周期；
根据第三DRX周期，确定第一DRX周期。
可选地，在本公开的一个实施例之中，确定模块2202，用于采用AI模型对终端设备运行的业务类型集合进行DRX周期预测，确定第三DRX周期时，具体用于：
对终端设备运行的业务集合进行分类，确定业务集合的业务类型集合；
采用与业务类型集合对应的AI模型进行DRX周期预测，确定第三DRX周期。
可选地，在本公开的一个实施例之中，确定模块2202，用于采用与业务类型集合对应的AI模型进行DRX周期预测，确定第三DRX周期时，具体用于：
响应于业务类型集合包括一种业务类型，采用与业务类型对应的AI模型进行DRX周期预测，确定第三DRX周期。
可选地，在本公开的一个实施例之中，确定模块2202，用于采用与业务类型集合对应的AI模型进行DRX周期预测，确定第三DRX周期时，具体用于：
响应于业务类型集合包括至少两种业务类型，采用与至少两种业务类型对应的AI模型进行DRX周期预测，确定第三DRX周期。
可选地，在本公开的一个实施例之中，确定模块2202，用于采用与业务类型集合对应的AI模型进行DRX周期预测，确定第三DRX周期时，具体用于：
响应于业务类型集合包括至少两种业务类型，且未存在与至少两种业务类型对应的AI模型，采用与至少两种业务类型中各业务类型对应的AI模型分别确定各业务类型对应的第四DRX周期；
基于至少两个第四DRX周期，确定第三DRX周期；
或，
响应于业务类型集合包括至少两种业务类型，且未存在与至少两种业务类型对应的AI模型，不采用AI模型进行DRX周期预测。
可选地，在本公开的一个实施例之中，图24为本公开实施例所提供的一种DRX周期确定装置的结构示意图，如图24所示，该装置设置于网络侧，该装置2200还可以包括接收模块2203，用于在所述发送第一DRX周期至终端设备之前：
响应于AI模型部署于终端设备，接收终端设备发送的终端设备采用AI模型确定的第二DRX周期。
根据第二DRX周期，确定第一DRX周期。
可选地，在本公开的一个实施例之中，发送模块2201，还用于：
接收终端设备发送的第一模型下载请求，其中，第一模型下载请求为针对终端设备运行的业务集合的请求；
发送针对第一模型下载请求的AI模型至终端设备，其中，AI模型与业务集合的业务类型集合对应。
可选地，在本公开的一个实施例之中，发送模块2201，还用于：
接收终端设备针对AI模型的模型下载指令发送的第二模型下载请求；
发送针对第二模型下载请求的AI模型至终端设备。
可选地，在本公开的一个实施例之中，其中，AI模型为基于与AI模型对应的业务类型进行训练得到的模型。
图25为本公开实施例所提供的一种DRX周期确定装置的结构示意图，如图25所示，该装置设置于终端侧，该装置2500还可以包括确定模块2501和发送模块2502，其中：
确定模块2501，用于响应于AI模型部署于终端设备，采用AI模型对终端设备运行的业务类型集合进行DRX周期预测，确定第二DRX周期；
发送模块2502，用于发送第二DRX周期至网络侧设备。
综上所述，在本公开实施例的DRX周期确定装置之中，确定模块响应于AI模型部署于终端设备，采用AI模型对终端设备运行的业务类型集合进行DRX周期预测，确定第二DRX周期；发送模块发送第二DRX周期至网络侧设备。在本公开实施例之中，由于第二DRX周期为根据终端设备运行的业务类型集合对应的AI模型确定的，可以提高第二DRX周期确定的准确性。本公开针对于“DRX周期确定”这一情形提供了一种处理方法，以提供基于与终端设备运行的业务类型集合对应AI模型确定的DRX周期至网络侧设备，可以提高DRX周期确定的准确性。
可选地，在本公开的一个实施例之中，确定模块2501，用于采用AI模型对终端设备运行的业务类型集合进行DRX周期预测，确定第二DRX周期时，具体用于：
对终端设备运行的业务集合进行分类，确定业务集合的业务类型集合；
采用与业务类型集合对应的AI模型进行DRX周期预测，确定第二DRX周期。
可选地，在本公开的一个实施例之中，确定模块2501，用于采用与业务类型集合对应的AI模型进行DRX周期预测，确定第二DRX周期时，具体用于：
