Device switching method based on artificial intelligence computing power factory value of access network device, terminal and non-transitory computer-readable storage medium
AssigneeBeijing Xiaomi Mobile Software Co., Ltd.
InventorJuejia Zhou
Life of this patent
Estimating the term…
Abstract
A device switching method is applied to a terminal device, and includes: determining a device switching situation of switching between a source access network device and a target access network device by taking an artificial intelligence (AI) computing power factor value of at least one access network device of the source access network device and the target access network device as an offset parameter.
Claims16
A device switching method, applied to a terminal device, the method comprising:
- receiving a downlink signaling including an indication field indicating a second artificial intelligence (AI) computing power factor value of a target access network device;
- determining a computing power factor value difference by subtracting a first AI computing power factor value from the second AI computing power factor value;
- in response to the difference being greater than or equal to a third threshold, determining the difference as a forward offset parameter;
- and
- switching when a sum of a switching parameter difference and the computing power factor value difference is greater than or equal to a switching threshold, wherein the switching parameter difference is based on a reference signal receiving power (RSRP) or a reference signal receiving quality (RSRQ) of the target access network device and a source access network device;
- wherein the first AI computing power factor value and the second AI computing power factor value respectively indicate a maximum AI computing power or a maximum available AI computing power of the source access network device and the target access network device, and the maximum AI computing power and the maximum available AI computing power include a maximum memory occupancy, a maximum central processing unit (CPU) occupancy or a maximum storage occupancy supported by the terminal for an AI computing power.
A terminal, comprising:
- a processor;
- and
- a memory having stored therein instructions executable by the processor,
- wherein the processor is configured to:
- receiving a downlink signaling including an indication field indicating a second artificial intelligence (AI) computing power factor value of a target access network device;
- determining a computing power factor value difference by subtracting a first AI computing power factor value from the second AI computing power factor value;
- in response to the difference being greater than or equal to a third threshold, determining the difference as a forward offset parameter;
- and
- switching when a sum of a switching parameter difference and the computing power factor value difference is greater than or equal to a switching threshold, wherein the switching parameter difference is based on a reference signal receiving power (RSRP) or a reference signal receiving quality (RSRQ) of the target access network device and a source access network device;
- wherein the first AI computing power factor value and the second AI computing power factor value respectively indicate a maximum AI computing power or a maximum available AI computing power of the source access network device and the target access network device, and the maximum AI computing power and the maximum available AI computing power include a maximum memory occupancy, a maximum central processing unit (CPU) occupancy or a maximum storage occupancy supported by the terminal for an AI computing power.
A non-transitory computer-readable storage medium having stored therein at least one instruction, at least one program, a set of codes, or a set of instructions that, when loaded and executed by a processor, causes the processor to perform a device switching method, the method comprising:
- receiving a downlink signaling including an indication field indicating a second artificial intelligence (AI) computing power factor value of a target access network device;
- determining a computing power factor value difference by subtracting a first AI computing power factor value from the second AI computing power factor value;
- in response to the difference being greater than or equal to a third threshold, determining the difference as a forward offset parameter;
- and
- switching when a sum of a switching parameter difference and the computing power factor value difference is greater than or equal to a switching threshold, wherein the switching parameter difference is based on a reference signal receiving power (RSRP) or a reference signal receiving quality (RSRQ) of the target access network device and a source access network device;
- wherein the first AI computing power factor value and the second AI computing power factor value respectively indicate a maximum AI computing power or a maximum available AI computing power of the source access network device and the target access network device, and the maximum AI computing power and the maximum available AI computing power include a maximum memory occupancy, a maximum central processing unit (CPU) occupancy or a maximum storage occupancy supported by a terminal for an AI computing power.
Dependencies are inferred from the claim text.