Ai unit activation method, and terminal and network-side device

Abstract

The present application belongs to the technical field of communications. Disclosed are an AI unit activation method, and a terminal and a network-side device. The AI unit activation method in the embodiments of the present application comprises: a terminal activating a target AI unit on the basis of target information, wherein the target information comprises at least one of indication information and activation conditions of the AI unit, and the indication information is configured to activate the target AI unit.

Description

AI unit activation method, terminal, and network-side equipment

[0001] Cross-references

[0002] This application claims priority to a Chinese patent application filed with the Patent Office of China on January 5, 2024, with application number 202410025166.2 and invention name “AI unit activation method, terminal and network side device”. The entire contents of the application are incorporated by reference into this application. Technical Field

[0003] The present application belongs to the field of communication technology, and specifically relates to an activation method, terminal and network-side device of an AI unit. Background Art

[0004] In wireless communication networks, terminals can use artificial intelligence (AI) units to make predictions and make relevant decisions based on the prediction results, such as channel estimation and signal processing.

[0005] Currently, to ensure the high quality, efficiency, and reliability of AI units, thereby meeting business needs and improving work efficiency, AI unit lifecycle management is necessary. AI unit lifecycle management generally refers to managing and maintaining the entire lifecycle of an AI unit, including but not limited to how to activate and deactivate the AI ​​unit. However, there is currently no solution for activating AI units. Summary of the Invention

[0006] The embodiments of the present application provide an activation method, a terminal, and a network-side device for an AI unit, which can solve the problem of how a terminal activates an AI unit.

[0007] In a first aspect, a method for activating an AI unit is provided, which is executed by a terminal, and the method includes:

[0008] The terminal activates the target AI unit according to the target information, where the target information includes at least one of indication information and an activation condition of the AI ​​unit, and the indication information is used to activate the target AI unit.

[0009] In a second aspect, a method for activating an AI unit is provided, which is performed by a network-side device. The method includes:

[0010] The network-side device sends instruction information, where the instruction information is used to activate the target AI unit.

[0011] In a third aspect, an activation device for an AI unit is provided, comprising any one of the following:

[0012] The activation module is configured to activate a target AI unit according to target information, wherein the target information includes at least one of indication information and an activation condition of the AI ​​unit, and the indication information is used to activate the target AI unit.

[0013] In a fourth aspect, an activation device for an AI unit is provided, comprising:

[0014] The sending module is used to send instruction information, where the instruction information is used to activate the target AI unit.

[0015] In a fifth aspect, a terminal is provided, comprising a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the method described in the first aspect are implemented.

[0016] In a sixth aspect, a terminal is provided, comprising a processor and a communication interface, wherein the processor is used to activate a target AI unit according to target information, the target information including at least one of indication information and an activation condition of the AI ​​unit, and the indication information is used to activate the target AI unit.

[0017] In the seventh aspect, a network side device is provided, which includes a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the program or instructions are executed by the processor, the steps of the method described in the second aspect are implemented.

[0018] In an eighth aspect, a network side device is provided, comprising a processor and a communication interface, wherein the communication interface is used to send indication information, and the indication information is used to activate a target AI unit.

[0019] In the ninth aspect, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented, or the steps of the method described in the second aspect are implemented.

[0020] In the tenth aspect, a wireless communication system is provided, comprising: a terminal and a network side device, wherein the terminal can be used to execute the steps of the method described in the first aspect, and the network side device can be used to execute the steps of the method described in the second aspect.

[0021] In the eleventh aspect, a chip is provided, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the method as described in the first aspect, or to implement the method as described in the second aspect.

[0022] In the twelfth aspect, a computer program / program product is provided, which is stored in a storage medium and is executed by at least one processor to implement the steps of the method described in the first aspect, or to implement the method described in the second aspect.

[0023] In this embodiment of the present application, the terminal can activate the target AI unit based on at least one of the indication information and the activation conditions of the AI ​​unit. Thus, the terminal can determine how to activate the AI ​​unit, thereby optimizing the AI ​​lifecycle management process, ensuring the high quality, efficiency, and reliability of the AI ​​unit, meeting business needs, and improving work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] FIG1 is a schematic diagram of a wireless communication system according to an embodiment of the present application;

[0025] FIG2 is a schematic flow chart of a method for activating an AI unit according to an embodiment of the present application;

[0026] FIG3 is a second schematic flow chart of the method for activating an AI unit according to an embodiment of the present application;

[0027] FIG4 is a schematic diagram of a structure of an activation device of an AI unit according to an embodiment of the present application;

[0028] FIG5 is a second structural diagram of the activation device of the AI ​​unit according to an embodiment of the present application;

[0029] FIG6 is a schematic structural diagram of a communication device according to an embodiment of the present application;

[0030] FIG7 is a schematic structural diagram of a terminal according to an embodiment of the present application;

[0031] FIG8 is a schematic structural diagram of a network-side device according to an embodiment of the present application. DETAILED DESCRIPTION

[0032] The following will be combined with the accompanying drawings in the embodiments of this application to clearly describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of this application.

[0033] The terms "first", "second", etc. in this application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable where appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same type, and do not limit the number of objects, for example, the first object can be one or more. In addition, "or" in this application represents at least one of the connected objects. For example, "A or B" covers three options, namely, Option 1: including A but not including B; Option 2: including B but not including A; Option 3: including both A and B. The character " / " generally indicates that the objects associated before and after are in an "or" relationship.

[0034] The term "indication" in this application can be either a direct indication (or explicit indication) or an indirect indication (or implicit indication). A direct indication can be understood as the sender explicitly informing the receiver of specific information, the operation to be performed, or the requested result, etc. in the instruction sent; an indirect indication can be understood as the receiver determining the corresponding information based on the instruction sent by the sender, or making a judgment and determining the operation to be performed or the requested result, etc. based on the judgment result.

[0035] It is worth noting that the technology described in the embodiments of the present application is not limited to the Long Term Evolution (LTE) / LTE-Advanced (LTE-A) system, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency Division Multiple Access (SC-FDMA) or other systems. The terms "system" and "network" in the embodiments of the present application are often used interchangeably, and the described technology can be used for the systems and radio technologies mentioned above, as well as for other systems and radio technologies. The following description describes a New Radio (NR) system for example purposes, and NR terminology is used in most of the following description, but these technologies can also be applied to systems other than NR systems, such as 6th Generation (6G) communication systems.

[0036] FIG1 is a block diagram of a wireless communication system applicable to an embodiment of the present application. The wireless communication system includes a terminal 11 and a network-side device 12. The terminal 11 may be a mobile phone, a tablet computer (Tablet Personal Computer), a laptop computer (Laptop Computer), a notebook computer, a personal digital assistant (PDA), a handheld computer, a netbook, an ultra-mobile personal computer (UMPC), a mobile internet device (MID), an augmented reality (AR), a virtual reality (VR) device, a robot, a wearable device (Wearable Device), an aircraft (Flight Vehicle), a vehicle-mounted device (VUE), a ship-mounted device, a pedestrian user equipment (PUE), a smart home (home appliances with wireless communication capabilities, such as refrigerators, televisions, washing machines, or furniture), a game console, a personal computer (PC), an ATM, or a self-service machine, or other terminal-side devices. Wearable devices include: smart watches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. Among them, the vehicle-mounted device can also be called a vehicle-mounted terminal, a vehicle-mounted controller, a vehicle-mounted module, a vehicle-mounted component, a vehicle-mounted chip or a vehicle-mounted unit, etc. It should be noted that the specific type of the terminal 11 is not limited in the embodiment of the present application. The network side device 12 may include an access network device or a core network device, wherein the access network device may also be called a radio access network (Radio Access Network, RAN) device, a radio access network function or a radio access network unit. The access network device may include a base station, a wireless local area network (Wireless Local Area Network, WLAN) access point (Access Point, AP) or a wireless fidelity (Wireless Fidelity, WiFi) node, etc.Among them, the base station can be referred to as Node B (NB), Evolved Node B (eNB), the next generation Node B (gNB), New Radio Node B (NR Node B), access point, Relay Base Station (RBS), Serving Base Station (SBS), Base Transceiver Station (BTS), radio base station, radio transceiver, Basic Service Set (BSS), Extended Service Set (ESS), Home Node B (HNB), Home Evolved Node B (home evolved Node B), Transmission Reception Point (TRP) or other appropriate terms in the field. As long as the same technical effect is achieved, the base station is not limited to specific technical vocabulary. It should be noted that in the embodiment of the present application, only the base station in the NR system is used as an example for introduction, and the specific type of the base station is not limited.

[0037] The AI ​​unit in the embodiments of the present application may also be referred to as an AI model, a machine learning (ML) model, an ML unit, an AI structure, an AI function, an AI feature, a machine learning model, a neural network, a neural network function, a neural network function, etc., and the embodiments of the present application are described only by taking the AI ​​unit as an example. Among them, the AI ​​unit can be a processing unit that can implement specific algorithms, formulas, processing flows, capabilities, etc. related to AI, or it can be a processing method, algorithm, function, module or unit for a specific data set (including at least one of the input and output of the AI ​​unit), or it can be a processing method, algorithm, function, module or unit running on AI / ML related hardware such as a graphics processing unit (GPU), a neural network processing unit (NPU), a tensor processing unit (TPU), an application specific integrated circuit (ASIC), etc., without specific limitation here.

[0038] Optionally, the identifier of the AI ​​unit can be an AI model identifier, an AI structure identifier, an AI algorithm identifier, or an identifier of a specific data set associated with the AI ​​unit, or an identifier of a specific scenario, environment, channel feature, or device related to AI / ML, or an identifier of an AI / ML-related function, feature, capability, or module, which is not specifically limited here.

[0039] Below, in combination with the accompanying drawings, the activation method, terminal and network-side device of the AI ​​unit provided in the embodiments of the present application are described in detail through some embodiments and their application scenarios.

[0040] As shown in Figure 2, an embodiment of the present application provides an activation method 200 for an AI unit, which can be executed by a terminal. In other words, the activation method of the AI ​​unit can be executed by software or hardware installed in the terminal. The activation method of the AI ​​unit includes the following steps.

[0041] S202: The terminal activates the target AI unit according to the target information, where the target information includes at least one of indication information and an activation condition of the AI ​​unit, and the indication information is used to activate the target AI unit.

[0042] Whether the AI ​​function is enabled or disabled, the terminal can activate a target AI unit based on target information. The target information includes at least one of indication information and activation conditions for the AI ​​unit. The indication information can be sent by a network device. The activation conditions for the AI ​​unit can be configured by the terminal, by the network device, or jointly by the terminal and the network device, without specific limitations. The target AI unit can be an inactivated AI unit in the terminal. The number of target AI units can be one or more.

[0043] In this way, since the terminal can activate the target AI unit based on the indication information and at least one of the activation conditions of the AI ​​unit, the terminal can determine how to activate the AI ​​unit, thereby optimizing the AI ​​lifecycle management process, ensuring the high quality, high efficiency and high reliability of the AI ​​unit, meeting business needs and improving work efficiency.

[0044] Optionally, in some implementations, when the target information includes indication information, the terminal may further perform the following operations:

[0045] The terminal receives the indication information.

