Device switching method, device, device and readable storage medium

Abstract

The present disclosure provides a device switching method, apparatus, device and readable storage medium, which relate to the field of communications. The method includes: using the AI ​​computing power factor value of the access network device as an offset parameter to determine the device switching situation between the access network devices. The AI ​​computing power factor value of the access network device is used as an offset parameter. When determining whether to switch from the source access network device to the target access network device, the original determination process is offset according to the AI ​​computing power factor value. When the AI ​​computing power factor value indicates that the AI ​​computing power is suitable for switching, the offset is performed in the positive offset direction to complete the determination of the device switching. Similarly, when the AI ​​computing power factor indicates that the AI ​​computing power is not suitable for switching, the offset is performed in the reverse offset direction to complete the determination of the device switching, thereby improving the accuracy of the device switching process.

Description

Technical Field

[0001] The present disclosure relates to the field of communications, and in particular to a device switching method, apparatus, device, and readable storage medium. Background Art

[0002] When artificial intelligence (AI) technology is deployed on the basis of 6G cellular networks, the learning ability or computing resources of edge nodes become the key factors in the implementation of AI applications, such as speech recognition, video understanding and other AI applications.

[0003] However, in the related art, when a user terminal (UE) moves in a cellular network, only the signal strength or quality of the cellular network is considered to switch between base stations, and the factors considered in the device switching process are relatively simple. Summary of the invention

[0004] The embodiments of the present disclosure provide a device switching method, apparatus, device and readable storage medium, which can improve the switching accuracy and comprehensiveness of considerations during base station switching. The technical solution is as follows:

[0005] On the one hand, a device switching method is provided, which is applied to a terminal device, and the method includes:

[0006] The AI ​​computing power factor value of the access network device is used as an offset parameter to determine the device switching situation between the access network devices.

[0007] On the other hand, a device switching apparatus is provided, which is applied to a terminal device, and the apparatus includes:

[0008] The processing module is configured to use the AI ​​computing power factor value of the access network device as an offset parameter to determine the device switching status between the access network devices.

[0009] In another aspect, a terminal is provided, the terminal comprising:

[0010] processor;

[0011] a transceiver coupled to the processor;

[0012] a memory for storing executable signaling for the processor;

[0013] The processor is configured to load and execute executable instructions to implement the device switching method as described in the above-mentioned embodiment of the present disclosure.

[0014] On the other hand, a computer-readable storage medium is provided, in which at least one instruction, at least one program, code set or instruction set is stored, and the at least one instruction, at least one program, code set or instruction set is loaded and executed by a processor to implement the device switching method as described in the above-mentioned embodiment of the present disclosure.

[0015] The beneficial effects brought by the technical solution provided by the embodiments of the present disclosure include at least:

[0016] The AI ​​computing power factor value of the access network device is used as an offset parameter. When determining whether to switch from the source access network device to the target access network device, the original determination process is offset according to the AI ​​computing power factor value. When the AI ​​computing power factor value indicates that the AI ​​computing power is suitable for switching, the offset is performed in the positive offset direction to complete the determination of the device switching. Similarly, when the AI ​​computing power factor indicates that the AI ​​computing power is not suitable for switching, the offset is performed in the reverse offset direction to complete the determination of the device switching, thereby improving the accuracy of the device switching process. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 is a block diagram of a communication system provided by an exemplary embodiment of the present disclosure;

[0019] Figure 2 It is a schematic diagram of a distribution method of AI computing power value provided by an exemplary embodiment of the present disclosure;

[0020] Figure 3 is a schematic diagram of a distribution method of AI computing power value provided by another exemplary embodiment of the present disclosure;

[0021] Figure 4 is a schematic diagram of a distribution method of AI computing power value provided by another exemplary embodiment of the present disclosure;

[0022] Figure 5 is a flow chart of a device switching method provided by an exemplary embodiment of the present disclosure;

[0023] Figure 6 is a flow chart of a device switching method provided by another exemplary embodiment of the present disclosure;

[0024] Figure 7 is a structural block diagram of a device switching apparatus provided by an exemplary embodiment of the present disclosure;

[0025] Figure 8 is a block diagram of a terminal provided by an exemplary embodiment of the present disclosure;

[0026] Fig. 9 It is a block diagram of an access network device provided by an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0027] In order to make the objectives, technical solutions and advantages of the present disclosure more clear, the embodiments of the present disclosure will be further described in detail below with reference to the accompanying drawings.

[0028] Figure 1 A block diagram of a communication system provided by an exemplary embodiment of the present disclosure is shown. The communication system includes: a core network 11, an access network 12 and a terminal 13.

[0029] The core network 11 includes several core network devices 110. The core network device 110 includes devices such as Access and Mobility Management Function (AMF), Session Management Function (SMF) and User Plane Function (UPF), among which AMF is used to control the access authority and switching functions of the terminal, and SMF is used to provide server continuity and uninterrupted user experience of the server, such as: IP address and anchor point changes.

[0030] The access network 12 includes several access network devices 120. In some embodiments, the access network device 120 is a base station, which is a device deployed in the access network to provide wireless communication functions for terminals. Base stations include various forms of macro base stations, micro base stations, relay stations, access points, etc. In systems using different wireless access technologies, the names of devices with base station functions may be different. For example, in the Long Term Evolution (LTE) system, it is called eNodeB or eNB; in the 5G New Radio (NR) system, it is called gNode B or gNB. With the evolution of communication technology, the name "base station" may be described and changed. For the convenience of the embodiments of the present disclosure, the above-mentioned devices that provide wireless communication functions for terminals are collectively referred to as access network devices.

[0031] Optionally, the access network device 120 involved in the embodiments of the present disclosure has edge computing capabilities.

[0032] The terminal 13 includes various handheld devices with wireless communication functions, vehicle-mounted devices, wearable devices, computing devices or other processing devices connected to a wireless modem, as well as various forms of terminals (User Equipment, UE), mobile stations (Mobile Station, MS), terminals (terminal devices), etc. For the convenience of description, the above-mentioned devices are collectively referred to as terminals. The access network device 120 and the terminal 13 communicate with each other through some air interface technology, such as a Uu interface.

[0033] Edge computing refers to a computing technology that sets up edge nodes on the edge of the network close to the terminal or data source, integrates a distributed open platform with network, computing, storage, and application core capabilities, and provides edge intelligent services nearby. Optionally, the network edge refers to the server and corresponding hardware devices at the edge of the network, which are different from the central server of a network and the corresponding hardware devices. In an example, when the data sent by a UE is processed at the edge node of the network, because the edge node of the network has a smaller task volume, is closer to the UE, and has better communication effect, the corresponding time will be faster than the corresponding time of processing at the central server of the network. Optionally, in the related technology, the network edge can be implemented as a base station gNB.

