Parameter determination method, communication device, and storage medium

Abstract

The embodiments of the present disclosure provide an artificial intelligence parameter determination method, a communication device and a storage medium. A use method of an AI function performed by a terminal comprises: determining whether to take a first prediction result as an input parameter of an artificial intelligence AI function according to first information, the AI function being used to output a prediction result of a wireless measurement, the first prediction result being an output parameter of the AI function.

Description

Parameter determination method, communication equipment and storage medium Technical Field

[0001] This disclosure relates to the field of communication technology, and in particular to a method for controlling the use of artificial intelligence (AI) functions, a communication device, and a storage medium. Background Technology

[0002] Machine learning algorithms are one of the most important methods for implementing artificial intelligence technology. Machine learning can build models using large amounts of training data, and these models can then predict events. In many fields, machine learning models can achieve very accurate predictions.

[0003] Summary of the Invention

[0004] This disclosure provides a method for determining artificial intelligence parameters, a communication device, and a storage medium.

[0005] According to a first aspect of the present disclosure, a parameter determination method is provided, wherein the method is executed by a terminal, the method comprising: determining, based on first information, whether to use a first prediction result as an input parameter of an artificial intelligence (AI) function, wherein the AI ​​function is used to output a prediction result of wireless measurement, and the first prediction result is an output parameter of the AI ​​function.

[0006] According to a second aspect of the present disclosure, a parameter determination method is provided, wherein the method is performed by a network device, the method comprising: sending first information to a terminal, the first information being used by the terminal to determine whether to use a first prediction result as an input parameter of an artificial intelligence (AI) function, the AI ​​function being used to output a prediction result of wireless measurement; the first prediction result being an output parameter of the AI ​​function.

[0007] According to a third aspect of the present disclosure, a parameter determination apparatus is provided, wherein the parameter determination apparatus includes: a processing module configured to determine, based on first information, whether to use a first prediction result as an input parameter of an artificial intelligence (AI) function, wherein the AI ​​function is used to output a prediction result of wireless measurement, and the first prediction result is an output parameter of the AI ​​function.

[0008] According to a fourth aspect of the present disclosure, a sending module is provided, configured to send first information to a terminal, the first information being used by the terminal to determine whether to use a first prediction result as an input parameter of an artificial intelligence (AI) function, the AI ​​function being used to output a prediction result of wireless measurement; the first prediction result being an output parameter of the AI ​​function.

[0009] A communication system is provided according to a fifth aspect of the present disclosure, wherein the communication system includes: a terminal configured to perform the method described in any technical solution of the first aspect; and a network device configured to perform the method described in any technical solution of the second aspect.

[0010] According to a sixth aspect of the present disclosure, a communication device is provided, wherein the communication device includes: one or more processors; wherein the processors are configured to invoke instructions to cause the communication device to perform the method provided by any of the techniques described in the first to second aspects.

[0011] A storage medium is provided according to a seventh aspect of the present disclosure, wherein the storage medium stores instructions that, when executed on a communication device, cause the communication device to perform the method provided by any one of the first to second aspects.

[0012] According to an eighth aspect of the present disclosure, a program product is provided, wherein the program product includes a computer program, which, when executed by a communication device, enables the communication device to implement the method provided by any of the technical means of the first to second aspects.

[0013] The technical approach provided in this disclosure allows the terminal to determine whether to use the first prediction result as the input parameter of the AI ​​function based on the first information. Compared to using the first prediction result as the input of the AI ​​function without making any judgment, this approach can reduce the problem of using inappropriate first prediction results or using too many first prediction results as the input of the AI ​​function, which leads to poor output performance of the AI ​​function and improves the accuracy of the AI ​​function output results.

[0014] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the embodiments of this disclosure. Attached Figure Description

[0015] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of embodiments of this disclosure.

[0016] Figure 1A is a schematic diagram of the architecture of a communication system according to an exemplary embodiment;

[0017] Figure 1B is a time-series diagram illustrating a general measurement result and a prediction result according to an exemplary embodiment;

[0018] Figure 1C is a timing diagram illustrating a general measurement result and a prediction result according to an exemplary embodiment;

[0019] Figure 2A is a flowchart illustrating an artificial intelligence parameter determination method according to an exemplary embodiment;

[0020] Figure 2B is a flowchart illustrating an artificial intelligence parameter determination method according to an exemplary embodiment;

[0021] Figure 2C is a flowchart illustrating an artificial intelligence parameter determination method according to an exemplary embodiment;

[0022] Figure 3A is a schematic diagram of the structure of a terminal according to an exemplary embodiment;

[0023] Figure 3B is a schematic diagram of the structure of a network device according to an exemplary embodiment;

[0024] Figure 4A is a schematic diagram of the structure of a communication device according to an exemplary embodiment;

[0025] Figure 4B is a schematic diagram of the structure of a chip according to an exemplary embodiment. Detailed Implementation

[0026] This disclosure provides a method for determining artificial intelligence parameters, a communication device, a communication system, and a storage medium.

[0027] A first aspect provides a method for determining artificial intelligence parameters, wherein the method is executed by a terminal, the method comprising: determining, based on first information, whether to use a first prediction result as an input parameter of an artificial intelligence (AI) function, wherein the AI ​​function is used to output a prediction result of wireless measurement, and the first prediction result is an output parameter of the AI ​​function.