[0046] The terminal receiving the indication information may be the terminal receiving the indication information from the network side device. The indication information may be carried by Radio Resource Control (RRC) signaling, or carried by Downlink Control Information (DCI), or carried by Medium Access Control-Control Element (MAC-CE).

[0047] Optionally, in some implementations, the indication information may be proactively sent by the network side device to the terminal. In this case, the indication information may indicate any of the following:

[0048] Activate the target AI unit;

[0049] Activates the target AI unit and deactivates the activated AI unit.

[0050] The activated AI unit may be one or more AI units already activated in the terminal. If the instruction information indicates activation of the target AI unit, the terminal performs the operation of activating the target AI unit. If the instruction information indicates activation of the target AI unit and deactivation of the activated AI unit, the terminal performs the operation of deactivating the activated AI unit and activating the target AI unit.

[0051] Optionally, in some other implementations, the indication information may also be sent by the network side device to the terminal when receiving the AI ​​unit activation request from the terminal. That is, the terminal receives the indication information, which may include:

[0052] The terminal determines whether the activated AI unit meets the deactivation conditions;

[0053] When the terminal determines that the activated AI unit meets the deactivation conditions, it sends an AI unit activation request;

[0054] The terminal receives the indication information.

[0055] The deactivation condition may be configured by the terminal itself, or by the network side device, or by the terminal and the network side device together, and is not specifically limited here. Optionally, the deactivation condition may be related to at least one of the following:

[0056] Performance when applying activated AI units;

[0057] The computing and storage capabilities supported by the terminal;

[0058] The identifier (ID) of the activated AI unit;

[0059] Scenarios in which activated AI units are applicable;

[0060] Information about functions supported by activated AI units;

[0061] Cell information supported by the activated AI unit;

[0062] Information about the regions supported by the activated AI unit;

[0063] Input and output type information of activated AI units;

[0064] The inference accuracy supported by the activated AI unit;

[0065] The terminal computing and storage capabilities corresponding to the activated AI unit;

[0066] Data sets related to activated AI units;

[0067] Performance thresholds of activated AI units;

[0068] The complexity threshold of the activated AI unit.

[0069] When determining whether an activated AI unit meets the deactivation condition, the terminal may make a determination based on at least one of the aforementioned factors related to the deactivation condition, and determine whether the activated AI unit meets the deactivation condition based on the determination result. For example, the terminal may determine whether the performance of the activated AI unit when applied is greater than or equal to a certain threshold. If so, this indicates that the terminal's performance when applying the activated AI unit is good and there is no need to deactivate the AI ​​unit. In this case, it can be determined that the deactivation condition is not met. If not, this indicates that the terminal's performance when applying the activated AI unit is poor and the AI ​​unit needs to be deactivated. In this case, it can be determined that the deactivation condition is met. For another example, the terminal may determine whether the currently supported computing and storage capabilities match the computing and storage capabilities required by the activated AI unit. If so, this indicates that the currently supported computing and storage capabilities allow the terminal to continue using the AI ​​unit. In this case, it can be determined that the deactivation condition is not met. If not, this indicates that the currently supported computing and storage capabilities do not allow the terminal to continue using the AI ​​unit. In this case, it can be determined that the deactivation condition is met. For example, the terminal can determine whether the current scenario is applicable to the activated AI unit. If so, it can be determined that the AI ​​unit can be used in the current scenario, and the deactivation condition can be determined not to be met. If not, it can be determined that the current scenario does not match the applicable scenario of the AI ​​unit and the AI ​​unit can no longer be used, and the deactivation condition can be determined to be met. And so on. Here, we will not provide examples of how to determine whether an activated AI unit meets the deactivation condition based on other factors.

[0070] It should be noted that, for at least one of the above-mentioned factors related to the deactivation condition, when the terminal determines whether the activated AI unit meets the deactivation condition, it can be determined that the activated AI unit meets the deactivation condition when one of the factors meets the deactivation condition, or it can be determined that the activated AI unit meets the deactivation condition when multiple factors meet the deactivation condition. No specific limitation is made here.

[0071] If the terminal determines that the activated AI unit meets the deactivation conditions, it can send an AI unit activation request to the network device. After receiving the AI ​​unit activation request, the network device can send an instruction to the terminal. After receiving the instruction, the terminal can activate the target AI unit according to the instruction. The instruction received by the terminal can indicate any of the following:

[0072] Activate the target AI unit;

[0073] Activate target AI units and deactivate activated AI units;

[0074] The terminal selects the target AI unit to be activated.

[0075] If the instruction information indicates activation of the target AI unit, the terminal activates the target AI unit. If the instruction information indicates activation of the target AI unit and deactivation of the activated AI unit, the terminal deactivates the activated AI unit and activates the target AI unit. If the instruction information indicates selection of the target AI unit to be activated by the terminal, the terminal selects the target AI unit for activation.

[0076] Optionally, in some embodiments, when the target information includes activation conditions and instruction information for an AI unit, and the instruction information indicates activation of the target AI unit or activation of the target AI unit and deactivation of an already activated AI unit, the terminal may determine whether the target AI unit meets the activation conditions when activating the target AI unit, and activate the target AI unit if the activation conditions are met. Optionally, the instruction information may include unit information of the target AI unit. Thus, when determining whether the target AI unit meets the activation conditions, the terminal may determine whether the target AI unit meets the activation conditions based on the unit information of the target AI unit included in the instruction information, and activate the target AI unit if it is determined that the target AI unit meets the activation conditions.

[0077] The unit information of the target AI unit may include at least one of the following:

[0078] The ID of the target AI unit;

[0079] Scenarios in which the target AI unit is applicable;

[0080] Function information supported by the target AI unit;

[0081] Cell information supported by the target AI unit;

[0082] The region information supported by the target AI unit;

[0083] Input and output type information of the target AI unit;

[0084] The inference accuracy supported by the target AI unit;

[0085] The terminal computing and storage capabilities corresponding to the target AI unit;

[0086] Datasets relevant to the target AI unit;

[0087] Performance threshold of the target AI unit;

[0088] The complexity threshold of the target AI unit.

[0089] Optionally, the activation condition may be related to at least one of the following:

[0090] The computing and storage capabilities supported by the terminal;

[0091] The ID of the target AI unit;

[0092] Scenarios in which the target AI unit is applicable;

[0093] Function information supported by the target AI unit;

[0094] Cell information supported by the target AI unit;

[0095] The region information supported by the target AI unit;

[0096] Input and output type information of the target AI unit;

[0097] The inference accuracy supported by the target AI unit;

[0098] The terminal computing and storage capabilities corresponding to the target AI unit;

[0099] Datasets relevant to the target AI unit;

[0100] Performance threshold of the target AI unit;

[0101] The complexity threshold of the target AI unit.

[0102] When determining whether the target AI unit meets activation conditions based on the unit information of the target AI unit, the terminal may perform a determination based on the unit information of the target AI unit and at least one of the aforementioned factors related to the activation conditions, and determine whether the target AI unit meets the activation conditions based on the determination result. For example, the terminal may determine whether the currently supported computing and storage capabilities allow activation of the target AI unit. If so, the terminal may support the use of the target AI unit, and the activation conditions may be determined to be met. If not, the terminal may determine that the target AI unit is not supported, and the activation conditions may be determined to be met. For another example, the terminal may determine whether the current scenario is applicable to the target AI unit. If so, the target AI unit may be used in the current scenario, and the activation conditions may be determined to be met. If not, the current scenario does not match the applicable scenario of the target AI unit and the target AI unit cannot be used, and the activation conditions may be determined to be met. For another example, the terminal may determine whether the performance threshold of the target AI unit meets service requirements. If so, the target AI unit may be used to execute the relevant service, and the activation conditions may be determined to be met. If not, the target AI unit is not suitable for executing the relevant service, and the activation conditions may be determined to be met. And so on. Here we will not provide examples one by one to illustrate how to determine whether the target AI unit meets the activation conditions based on other factors.

[0103] It should be noted that, for at least one of the above-mentioned factors related to the activation conditions, when the terminal determines whether the target AI unit meets the activation conditions, it can be determined that the target AI unit meets the activation conditions when one of the factors meets the activation conditions, or it can be determined that the target AI unit meets the activation conditions when multiple factors meet the activation conditions. No specific limitation is made here.

[0104] Optionally, in some implementations, if the terminal determines that the target AI unit does not meet the activation condition, the terminal may perform at least one of the following operations:

[0105] The terminal sends first information, where the first information indicates that the target AI unit does not meet the activation condition;

[0106] The terminal receives the second information, where the second information indicates deactivation of the target AI unit;

[0107] The terminal deactivates the target AI unit;

[0108] The terminal sends third information, where the third information indicates that the target AI unit is not activated;

[0109] The terminal receives fourth information, where the fourth information instructs to perform the first operation;

[0110] The terminal performs a first operation.

[0111] For example, if the terminal determines that the target AI unit does not meet the activation conditions, it may send a first message to the network-side device to inform the network-side device that the target AI unit does not meet the activation conditions. After receiving the first message, the network-side device may send a second message to the terminal, and the second message may indicate the deactivation of the target AI unit. After receiving the second message, the terminal may deactivate the target AI unit, that is, not activate the target AI unit. Optionally, if the target AI unit is deactivated, the terminal may send a third message to the network-side device to inform the network-side device that the target AI unit is not activated. Optionally, after receiving the third message, the network-side device may send a fourth message to the terminal, and the fourth message may indicate the execution of the first operation. After receiving the fourth message, the terminal may perform the first operation.

[0112] For another example, if the terminal determines that the target AI unit does not meet the activation conditions, it may automatically deactivate the target AI unit. Optionally, when the terminal automatically deactivates the target AI unit, it may send a third message to the network device to inform the network device that the target AI unit has not been activated. Optionally, after receiving the third message, the network device may send a fourth message to the terminal, the fourth message instructing the terminal to perform the first operation. After receiving the fourth message, the terminal may perform the first operation.

[0113] For another example, if the terminal determines that the target AI unit does not meet the activation conditions, it can automatically deactivate the target AI unit. Optionally, if the terminal automatically deactivates the target AI unit, it can send a third message to the network device to inform the network device that the target AI unit has not been activated. Optionally, after sending the third message to the network device, the terminal can automatically perform the first operation.

[0114] The first information and the third information sent by the terminal can be carried by RRC signaling, or by uplink control information (UCI). The second information and the fourth information received by the terminal can be carried by RRC signaling, or by DCI, or by MAC-CE. The first operation may include fine-tuning the target AI unit, retraining the target AI unit, upgrading the target AI unit, downgrading the target AI unit, rolling back the target AI unit, collecting data, and performing AI unit transfer with other devices. At least one of the other devices may be a network-side device or the terminal's own server. Performing AI unit transfer with other devices may be that the other device transfers the new AI unit to the terminal.

[0115] Optionally, in some embodiments, when the instruction information instructs the terminal to select a target AI unit to be activated, the terminal activates the target AI unit according to the target information. Alternatively, the terminal may independently select the target AI unit to be activated. Optionally, when the target information includes activation conditions for the AI ​​unit, the terminal may include the following steps when independently selecting the target AI unit to be activated:

[0116] The terminal determines whether the one or more AI units meet activation conditions based on the unit information of the one or more AI units;

[0117] The terminal determines an AI unit that meets the activation condition among the one or more AI units as a target AI unit, and activates the target AI unit.