[0034] In the disclosed embodiments, the AI ​​computing power of the edge node is used as an offset factor for mobility management. For example, the AI ​​computing power of the base station or the upper-layer management network element, such as the key control node (Mobility Management Entity, MME), is used as an offset factor for base station switching, so that the UE can switch to a base station with more available AI computing power without affecting connectivity.

[0035] Optionally, the AI ​​computing power of the edge node is used to indicate the computing capacity of the edge node, where the computing capacity includes the memory occupancy, central processing unit (CPU) occupancy or storage occupancy of the edge node, etc. It can also be an indicator generated for the purpose of AI computing to indicate the AI ​​computing capacity, which is not limited in the embodiments of the present disclosure.

[0036] Optionally, the edge-side AI computing power can be deployed at the base station side, that is, the AI ​​computing power of the base station is used as the offset factor of mobility management, or it can be an upper-level management network element above the base station, such as MME.

[0037] Among them, when the AI ​​computing power deployment is sunk to the base station side, the AI ​​computing power factor is directly marked in the base station; when the AI ​​computing power deployment is sunk to the upper-layer management network element, the base station managed by the upper-layer management network element can inherit the AI ​​computing power of the upper-layer management network element, wherein the inheritance method includes at least one of the following methods according to the resource allocation method between base stations:

[0038] First, the AI ​​computing power of subordinate base stations is consistent with that of upper-level management network elements;

[0039] For illustration, please refer to Figure 2 , the AI ​​computing power of the upper-level management network element 210 is u, the AI ​​computing power of the edge node (base station) 221 is u, and the AI ​​computing power of the edge node (base station) 222 is also u.

[0040] Optionally, in this mode, subordinate base stations divide and use time-frequency resources.

[0041] Second, the AI ​​computing power of the upper-level management network elements is evenly distributed to the subordinate base stations;

[0042] For illustration, please refer to Figure 3 , the AI ​​computing power of the upper-level management network element 310 is u, the AI ​​computing power of the edge node (base station) 321 is u / 2, and the AI ​​computing power of the edge node (base station) 322 is also u / 2.

[0043] Third, the AI ​​computing power of the upper-level management network element is allocated to the subordinate base stations according to the preset allocation mechanism.

[0044] Indicatively, the upper-level management network element allocates AI computing power according to the service deployment density of the subordinate base stations. Please refer to Figure 4 , the AI ​​computing power of the upper management network element 410 is u, where u = u a +u b According to the service deployment density, the AI ​​computing power allocated to the edge node (base station) 421 is u a , and the AI ​​computing power of edge node (base station) 422 is u b .

[0045] It is worth noting that the above-mentioned AI computing power refers to the maximum AI computing power of the base station or the upper-level management network element; or, the above-mentioned AI computing power refers to the maximum available AI computing power of the base station or the upper-level management network element within a certain time period, that is, the remaining AI computing power.

[0046] Optionally, the upper-layer management network element updates the AI ​​computing power factor value to the edge node (ie, the base station) through the transmission interface between the edge nodes, such as updating the AI ​​computing power to the base station through S1 signaling.

[0047] Figure 5FIG. 1 is a flow chart of a device switching method provided by an exemplary embodiment of the present disclosure, and takes the method applied to a terminal device as an example for explanation. Figure 5 As shown, the method includes:

[0048] Step 501, using the AI ​​computing power factor value of the access network device as an offset parameter, determines the device switching status between the access network devices.

[0049] Optionally, the AI ​​computing power factor value used as the offset parameter is the first AI computing power factor value of the source access network device; or, the AI ​​computing power factor value used as the offset parameter is the second AI computing power factor value of the target access network device; or, the AI ​​computing power factor value used as the offset parameter is the computing power factor difference between the second AI computing power factor value and the first AI computing power factor value. Optionally, the computing power factor difference is the difference obtained by subtracting the absolute value of the first AI computing power factor value from the absolute value of the second AI computing power factor value.

[0050] Optionally, the terminal receives downlink signaling sent by the access network device, and the downlink signaling includes the AI ​​computing power of the access network device.

[0051] Optionally, the AI ​​computing power factor value is the AI ​​computing power of the access network device; or, the AI ​​computing power of the access network device is converted according to a preset conversion method to obtain the AI ​​computing power factor value, wherein the conversion method includes at least one of linear conversion, exponential conversion, and logarithmic conversion. Schematically, different conversion methods are explained. When the preset conversion method includes linear conversion, the AI ​​computing power factor value is determined according to the product of a and the AI ​​computing power, where a is a natural number; when the preset conversion method includes exponential conversion, the AI ​​computing power factor value is determined according to the ath power of the AI ​​computing power; when the preset conversion method includes logarithmic conversion, the AI ​​computing power factor value is determined with a as the base and the AI ​​computing power as a real number.

[0052] Optionally, the preset conversion mode is configured by the access network device to the terminal, such as: the access network device configures the preset conversion mode to the terminal through at least one of physical layer signaling, MAC layer signaling, radio resource control layer (Radio Resource Control, RRC) signaling or broadcast signaling.

[0053] The above conversion method is only an illustrative example. The method for determining the AI ​​computing power factor value may also include other conversion forms, which are not limited in the embodiments of the present disclosure.

[0054] Optionally, when the first AI computing power factor value is used as an offset parameter to determine the device switching situation, any one of the following situations is included:

[0055] 1.1. In response to the first AI computing power factor value being less than the first threshold value or the first AI computing power factor value being equal to the first threshold value, determining a device switching situation between a source access network device and a target access network device using the first AI computing power factor value as a positive offset parameter;

[0056] Optionally, since the first AI computing power factor value is used to reflect the AI ​​computing power of the source access network device, when the first AI computing power factor value is small, it indicates that the source access network device has low availability in AI computing power. Then, a switching offset is performed in the direction of switching according to the first AI computing power factor value to determine whether to switch from the source access network device to the target access network device.

[0057] 1.2. In response to the first AI computing power factor value being greater than the first threshold value or the first AI computing power factor value being equal to the first threshold value, determining a device switching situation between the source access network device and the target access network device using the first AI computing power factor value as a reverse offset parameter.

[0058] Optionally, when the first AI computing power factor value is greater than or equal to the first threshold value (that is, the first AI computing power factor value is larger), it indicates that the source access network device has a higher availability of AI computing power. Then, the switching is offset in the direction of not switching according to the first AI computing power factor value, thereby determining whether to switch from the source access network device to the target access network device.