响应于业务类型集合包括一种业务类型，采用与业务类型对应的AI模型进行DRX周期预测，确定第二DRX周期。
可选地，在本公开的一个实施例之中，确定模块2501，用于采用与业务类型集合对应的AI模型进行DRX周期预测，确定第二DRX周期时，具体用于：
响应于业务类型集合包括至少两种业务类型，采用与至少两种业务类型对应的AI模型进行DRX周期预测，确定第二DRX周期。
可选地，在本公开的一个实施例之中，确定模块2501，用于采用与业务类型集合对应的AI模型进行DRX周期预测，确定第二DRX周期时，具体用于：
响应于业务类型集合包括至少两种业务类型，且未存在与至少两种业务类型对应的AI模型，采用与至少两种业务类型中各业务类型对应的AI模型分别确定各业务类型对应的第五DRX周期；
基于至少两个第五DRX周期，确定第二DRX周期；
或，
响应于业务类型集合包括至少两种业务类型，且未存在与至少两种业务类型对应的AI模型，不采用AI模型进行DRX周期预测。
可选地，在本公开的一个实施例之中，发送模块2502，还用于：
基于终端设备运行的业务集合，发送针对业务集合的第一模型下载请求至网络侧设备；
接收网络侧设备针对第一模型下载请求发送的AI模型，其中，AI模型与业务集合的业务类型集合对应。
可选地，在本公开的一个实施例之中，发送模块2502，还用于：
响应于针对AI模型的模型下载指令，发送第二模型下载请求至网络侧设备；
接收网络侧设备针对第二模型下载请求发送的AI模型。
图26为本公开实施例所提供的一种DRX周期确定装置的结构示意图，如图26所示，该装置设置于终端侧，该装置2600还可以包括接收模块2601，其中：
接收模块2601，用于响应于AI模型部署于终端设备，接收所述终端设备发送的所述终端设备采用所述AI模型确定的第二DRX周期。
综上所述，在本公开实施例的DRX周期确定装置之中，接收模块响应于AI模型部署于终端设备，接收所述终端设备发送的所述终端设备采用所述AI模型确定的第二DRX周期。在本公开实施例之中，由于第二DRX周期为根据终端设备运行的业务类型集合对应的AI模型确定的，可以提高第二DRX周期确定的准确性。本公开针对于“DRX周期确定”这一情形提供了一种处理方法，以接收终端设备发送的终端设备基于与终端设备运行的业务类型集合对应AI模型确定的DRX周期，可以提高DRX周期确定的准确性。
图27是本公开一个实施例所提供的一种终端设备UE2700的框图。例如，UE2700可以是移动电话，计算机，数字广播终端设备，消息收发设备，游戏控制台，平板设备，医疗设备，健身设备，个人数字助理等。
参照图27，UE2700可以包括以下至少一个组件：处理组件2702，存储器2704，电源组件2706，多媒体组件2708，音频组件2710，输入/输出(I/O)的接口2712，传感器组件2714，以及通信组件2716。
处理组件2702通常控制UE2700的整体操作，诸如与显示，电话呼叫，数据通信，相机操作和记录操作相关联的操作。处理组件2702可以包括至少一个处理器2720来执行指令，以完成上述的方法的全部或部分步骤。此外，处理组件2702可以包括至少一个模块，便于处理组件2702和其他组件之间的交互。例如，处理组件2702可以包括多媒体模块，以方便多媒体组件2708和处理组件2702之间的交互。
存储器2704被配置为存储各种类型的数据以支持在UE2700的操作。这些数据的示例包括用于在UE2700上操作的任何应用程序或方法的指令，联系人数据，电话簿数据，消息，图片，视频等。存储器2704可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，如静态随机存取存储器(SRAM)，电可擦除可编程只读存储器(EEPROM)，可擦除可编程只读存储器(EPROM)，可编程只读存储器(PROM)，只读存储器(ROM)，磁存储器，快闪存储器，磁盘或光盘。
电源组件2706为UE2700的各种组件提供电力。电源组件2706可以包括电源管理系统，至少一个电源，及其他与为UE2700生成、管理和分配电力相关联的组件。