[0118] The one or more AI units mentioned above may be existing and unactivated AI units in the terminal. For each AI unit, the unit information of the AI ​​unit may include at least one of the following:

[0119] The ID of the AI ​​unit;

[0120] Scenarios where AI units are applicable;

[0121] Information about functions supported by the AI ​​unit;

[0122] Information about cells supported by the AI ​​unit;

[0123] AI unit supported region information;

[0124] AI unit input and output type information;

[0125] The inference accuracy supported by the AI ​​unit;

[0126] Terminal computing and storage capabilities corresponding to the AI ​​unit;

[0127] Data sets related to AI units;

[0128] Performance threshold of AI unit;

[0129] The complexity threshold of the AI ​​unit.

[0130] When the terminal determines whether one or more AI units meet the activation conditions based on the unit information of the one or more AI units, it can determine whether the AI ​​unit meets the activation conditions for each AI unit. For an AI unit, the activation condition can be related to at least one of the following:

[0131] The computing and storage capabilities supported by the terminal;

[0132] The ID of the AI ​​unit;

[0133] Scenarios where AI units are applicable;

[0134] Information about functions supported by the AI ​​unit;

[0135] Information about cells supported by the AI ​​unit;

[0136] AI unit supported region information;

[0137] AI unit input and output type information;

[0138] The inference accuracy supported by the AI ​​unit;

[0139] Terminal computing and storage capabilities corresponding to the AI ​​unit;

[0140] Data sets related to AI units;

[0141] Performance threshold of AI unit;

[0142] The complexity threshold of the AI ​​unit.

[0143] When determining whether an AI unit satisfies the activation condition based on its unit information, a determination can be made based on the AI ​​unit information and at least one of the aforementioned factors related to the activation condition, and the determination of whether the AI ​​unit satisfies the activation condition is made based on the determination result. For specific implementations, see the aforementioned specific implementation of the terminal determining whether a target AI unit satisfies the activation condition based on the unit information of the target AI unit, and will not be described in detail here.

[0144] After determining whether one or more AI units meet the activation conditions, the terminal may determine the AI ​​units that meet the activation conditions as target AI units and activate the target AI units. The number of AI units that meet the activation conditions may be one or more.

[0145] Optionally, in some implementations, when the target information includes an AI unit activation condition, the terminal activating the target AI unit according to the target information may include:

[0146] The terminal determines whether the target AI unit meets the activation conditions;

[0147] When determining that the target AI unit meets the activation condition, the terminal activates the target AI unit.

[0148] The activation condition can be configured by the terminal itself, or by the network side device, or by the terminal and the network side device together, and is not specifically limited here. Optionally, the activation condition is related to at least one of the following:

[0149] The computing and storage capabilities supported by the terminal;

[0150] The ID of the target AI unit;

[0151] Scenarios in which the target AI unit is applicable;

[0152] Function information supported by the target AI unit;

[0153] Cell information supported by the target AI unit;

[0154] The region information supported by the target AI unit;

[0155] Input and output type information of the target AI unit;

[0156] The inference accuracy supported by the target AI unit;

[0157] The terminal computing and storage capabilities corresponding to the target AI unit;

[0158] Datasets relevant to the target AI unit;

[0159] Performance threshold of the target AI unit;

[0160] The complexity threshold of the target AI unit.

[0161] When determining whether the target AI unit meets the activation conditions, the terminal may make a determination based on at least one of the aforementioned factors related to the activation conditions, and determine whether the target AI unit meets the activation conditions based on the determination result. For example, the terminal may determine whether the currently supported computing and storage capabilities allow activation of the target AI unit. If so, the terminal may indicate that the target AI unit is supported, and the activation conditions may be determined to be met. If not, the terminal may indicate that the target AI unit is not supported, and the activation conditions may be determined to be met. For another example, the terminal may determine whether the current scenario is applicable to the target AI unit. If so, the target AI unit can be used in the current scenario, and the activation conditions may be determined to be met. If not, the current scenario does not match the applicable scenario of the target AI unit, and the target AI unit cannot be used, and the activation conditions may be determined to be met. And so on. Examples of how to determine whether the target AI unit meets the activation conditions based on other factors will not be provided here.

[0162] It should be noted that, for at least one of the above-mentioned factors related to the activation conditions, when the terminal determines whether the target AI unit meets the activation conditions, it can be determined that the target AI unit meets the activation conditions when one of the factors meets the activation conditions, or it can be determined that the target AI unit meets the activation conditions when multiple factors meet the activation conditions. No specific limitation is made here.

[0163] Optionally, in some implementations, the terminal determines whether the target AI unit meets the activation condition, which may include:

[0164] The terminal determines whether the activated AI unit meets the deactivation conditions;

[0165] When determining that the activated AI unit meets the deactivation condition, the terminal determines whether the target AI unit meets the activation condition.

[0166] That is to say, the premise for the terminal to determine whether the target AI unit meets the activation conditions is that the activated AI unit in the terminal meets the deactivation conditions. When the activated AI unit meets the deactivation conditions, the target AI unit needs to be activated. Before activating the target AI unit, it is necessary to determine whether the target AI unit meets the activation conditions, and activate the target AI unit if the activation conditions are met.

[0167] The above deactivation condition can be configured by the terminal itself, or by the network side device, or by the terminal and the network side device together, and is not specifically limited here. Optionally, the deactivation condition can be related to at least one of the following:

[0168] Performance when applying activated AI units;

[0169] The computing and storage capabilities supported by the terminal;

[0170] The ID of the activated AI unit;

[0171] Scenarios in which activated AI units are applicable;

[0172] Information about functions supported by activated AI units;

[0173] Cell information supported by the activated AI unit;

[0174] Information about the regions supported by the activated AI unit;

[0175] Input and output type information of activated AI units;

[0176] The inference accuracy supported by the activated AI unit;

[0177] The terminal computing and storage capabilities corresponding to the activated AI unit;

[0178] Data sets related to activated AI units;

[0179] Performance thresholds of activated AI units;

[0180] The complexity threshold of the activated AI unit.

[0181] When determining whether an activated AI unit meets the deactivation condition, the terminal may make a determination based on at least one of the aforementioned factors related to the deactivation condition, and determine whether the activated AI unit meets the deactivation condition based on the determination result. The specific implementation method for determining whether an activated AI unit meets the deactivation condition by the terminal may be the same as the specific implementation method described above, and will not be described in detail here.

[0182] Optionally, in some implementations, when activating the target AI unit, the terminal may include:

[0183] After performing the first processing or the second processing on the target AI unit, the terminal applies the target AI unit; or,

[0184] The terminal deactivates the activated AI unit and performs the first processing or the second processing on the target AI unit, and then applies the target AI unit.

[0185] Specifically, if the indication information indicates activation of the target AI unit, when the terminal activates the target AI unit, the terminal may first perform a first process or a second process on the target AI unit, and then apply the target AI unit. The first process includes reading or loading at least a portion of the target AI unit's information, and the second process includes reading or loading the remaining information of the target AI unit. Applying the target AI unit may involve using the target AI unit to execute related service processing. If the indication information indicates activation of the target AI unit and deactivation of an already activated AI unit, when the terminal activates the target AI unit, the terminal may first deactivate the already activated AI unit, then perform the first process or the second process on the target AI unit, and finally apply the target AI unit. Alternatively, if the terminal supports parallel processing capabilities, the terminal may deactivate the already activated AI unit, execute the first process or the second process on the target AI unit in parallel during deactivation, and then apply the target AI unit. If the indication information indicates that the terminal selects a target AI unit to be activated or that the terminal selects a target AI unit for activation based on the activation condition, then when activating the target AI unit, the terminal may apply the target AI unit after performing the first processing or the second processing on the target AI unit, or deactivate the activated AI unit and apply the target AI unit after performing the first processing or the second processing on the target AI unit.

[0186] The aforementioned first or second processing of the target AI unit may be the first processing of the target AI unit (in which case the first processing may include reading or loading all the information of the target AI unit), or the first and second processing of the target AI unit (in which case the first processing may include reading or loading part of the information of the target AI unit). For example, if the target AI unit is small, the reading or loading process of the target AI unit can be completed in one go. In this case, when the terminal reads or loads the target AI unit, the first processing may include reading or loading all the information of the target AI unit. If the target AI unit is large, the reading or loading process of the target AI unit may not be completed in one go. In this case, when the terminal reads or loads the target AI unit, the first processing may include reading or loading part of the information of the target AI unit, and the second processing may include reading or loading the remaining information of the target AI unit.

[0187] Optionally, in some implementations, after activating the target AI unit, the terminal may further perform the following operations:

[0188] The terminal sends fifth information, where the fifth information indicates that the terminal has completed activation of the target AI unit. The fifth information is carried by RRC signaling or UCI.

[0189] In an embodiment of the present application, when the terminal activates the target AI unit according to the indication information, it needs to meet certain delay requirements. Specifically, when the number of target AI units is one, the activation delay of the one target AI unit (that is, the time actually used by the terminal when activating a target AI unit) needs to be less than or equal to the first delay. The first delay can be configured by the network side device or agreed upon by the protocol. When the number of target AI units is multiple, the activation delay of multiple target AI units (that is, the time actually used by the terminal when activating multiple target AI units) needs to be less than or equal to the second delay, and the second delay is less than or equal to the sum of the activation delays of multiple target AI units. The second delay can be configured by the network side device or agreed upon by the protocol. In this way, by constraining the activation delay of the AI ​​unit, the process of AI lifecycle management can be optimized and the definition of the communication system can be improved.

[0190] Optionally, for a target AI unit, the activation delay of the target AI unit may include at least one of the following:

[0191] The delay between the terminal sending the AI ​​unit activation request and receiving the indication information;

[0192] The delay in processing or parsing the signaling carrying the indication information by the terminal;

[0193] The latency of the terminal performing Hybrid Automatic Repeat reQuest (HARQ) feedback;

[0194] The delay for the terminal to deactivate an activated AI unit;

[0195] The latency of the terminal performing a first process on the target AI unit, where the first process includes reading or loading part of the target AI unit's information;

[0196] The latency of the terminal performing a second process and application on the target AI unit, where the second process includes reading or loading the remaining information of the target AI unit.

[0197] For example, when a network-side device instructs a terminal to activate a target AI unit through RRC or DCI, the activation delay of the target AI unit may include the delay in the terminal processing or parsing the signaling (i.e., RRC or DCI) carrying the indication information, the delay in the terminal performing the first processing of the target AI unit, and the delay in the terminal performing the second processing and application of the target AI unit. When a network-side device instructs a terminal to activate a target AI unit and deactivate an activated AI unit through MAC-CE, the activation delay of the target AI unit may include the delay in the terminal processing or parsing the signaling (i.e., MAC-CE) carrying the indication information, the delay in the terminal performing HARQ feedback, the delay in the terminal deactivating the activated AI unit, the delay in the terminal performing the first processing of the target AI unit, and the delay in the terminal performing the second processing and application of the target AI unit. When a network-side device instructs a terminal to activate a target AI unit via RRC or DCI based on an AI unit activation request from a terminal, the activation delay of the target AI unit may include the delay between the terminal sending the AI ​​unit activation request and receiving the indication information, the delay in the terminal processing or parsing the signaling carrying the indication information, the delay in the terminal performing the first processing on the target AI unit, and the delay in the terminal performing the second processing and application of the target AI unit. When a network-side device instructs a terminal to activate a target AI unit and deactivate an activated AI unit via MAC-CE based on an AI unit activation request from a terminal, the activation delay of the target AI unit may include the delay between the terminal sending the AI ​​unit activation request and receiving the indication information, the delay in the terminal processing or parsing the signaling carrying the indication information, the delay in the terminal performing HARQ feedback, the delay in the terminal deactivating the activated AI unit, the delay in the terminal performing the first processing on the target AI unit, and the delay in the terminal performing the second processing and application of the target AI unit. When the network device indicates via RRC or DCI that the terminal independently selects the target AI unit to be activated, the activation latency of the target AI unit may include the latency of the terminal processing or parsing the signaling carrying the indication information, the latency of the terminal performing the first processing of the target AI unit, and the latency of the terminal performing the second processing and application of the target AI unit. Examples are not provided here. The latency of the terminal performing HARQ feedback may include the latency between the terminal receiving the downlink data transmission and the terminal sending the acknowledgment indication.