[0059] It is worth noting that when the first AI computing power factor value is equal to the first threshold value, the first AI computing power factor value is used as a positive offset parameter for switching offset, or the first AI computing power factor value is used as a reverse offset parameter for switching offset. The embodiment of the present disclosure does not limit the offset method when the first AI computing power factor value is equal to the first threshold value.

[0060] Optionally, when the second AI computing power factor value is used as an offset parameter to determine the device switching situation, any one of the following situations is included:

[0061] 2.1. In response to the second AI computing power factor value being less than the second threshold value or the second AI computing power factor value being equal to the second threshold value, determining a device switching condition between the source access network device and the target access network device using the second AI computing power factor value as a reverse offset parameter;

[0062] Optionally, since the second AI computing power factor value is used to reflect the AI ​​computing power of the target access network device, when the second AI computing power factor value is small, it means that the target access network device has low availability in AI computing power. Then, the switching is offset in the direction of not switching according to the second AI computing power factor value, so as to determine whether to switch from the source access network device to the target access network device.

[0063] 2.2. In response to the second AI computing power factor value being greater than the second threshold or the second AI computing power factor value being equal to the second threshold, the second AI computing power factor value is used as a positive offset parameter to determine a device switching situation between the source access network device and the target access network device.

[0064] Optionally, when the second AI computing power factor value is greater than or equal to the second threshold value (that is, the second AI computing power factor value is larger), it indicates that the target access network device has a higher availability of AI computing power. Then, the switching is offset in the direction of switching according to the second AI computing power factor value, thereby determining whether to switch from the source access network device to the target access network device.

[0065] It is worth noting that when the second AI computing power factor value is equal to the second threshold value, the second AI computing power factor value is used as a positive offset parameter for switching offset, or the second AI computing power factor value is used as a reverse offset parameter for switching offset. The embodiment of the present disclosure does not limit the offset method when the second AI computing power factor value is equal to the second threshold value.

[0066] Optionally, when the computing power factor difference is used as an offset parameter to determine the device switching situation, any of the following situations is included:

[0067] 3.1. In response to the computing power factor difference being greater than a third threshold or the computing power factor difference being equal to the third threshold, determining a device switching situation between the source access network device and the target access network device using the computing power factor difference as a positive offset parameter;

[0068] Optionally, when the computing power factor difference is greater than or equal to the third threshold value (that is, the computing power factor difference is large), it means that the target access network device has higher availability of AI computing power than the source access network device. Then, the switching is offset in the direction of switching according to the computing power factor difference, so as to determine whether to switch from the source access network device to the target access network device.

[0069] 3.2. In response to the computing power factor difference being less than the third threshold or the computing power factor difference being equal to the third threshold, the computing power factor difference is used as a reverse offset parameter to determine a device switching situation between the source access network device and the target access network device.

[0070] Optionally, when the computing power factor difference is less than or equal to the third threshold, it means that the target access network device has little difference in AI computing power relative to the source access network device. Then, the switching is offset in the direction of not switching according to the computing power factor difference, so as to determine whether to switch from the source access network device to the target access network device.

[0071] It is worth noting that when the computing power factor difference is equal to the third threshold, the computing power factor difference is used as the positive offset parameter for switching offset, or the computing power factor difference is used as the reverse offset parameter for switching offset. The embodiment of the present disclosure does not limit the offset method when the computing power factor difference is equal to the third threshold.

[0072] Optionally, the offset parameter is determined by the access network device configuring the terminal device, such as: the access network device configures the offset parameter to the terminal through at least one of physical layer signaling, MAC layer signaling, RRC signaling or broadcast signaling.

[0073] Optionally, the first threshold, the second threshold or the third threshold is configured by the access network device to the terminal device, such as: the access network device configures the first threshold, the second threshold or the third threshold to the terminal through at least one of physical layer signaling, MAC layer signaling, RRC signaling or broadcast signaling.

[0074] In the above embodiment, the terminal determines the device switching situation as an example. In an optional embodiment, after the terminal determines the AI ​​computing power factor value of the access network device, it reports the AI ​​computing power factor value to the source access network device, and the source access network device determines whether to switch; or, after the source access network device determines the AI ​​computing power factor value from the upper-level management network element, it determines whether to switch according to the RSRP or RSRQ reported by the terminal.

[0075] To summarize, the device switching method provided in this embodiment uses the AI ​​computing power factor value of the access network device as an offset parameter. When determining whether to switch from the source access network device to the target access network device, the original determination process is offset according to the AI ​​computing power factor value. When the AI ​​computing power factor value indicates that the AI ​​computing power is suitable for switching, the offset is performed in the positive offset direction to complete the determination of the device switching. Similarly, when the AI ​​computing power factor indicates that the AI ​​computing power is not suitable for switching, the offset is performed in the reverse offset direction to complete the determination of the device switching, thereby improving the accuracy of the device switching process.

[0076] In an optional embodiment, the positive offset and the reverse offset are achieved by adjusting the reference switching parameters. Figure 6 is a flow chart of a device switching method provided by another exemplary embodiment of the present disclosure, and the method is described by taking the application of the method in a terminal as an example. Figure 6 As shown, the method includes:

[0077] Step 601, determine the first AI computing power factor value of the source access network device.

[0078] Optionally, the source access network device sends downlink signaling to the terminal device, and the downlink signaling includes an indication field, where the indication field is used to indicate the first AI computing power factor value of the source access network device.

[0079] Step 602: In response to the first AI computing power factor value being less than or equal to the first threshold value, the first AI computing power factor value is used as a positive offset parameter to determine a device switching status between a source access network device and a target access network device.

[0080] Optionally, using the first AI computing power factor value as a positive offset parameter for offset processing includes at least one of the following situations:

[0081] First, in response to the sum of the first benchmark switching parameter of the target access network device and the first AI computing power factor value reaching the switching threshold, the source access network device is switched to the target access network device;

[0082] The first reference switching parameter includes at least one of a reference signal receiving quality (RSRQ) and a reference signal receiving power (RSRP) of the target access network device.

[0083] Optionally, in response to the sum of the first benchmark switching parameter and the first AI computing power factor value being greater than or equal to the switching threshold, the source access network device is switched to the target access network device.

[0084] Second, in response to the product of the first benchmark switching parameter of the target access network device and the first AI computing power factor value reaching the switching threshold, the source access network device is switched to the target access network device;

[0085] Optionally, in response to the product of the first benchmark switching parameter and the first AI computing power factor value being greater than or equal to the switching threshold, the source access network device is switched to the target access network device.