多媒体组件2708包括在所述UE2700和用户之间的提供一个输出接口的屏幕。在一些实施例中，屏幕可以包括液晶显示器(LCD)和触摸面板(TP)。如果屏幕包括触摸面板，屏幕可以被实现为触摸屏，以接收来自用户的输入信号。触摸面板包括至少一个触摸传感器以感测触摸、滑动和触摸面板上的手势。所述触摸传感器可以不仅感测触摸或滑动动作的边界，而且还检测与所述触摸或滑动操作相关的唤醒时间和压力。在一些实施例中，多媒体组件2708包括一个前置摄像头和/或后置摄像头。当UE2700处于操作模式，如拍摄模式或视频模式时，前置摄像头和/或后置摄像头可以接收外部的多媒体数据。每个前置摄像头和后置摄像头可以是一个固定的光学透镜系统或具有焦距和光学变焦能力。
音频组件2710被配置为输出和/或输入音频信号。例如，音频组件2710包括一个麦克风(MIC)，当UE2700处于操作模式，如呼叫模式、记录模式和语音识别模式时，麦克风被配置为接收外部音频信号。所接收的音频信号可以被进一步存储在存储器2704或经由通信组件2716发送。在一些实施例中，音频组件2710还包括一个扬声器，用于输出音频信号。
I/O接口2712为处理组件2702和外围接口模块之间提供接口，上述外围接口模块可以是键盘，点击轮，按钮等。这些按钮可包括但不限于：主页按钮、音量按钮、启动按钮和锁定按钮。
传感器组件2714包括至少一个传感器，用于为UE2700提供各个方面的状态评估。例如，传感器组件2714可以检测到设备1600的打开/关闭状态，组件的相对定位，例如所述组件为UE2700的显示器和小键盘，传感器组件2714还可以检测UE2700或UE2700的一个组件的位置改变，用户与UE2700接触的存在或不存在，UE2700方位或加速/减速和UE2700的温度变化。传感器组件2714可以包括接近传感器，被配置用来在没有任何的物理接触时检测附近物体的存在。传感器组件2714还可以包括光传感器，如CMOS或CCD图像传感器，用于在成像应用中使用。在一些实施例中，该传感器组件2714还可以包括加速度传感器，陀螺仪传感器，磁传感器，压力传感器或温度传感器。
通信组件2716被配置为便于UE2700和其他设备之间有线或无线方式的通信。UE2700可以接入基于通信标准的无线网络，如WiFi，2G或3G，或它们的组合。在一个示例性实施例中，通信组件2716经由广播信道接收来自外部广播管理系统的广播信号或广播相关信息。在一个示例性实施例中，所述通信组件2716还包括近场通信(NFC)模块，以促进短程通信。例如，在NFC模块可基于射频识别(RFID)技术，红外数据协会(IrDA)技术，超宽带(UWB)技术，蓝牙(BT)技术和其他技术来实现。
在示例性实施例中，UE2700可以被至少一个应用专用集成电路(ASIC)、数字信号处理器(DSP)、数字信号处理设备(DSPD)、可编程逻辑器件(PLD)、现场可编程门阵列(FPGA)、控制器、微控制器、微处理器或其他电子元件实现，用于执行上述方法。
图28是本公开实施例所提供的一种网络侧设备2800的框图。例如，网络侧设备2800可以被提供为一网络侧设备。参照图28，网络侧设备2800包括处理组件2822，其进一步包括至少一个处理器，以及由存储器2832所代表的存储器资源，用于存储可由处理组件2822的执行的指令，例如应用程序。存储器2832中存储的应用程序可以包括一个或一个以上的每一个对应于一组指令的模块。此外，处理组件2822被配置为执行指令，以执行上述方法前述应用在所述网络侧设备的任意方法，例如，如图10所示方法。
网络侧设备2800还可以包括一个电源组件2826被配置为执行网络侧设备2800的电源管理，一个有线或无线网络接口2850被配置为将网络侧设备2800连接到网络，和一个输入/输出(I/O)接口2858。网络侧设备2800可以操作基于存储在存储器2832的操作系统，例如Windows Server TM，Mac OS XTM，Unix TM,Linux TM，Free BSDTM 或类似。
上述本公开提供的实施例中，分别从网络侧设备、UE的角度对本公开实施例提供的方法进行了介绍。为了实现上述本公开实施例提供的方法中的各功能，网络侧设备和UE可以包括硬件结构、软件模块，以硬件结构、软件模块、或硬件结构加软件模块的形式来实现上述各功能。上述各功能中的某个功能可以以硬件结构、软件模块、或者硬件结构加软件模块的方式来执行。