[0198] For multiple target AI units, optionally, if the multiple target AI units can be activated in parallel, the second delay can be less than or equal to the maximum of the activation delays of the multiple target AI units. If the differences between the multiple target AI units are within a specified range, the activation delays of the multiple target AI units can be less than or equal to a third delay, where the third delay is less than the second delay. In other words, if the differences between the multiple target AI units are within a specified range, the delay requirement for the activation delays of the multiple target AI units can be further shortened. The differences between the multiple target AI units are related to at least one of the structure, parameters, complexity, size, quantization level, functions, corresponding terminal computing and storage capabilities, and applicable scenarios of the A1 unit.

[0199] In this embodiment of the present application, the terminal can activate the target AI unit based on at least one of the indication information and the activation conditions of the AI ​​unit. Thus, the terminal can determine how to activate the AI ​​unit, thereby optimizing the AI ​​lifecycle management process, ensuring the high quality, efficiency, and reliability of the AI ​​unit, meeting business needs, and improving work efficiency.

[0200] As shown in Figure 3, an embodiment of the present application provides an activation method 300 for an AI unit, which can be executed by a network-side device. In other words, the activation method of the AI ​​unit can be executed by software or hardware installed in the network-side device. The activation method of the AI ​​unit includes the following steps.

[0201] S302: The network-side device sends instruction information, which is used to activate the target AI unit.

[0202] When communicating with a terminal, the network device may send an instruction to the terminal to activate a target AI unit. The target AI unit may be an inactivated AI unit in the terminal. The number of target AI units may be one or more.

[0203] The indication information may be carried by RRC signaling, or by DCI, or by MAC-CE.

[0204] Optionally, in some implementations, the network side device may proactively send instruction information to the terminal. In this case, the instruction information may indicate any of the following:

[0205] Activate the target AI unit;

[0206] Activates the target AI unit and deactivates the activated AI unit.

[0207] Optionally, in some other implementations, the network side device may also send indication information to the terminal upon receiving the AI ​​unit activation request from the terminal. That is, the indication information sent by the network side device may include:

[0208] The network-side device receives the AI ​​unit activation request;

[0209] The network-side device sends an indication message according to the AI ​​unit activation request.

[0210] The AI ​​unit activation request may be sent by the terminal to the network device when it determines that the activated AI unit does not meet the activation conditions. The specific implementation of the terminal determining that the activated AI unit does not meet the activation conditions can be found in the specific implementation of the corresponding steps in the embodiment shown in FIG2 , and will not be repeated here. After receiving the AI ​​unit activation request, the network device may send an indication to the terminal based on the AI ​​unit activation request. The indication sent by the network device may indicate any of the following:

[0211] Activate the target AI unit;

[0212] Activate target AI units and deactivate activated AI units;

[0213] The terminal selects the target AI unit to be activated.

[0214] The target AI unit may be an AI unit selected or determined by the network device based on actual service requirements. The method by which the network device selects or determines the target AI unit is not limited herein. The target AI unit may be an AI unit already present in the terminal. Optionally, if the terminal does not have the target AI unit, the network device may indicate the target AI unit to the terminal. The number of target AI units may be one or more.

[0215] After the network side device sends the instruction information to the terminal, the terminal can activate the target AI unit according to the instruction information. The specific implementation method of the terminal activating the target AI unit according to the instruction information can be referred to the specific implementation of the corresponding steps in the embodiment shown in Figure 2, and will not be described in detail here.

[0216] Optionally, in some embodiments, when the instruction information indicates activation of a target AI unit or activation of a target AI unit and deactivation of an activated AI unit, the instruction information may include unit information of the target AI unit. The unit information of the target AI unit may be used by the terminal to determine whether the target AI unit meets the activation conditions. The unit information of the target AI unit may include at least one of the following:

[0217] The ID of the target AI unit;

[0218] Scenarios in which the target AI unit is applicable;

[0219] Function information supported by the target AI unit;

[0220] Cell information supported by the target AI unit;

[0221] The region information supported by the target AI unit;

[0222] Input and output type information of the target AI unit;

[0223] The inference accuracy supported by the target AI unit;

[0224] The terminal computing and storage capabilities corresponding to the target AI unit;

[0225] Datasets relevant to the target AI unit;

[0226] Performance threshold of the target AI unit;

[0227] The complexity threshold of the target AI unit.

[0228] After receiving the indication information, the terminal can determine whether the target AI unit meets the activation conditions based on the unit information of the target AI unit included in the indication information. If so, the target AI unit is activated. The specific implementation of the terminal determining whether the target AI unit meets the activation conditions can be found in the specific implementation of the corresponding steps in the embodiment shown in Figure 2, and will not be repeated here.

[0229] Optionally, in some embodiments, after determining whether the target AI unit meets the activation conditions, the terminal may determine that the target AI unit does not meet the activation conditions. In this case, the terminal may report relevant information to the network device, and the network device may perform at least one of the following operations:

[0230] The network-side device receives first information, where the first information indicates that the target AI unit does not meet the activation condition;

[0231] The network-side device sends a second message, where the second message indicates to deactivate the target AI unit;

[0232] The network-side device receives third information, where the third information indicates that the target AI unit is not activated;

[0233] The network side device sends fourth information, where the fourth information instructs to perform the first operation.

[0234] For example, if the terminal determines that the target AI unit does not meet the activation conditions, it may send first information to the network device to inform the network device that the target AI unit does not meet the activation conditions. The network device may receive the first information and then send second information to the terminal. The second information may instruct the deactivation of the target AI unit. After receiving the second information, the terminal may deactivate the target AI unit, i.e., deactivate the target AI unit. Optionally, if the terminal deactivates the target AI unit, it may send third information to the network device to inform the network device that the target AI unit is not activated. The network device may receive the third information. Optionally, after receiving the third information, the network device may send fourth information to the terminal to instruct the execution of the first operation. For another example, if the terminal determines that the target AI unit does not meet the activation conditions, it may deactivate the target AI unit. Optionally, if the terminal deactivates the target AI unit, it may send third information to the network device to inform the network device that the target AI unit is not activated. The network device may receive the third information. Optionally, after receiving the third information, the network device may send fourth information to the terminal to instruct the execution of the first operation.

[0235] The first information and third information received by the network-side device may be carried by RRC signaling or UCI. The second information and fourth information sent by the network-side device may be carried by RRC signaling, DCI, or MAC-CE. The first operation may include at least one of fine-tuning the target AI unit, retraining the target AI unit, upgrading the target AI unit, downgrading the target AI unit, rolling back the target AI unit, collecting data, and transferring the AI ​​unit to another device. The other device may be a network-side device or a server of the terminal itself. Transferring the AI ​​unit to another device may involve the other device transferring the new AI unit to the terminal.

[0236] Optionally, in some embodiments, when activating the target AI unit, the terminal may send fifth information to the network device, and the network device may receive the fifth information. The fifth information indicates that the terminal has completed activation of the target AI unit. The fifth information is carried by RRC signaling or UCI.

[0237] In this embodiment of the present application, the network-side device can send an instruction, and the terminal can activate the target AI unit according to the instruction upon receiving the instruction. Thus, the terminal can determine how to activate the AI ​​unit, thereby optimizing the AI ​​lifecycle management process, ensuring the high quality, efficiency, and reliability of the AI ​​unit, meeting business needs, and improving work efficiency.

[0238] In order to facilitate understanding of the activation method of the AI ​​unit provided in the embodiments of the present application, some more specific embodiments will be used as examples for illustration below.

[0239] Example 1: The network-side device instructs the terminal to activate the target AI unit.

[0240] The activation process of Example 1 is applicable to the following two scenarios:

[0241] Scenario 1: The AI ​​function is not enabled before the terminal receives the instruction information;

[0242] Scenario 2: Before the terminal receives the indication information, the AI ​​function is enabled but the previously used AI unit is deactivated.

[0243] The activation process can include the following steps:

[0244] Step 1: The network-side device sends an instruction message to the terminal, where the instruction message indicates to activate the target AI unit, and the instruction message includes unit information of the target AI unit.

[0245] The indication information may be carried by RRC signaling, DCI or MAC-CE.

[0246] The unit information of the target AI unit may include at least one of the target AI unit ID, applicable scenarios of the target AI unit, function information supported by the target AI unit, cell information supported by the target AI unit, area information supported by the target AI unit, input and output type information of the target AI unit, inference accuracy supported by the target AI unit, terminal computing and storage capabilities corresponding to the target AI unit, a data set related to the target AI unit, a performance threshold value of the target AI unit, and a complexity threshold value of the target AI unit.

[0247] Step 2: The terminal determines whether the target AI unit meets the activation conditions based on the unit information of the target AI unit.

[0248] If the terminal determines that the target AI unit meets the activation condition, it can execute step 4. If the terminal determines that the target AI unit does not meet the activation condition, it can execute step 3.

[0249] Step 3: The terminal sends first information to the network-side device, where the first information indicates that the target AI unit does not meet the activation condition.

[0250] For the network side device, after receiving the first information, it can send second information to the terminal, where the second information indicates to deactivate the target AI unit.

[0251] Optionally, step 3 may also be replaced by the terminal automatically deactivating the target AI unit and then sending third information to the network-side device, where the third information indicates that the target AI unit is not activated.

[0252] Optionally, when the target AI unit is deactivated, the terminal may also independently perform the first operation, or the network-side device may send fourth information to the terminal, instructing the terminal to perform the first operation. The first operation may include at least one of fine-tuning the target AI unit, retraining the target AI unit, upgrading the target AI unit, downgrading the target AI unit, rolling back the target AI unit, collecting data, and transferring the AI ​​unit to another device.

[0253] Step 4: The terminal performs a first process on the target AI unit, where the first process includes reading or loading part of the information of the target AI unit.

[0254] Step 5: The terminal performs a second process and application on the target AI unit. The second process includes reading or loading the remaining information of the target AI unit.

[0255] Optionally, after activating the target AI unit, the terminal may send fifth information to the network-side device, where the fifth information indicates that the terminal has completed activation of the target AI unit.

[0256] For the above activation process, the starting point is that the terminal receives the indication information sent by the network side device, and the end point can be that the terminal completes the second processing and application of the target AI unit, or the terminal completes the activation of the target AI unit and sends the fifth information to the network side device for reporting.