[0086] It is worth noting that in the above-mentioned first and second comparison processes, the comparison results of the sum or product value and the switching threshold are used as an example for explanation. The first benchmark switching parameter and the first AI computing power factor value can also be calculated in a forward calculation manner and then compared with the switching threshold. That is, the first benchmark switching parameter and the first AI computing power factor value are calculated in a forward addition manner, and the calculation result is compared with the switching threshold.

[0087] Third, in response to the sum of the opposite number of the first AI computing power factor value and the second reference switching parameter of the source access network device being less than the switching threshold, the source access network device is switched to the target access network device, and the second reference switching parameter includes at least one of the RSRQ and RSRP of the source access network device;

[0088] Optionally, in response to the sum of the opposite of the first AI computing power factor value and the second benchmark switching parameter being less than or equal to the switching threshold, the source access network device switches to the target access network device.

[0089] Fourth, in response to a ratio of the second reference switching parameter of the source access network device to the first AI computing power factor value being less than the switching threshold, switching from the source access network device to the target access network device;

[0090] Optionally, in response to the ratio of the second benchmark switching parameter to the first AI computing power factor value being less than or equal to the switching threshold, the source access network device is switched to the target access network device.

[0091] It is worth noting that in the above comparison process, the comparison result between the difference or ratio and the switching threshold is used as an example for explanation. The second benchmark switching parameter and the first AI computing power factor value can also be calculated in a reverse calculation manner and then compared with the switching threshold. That is, the second benchmark switching parameter and the first AI computing power factor value are calculated in a reverse reduction manner, and the calculation result is compared with the switching threshold.

[0092] Fifth, in response to the sum / product of the switching parameter difference and the first AI computing power factor value reaching the switching threshold, the source access network device switches to the target access network device, wherein the switching parameter difference is the difference between the first benchmark switching parameter of the target access network device and the second benchmark switching parameter of the source access network device.

[0093] Optionally, in response to the sum / product of the switching parameter difference and the first AI computing power factor value being greater than or equal to the switching threshold, the source access network device is switched to the target access network device.

[0094] Step 603: In response to the first AI computing power factor value being greater than or equal to the first threshold value, the first AI computing power factor value is used as a reverse offset parameter to determine the device switching status between the source access network device and the target access network device.

[0095] Optionally, using the first AI computing power factor value as a reverse offset parameter for offset processing includes at least one of the following situations:

[0096] First, in response to the sum of the opposite number of the first AI computing power factor value and the first benchmark switching parameter of the target access network device reaching the switching threshold, the source access network device is switched to the target access network device;

[0097] Optionally, in response to the sum of the opposite of the first AI computing power factor value and the first benchmark switching parameter being greater than or equal to the switching threshold, the source access network device switches to the target access network device.

[0098] Second, in response to a ratio of a first benchmark switching parameter of the target access network device to a first AI computing power factor value reaching a switching threshold, switching from the source access network device to the target access network device;

[0099] Optionally, in response to a ratio of the first benchmark switching parameter to the first AI computing power factor value being greater than or equal to a switching threshold, the source access network device is switched to the target access network device.

[0100] Third, in response to the sum of the second benchmark switching parameter of the source access network device and the first AI computing power factor value being less than the switching threshold, the source access network device is switched to the target access network device;

[0101] Optionally, in response to the sum of the second benchmark switching parameter and the first AI computing power factor value being less than or equal to the switching threshold, the source access network device is switched to the target access network device.

[0102] Fourth, in response to the product of the second benchmark switching parameter of the source access network device and the first AI computing power factor value being less than the switching threshold, the source access network device is switched to the target access network device.

[0103] Optionally, in response to the product of the second benchmark switching parameter and the first AI computing power factor value being less than or equal to the switching threshold, the source access network device is switched to the target access network device.

[0104] Fifth, in response to the sum of the opposite number of the first AI computing power factor value and the switching parameter difference reaching the switching threshold; or, the ratio of the switching parameter difference to the first AI computing power factor value reaches the switching threshold, the source access network device switches to the target access network device.

[0105] Optionally, the reaching of the switching threshold is implemented as being greater than the switching threshold, or being greater than or equal to the switching threshold.

[0106] Step 604, determine the second AI computing power factor value of the target access network device.

[0107] Optionally, the source access network device sends downlink signaling to the terminal device, and the downlink signaling includes an indication field, where the indication field is used to indicate the first AI computing power factor value of the source access network device.

[0108] Step 605: In response to the second AI computing power factor value being less than or equal to the second threshold value, the second AI computing power factor value is used as a reverse offset parameter to determine the device switching status between the source access network device and the target access network device.

[0109] Optionally, using the second AI computing power factor value as a reverse offset parameter for offset processing includes at least one of the following situations:

[0110] First, in response to the sum of the opposite number of the second AI computing power factor value and the first benchmark switching parameter of the target access network device reaching the switching threshold, the source access network device is switched to the target access network device;

[0111] Second, in response to a ratio of a first benchmark switching parameter of the target access network device to a second AI computing power factor value reaching a switching threshold, switching from the source access network device to the target access network device;

[0112] Third, in response to the sum of the second benchmark switching parameter of the source access network device and the second AI computing power factor value being less than the switching threshold, the source access network device is switched to the target access network device;

[0113] Fourth, in response to the product of the second benchmark switching parameter of the source access network device and the second AI computing power factor value being less than the switching threshold, the source access network device is switched to the target access network device.

[0114] Fifth, in response to the sum of the inverse of the second AI computing power factor value and the switching parameter difference reaching the switching threshold; or, the ratio of the switching parameter difference to the second AI computing power factor value reaches the switching threshold, the source access network device is switched to the target access network device.

[0115] It is worth noting that the above-mentioned reaching the switching threshold is implemented as being greater than the switching threshold, or being implemented as being greater than or equal to the switching threshold; the above-mentioned being less than the switching threshold can also be implemented as being less than or equal to the switching threshold.

[0116] Step 606: In response to the second AI computing power factor value reaching the second threshold, the second AI computing power factor value is used as a positive offset parameter to determine the device switching status between the source access network device and the target access network device.