上述本公开提供的实施例中，分别从网络侧设备、UE的角度对本公开实施例提供的方法进行了介绍。为了实现上述本公开实施例提供的方法中的各功能，网络侧设备和UE可以包括硬件结构、软件模块，以硬件结构、软件模块、或硬件结构加软件模块的形式来实现上述各功能。上述各功能中的某个功能可以以硬件结构、软件模块、或者硬件结构加软件模块的方式来执行。
本公开实施例提供的一种通信装置。通信装置可包括收发模块和处理模块。收发模块可包括发送模块和/或接收模块，发送模块用于实现发送功能，接收模块用于实现接收功能，收发模块可以实现发送功能和/或接收功能。
通信装置可以是终端设备(如前述方法实施例中的终端设备)，也可以是终端设备中的装置，还可以是能够与终端设备匹配使用的装置。或者，通信装置可以是网络设备，也可以是网络设备中的装置，还可以是能够与网络设备匹配使用的装置。
本公开实施例提供的另一种通信装置。通信装置可以是网络设备，也可以是终端设备(如前述方法实施例中的终端设备)，也可以是支持网络设备实现上述方法的芯片、芯片系统、或处理器等，还可以是支持终端设备实现上述方法的芯片、芯片系统、或处理器等。该装置可用于实现上述方法实施例中描述的方法，具体可以参见上述方法实施例中的说明。
通信装置可以包括一个或多个处理器。处理器可以是通用处理器或者专用处理器等。例如可以是基带处理器或中央处理器。基带处理器可以用于对通信协议以及通信数据进行处理，中央处理器可以用于对通信装置(如，网络侧设备、基带芯片，终端设备、终端设备芯片，DU或CU等)进行控制，执行计算机程序，处理计算机程序的数据。
可选地，通信装置中还可以包括一个或多个存储器，其上可以存有计算机程序，处理器执行所述计算机程序，以使得通信装置执行上述方法实施例中描述的方法。可选地，所述存储器中还可以存储有数据。通信装置和存储器可以单独设置，也可以集成在一起。
可选地，通信装置还可以包括收发器、天线。收发器可以称为收发单元、收发机、或收发电路等，用于实现收发功能。收发器可以包括接收器和发送器，接收器可以称为接收机或接收电路等，用于实现接收功能；发送器可以称为发送机或发送电路等，用于实现发送功能。
可选地，通信装置中还可以包括一个或多个接口电路。接口电路用于接收代码指令并传输至处理器。处理器运行所述代码指令以使通信装置执行上述方法实施例中描述的方法。
通信装置为终端设备(如前述方法实施例中的终端设备)：处理器用于执行图1-图9或19任一所示的方法。
通信装置为网络侧设备：处理器用于执行图10-图18或20任一所示的方法。
在一种实现方式中，处理器中可以包括用于实现接收和发送功能的收发器。例如该收发器可以是收发电路，或者是接口，或者是接口电路。用于实现接收和发送功能的收发电路、接口或接口电路可以是分开的，也可以集成在一起。上述收发电路、接口或接口电路可以用于代码/数据的读写，或者，上述收发电路、接口或接口电路可以用于信号的传输或传递。
在一种实现方式中，处理器可以存有计算机程序，计算机程序在处理器上运行，可使得通信装置执行上述方法实施例中描述的方法。计算机程序可能固化在处理器中，该种情况下，处理器可能由硬件实现。
在一种实现方式中，通信装置可以包括电路，所述电路可以实现前述方法实施例中发送或接收或者通信的功能。本公开中描述的处理器和收发器可实现在集成电路(integrated circuit，IC)、模拟IC、射频集成电路RFIC、混合信号IC、专用集成电路(application specific integrated circuit，ASIC)、印刷电路板(printed circuit board，PCB)、电子设备等上。该处理器和收发器也可以用各种IC工艺技术来制造，例如互补金属氧化物半导体(complementary metal oxide semiconductor，CMOS)、N型金属氧化物半导体(nMetal-oxide-semiconductor，NMOS)、P型金属氧化物半导体(positive channel metal oxide semiconductor，PMOS)、双极结型晶体管(bipolar junction transistor，BJT)、双极CMOS(BiCMOS)、硅锗(SiGe)、砷化镓(GaAs)等。