[0257] In the above activation process, if the number of target AI units is 1, the activation delay of the target AI unit includes at least:

[0258] The delay in processing or parsing the signaling carrying the indication information by the terminal;

[0259] The delay of the terminal performing HARQ feedback (for the case where the indication information is carried by MAC-CE, this may include the delay between the terminal receiving the downlink data transmission and the terminal sending the acknowledgment indication);

[0260] The latency of the terminal performing the first processing on the target AI unit;

[0261] The delay of the terminal performing the second processing and application on the target AI unit.

[0262] If there are multiple target AI units, when the terminal activates multiple target AI units, the total activation latency of the terminal should be less than or equal to the sum of the latency requirements of each target AI unit. Optionally, when the terminal can activate more than one target AI unit in parallel, the activation latency is the activation latency of the largest single AI unit currently activated in parallel. Optionally, when more than one of the multiple target AI units is within a specified variance, the corresponding activation latency requirement can be shortened. The variance between the AI ​​units is related to at least one of the A1 unit's structure, parameters, complexity, size, quantization level, functionality, corresponding terminal computing and storage capabilities, and applicable scenarios.

[0263] Example 2: The terminal initiates activation of the AI ​​unit to the network-side device.

[0264] The activation process of Example 2 is applicable to the following two scenarios:

[0265] Scenario 1: The AI ​​function is not enabled before the terminal receives the instruction information or sends the activation request on its own;

[0266] Scenario 2: Before the terminal receives the indication information or sends the activation request on its own, the AI ​​function is enabled but the previously used AI unit is deactivated.

[0267] The activation process can include the following steps:

[0268] Step 1: The terminal may select an AI unit that meets the activation conditions among one or more AI units as a target AI unit and activate the target AI unit, or the terminal may send an AI unit activation request to the network side device.

[0269] When the terminal sends an AI activation request to the network-side device, step 2 can be executed.

[0270] Step 2: The network-side device sends instruction information to the terminal, where the instruction information instructs the terminal to activate the target AI unit or instructs the terminal to select the target AI unit to be activated.

[0271] If the indication information indicates activation of the target AI unit, step 3 may be performed; if the indication information indicates that the terminal selects the target AI unit to be activated, the terminal may select an AI unit that meets the activation conditions among one or more AI units as the target AI unit and activate the target AI unit.

[0272] Step 3: The terminal performs a first process on the target AI unit, where the first process includes reading or loading part of the information of the target AI unit.

[0273] Step 4: The terminal performs a second process and application on the target AI unit. The second process includes reading or loading the remaining information of the target AI unit.

[0274] Optionally, after activating the target AI unit, the terminal may send fifth information to the network-side device, where the fifth information indicates that the terminal has completed activation of the target AI unit.

[0275] For the above activation process, the starting point is that the terminal sends an AI unit activation request to the network side device, and the end point can be that the terminal completes the second processing and application of the target AI unit, or the terminal completes the activation of the target AI unit and sends the fifth information to the network side device for reporting.

[0276] In the above activation process, if the number of target AI units is 1 and the instruction information indicates to activate the target AI unit, the activation delay of the target AI unit includes at least:

[0277] The delay between the terminal sending the AI ​​unit activation request and receiving the indication information;

[0278] The delay in processing or parsing the signaling carrying the indication information by the terminal;

[0279] The delay of the terminal performing HARQ feedback (for the case where the indication information is carried by MAC-CE, this may include the delay between the terminal receiving the downlink data transmission and the terminal sending the acknowledgment indication);

[0280] The latency of the terminal performing the first processing on the target AI unit;

[0281] The delay of the terminal performing the second processing and application on the target AI unit.

[0282] If the number of target AI units is 1 and the indication information instructs the terminal to select the target AI unit to be activated, the activation delay of the target AI unit includes at least:

[0283] The delay between the terminal sending the AI ​​unit activation request and receiving the indication information;

[0284] The delay in processing or parsing the signaling carrying the indication information by the terminal;

[0285] The delay of the terminal performing HARQ feedback (for the case where the indication information is carried by MAC-CE, this may include the delay between the terminal receiving the downlink data transmission and the terminal sending the acknowledgment indication);

[0286] The latency of the terminal performing the first processing on the target AI unit;

[0287] The delay of the terminal performing the second processing and application on the target AI unit.

[0288] If there are multiple target AI units, when the terminal activates multiple target AI units, the total activation latency of the terminal should be less than or equal to the sum of the latency requirements of each target AI unit. Optionally, when the terminal can activate more than one target AI unit in parallel, the activation latency is the activation latency of the largest single AI unit currently activated in parallel. Optionally, when more than one of the multiple target AI units is within a specified variance, the corresponding activation latency requirement can be shortened. The variance between the AI ​​units is related to at least one of the A1 unit's structure, parameters, complexity, size, quantization level, functionality, corresponding terminal computing and storage capabilities, and applicable scenarios.

[0289] Embodiment 3: The network-side device instructs the terminal to switch the AI ​​unit, including deactivating the activated AI unit and activating the target AI unit.

[0290] The switching process of Example 3 is applicable to the following scenarios:

[0291] Before the terminal receives the instruction information, the AI ​​function has been enabled and the previously used AI unit is still activated.

[0292] The switching process may include the following steps:

[0293] Step 1: The network-side device sends an instruction message to the terminal, where the instruction message indicates activation of the target AI unit and deactivation of the activated AI unit. The instruction message includes unit information of the target AI unit.

[0294] The indication information may be carried by RRC signaling, DCI or MAC-CE.

[0295] The unit information of the target AI unit may include at least one of the target AI unit ID, applicable scenarios of the target AI unit, function information supported by the target AI unit, cell information supported by the target AI unit, area information supported by the target AI unit, input and output type information of the target AI unit, inference accuracy supported by the target AI unit, terminal computing and storage capabilities corresponding to the target AI unit, a data set related to the target AI unit, a performance threshold value of the target AI unit, and a complexity threshold value of the target AI unit.

[0296] Step 2: The terminal determines whether the target AI unit meets the activation conditions based on the unit information of the target AI unit.

[0297] If the terminal determines that the target AI unit meets the activation condition, it can execute step 4. If the terminal determines that the target AI unit does not meet the activation condition, it can execute step 3.

[0298] Step 3: The terminal sends first information to the network-side device, where the first information indicates that the target AI unit does not meet the activation condition.

[0299] For the network side device, after receiving the first information, it can send second information to the terminal, where the second information indicates to deactivate the target AI unit.

[0300] Optionally, step 3 may also be replaced by the terminal automatically deactivating the target AI unit and then sending third information to the network-side device, where the third information indicates that the target AI unit is not activated.

[0301] Optionally, when the target AI unit is deactivated, the terminal may also independently perform the first operation, or the network-side device may send fourth information to the terminal, instructing the terminal to perform the first operation. The first operation may include at least one of fine-tuning the target AI unit, retraining the target AI unit, upgrading the target AI unit, downgrading the target AI unit, rolling back the target AI unit, collecting data, and transferring the AI ​​unit to another device.

[0302] Step 4: The terminal deactivates the activated AI unit.

[0303] Step 5: The terminal performs a first process on the target AI unit, where the first process includes reading or loading part of the information of the target AI unit.

[0304] Optionally, if the terminal supports parallel processing capabilities, steps 4 and 5 may be executed in parallel.

[0305] Step 6: The terminal performs a second process and application on the target AI unit. The second process includes reading or loading the remaining information of the target AI unit.

[0306] Optionally, after activating the target AI unit, the terminal may send fifth information to the network-side device, where the fifth information indicates that the terminal has completed activation of the target AI unit.

[0307] For the above-mentioned switching process, the starting point is that the terminal receives the indication information sent by the network side device, and the end point can be that the terminal completes the second processing and application of the target AI unit, or the terminal completes the activation of the target AI unit and sends the fifth information to the network side device for reporting.

[0308] In the above switching process, if the number of target AI units is 1, the activation delay of the target AI unit (i.e., the switching delay) includes at least:

[0309] The delay in processing or parsing the signaling carrying the indication information by the terminal;

[0310] The delay of the terminal performing HARQ feedback (for the case where the indication information is carried by MAC-CE, this may include the delay between the terminal receiving the downlink data transmission and the terminal sending the acknowledgment indication);

[0311] The delay for the terminal to deactivate an activated AI unit;

[0312] The latency of the terminal performing the first processing on the target AI unit;

[0313] The delay of the terminal performing the second processing and application on the target AI unit.

[0314] If there are multiple target AI units, when the terminal activates multiple target AI units, the total activation delay should be less than or equal to the sum of the delay requirements of each target AI unit. Optionally, when the terminal can activate more than one target AI unit in parallel, the activation delay is the activation delay of the largest single AI unit currently activated in parallel. Optionally, when more than one of the multiple target AI units is within a specified difference, the corresponding activation delay requirement can be shortened. The difference between the AI ​​units is related to at least one of the A1 unit's structure, parameters, complexity, size, quantization level, functionality, corresponding terminal computing and storage capabilities, and applicable scenarios.

[0315] Embodiment 4: The terminal initiates the switching of the AI ​​unit to the network-side device, including activating the target AI unit and deactivating the activated AI unit.

[0316] The switching process of Example 4 is applicable to the following scenarios:

[0317] Before the terminal receives the instruction information or sends the activation request on its own, the AI ​​function has been enabled and the previously used AI unit is still in the activated state.

[0318] The switching process may include the following steps:

[0319] Step 1: When the terminal determines that an activated AI unit meets the deactivation condition, the terminal can use the AI ​​unit that meets the activation condition among one or more AI units as the target AI unit and activate the target AI unit and deactivate the activated AI unit, or the terminal can send an AI unit activation request to the network side device.

[0320] The deactivation conditions can be configured by the terminal, by the network device, or jointly by the terminal and the network device. The specific implementation of how the terminal determines whether an activated AI unit meets the deactivation conditions and how the terminal selects a target AI unit that meets the activation conditions for activation can be found in the specific implementations of the corresponding steps in Figures 2 and 3 and will not be repeated here.

[0321] When the terminal sends an AI activation request to the network-side device, step 2 can be executed.

[0322] Step 2: The network-side device sends instruction information to the terminal, where the instruction information instructs the terminal to activate the target AI unit and deactivate the activated AI unit, or instructs the terminal to select the target AI unit to be activated.

[0323] If the indication information indicates activation of the target AI unit and deactivation of the activated AI unit, step 3 may be performed. If the indication information indicates that the terminal selects the target AI unit to be activated, the terminal may select an AI unit that meets the activation conditions among one or more AI units as the target AI unit and activate the target AI unit and deactivate the activated AI unit.

[0324] Step 3: The terminal deactivates the activated AI unit.

[0325] Step 4: The terminal performs a first process on the target AI unit, where the first process includes reading or loading part of the information of the target AI unit.

[0326] Optionally, if the terminal supports parallel processing capabilities, steps 3 and 4 may be executed in parallel.

[0327] Step 5: The terminal performs a second process and application on the target AI unit. The second process includes reading or loading the remaining information of the target AI unit.

[0328] Optionally, after activating the target AI unit, the terminal may send fifth information to the network-side device, where the fifth information indicates that the terminal has completed activation of the target AI unit.