[0117] Optionally, using the second AI computing power factor value as a positive offset parameter for offset processing includes at least one of the following situations:

[0118] First, in response to the sum of the first benchmark switching parameter of the target access network device and the second AI computing power factor value reaching the switching threshold, the source access network device is switched to the target access network device;

[0119] Second, in response to the product of the first benchmark switching parameter of the target access network device and the second AI computing power factor value reaching the switching threshold, switching from the source access network device to the target access network device;

[0120] Third, in response to the sum of the inverse of the second AI computing power factor value and the second benchmark switching parameter of the source access network device being less than the switching threshold, switching from the source access network device to the target access network device;

[0121] Fourth, in response to a ratio of the second reference switching parameter of the source access network device to the second AI computing power factor value being less than the switching threshold, switching from the source access network device to the target access network device;

[0122] Fifth, in response to the sum / product of the switching parameter difference and the first AI computing power factor value reaching the switching threshold, the source access network device switches to the target access network device, wherein the switching parameter difference is the difference between the first benchmark switching parameter of the target access network device and the second benchmark switching parameter of the source access network device.

[0123] It is worth noting that the above-mentioned reaching the switching threshold is implemented as being greater than the switching threshold, or being implemented as being greater than or equal to the switching threshold; the above-mentioned being less than the switching threshold can also be implemented as being less than or equal to the switching threshold.

[0124] Step 607: Determine a computing power factor difference between the second AI computing power factor value and the first AI computing power factor value.

[0125] Optionally, the opposite of the first AI computing power factor value is added to the second AI computing power factor value to obtain a computing power factor difference, that is, the first AI computing power factor value is subtracted from the second AI computing power factor value to obtain the computing power factor difference.

[0126] Step 608, in response to the computing power factor difference reaching the third threshold, the computing power factor difference is used as a positive offset parameter to determine the device switching status between the source access network device and the target access network device.

[0127] Optionally, using the computing power factor difference as a positive offset parameter for offset processing includes at least one of the following situations:

[0128] First, in response to the sum of the switching parameter difference and the computing power factor difference reaching the switching threshold, switching from the source access network device to the target access network device;

[0129] Second, in response to the product of the difference in the switching parameter used for the difference in the computing power factor reaching the switching, the source access network device is switched to the target access network device;

[0130] Third, in response to the sum / product of the difference between the first reference switching parameter of the target access network device and the computing power factor reaching a switching threshold, switching from the source access network device to the target access network device;

[0131] Fourth, in response to the sum of the inverse of the difference in the computing power factor and the second reference switching parameter being less than the switching threshold, switching from the source access network device to the target access network device;

[0132] Fifth, in response to the ratio of the second benchmark switching parameter to the computing power factor difference being less than the switching threshold, the source access network device is switched to the target access network device.

[0133] It is worth noting that the above-mentioned reaching the switching threshold is implemented as being greater than the switching threshold, or being implemented as being greater than or equal to the switching threshold; the above-mentioned being less than the switching threshold can also be implemented as being less than or equal to the switching threshold.

[0134] Step 609, in response to the computing power factor difference being less than the third threshold, the computing power factor difference is used as a reverse offset parameter to determine the device switching status between the source access network device and the target access network device.

[0135] Optionally, using the computing power factor difference as a reverse offset parameter for offset processing includes at least one of the following situations:

[0136] First, in response to the sum of the inverse of the difference in the computing power factor and the difference in the switching parameter reaching a switching threshold, switching from the source access network device to the target access network device;

[0137] Second, in response to the ratio of the switching parameter difference to the computing power factor difference reaching a switching threshold, switching from the source access network device to the target access network device;

[0138] Third, in response to the sum of the inverse of the difference in the computing power factor and the first reference switching parameter reaching a switching threshold, switching from the source access network device to the target access network device;

[0139] Fourth, in response to the ratio of the first reference switching parameter to the difference between the computing power factor reaching the switching threshold, switching from the source access network device to the target access network device;

[0140] Fifth, in response to the sum / product of the second benchmark switching parameter and the difference between the computing power factor being less than the switching threshold, switching from the source access network device to the target access network device.

[0141] It is worth noting that the above-mentioned reaching the switching threshold is implemented as being greater than the switching threshold, or being implemented as being greater than or equal to the switching threshold; the above-mentioned being less than the switching threshold can also be implemented as being less than or equal to the switching threshold.

[0142] It is worth noting that the above embodiments are mainly for explaining the switching between base stations. When the terminal initializes access to the base station, the access base station can also be determined in combination with the AI ​​computing power factor value and the benchmark access parameters (such as RSRP, RSRQ, etc.).

[0143] To summarize, the device switching method provided in this embodiment uses the AI ​​computing power factor value of the access network device as an offset parameter. When determining whether to switch from the source access network device to the target access network device, the original determination process is offset according to the AI ​​computing power factor value. When the AI ​​computing power factor value indicates that the AI ​​computing power is suitable for switching, the offset is performed in the positive offset direction to complete the determination of the device switching. Similarly, when the AI ​​computing power factor indicates that the AI ​​computing power is not suitable for switching, the offset is performed in the reverse offset direction to complete the determination of the device switching, thereby improving the accuracy of the device switching process.

[0144] Figure 7 is a structural block diagram of a device switching apparatus provided by an exemplary embodiment of the present disclosure, such as Figure 7 As shown, the device comprises:

[0145] The processing module 710 is configured to use the AI ​​computing power factor value of the access network device as an offset parameter to determine the device switching status between the access network devices.

[0146] In an optional embodiment, the processing module 710 is further configured to determine a first AI computing power factor value of the source access network device;

[0147] The processing module 710 is also configured to determine the device switching status between the source access network device and the target access network device using the first AI computing power factor value as a positive offset parameter in response to the first AI computing power factor value being less than a first threshold or the first AI computing power factor value being equal to the first threshold.

[0148] In an optional embodiment, the processing module 710 is further configured to switch from the source access network device to the target access network device in response to the sum of a first benchmark switching parameter of the target access network device and the first AI computing power factor value reaching a switching threshold, wherein the first benchmark switching parameter includes at least one of a reference signal received quality RSRQ and a reference signal received power RSRP of the target access network device;

[0149] or,

[0150] The processing module 710 is further configured to switch from the source access network device to the target access network device in response to the product of the first benchmark switching parameter of the target access network device and the first AI computing power factor value reaching a switching threshold;

[0151] or,

[0152] The processing module 710 is further configured to, in response to the sum of the opposite number of the first AI computing power factor value and the second benchmark switching parameter of the source access network device being less than a switching threshold, switch from the source access network device to the target access network device, wherein the second benchmark switching parameter includes at least one of RSRQ and RSRP of the source access network device;

[0153] or,

[0154] The processing module 710 is further configured to switch from the source access network device to the target access network device in response to a ratio of the second benchmark switching parameter of the source access network device to the first AI computing power factor value being less than a switching threshold.