以上实施例描述中的通信装置可以是网络设备或者终端设备(如前述方法实施例中的终端设备)，但本公开中描述的通信装置的范围并不限于此，而且通信装置的结构可以不受的限制。通信装置可以是独立的设备或者可以是较大设备的一部分。例如所述通信装置可以是：
(1)独立的集成电路IC，或芯片，或，芯片系统或子系统；
(2)具有一个或多个IC的集合，可选地，该IC集合也可以包括用于存储数据，计算机程序的存储部件；
(3)ASIC，例如调制解调器(Modem)；
(4)可嵌入在其他设备内的模块；
(5)接收机、终端设备、智能终端设备、蜂窝电话、无线设备、手持机、移动单元、车载设备、网络设备、云设备、人工智能设备等等；
(6)其他等等。
对于通信装置可以是芯片或芯片系统的情况，芯片包括处理器和接口。其中，处理器的数量可以是一个或多个，接口的数量可以是多个。
可选地，芯片还包括存储器，存储器用于存储必要的计算机程序和数据。
本领域技术人员还可以了解到本公开实施例列出的各种说明性逻辑块(illustrative logical block)和步骤(step)可以通过电子硬件、电脑软件，或两者的结合进行实现。这样的功能是通过硬件还是软件来实现取决于特定的应用和整个系统的设计要求。本领域技术人员可以对于每种特定的应用，可以使用各种方法实现所述的功能，但这种实现不应被理解为超出本公开实施例保护的范围。
本公开还提供一种可读存储介质，其上存储有指令，该指令被计算机执行时实现上述任一方法实施例的功能。
本公开还提供一种计算机程序产品，该计算机程序产品被计算机执行时实现上述任一方法实施例的功能。
在上述实施例中，可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机程序。在计算机上加载和执行所述计算机程序时，全部或部分地产生按照本公开实施例所述的流程或功能。所述计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。所述计算机程序可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，所述计算机程序可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(digital subscriber line，DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质(例如，软盘、硬盘、磁带)、光介质(例如，高密度数字视频光盘(digital video disc，DVD))、或者半导体介质(例如，固态硬盘(solid state disk，SSD))等。
本领域普通技术人员可以理解：本公开中涉及的第一、第二等各种数字编号仅为描述方便进行的区分，并不用来限制本公开实施例的范围，也表示先后顺序。
本公开中的至少一个还可以描述为一个或多个，多个可以是两个、三个、四个或者更多个，本公开不做限制。在本公开实施例中，对于一种技术特征，通过“第一”、“第二”、“第三”、“A”、“B”、“C”和“D”等区分该种技术特征中的技术特征，该“第一”、“第二”、“第三”、“A”、“B”、“C”和“D”描述的技术特征间无先后顺序或者大小顺序。
本领域技术人员在考虑说明书及实践这里公开的发明后，将容易想到本发明的其它实施方案。本公开旨在涵盖本发明的任何变型、用途或者适应性变化，这些变型、用途或者适应性变化遵循本发明的一般性原理并包括本公开未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施例仅被视为示例性的，本公开的真正范围和精神由下面的权利要求指出。
应当理解的是，本公开并不局限于上面已经描述并在附图中示出的精确结构，并且可以在不脱离其范围进行各种修改和改变。本公开的范围仅由所附的权利要求来限制。