[0329] For the above-mentioned switching process, the starting point is that the terminal sends an AI unit activation request to the network side device, and the end point can be that the terminal completes the second processing and application of the target AI unit, or the terminal completes the activation of the target AI unit and sends the fifth information to the network side device for reporting.

[0330] In the above switching process, if the number of target AI units is 1 and the indication information indicates activation of the target AI unit and deactivation of the activated AI unit, the activation delay of the target AI unit includes at least:

[0331] The delay between the terminal sending the AI ​​unit activation request and receiving the indication information;

[0332] The delay for the terminal to deactivate an activated AI unit;

[0333] The delay in processing or parsing the signaling carrying the indication information by the terminal;

[0334] The delay of the terminal performing HARQ feedback (for the case where the indication information is carried by MAC-CE, this may include the delay between the terminal receiving the downlink data transmission and the terminal sending the acknowledgment indication);

[0335] The latency of the terminal performing the first processing on the target AI unit;

[0336] The delay of the terminal performing the second processing and application on the target AI unit.

[0337] If the number of target AI units is 1 and the indication information instructs the terminal to select the target AI unit to be activated, the activation delay of the target AI unit includes at least:

[0338] The delay between the terminal sending the AI ​​unit activation request and receiving the indication information;

[0339] The delay in processing or parsing the signaling carrying the indication information by the terminal;

[0340] The delay of the terminal performing HARQ feedback (for the case where the indication information is carried by MAC-CE, this may include the delay between the terminal receiving the downlink data transmission and the terminal sending the acknowledgment indication);

[0341] The delay for the terminal to deactivate an activated AI unit;

[0342] The latency of the terminal performing the first processing on the target AI unit;

[0343] The delay of the terminal performing the second processing and application on the target AI unit.

[0344] If there are multiple target AI units, when the terminal activates multiple target AI units, the total activation latency of the terminal should be less than or equal to the sum of the latency requirements of each target AI unit. Optionally, when the terminal can activate more than one target AI unit in parallel, the activation latency is the activation latency of the largest single AI unit currently activated in parallel. Optionally, when more than one of the multiple target AI units is within a specified variance, the corresponding activation latency requirement can be shortened. The variance between the AI ​​units is related to at least one of the A1 unit's structure, parameters, complexity, size, quantization level, functionality, corresponding terminal computing and storage capabilities, and applicable scenarios.

[0345] Based on the above-mentioned Examples 1 to 4, the embodiments of the present application propose a method for activating and deactivating AI units in AI unit lifecycle management, which is applicable to various processes including activation and deactivation in AI lifecycle management, and stipulates corresponding wireless resource management delay requirements, thereby optimizing the AI ​​lifecycle management process and improving the definition of the communication system.

[0346] The activation method of the AI ​​unit provided in the embodiment of the present application can be executed by the activation device of the AI ​​unit. In the embodiment of the present application, the activation method of the AI ​​unit performed by the activation device of the AI ​​unit is taken as an example to illustrate the activation device of the AI ​​unit provided in the embodiment of the present application.

[0347] FIG4 is a schematic diagram of the structure of an activation device for an AI unit according to an embodiment of the present application, which may correspond to a terminal in other embodiments. As shown in FIG4 , the device 400 includes the following modules.

[0348] The activation module 401 is configured to activate a target AI unit according to target information, wherein the target information includes at least one of indication information and an activation condition of the AI ​​unit, and the indication information is used to activate the target AI unit.

[0349] Optionally, in some implementations, when the target information includes the indication information, the apparatus 400 further includes a receiving module;

[0350] The receiving module is configured to receive the indication information.

[0351] Optionally, in some embodiments, the apparatus 400 further includes a sending module;

[0352] The activation module 401 is used to determine whether the activated AI unit meets the deactivation condition;

[0353] The sending module is configured to send an AI unit activation request if it is determined that the activated AI unit meets the deactivation condition;

[0354] The receiving module is configured to receive the indication information.

[0355] Optionally, in some implementations, the indication information indicates any one of the following:

[0356] activating the target AI unit;

[0357] activating the target AI unit and deactivating the activated AI unit;

[0358] The terminal selects a target AI unit to be activated.

[0359] Optionally, in some embodiments, when the indication information indicates activation of the target AI unit or activation of the target AI unit and deactivation of an activated AI unit, the indication information includes unit information of the target AI unit; wherein the activation module 401 is configured to:

[0360] Determining whether the target AI unit meets the activation condition according to the unit information;

[0361] If it is determined that the target AI unit meets the activation condition, the target AI unit is activated.

[0362] Optionally, in some embodiments, at least one of the following is further included:

[0363] A sending module, configured to send first information, where the first information indicates that the target AI unit does not meet the activation condition;

[0364] a receiving module, configured to receive second information indicating deactivation of the target AI unit;

[0365] The activation module 401 is used to deactivate the target AI unit;

[0366] The sending module is configured to send third information, where the third information indicates that the target AI unit is not activated;

[0367] The receiving module is configured to receive fourth information, where the fourth information indicates to perform the first operation;

[0368] The activation module 401 is configured to perform the first operation;

[0369] The first information and the third information are carried by RRC signaling or uplink control information (UCI), the second information and the fourth information are carried by RRC signaling, DCI, or MAC-CE, and the first operation includes at least one of fine-tuning the target AI unit, retraining the target AI unit, upgrading the target AI unit, downgrading the target AI unit, rolling back the target AI unit, collecting data, and transferring the AI ​​unit to another device.

[0370] Optionally, in some implementations, the activation module 401 is further configured to:

[0371] determining, based on unit information of the one or more AI units, whether the one or more AI units meet the activation condition;

[0372] An AI unit that meets the activation condition among the one or more AI units is determined as a target AI unit, and the target AI unit is activated.

[0373] Optionally, in some implementations, the unit information includes at least one of the following:

[0374] The ID of the AI ​​unit;

[0375] Scenarios where AI units are applicable;

[0376] Information about functions supported by the AI ​​unit;

[0377] Information about cells supported by the AI ​​unit;

[0378] AI unit supported region information;

[0379] AI unit input and output type information;

[0380] The inference accuracy supported by the AI ​​unit;

[0381] Terminal computing and storage capabilities corresponding to the AI ​​unit;

[0382] Data sets related to AI units;

[0383] Performance threshold of AI unit;

[0384] The complexity threshold of the AI ​​unit.

[0385] Optionally, in some implementations, when the target information includes the AI ​​unit activation condition, the activation module 401 is configured to:

[0386] Determining whether the target AI unit meets the activation condition;

[0387] If it is determined that the target AI unit meets the activation condition, the target AI unit is activated.

[0388] Optionally, in some implementations, the activation module 401 is configured to:

[0389] Determine whether the activated AI unit meets the deactivation conditions;

[0390] If it is determined that the activated AI unit meets the deactivation condition, it is determined whether the target AI unit meets the activation condition.

[0391] Optionally, in some embodiments, the deactivation condition is related to at least one of the following:

[0392] the performance of said activated AI unit when applied;

[0393] The computing and storage capabilities supported by the terminal;

[0394] The ID of the activated AI unit;

[0395] The scenarios to which the activated AI unit is applicable;

[0396] Function information supported by the activated AI unit;

[0397] Information about cells supported by the activated AI unit;

[0398] Regional information supported by the activated AI unit;

[0399] Input and output type information of the activated AI unit;

[0400] The inference accuracy supported by the activated AI unit;

[0401] The terminal computing and storage capabilities corresponding to the activated AI unit;

[0402] a data set associated with the activated AI unit;

[0403] The performance threshold of the activated AI unit;

[0404] The complexity threshold of the activated AI unit.

[0405] Optionally, in some embodiments, the activation condition is related to at least one of the following:

[0406] The computing and storage capabilities supported by the terminal;

[0407] The ID of the target AI unit;

[0408] The scenarios in which the target AI unit is applicable;

[0409] Function information supported by the target AI unit;

[0410] Cell information supported by the target AI unit;

[0411] Regional information supported by the target AI unit;

[0412] Input and output type information of the target AI unit;

[0413] The inference accuracy supported by the target AI unit;

[0414] The terminal computing and storage capabilities corresponding to the target AI unit;

[0415] A dataset related to the target AI unit;

[0416] The performance threshold value of the target AI unit;

[0417] The complexity threshold of the target AI unit.

[0418] Optionally, in some implementations, the activation module 401 is configured to:

[0419] Applying the target AI unit after performing the first processing or the second processing on the target AI unit; or

[0420] deactivating the activated AI unit and applying the target AI unit after performing the first processing or the second processing on the target AI unit;

[0421] The first processing includes reading or loading at least part of the information of the target AI unit, and the second processing includes reading or loading the remaining information of the target AI unit.

[0422] Optionally, in some embodiments, the method further comprises:

[0423] A sending module is configured to send fifth information, where the fifth information indicates that the terminal has completed activation of the target AI unit, and the fifth information is carried by RRC signaling or UCI.

[0424] Optionally, in some embodiments, when the number of the target AI unit is one, the activation delay of the one target AI unit is less than or equal to the first delay; when the number of the target AI unit is multiple, the activation delay of the multiple target AI units is less than or equal to the second delay, and the second delay is less than or equal to the sum of the activation delays of the multiple target AI units;

[0425] In which, when multiple target AI units can be activated in parallel, the second delay is less than or equal to the maximum value of the activation delays of the multiple target AI units; when the difference between the multiple target AI units is within a specified difference, the activation delay of the multiple target AI units is less than or equal to the third delay, and the third delay is less than the second delay. The difference is related to at least one of the structure, parameters, complexity, size, quantization level, function, corresponding terminal computing and storage capabilities, and applicable scenarios of the A1 unit.

[0426] Optionally, in some embodiments, the activation delay of a target AI unit includes at least one of the following:

[0427] The delay between the terminal sending the AI ​​unit activation request and receiving the indication information;

[0428] Delay in processing or parsing the signaling carrying the indication information by the terminal;

[0429] The delay of the terminal performing hybrid automatic repeat request HARQ feedback;

[0430] The delay for the terminal to deactivate an activated AI unit;

[0431] a delay in the terminal performing a first process on the target AI unit, the first process comprising reading or loading partial information of the target AI unit;

[0432] The terminal performs a second process and a delay on the target AI unit, wherein the second process includes reading or loading the remaining information of the target AI unit.

[0433] According to the device 400 of the embodiment of the present application, the process of the method 200 corresponding to the embodiment of the present application can be referred to, and the various units / modules in the device 400 and the above-mentioned other operations and / or functions are respectively for implementing the corresponding processes in the method 200, and can achieve the same or equivalent technical effects. For the sake of brevity, they will not be repeated here.

[0434] FIG5 is a schematic diagram of the structure of an activation device for an AI unit according to an embodiment of the present application, which may correspond to a network-side device in other embodiments. As shown in FIG5 , the device 500 includes the following modules.

[0435] The sending module 501 is configured to send instruction information, where the instruction information is used to activate a target AI unit.

[0436] Optionally, in some embodiments, the device further comprises a receiving module;

[0437] The receiving module is configured to receive an AI unit activation request;

[0438] The sending module is configured to send the indication information according to the AI ​​unit activation request.

[0439] Optionally, in some implementations, the indication information is carried by RRC signaling, DCI or MAC-CE.

[0440] Optionally, in some implementations, the indication information indicates any one of the following:

[0441] activating the target AI unit;

[0442] activating the target AI unit and deactivating the activated AI unit;

[0443] The terminal selects the target AI unit to be activated.