[0155] In an optional embodiment, the processing module 710 is also configured to determine a first AI computing power factor value of the source access network device; in response to the first AI computing power factor value being equal to a first threshold value or the first AI computing power factor value being greater than the first threshold value, the first AI computing power factor value is used as a reverse offset parameter to determine the device switching status between the source access network device and the target access network device.

[0156] In an optional embodiment, the processing module 710 is further configured to switch from the source access network device to the target access network device in response to the sum of the opposite number of the first AI computing power factor value and the first benchmark switching parameter of the target access network device reaching a switching threshold, wherein the first benchmark switching parameter includes at least one of the RSRQ and RSRP of the target access network device;

[0157] or,

[0158] The processing module 710 is further configured to switch from the source access network device to the target access network device in response to a ratio of the first benchmark switching parameter of the target access network device to the first AI computing power factor value reaching a switching threshold;

[0159] or,

[0160] The processing module 710 is further configured to, in response to a sum of a second reference switching parameter of the source access network device and the first AI computing power factor value being less than a switching threshold, switch from the source access network device to the target access network device, wherein the second reference switching parameter includes at least one of an RSRQ and an RSRP of the source access network device;

[0161] or,

[0162] The processing module 710 is further configured to switch from the source access network device to the target access network device in response to the product of the second benchmark switching parameter of the source access network device and the first AI computing power factor value being less than a switching threshold.

[0163] In an optional embodiment, the processing module 710 is further configured to determine a second AI computing power factor value of the target access network device;

[0164] The processing module 710 is also configured to determine the device switching status between the source access network device and the target access network device using the second AI computing power factor value as a reverse offset parameter in response to the second AI computing power factor value being less than a second threshold or the second AI computing power factor value being equal to the second threshold.

[0165] In an optional embodiment, the processing module 710 is further configured to switch from the source access network device to the target access network device in response to the sum of the opposite number of the second AI computing power factor value and the first benchmark switching parameter of the target access network device reaching a switching threshold, wherein the first benchmark switching parameter includes at least one of the RSRQ and RSRP of the target access network device;

[0166] or,

[0167] The processing module 710 is further configured to switch from the source access network device to the target access network device in response to a ratio of the first benchmark switching parameter of the target access network device to the second AI computing power factor value reaching a switching threshold;

[0168] or,

[0169] The processing module 710 is further configured to, in response to a sum of a second benchmark switching parameter of the source access network device and the second AI computing power factor value being less than a switching threshold, switch from the source access network device to the target access network device, wherein the second benchmark switching parameter includes at least one of an RSRQ and an RSRP of the source access network device;

[0170] or,

[0171] The processing module 710 is further configured to switch from the source access network device to the target access network device in response to the product of the second benchmark switching parameter of the source access network device and the second AI computing power factor value being less than a switching threshold.

[0172] In an optional embodiment, the processing module 710 is also configured to determine a second AI computing power factor value of the target access network device; in response to the second AI computing power factor value being equal to a second threshold value or the second AI computing power factor value being greater than the second threshold value, the second AI computing power factor value is used as a positive offset parameter to determine the device switching status between the source access network device and the target access network device.

[0173] In an optional embodiment, the processing module 710 is further configured to switch from the source access network device to the target access network device in response to the sum of the first benchmark switching parameter of the target access network device and the second AI computing power factor value reaching a switching threshold, wherein the first benchmark switching parameter includes at least one of the RSRQ and RSRP of the target access network device;

[0174] or,

[0175] The processing module 710 is further configured to switch from the source access network device to the target access network device in response to the product of the first benchmark switching parameter of the target access network device and the second AI computing power factor value reaching a switching threshold;

[0176] or,

[0177] The processing module 710 is further configured to, in response to the sum of the opposite number of the second AI computing power factor value and the second benchmark switching parameter of the source access network device being less than a switching threshold, switch from the source access network device to the target access network device, wherein the second benchmark switching parameter includes at least one of RSRQ and RSRP of the source access network device;

[0178] or,

[0179] The processing module 710 is further configured to switch from the source access network device to the target access network device in response to a ratio of the second benchmark switching parameter of the source access network device to the second AI computing power factor value being less than a switching threshold.

[0180] In an optional embodiment, the processing module 710 is further configured to determine a first AI computing power factor value of a source access network device and a second AI computing power factor value of a target access network device; determine a computing power factor difference between the second AI computing power factor value and the first AI computing power factor value;

[0181] The processing module 710 is also configured to determine the device switching status between the source access network device and the target access network device using the computing power factor difference as a positive offset parameter in response to the computing power factor difference being equal to a third threshold or the computing power factor difference being greater than the third threshold.

[0182] In an optional embodiment, the processing module 710 is further configured to switch from the source access network device to the target access network device in response to the sum of the switching parameter difference and the computing power factor difference reaching a switching threshold, wherein the switching parameter difference is the difference between the first benchmark switching parameter of the target access network device and the second benchmark switching parameter of the source access network device;

[0183] or,

[0184] The processing module 710 is further configured to switch from the source access network device to the target access network device in response to the product of the switching parameter difference and the computing power factor difference reaching a switching threshold.

[0185] In an optional embodiment, the processing module 710 is also configured to determine a first AI computing power factor value of a source access network device and a second AI computing power factor value of a target access network device; determine a computing power factor difference between the second AI computing power factor value and the first AI computing power factor value; in response to the computing power factor difference being less than a third threshold or the computing power factor difference being equal to the third threshold, use the computing power factor difference as a reverse offset parameter to determine the device switching status between the source access network device and the target access network device.

[0186] In an optional embodiment, the processing module 710 is further configured to switch from the source access network device to the target access network device in response to the sum of the inverse of the computing power factor difference and the switching parameter difference reaching a switching threshold, wherein the switching parameter difference is the difference between the first benchmark switching parameter of the target access network device and the second benchmark switching parameter of the source access network device;

[0187] or,

[0188] The processing module 710 is further configured to switch from the source access network device to the target access network device in response to a ratio of a switching parameter difference to a computing power factor difference reaching a switching threshold.

[0189] In an optional embodiment, the processing module 710 is further configured to convert the AI ​​computing power of the access network device according to a preset conversion method to obtain the AI ​​computing power factor value;

[0190] The conversion method includes at least one of linear conversion, exponential conversion and logarithmic conversion.

[0191] To summarize, the device switching apparatus provided in this embodiment uses the AI ​​computing power factor value of the access network device as an offset parameter. When determining whether to switch from the source access network device to the target access network device, the original determination process is offset according to the AI ​​computing power factor value. When the AI ​​computing power factor value indicates that the AI ​​computing power is suitable for switching, the offset is performed in the positive offset direction to complete the determination of the device switching. Similarly, when the AI ​​computing power factor indicates that the AI ​​computing power is not suitable for switching, the offset is performed in the reverse offset direction to complete the determination of the device switching, thereby improving the accuracy of the device switching process.