Claims (32)

  1. 一种非连续接收DRX周期确定方法，其特征在于，所述方法由终端设备执行，所述方法包括：
    接收网络侧设备发送的第一DRX周期，其中，所述第一DRX周期是基于人工智能AI模型确定的，且所述AI模型与所述终端设备运行的业务类型集合对应。
  2. 根据权利要求1所述的方法，其特征在于，所述接收网络侧设备发送的第一DRX周期，包括：
    响应于AI模型部署于所述网络侧设备，接收所述网络侧设备发送的所述网络侧设备采用所述AI模型确定的所述第一DRX周期。
  3. 根据权利要求1所述的方法，其特征在于，所述接收网络侧设备发送的第一DRX周期，包括：
    响应于所述AI模型部署于所述终端设备，采用所述AI模型对所述终端设备运行的业务类型集合进行DRX周期预测，确定第二DRX周期；
    发送所述第二DRX周期至所述网络侧设备；
    接收所述网络侧设备根据所述第二DRX周期确定的所述第一DRX周期。
  4. 根据权利要求1所述的方法，其特征在于，其中，所述AI模型为基于与所述AI模型对应的业务类型进行训练得到的模型。
  5. 一种DRX周期确定方法，其特征在于，所述方法由网络侧设备执行，所述方法包括：
    发送第一DRX周期至终端设备，其中，所述第一DRX周期是基于人工智能AI模型确定的，且所述AI模型与所述终端设备运行的业务类型集合对应。
  6. 根据权利要求5所述的方法，其特征在于，在所述发送第一DRX周期至终端设备之前，还包括：
    响应于AI模型部署于所述网络侧设备，采用所述AI模型对所述终端设备运行的业务类型集合进行DRX周期预测，生成第三DRX周期；
    根据所述第三DRX周期，确定所述第一DRX周期。
  7. 根据权利要求6所述的方法，其特征在于，所述采用所述AI模型对所述终端设备运行的业务类型集合进行DRX周期预测，确定第三DRX周期，包括：
    对所述终端设备运行的业务集合进行分类，确定所述业务集合的业务类型集合；
    采用与所述业务类型集合对应的AI模型进行DRX周期预测，确定第三DRX周期。
  8. 根据权利要求7所述的方法，其特征在于，所述采用与所述业务类型集合对应的AI模型进行DRX周期预测，确定第三DRX周期，包括：
    响应于所述业务类型集合包括一种业务类型，采用与所述业务类型对应的AI模型进行DRX周期预测，确定所述第三DRX周期。
  9. 根据权利要求7所述的方法，其特征在于，所述采用与所述业务类型集合对应的AI模型进行DRX周期预测，确定第三DRX周期，包括：
    响应于所述业务类型集合包括至少两种业务类型，采用与所述至少两种业务类型对应的AI模型进行DRX周期预测，确定所述第三DRX周期。
  10. 根据权利要求7所述的方法，其特征在于，所述采用与所述业务类型集合对应的AI模型进行DRX周期预测，确定第三DRX周期，包括：
    响应于所述业务类型集合包括至少两种业务类型，且未存在与所述至少两种业务类型对应的AI模型，采用与所述至少两种业务类型中各业务类型对应的AI模型分别确定所述各业务类型对应的第四DRX周期；
    基于至少两个第四DRX周期，确定所述第三DRX周期；
    或，
    响应于所述业务类型集合包括至少两种业务类型，且未存在与所述至少两种业务类型对应的AI模型，不采用AI模型进行DRX周期预测。
  11. 根据权利要求5所述的方法，其特征在于，在所述发送第一DRX周期至终端设备之前，还包括：
    响应于所述AI模型部署于所述终端设备，接收所述终端设备发送的所述终端设备采用所述AI模型确定的第二DRX周期；
    根据所述第二DRX周期，确定所述第一DRX周期。
  12. 根据权利要求5所述的方法，其特征在于，所述方法还包括：
    接收所述终端设备发送的第一模型下载请求，其中，所述第一模型下载请求为针对所述终端设备运行的业务集合的请求；
    发送针对所述第一模型下载请求的AI模型至所述终端设备，其中，所述AI模型与所述业务集合的业务类型集合对应。
  13. 根据权利要求5所述的方法，其特征在于，所述方法还包括：
    接收所述终端设备针对AI模型的模型下载指令发送的第二模型下载请求；
    发送针对所述第二模型下载请求的AI模型至所述终端设备。
  14. 根据权利要求5所述的方法，其特征在于，其中，所述AI模型为基于与所述AI模型对应的业务类型进行训练得到的模型。
  15. 一种DRX周期确定方法，其特征在于，所述方法由终端设备执行，所述方法包括：
    响应于AI模型部署于终端设备，采用所述AI模型对所述终端设备运行的业务类型集合进行DRX周期预测，确定第二DRX周期；
    发送所述第二DRX周期至网络侧设备。
  16. 根据权利要求15所述的方法，其特征在于，所述采用所述AI模型对所述终端设备运行的业务类型集合进行DRX周期预测，确定第二DRX周期，包括：
    对所述终端设备运行的业务集合进行分类，确定所述业务集合的业务类型集合；
    采用与所述业务类型集合对应的AI模型进行DRX周期预测，确定第二DRX周期。
  17. 根据权利要求16所述的方法，其特征在于，所述采用与所述业务类型集合对应的AI模型进行DRX周期预测，确定第二DRX周期，包括：