[0444] Optionally, in some embodiments, when the indication information is used to indicate activation of the target AI unit or activation of the target AI unit and deactivation of the activated AI unit, the indication information includes unit information of the target AI unit, and the unit information is used by the terminal to determine whether the target AI unit meets the activation conditions.

[0445] Optionally, in some implementations, the unit information includes at least one of the following:

[0446] The ID of the target AI unit;

[0447] The scenarios in which the target AI unit is applicable;

[0448] Function information supported by the target AI unit;

[0449] Cell information supported by the target AI unit;

[0450] Regional information supported by the target AI unit;

[0451] Input and output type information of the target AI unit;

[0452] The inference accuracy supported by the target AI unit;

[0453] The terminal computing and storage capabilities corresponding to the target AI unit;

[0454] A dataset related to the target AI unit;

[0455] The performance threshold value of the target AI unit;

[0456] The complexity threshold of the target AI unit.

[0457] Optionally, in some embodiments, the apparatus 500 further includes at least one of the following:

[0458] A receiving module, configured to receive first information, wherein the first information indicates that the target AI unit does not meet an activation condition;

[0459] The sending module 501 is configured to send second information, where the second information indicates deactivation of the target AI unit;

[0460] The receiving module is configured to receive third information, wherein the third information indicates that the target AI unit is not activated;

[0461] The sending module 501 is configured to send fourth information, where the fourth information indicates to perform the first operation;

[0462] The first information and the third information are carried by RRC signaling or UCI, the second information and the fourth information are carried by RRC signaling, DCI or MAC-CE, and the first operation includes at least one of fine-tuning the target AI unit, retraining the target AI unit, upgrading the target AI unit, downgrading the target AI unit, rolling back the target AI unit, collecting data, and performing AI unit transfer with other devices.

[0463] Optionally, in some embodiments, the method further comprises:

[0464] The receiving module is configured to receive fifth information, where the fifth information indicates that the terminal has completed activation of the target AI unit, and the fifth information is carried by RRC signaling or UCI.

[0465] According to the device 500 of the embodiment of the present application, the process of the method 300 corresponding to the embodiment of the present application can be referred to, and the various units / modules in the device 500 and the above-mentioned other operations and / or functions are respectively for implementing the corresponding processes in the method 300, and can achieve the same or equivalent technical effects. For the sake of brevity, they will not be repeated here.

[0466] The activation device of the AI ​​unit in the embodiment of the present application can be an electronic device, such as an electronic device with an operating system, or a component in an electronic device, such as an integrated circuit or chip. The electronic device can be a terminal, or it can be other devices other than a terminal. For example, the terminal can include but is not limited to the types of terminals 11 listed above, and other devices can be servers, network attached storage (NAS), etc., which are not specifically limited in the embodiment of the present application.

[0467] The activation device of the AI ​​unit provided in the embodiment of the present application can implement the various processes implemented in the method embodiments of Figures 2 and 3 and achieve the same technical effects. To avoid repetition, they will not be described here.

[0468] As shown in Figure 6, an embodiment of the present application further provides a communication device 600, including a processor 601 and a memory 602. The memory 602 stores a program or instruction that can be run on the processor 601. For example, when the communication device 600 is a terminal, the program or instruction is executed by the processor 601 to implement the various steps of the above-mentioned AI unit activation method embodiment and can achieve the same technical effect. When the communication device 600 is a network-side device, the program or instruction is executed by the processor 601 to implement the various steps of the above-mentioned AI unit activation method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0469] The present application also provides a terminal comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is configured to execute a program or instruction to implement the steps of the method embodiment shown in FIG2 . This terminal embodiment corresponds to the aforementioned terminal-side method embodiment, and each implementation process and implementation method of the aforementioned method embodiment is applicable to this terminal embodiment and can achieve the same technical effects. Specifically, FIG7 is a schematic diagram of the hardware structure of a terminal implementing an embodiment of the present application.

[0470] The terminal 700 includes but is not limited to: a radio frequency unit 701, a network module 702, an audio output unit 703, an input unit 704, a sensor 705, a display unit 706, a user input unit 707, an interface unit 708, a memory 709 and at least some of the components of the processor 710.

[0471] Those skilled in the art will appreciate that the terminal 700 may also include a power supply (such as a battery) to power various components. The power supply may be logically connected to the processor 710 via a power management system, thereby enabling the power management system to manage charging, discharging, and power consumption. The terminal structure shown in FIG7 does not limit the terminal. The terminal may include more or fewer components than shown, or may combine certain components, or have different component arrangements, which will not be described in detail here.

[0472] It should be understood that in an embodiment of the present application, the input unit 704 may include a graphics processing unit (GPU) 7041 and a microphone 7042, and the graphics processor 7041 processes the image data of a static picture or video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 706 may include a display panel 7061, and the display panel 7061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 707 includes a touch panel 7071 and at least one of other input devices 7072. The touch panel 7071 is also called a touch screen. The touch panel 7071 may include two parts: a touch detection device and a touch controller. Other input devices 7072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and an operating stick, which will not be repeated here.

[0473] In the embodiment of the present application, after receiving downlink data from a network-side device, the RF unit 701 may transmit the data to the processor 710 for processing. Furthermore, the RF unit 701 may send uplink data to the network-side device. Typically, the RF unit 701 includes, but is not limited to, an antenna, an amplifier, a transceiver, a coupler, a low-noise amplifier, a duplexer, and the like.

[0474] The memory 709 can be used to store software programs or instructions and various data. The memory 709 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, applications or instructions required for at least one function (such as a sound playback function, an image playback function, etc.). In addition, the memory 709 may include a volatile memory or a non-volatile memory. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM), and a direct memory bus random access memory (DRRAM). The memory 709 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

[0475] Processor 710 may include one or more processing units. Optionally, processor 710 integrates an application processor and a modem processor. The application processor primarily handles operations related to the operating system, user interface, and application programs, while the modem processor primarily processes wireless communication signals, such as a baseband processor. It is understood that the modem processor may not be integrated into processor 710.

[0476] The processor 710 is configured to activate a target AI unit according to target information, where the target information includes at least one of indication information and an activation condition of the AI ​​unit, and the indication information is used to activate the target AI unit.

[0477] In this embodiment of the present application, the terminal can activate the target AI unit based on at least one of the indication information and the activation conditions of the AI ​​unit. Thus, the terminal can determine how to activate the AI ​​unit, thereby optimizing the AI ​​lifecycle management process, ensuring the high quality, efficiency, and reliability of the AI ​​unit, meeting business needs, and improving work efficiency.

[0478] It can be understood that the implementation process of each implementation method mentioned in this embodiment can refer to the relevant description of method embodiment 200 and achieve the same or corresponding technical effects. To avoid repetition, it will not be repeated here.

[0479] The present application also provides a network-side device, including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is configured to execute a program or instruction to implement the steps of the method embodiment shown in FIG3 . This network-side device embodiment corresponds to the aforementioned network-side device method embodiment, and each implementation process and implementation method of the aforementioned method embodiment are applicable to this network-side device embodiment and can achieve the same technical effects.

[0480] Specifically, embodiments of the present application also provide a network-side device. As shown in Figure 8, the network-side device 800 includes an antenna 81, a radio frequency device 82, a baseband device 83, a processor 84, and a memory 85. Antenna 81 is connected to radio frequency device 82. In the uplink direction, radio frequency device 82 receives information via antenna 81 and sends the received information to baseband device 83 for processing. In the downlink direction, baseband device 83 processes the information to be transmitted and sends it to radio frequency device 82. Radio frequency device 82 processes the received information and then sends it through antenna 81.

[0481] The method executed by the network-side device in the above embodiment may be implemented in the baseband device 83 , which includes a baseband processor.

[0482] The baseband device 83 may include, for example, at least one baseband board, on which multiple chips are arranged, as shown in Figure 8, one of the chips is, for example, a baseband processor, which is connected to the memory 85 through a bus interface to call the program in the memory 85 to execute the network device operations shown in the above method embodiment.

[0483] The network side device may further include a network interface 86, which is, for example, a Common Public Radio Interface (CPRI).

[0484] Specifically, the network side device 800 of the embodiment of the present application also includes: instructions or programs stored in the memory 85 and can be run on the processor 84. The processor 84 calls the instructions or programs in the memory 85 to execute the methods executed by each module shown in Figure 5 and achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0485] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the above-mentioned AI unit activation method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0486] The processor is the processor in the terminal described in the above embodiment. The readable storage medium includes a computer-readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk. In some examples, the readable storage medium may be a non-transitory readable storage medium.

[0487] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned AI unit activation method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0488] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0489] An embodiment of the present application further provides a computer program / program product, which is stored in a storage medium. The computer program / program product is executed by at least one processor to implement the various processes of the above-mentioned AI unit activation method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0490] An embodiment of the present application also provides a wireless communication system, including: a terminal and a network side device, wherein the terminal can be used to execute the steps of the activation method of the AI ​​unit as described above, and the network side device can be used to execute the steps of the activation method of the AI ​​unit as described above.

[0491] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0492] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of a computer software product plus a necessary general-purpose hardware platform, or of course, by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disk, etc.) and includes a number of instructions for enabling a terminal or network-side device to execute the methods described in each embodiment of the present application.

[0493] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms of implementation methods without departing from the purpose of this application and the scope of protection of the claims. These implementation methods are all within the protection of this application.

Claims

1. A method for activating an AI unit, including the following: The terminal activates a target AI unit according to target information, where the target information includes at least one of indication information and an activation condition of the AI unit, and the indication information is used to activate the target AI unit.

2. The method according to claim 1, wherein, When the target information includes the indication information, the method further includes: The terminal receives the indication information.

3. The method according to claim 2, wherein The terminal receiving the indication information includes: The terminal determines whether the already-activated AI unit satisfies a deactivation condition; When the terminal determines that the already-activated AI unit satisfies the deactivation condition, the terminal sends an AI unit activation request; The terminal receives the indication information.

4. The method according to any one of claims 1 to 3, wherein, The indication information indicates any one of the following: Activate the target AI unit; Activate the target AI unit and deactivate the already-activated AI unit; The terminal selects a target AI unit to be activated.

5. The method according to claim 4, wherein, When the indication information indicates to activate the target AI unit or activate the target AI unit and deactivate the already-activated AI unit, the unit information of the target AI unit is included in the indication information; Wherein, the terminal activating the target AI unit according to the target information includes: The terminal determines whether the target AI unit satisfies the activation condition according to the unit information; When the terminal determines that the target AI unit satisfies the activation condition, the terminal activates the target AI unit.

6. The method according to claim 5, wherein When the terminal determines that the target AI unit does not satisfy the activation condition, the method further includes at least one of the following: The terminal sends first information, and the first information represents that the target AI unit does not satisfy the activation condition; The terminal receives second information, and the second information indicates canceling the activation of the target AI unit; The terminal cancels the activation of the target AI unit; The terminal sends third information, and the third information represents that the target AI unit is not activated; The terminal receives fourth information, and the fourth information indicates performing a first operation; The terminal performs the first operation; Wherein, the first information and the third information are carried by RRC signaling or uplink control information UCI, the second information and the fourth information are carried by RRC signaling, DCI or MAC-CE, and the first operation includes at least one of fine-tuning the target AI unit, retraining the target AI unit, upgrading the target AI unit, downgrading the target AI unit, rolling back the target AI unit, data collection, and performing AI unit transfer with other devices.