[0192] Figure 8 A schematic diagram of the structure of a terminal provided by an exemplary embodiment of the present disclosure is shown. The terminal includes: a processor 801, a receiver 802, a transmitter 803, a memory 804 and a bus 805.

[0193] The processor 801 includes one or more processing cores. The processor 801 executes various functional applications and information processing by running software programs and modules.

[0194] The receiver 802 and the transmitter 803 may be implemented as a communication component, which may be a communication chip.

[0195] The memory 804 is connected to the processor 801 via a bus 805 .

[0196] The memory 804 may be used to store at least one instruction, and the processor 801 may be used to execute the at least one instruction to implement each step in the above method embodiment.

[0197] In addition, the memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, and the volatile or non-volatile storage device includes but is not limited to: a magnetic disk or an optical disk, an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a static random access memory (SRAM), a read-only memory (ROM), a magnetic memory, a flash memory, and a programmable read-only memory (PROM).

[0198] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory including instructions, and the instructions can be executed by a processor of a terminal to complete the method performed by the terminal side in the above-mentioned device switching method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0199] A non-transitory computer-readable storage medium, when instructions in the non-transitory computer storage medium are executed by a processor of a terminal, enables the terminal to execute the above-mentioned device switching method.

[0200] Fig. 9 FIG. 9 is a block diagram of an access network device 900 according to an exemplary embodiment. In some embodiments, the access network device 900 is a base station.

[0201] The access network device 900 includes: a processor 901, a receiver 902, a transmitter 903 and a memory 904. The receiver 902, the transmitter 903 and the memory 904 are connected to the processor 901 via a bus respectively.

[0202] The processor 901 includes one or more processing cores, and the processor 901 executes the method performed by the access network device in the device switching method provided in the embodiment of the present disclosure by running software programs and modules. The memory 904 can be used to store software programs and modules. Specifically, the memory 904 can store an operating system 941 and an application module 942 required for at least one function. The receiver 902 is used to receive communication data sent by other devices, and the transmitter 903 is used to send communication data to other devices.

[0203] An exemplary embodiment of the present disclosure further provides a communication system, the system comprising: a terminal and an access network device;

[0204] The terminal includes Figure 7 The illustrated embodiment provides a device switching apparatus.

[0205] An exemplary embodiment of the present disclosure further provides a communication system, the communication system comprising: a terminal and an access network device;

[0206] The terminal includes Figure 8 The terminal provided by the illustrated embodiment;

[0207] The access network equipment includes: Fig. 9 The illustrated embodiment provides an access network device.

[0208] An exemplary embodiment of the present disclosure also provides a computer-readable storage medium, in which at least one instruction, at least one program, a code set or an instruction set is stored, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement the steps performed by the terminal or the access network device in the device switching method provided by the above-mentioned various method embodiments.

[0209] It should be understood that the "plurality" mentioned in this article refers to two or more. "And / or" describes the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects are in an "or" relationship.

[0210] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0211] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A device switching method, characterized in that: Applied in a terminal device, the method comprises: Taking the AI ​​computing power factor value of the access network device as an offset parameter, determine the device switching situation between the access network devices, the offset parameter is used to indicate the degree of tendency to perform device switching between the access network devices, and the AI ​​computing power factor value of the access network device is one of the following: the first AI computing power factor value of the source access network device, the second AI computing power factor value of the target access network device, and the computing power factor difference between the second AI computing power factor value and the first AI computing power factor value.

2. The method according to claim 1, characterized in that The method of using the AI ​​computing power factor value of the access network device as an offset parameter to determine the device switching situation between the access network devices includes: Determine a first AI computing power factor value of the source access network device; In response to the first AI computing power factor value being less than a first threshold value or the first AI computing power factor value being equal to the first threshold value, the device switching situation between the source access network device and the target access network device is determined using the first AI computing power factor value as a positive offset parameter, and the positive offset parameter is used to indicate the degree of tendency to switch from the source access network device to the target access network device.

3. The method according to claim 2, characterized in that The determining the device switching situation between the source access network device and the target access network device by using the first AI computing power factor value as a positive offset parameter includes: In response to the sum of a first benchmark switching parameter of the target access network device and the first AI computing power factor value reaching a switching threshold, the source access network device is switched to the target access network device, wherein the first benchmark switching parameter includes at least one of a reference signal received quality RSRQ and a reference signal received power RSRP of the target access network device; or, In response to the product of the first benchmark switching parameter of the target access network device and the first AI computing power factor value reaching a switching threshold, switching from the source access network device to the target access network device; or, In response to the sum of the opposite number of the first AI computing power factor value and the second benchmark switching parameter of the source access network device being less than a switching threshold, switching from the source access network device to the target access network device, where the second benchmark switching parameter includes at least one of an RSRQ and an RSRP of the source access network device; or, In response to a ratio of a second benchmark switching parameter of the source access network device to the first AI computing power factor value being less than a switching threshold, the source access network device is switched to the target access network device.

4. The method according to claim 1, characterized in that The method of using the AI ​​computing power factor value of the access network device as an offset parameter to determine the device switching situation between the access network devices includes: Determine a first AI computing power factor value of the source access network device; In response to the first AI computing power factor value being equal to a first threshold value or the first AI computing power factor value being greater than the first threshold value, the device switching situation between the source access network device and the target access network device is determined using the first AI computing power factor value as a reverse offset parameter, and the reverse offset parameter is used to indicate the degree of tendency not to switch from the source access network device to the target access network device.

5. The method according to claim 4, characterized in that The determining, using the first AI computing power factor value as a reverse offset parameter, a device switching situation between the source access network device and the target access network device, includes: In response to the sum of the opposite number of the first AI computing power factor value and the first benchmark switching parameter of the target access network device reaching a switching threshold, the source access network device is switched to the target access network device, where the first benchmark switching parameter includes at least one of an RSRQ and an RSRP of the target access network device; or, In response to a ratio of a first benchmark switching parameter of the target access network device to the first AI computing power factor value reaching a switching threshold, switching from the source access network device to the target access network device; or, In response to a sum of a second reference switching parameter of the source access network device and the first AI computing power factor value being less than a switching threshold, switching from the source access network device to the target access network device, wherein the second reference switching parameter includes at least one of an RSRQ and an RSRP of the source access network device; or, In response to the product of the second benchmark switching parameter of the source access network device and the first AI computing power factor value being less than a switching threshold, the source access network device is switched to the target access network device.