    响应于所述业务类型集合包括一种业务类型，采用与所述业务类型对应的AI模型进行DRX周期预测，确定所述第二DRX周期。
  18. 根据权利要求16所述的方法，其特征在于，所述采用与所述业务类型集合对应的AI模型进行DRX周期预测，确定第二DRX周期，包括：
    响应于所述业务类型集合包括至少两种业务类型，采用与所述至少两种业务类型对应的AI模型进行DRX周期预测，确定所述第二DRX周期。
  19. 根据权利要求16所述的方法，其特征在于，所述采用与所述业务类型集合对应的AI模型进行DRX周期预测，确定第二DRX周期，包括：
    响应于所述业务类型集合包括至少两种业务类型，且未存在与所述至少两种业务类型对应的AI模型，采用与所述至少两种业务类型中各业务类型对应的AI模型分别确定所述各业务类型对应的第五DRX周期；
    基于至少两个第五DRX周期，确定所述第二DRX周期；
    或，
    响应于所述业务类型集合包括至少两种业务类型，且未存在与所述至少两种业务类型对应的AI模型，不采用AI模型进行DRX周期预测。
  20. 根据权利要求15所述的方法，其特征在于，所述方法还包括：
    基于所述终端设备运行的业务集合，发送针对所述业务集合的第一模型下载请求至所述网络侧设备；
    接收所述网络侧设备针对所述第一模型下载请求发送的AI模型，其中，所述AI模型与所述业务集合的业务类型集合对应。
  21. 根据权利要求15所述的方法，其特征在于，所述方法还包括：
    响应于针对AI模型的模型下载指令，发送所述第二模型下载请求至所述网络侧设备；
    接收所述网络侧设备针对所述第二模型下载请求发送的AI模型。
  22. 一种DRX周期确定方法，其特征在于，所述方法由网络侧设备执行，所述方法包括：
    响应于AI模型部署于终端设备，接收所述终端设备发送的所述终端设备采用所述AI模型确定的第二DRX周期。
  23. 一种DRX周期确定装置，其特征在于，所述装置设置于终端侧，包括：
    接收模块，用于接收网络侧设备发送的第一DRX周期，其中，所述第一DRX周期是基于人工智能AI模型确定的，且所述AI模型与所述终端设备运行的业务类型集合对应。
  24. 一种DRX周期确定装置，其特征在于，所述装置设置于网络侧，包括：
    发送模块，用于发送第一DRX周期至终端设备，其中，所述第一DRX周期是基于人工智能AI模型确定的，且所述AI模型与所述终端设备运行的业务类型集合对应。
  25. 一种DRX周期确定装置，其特征在于，所述装置设置于终端侧，包括：
    确定模块，用于响应于AI模型部署于终端设备，采用所述AI模型对所述终端设备运行的业务类型集合进行 DRX周期预测，确定第二DRX周期；
    发送模块，用于发送所述第二DRX周期至网络侧设备。
  26. 一种DRX周期确定装置，其特征在于，所述装置设置于网络侧，包括：
    接收模块，用于响应于AI模型部署于终端设备，接收所述终端设备发送的所述终端设备采用所述AI模型确定的第二DRX周期。
  27. 一种终端设备，其特征在于，所述设备包括处理器和存储器，其中，所述存储器中存储有计算机程序，所述处理器执行所述存储器中存储的计算机程序，以使所述装置执行如权利要求1至4或15至21中任一项所述的方法。
  28. 一种网络侧设备，其特征在于，所述设备包括处理器和存储器，其中，所述存储器中存储有计算机程序，所述处理器执行所述存储器中存储的计算机程序，以使所述装置执行如权利要求5至14或22中任一项所述的方法。
  29. 一种通信装置，其特征在于，包括：处理器和接口电路，其中
    所述接口电路，用于接收代码指令并传输至所述处理器；
    所述处理器，用于运行所述代码指令以执行如权利要求1至4或15至21中任一项所述的方法。
  30. 一种通信装置，其特征在于，包括：处理器和接口电路，其中
    所述接口电路，用于接收代码指令并传输至所述处理器；
    所述处理器，用于运行所述代码指令以执行如权利要求5至14或22中任一项所述的方法。
  31. 一种计算机可读存储介质，其特征在于，用于存储有指令，当所述指令被执行时，使如权利要求1至4或15至21中任一项所述的方法被实现。
  32. 一种计算机可读存储介质，其特征在于，用于存储有指令，当所述指令被执行时，使如权利要求5至14或22中任一项所述的方法被实现。
PCT/CN2022/109260 2022-07-29 2022-07-29 Drx周期确定方法、装置 WO2024021131A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2022/109260 WO2024021131A1 (zh) 2022-07-29 2022-07-29 Drx周期确定方法、装置
CN202280002609.5A CN117796045A (zh) 2022-07-29 2022-07-29 Drx周期确定方法、装置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2022/109260 WO2024021131A1 (zh) 2022-07-29 2022-07-29 Drx周期确定方法、装置