7. The method according to claim 4, wherein, When the indication information indicates that the terminal selects a target AI unit to be activated, the terminal activating the target AI unit according to the target information includes: The terminal determines whether one or more AI units satisfy the activation condition according to the unit information of the one or more AI units; The terminal determines the AI unit that satisfies the activation condition among the one or more AI units as the target AI unit and activates the target AI unit.

8. The method according to claim 5 or 7, wherein The unit information includes at least one of the following: ID of the AI unit; Scenarios applicable to the AI unit; Function information supported by the AI unit; Cell information supported by the AI unit; Area information supported by the AI unit; Input / output type information of the AI unit; Inference accuracy supported by the AI unit; Terminal computing and storage capabilities corresponding to the AI unit; Datasets related to the AI unit; Performance threshold of the AI unit; Complexity threshold of the AI unit.

9. The method according to claim 1, wherein When the target information includes the activation condition of the AI unit, the terminal activates the target AI unit according to the target information, including: The terminal determines whether the target AI unit meets the activation condition; When the terminal determines that the target AI unit meets the activation condition, the terminal activates the target AI unit.

10. The method according to claim 9, wherein, The terminal determines whether the target AI unit meets the activation condition, including: The terminal determines whether the activated AI unit meets the deactivation condition; When the terminal determines that the activated AI unit meets the deactivation condition, the terminal determines whether the target AI unit meets the activation condition.

11. The method according to claim 3 or 10, wherein, The deactivation condition is related to at least one of the following: Performance when applying the activated AI unit; Computing and storage capabilities supported by the terminal; ID of the activated AI unit; Scenarios applicable to the activated AI unit; Function information supported by the activated AI unit; Cell information supported by the activated AI unit; Area information supported by the activated AI unit; Input / output type information of the activated AI unit; Inference accuracy supported by the activated AI unit; Terminal computing and storage capabilities corresponding to the activated AI unit; Datasets related to the activated AI unit; Performance threshold of the activated AI unit; Complexity threshold of the activated AI unit.

12. The method according to any one of claims 1, 5, 6, 7, 9 and 10, wherein, The activation condition is related to at least one of the following: Computing and storage capabilities supported by the terminal; ID of the target AI unit; Scenarios applicable to the target AI unit; Function information supported by the target AI unit; Cell information supported by the target AI unit; Area information supported by the target AI unit; Input / output type information of the target AI unit; Inference accuracy supported by the target AI unit; Terminal computing and storage capabilities corresponding to the target AI unit; Datasets related to the target AI unit; Performance threshold of the target AI unit; Complexity threshold of the target AI unit.

13. The method according to claim 1, wherein The terminal activates the target AI unit according to the target information, including: After the terminal performs the first processing or the second processing on the target AI unit, the terminal applies the target AI unit; or, The terminal deactivates the activated AI unit and, after performing the first processing or the second processing on the target AI unit, the terminal applies the target AI unit; Wherein, the first processing includes reading or loading at least part of the information of the target AI unit, and the second processing includes reading or loading the remaining information of the target AI unit.

14. The method according to claim 1 or 13, wherein, The method further includes: The terminal sends fifth information, where the fifth information indicates that the terminal has completed the activation of the target AI unit, and the fifth information is carried by an RRC signaling or UCI.

15. The method according to claim 1, wherein, When the number of target AI units is one, the activation delay of one target AI unit is less than or equal to a first delay; when the number of target AI units is multiple, the activation delay of multiple target AI units is less than or equal to a second delay, and the second delay is less than or equal to the sum of the activation delays of multiple target AI units; Among them, when multiple target AI units can be activated in parallel, the second delay is less than or equal to the maximum value of the activation delays of the multiple target AI units; when the difference between multiple target AI units is within a specified difference, the activation delay of the multiple target AI units is less than or equal to a third delay, the third delay is less than the second delay, and the difference is related to at least one of the structure, parameters, complexity, size, quantization level, function, corresponding terminal operation and storage capabilities, and applicable scenarios of the A1 unit.

16. The method according to claim 15, wherein, The activation delay of one target AI unit includes at least one of the following: The delay between the terminal sending an AI unit activation request and receiving the indication information; The processing or parsing delay of the signaling carrying the indication information by the terminal; The delay of the terminal performing hybrid automatic repeat request (HARQ) feedback; The delay of the terminal deactivating the activated AI unit; The delay of the terminal performing a first processing on the target AI unit, where the first processing includes reading or loading partial information of the target AI unit; The delay of the terminal performing a second processing and application on the target AI unit, where the second processing includes reading or loading the remaining information of the target AI unit.

17. A method for activating an AI unit, comprising: A network-side device sends indication information, where the indication information is used to activate a target AI unit.

18. The method according to claim 17, wherein, The network-side device sending the indication information includes: The network-side device receives an AI unit activation request; The network-side device sends the indication information according to the AI unit activation request.

19. The method according to claim 17 or 18, wherein, The indication information indicates any one of the following: Activating the target AI unit; Activating the target AI unit and deactivating the activated AI unit; The terminal selects a target AI unit to be activated.

20. The method according to claim 19, wherein, When the indication information is used to indicate activating the target AI unit or activating the target AI unit and deactivating the activated AI unit, the indication information includes unit information of the target AI unit, and the unit information is used for the terminal to determine whether the target AI unit meets the activation conditions.

21. The method according to claim 20, wherein, The unit information includes at least one of the following: The ID of the target AI unit; The applicable scenario of the target AI unit; The function information supported by the target AI unit; The cell information supported by the target AI unit; The area information supported by the target AI unit; The input-output type information of the target AI unit; The inference accuracy supported by the target AI unit; The corresponding terminal operation and storage capabilities of the target AI unit; A dataset related to the target AI unit; The performance threshold value of the target AI unit; The complexity threshold value of the target AI unit.

22. The method according to claim 19, wherein The method further includes at least one of the following: The network-side device receives first information, which characterizes that the target AI unit does not meet the activation condition; The network-side device sends second information, which indicates deactivating the target AI unit; The network-side device receives third information, which characterizes that the target AI unit is not activated; The network-side device sends fourth information, which indicates performing a first operation; Wherein, the first information and the third information are carried by RRC signaling or UCI, the second information and the fourth information are carried by RRC signaling, DCI or MAC-CE, and the first operation includes at least one of fine-tuning the target AI unit, retraining the target AI unit, upgrading the target AI unit, downgrading the target AI unit, rolling back the target AI unit, performing data collection, and performing AI unit transfer with other devices.

23. The method according to claim 17, wherein The method further includes: The network-side device receives fifth information, which characterizes that the terminal has completed the activation of the target AI unit, and the fifth information is carried by RRC signaling or UCI.

24. An activation device for an AI unit, comprising: An activation module, configured to activate a target AI unit according to target information, where the target information includes at least one of indication information and the activation condition of the AI unit, and the indication information is used to activate the target AI unit.

25. The device according to claim 24, wherein The device further includes: A receiving module, configured to receive the indication information.

26. The apparatus according to claim 25, wherein, The device further includes: A judging module, configured to judge whether the activated AI unit meets the deactivation condition; A sending module, configured to send an AI unit activation request when it is determined that the activated AI unit meets the deactivation condition; The receiving module, configured to receive the indication information.

27. The apparatus according to any one of claims 24 to 26, wherein The indication information indicates any one of the following: Activating the target AI unit; Activating the target AI unit and deactivating the activated AI unit; Letting the terminal select the target AI unit to be activated.

28. The device according to claim 27, wherein, When the indication information indicates activating the target AI unit or activating the target AI unit and deactivating the activated AI unit, the unit information of the target AI unit is included in the indication information; Wherein, the activation module is configured to: Judge whether the target AI unit meets the activation condition according to the unit information; Activate the target AI unit when it is determined that the target AI unit meets the activation condition.

29. The device according to claim 28, wherein, It further includes at least one of the following: A sending module, configured to send first information, which characterizes that the target AI unit does not meet the activation condition; A receiving module, configured to receive second information, which indicates canceling the activation of the target AI unit; The activation module, configured to cancel the activation of the target AI unit; The sending module, configured to send third information, which characterizes that the target AI unit is not activated; The receiving module is configured to receive fourth information, where the fourth information indicates to perform a first operation; The activation module is configured to perform the first operation; Wherein, the first information and the third information are carried by RRC signaling or uplink control information UCI, the second information and the fourth information are carried by RRC signaling, DCI, or MAC-CE, and the first operation includes at least one of fine-tuning the target AI unit, retraining the target AI unit, upgrading the target AI unit, downgrading the target AI unit, rolling back the target AI unit, performing data collection, and performing AI unit transfer with other devices.

30. The apparatus according to claim 27, wherein, The activation module is configured to: Judge whether one or more AI units meet the activation conditions according to the unit information of the one or more AI units; Determine the AI units that meet the activation conditions among the one or more AI units as target AI units, and activate the target AI units.

31. The apparatus according to claim 24, wherein, When the target information includes the AI unit activation conditions, the activation module is configured to: Judge whether the target AI unit meets the activation conditions; When it is determined that the target AI unit meets the activation conditions, activate the target AI unit.

32. The apparatus according to claim 31, wherein, The activation module is configured to: Judge whether the activated AI unit meets the deactivation conditions; When it is determined that the activated AI unit meets the deactivation conditions, judge whether the target AI unit meets the activation conditions.

33. The device according to claim 24, wherein, The activation module is configured to: After performing a first process or a second process on the target AI unit, apply the target AI unit; or, Deactivate the activated AI unit and, after performing a first process or a second process on the target AI unit, apply the target AI unit; Wherein, the first process includes reading or loading at least part of the information of the target AI unit, and the second process includes reading or loading the remaining information of the target AI unit.

34. The apparatus according to claim 24 or 33, wherein, It further includes: A sending module is configured to send fifth information, where the fifth information represents that the terminal has completed the activation of the target AI unit, and the fifth information is carried by RRC signaling or UCI.

35. An AI unit activation device, comprising: A sending module is configured to send indication information for activating a target AI unit.

36. The apparatus according to claim 35, wherein, The device further includes a receiving module; The receiving module is configured to receive an AI unit activation request; The sending module is configured to send the indication information according to the AI unit activation request.

37. The device according to claim 35 or 36, wherein, The indication information indicates any one of the following: Activate the target AI unit; Activate the target AI unit and deactivate the activated AI unit; The terminal selects the target AI unit to be activated.

38. A terminal, comprising a processor and a memory, where the memory stores a program or instruction that can run on the processor, and when the program or instruction is executed by the processor, the steps of the AI unit activation method according to any one of claims 1 to 16 are implemented.

39. A network-side device, comprising a processor and a memory, where the memory stores programs or instructions that can run on the processor, and when the programs or instructions are executed by the processor, the steps of the activation method of the AI unit according to any one of claims 17 to 23 are implemented.

40. A readable storage medium, where programs or instructions are stored on the readable storage medium, and when the programs or instructions are executed by a processor, the steps of the activation method of the AI unit according to any one of claims 1 to 16 are implemented, or the steps of the activation method of the AI unit according to any one of claims 17 to 23 are implemented.

Images