6. The method according to claim 1, characterized in that The method of using the AI ​​computing power factor value of the access network device as an offset parameter to determine the device switching situation between the access network devices includes: Determine the second AI computing power factor value of the target access network device; In response to the second AI computing power factor value being less than a second threshold or the second AI computing power factor value being equal to the second threshold, the second AI computing power factor value is used as a reverse offset parameter to determine the device switching situation between the source access network device and the target access network device, and the reverse offset parameter is used to indicate the degree of tendency not to switch from the source access network device to the target access network device.

7. The method according to claim 6, characterized in that The determining of a device switching situation between the source access network device and the target access network device by using the second AI computing power factor value as a reverse offset parameter includes: In response to the sum of the opposite number of the second AI computing power factor value and the first benchmark switching parameter of the target access network device reaching a switching threshold, the source access network device is switched to the target access network device, where the first benchmark switching parameter includes at least one of the RSRQ and RSRP of the target access network device; or, In response to a ratio of a first benchmark switching parameter of the target access network device to the second AI computing power factor value reaching a switching threshold, switching from the source access network device to the target access network device; or, In response to the sum of a second benchmark switching parameter of the source access network device and the second AI computing power factor value being less than a switching threshold, switching from the source access network device to the target access network device, wherein the second benchmark switching parameter includes at least one of an RSRQ and an RSRP of the source access network device; or, In response to the product of the second benchmark switching parameter of the source access network device and the second AI computing power factor value being less than a switching threshold, the source access network device is switched to the target access network device.

8. The method according to claim 1, characterized in that The method of using the AI ​​computing power factor value of the access network device as an offset parameter to determine the device switching situation between the access network devices includes: Determine the second AI computing power factor value of the target access network device; In response to the second AI computing power factor value being equal to the second threshold value or the second AI computing power factor value being greater than the second threshold value, the device switching situation between the source access network device and the target access network device is determined using the second AI computing power factor value as a positive offset parameter, and the positive offset parameter is used to indicate the degree of tendency to switch from the source access network device to the target access network device.

9. The method according to claim 8, characterized in that The determining the device switching situation between the source access network device and the target access network device by using the second AI computing power factor value as a positive offset parameter includes: In response to the sum of a first benchmark switching parameter of the target access network device and the second AI computing power factor value reaching a switching threshold, the source access network device is switched to the target access network device, wherein the first benchmark switching parameter includes at least one of an RSRQ and an RSRP of the target access network device; or, In response to the product of the first benchmark switching parameter of the target access network device and the second AI computing power factor value reaching a switching threshold, switching from the source access network device to the target access network device; or, In response to the sum of the opposite number of the second AI computing power factor value and the second benchmark switching parameter of the source access network device being less than a switching threshold, switching from the source access network device to the target access network device, where the second benchmark switching parameter includes at least one of an RSRQ and an RSRP of the source access network device; or, In response to a ratio of the second benchmark switching parameter of the source access network device to the second AI computing power factor value being less than a switching threshold, the source access network device is switched to the target access network device.

10. The method according to claim 1, characterized in that The method of using the AI ​​computing power factor value of the access network device as an offset parameter to determine the device switching situation between the access network devices includes: Determine a first AI computing power factor value of a source access network device and a second AI computing power factor value of a target access network device; Determine a computing power factor difference between the second AI computing power factor value and the first AI computing power factor value; In response to the computing power factor difference being equal to a third threshold value or the computing power factor difference being greater than the third threshold value, the computing power factor difference is used as a positive offset parameter to determine the device switching situation between the source access network device and the target access network device, and the positive offset parameter is used to indicate the degree of tendency to switch from the source access network device to the target access network device.

11. The method according to claim 10, characterized in that The determining of the device switching situation between the source access network device and the target access network device by using the computing power factor difference as a positive offset parameter includes: In response to the sum of the switching parameter difference and the computing power factor difference reaching a switching threshold, the source access network device is switched to the target access network device, wherein the switching parameter difference is the difference between a first reference switching parameter of the target access network device and a second reference switching parameter of the source access network device; or, In response to the product of the switching parameter difference and the computing power factor difference reaching a switching threshold, switching from the source access network device to the target access network device.

12. The method according to claim 1, characterized in that The method of using the AI ​​computing power factor value of the access network device as an offset parameter to determine the device switching situation between the access network devices includes: Determine a first AI computing power factor value of a source access network device and a second AI computing power factor value of a target access network device; Determine a computing power factor difference between the second AI computing power factor value and the first AI computing power factor value; In response to the computing power factor difference being less than a third threshold or the computing power factor difference being equal to the third threshold, the computing power factor difference is used as a reverse offset parameter to determine the device switching situation between the source access network device and the target access network device, and the reverse offset parameter is used to indicate the degree of tendency not to switch from the source access network device to the target access network device.

13. The method according to claim 12, characterized in that The determining of the device switching between the source access network device and the target access network device by using the computing power factor difference as a reverse offset parameter includes: In response to the sum of the inverse of the computing power factor difference and the switching parameter difference reaching a switching threshold, the source access network device is switched to the target access network device, wherein the switching parameter difference is the difference between a first reference switching parameter of the target access network device and a second reference switching parameter of the source access network device; or, In response to the ratio of the switching parameter difference to the computing power factor difference reaching a switching threshold, switching from the source access network device to the target access network device.

14. The method according to any one of claims 1 to 13, characterized in that: The method further comprises: Convert the AI ​​computing power of the access network device according to a preset conversion method to obtain the AI ​​computing power factor value; The conversion method includes at least one of linear conversion, exponential conversion and logarithmic conversion.

15. A device switching device, characterized in that: Applied in a terminal device, the device comprises: The processing module is configured to use the AI ​​computing power factor value of the access network device as an offset parameter to determine the device switching situation between the access network devices, where the offset parameter is used to indicate the degree of tendency to perform device switching between the access network devices, and the AI ​​computing power factor value of the access network device is one of the following: a first AI computing power factor value of the source access network device, a second AI computing power factor value of the target access network device, and a computing power factor difference between the second AI computing power factor value and the first AI computing power factor value.

16. A terminal, characterized in that: The terminal comprises: processor; a transceiver connected to the processor; a memory for storing executable signaling for the processor; The processor is configured to load and execute executable instructions to implement the device switching method as described in any one of claims 1 to 14.

17. A computer-readable storage medium, wherein at least one instruction, at least one program, a code set or an instruction set is stored in the computer-readable storage medium, wherein the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by a processor to implement the device switching method as described in any one of claims 1 to 14.

Images