Publications (1)

Publication Number Publication Date
WO2024021131A1 true WO2024021131A1 (zh) 2024-02-01

Family

ID=89705134

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/109260 WO2024021131A1 (zh) 2022-07-29 2022-07-29 Drx周期确定方法、装置

Country Status (2)

Country Link
CN (1) CN117796045A (zh)
WO (1) WO2024021131A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109462839A (zh) * 2018-11-26 2019-03-12 电子科技大学 一种基于自适应调整策略的drx机制通信方法
CN112714486A (zh) * 2019-10-25 2021-04-27 北京三星通信技术研究有限公司 Pdcch的检测方法、drx配置方法、终端、基站
CN114095377A (zh) * 2020-08-06 2022-02-25 中国移动通信有限公司研究院 模型训练、参数配置方法、装置及分析设备
CN114745712A (zh) * 2021-01-07 2022-07-12 中国移动通信有限公司研究院 基于终端能力的处理方法、装置、终端及网络设备

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109462839A (zh) * 2018-11-26 2019-03-12 电子科技大学 一种基于自适应调整策略的drx机制通信方法
CN112714486A (zh) * 2019-10-25 2021-04-27 北京三星通信技术研究有限公司 Pdcch的检测方法、drx配置方法、终端、基站
US20210126737A1 (en) * 2019-10-25 2021-04-29 Samsung Electronics Co., Ltd. Method and apparatus for detecting physical downlink control channel based on predicted information
CN114095377A (zh) * 2020-08-06 2022-02-25 中国移动通信有限公司研究院 模型训练、参数配置方法、装置及分析设备
CN114745712A (zh) * 2021-01-07 2022-07-12 中国移动通信有限公司研究院 基于终端能力的处理方法、装置、终端及网络设备

Also Published As

Publication number Publication date
CN117796045A (zh) 2024-03-29

Similar Documents

Publication Publication Date Title
WO2024011641A1 (zh) 定位辅助终端设备的确定方法、装置
WO2023201760A1 (zh) PScell添加或改变的成功报告的记录方法、装置
WO2023206183A1 (zh) 成功PScell添加或更换报告的相关信息记录方法、装置
WO2023201759A1 (zh) 成功PScell添加或更换报告的上报方法、装置
WO2023220901A1 (zh) 上报方法、装置
WO2023173381A1 (zh) 侧行链路通信方法及装置
WO2024021131A1 (zh) Drx周期确定方法、装置
WO2023028849A1 (zh) 参考信号测量方法、装置、用户设备、网络侧设备及存储介质
EP4354972A1 (en) Method and apparatus for determining time-domain window, and user equipment, base station and storage medium
WO2023173434A1 (zh) 一种信道估计方法、装置、设备及存储介质
WO2023178567A1 (zh) 一种上报方法/装置/设备及存储介质
WO2023184261A1 (zh) 一种上报方法/装置/设备及存储介质
WO2023206570A1 (zh) 一种配置管理方法、装置、设备及存储介质
WO2023184260A1 (zh) 一种信号传输方法/装置/设备及存储介质
WO2024016240A1 (zh) Pdsch传输方法、装置
WO2023039728A1 (zh) 一种基于用户设备ue能力的模型处理方法、装置、用户设备、基站及存储介质
WO2023173433A1 (zh) 一种信道估计方法/装置/设备及存储介质
WO2023201586A1 (zh) 一种物理信道重复传输的指示方法及设备/存储介质/装置
WO2023206181A1 (zh) 一种小区管理方法/装置/设备及存储介质
WO2023245589A1 (zh) 定位模型确定方法、装置
WO2023245586A1 (zh) 操作配置方法、装置
WO2023173254A1 (zh) 一种定时调整方法/装置/设备及存储介质
CN113544996B (zh) 时域窗口确定方法、装置、用户设备、基站及存储介质
WO2023206032A2 (zh) 直连sidelink非连续接收DRX的控制方法及装置
WO2023206297A1 (zh) 一种小区激活方法/装置/设备及存储介质

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: 202280002609.5

Country of ref document: CN

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22952576

Country of ref document: EP

Kind code of ref document: A1