[0028] In the above scheme, the terminal will determine whether to use the first prediction result as the input parameter of the AI ​​function based on the first information. Compared with using the first prediction result as the input of the AI ​​function without making any judgment, this can reduce the problem of using inappropriate first prediction results or using too many first prediction results as the input of the AI ​​function, which leads to poor output performance of the AI ​​function and improves the accuracy of the AI ​​function output results.

[0029] In some embodiments of the first aspect, the first information includes at least one of the following:

[0030] The output performance metrics of the AI ​​function;

[0031] A first indication is provided to indicate whether the first prediction result can be used as an input parameter for the AI ​​function.

[0032] The above scheme provides an example of the first information. In actual implementation, it is not limited to the above example. Network devices can flexibly use the output performance indicators or first indications of AI functions as needed to indicate to the terminal whether the first prediction result can be used as the input of AI functions.

[0033] In some embodiments of the first aspect, the output performance metrics include one or more of the following:

[0034] The first confidence level is used to indicate the accuracy of the AI ​​function;

[0035] The first difference is used to indicate the difference between the first prediction result and the actual measurement result;

[0036] The second confidence level is used to indicate the accuracy of the first prediction result.

[0037] The above solution provides output performance metrics for AI functions. In specific implementations, any of the above metrics can be flexibly selected as the output performance metrics for AI functions to meet the usage needs in different scenarios.

[0038] In some embodiments of the first aspect, determining whether to use the first prediction result as an input parameter of the AI ​​function based on the first information includes: determining to use the first prediction result as an input of the AI ​​function if the first information satisfies a first condition.

[0039] The above scheme determines that the first condition is met based on the first information, and then the corresponding first prediction result can be used as the input of the AI ​​function. In this way, it can be ensured that even if the first prediction result is used as the input of the AI ​​function, the accuracy of the prediction result output by the AI ​​function can be ensured.

[0040] In some embodiments of the first aspect, the first information satisfying the first condition includes one or more of the following: the first confidence level is higher than a first threshold; the first confidence level is continuously higher than a second threshold within a first time period; the first confidence level of the AI ​​function is higher than a third threshold for N consecutive times; N is a positive integer greater than or equal to 2; the first difference is less than a fourth threshold; and the second confidence level is higher than a fifth threshold.

[0041] The above solution provides a specific method for determining whether the first condition is met based on various output performance indicators, ensuring both the output performance of the AI ​​function and ease of implementation.

[0042] In some embodiments of the first aspect, the first prediction result includes multiple prediction results, and determining whether to use the first prediction result as an input parameter for an artificial intelligence (AI) function based on the first information includes: determining whether to use the multiple prediction results as input parameters for an AI function based on the first information; the method further includes: sending second information to a network device, the second information including information of a second prediction result; the second prediction result is the prediction result among the multiple prediction results that is used as an input parameter for the AI ​​function.

[0043] The second prediction result is the prediction result among the multiple prediction results used as the input parameter of the AI ​​function. In the above scheme, the second information indicates the information of the second prediction result, which can help network devices know which prediction results the terminal specifically used as the input of the AI ​​function.

[0044] In some embodiments of the first aspect, any two of the plurality of prediction results are of the same type and the resource locations associated with any two prediction results are different; or, any two of the plurality of prediction results are of different types.

[0045] The above scheme limits the commonalities or differences of multiple prediction results output at once, thus facilitating flexible use in different scenarios.

[0046] In some embodiments of the first aspect, the method further includes: receiving third information sent by a network device; the third information includes at least the first information, and the third information further includes one or more of the following: a second quantity, the second quantity being used to determine the number of first prediction results that can be used for one input of the AI ​​function; and second resource information, the second resource information being used by the terminal to determine resource locations that are allowed as first prediction results for input of the AI ​​function.

[0047] In the above scheme, the terminal receives one or more pieces of information from the network device at once. The first piece of information can be used as part of the third piece of information. This reduces the number of information exchanges between the terminal and the network device, reduces signaling overhead, and reduces the energy consumption of communication between the terminal and the network device.

[0048] Meanwhile, the above scheme provides examples of the information content of the third information, but the specific implementation is not limited to the above examples. By introducing the second quantity and / or the second resource information, the network device can better guide the terminal to use the AI ​​function, and ensure that even when using the AI ​​function to perform one or more related wireless functions such as wireless resource management, wireless link management or wireless positioning, the implementation quality of these functions can be ensured.

[0049] In some embodiments of the first aspect, the method further includes: sending fourth information to a network device, the fourth information being used by the network device to determine whether the first prediction result can be used as an input parameter for an AI function.

[0050] In the above scheme, the terminal sends fourth information to the network device, and then generates third information based on the determined result or reduces the reporting of the terminal's measurement results or prediction results. The network device, such as the base station, obtains the measurement results based on the execution of local AI functions.

[0051] In some embodiments of the first aspect, the fourth information includes one or more of the following:

[0052] The third confidence level is used to indicate the accuracy of the AI ​​function;

[0053] The second indicator is used to indicate that the third confidence level is higher than the sixth threshold;

[0054] The fourth confidence level is the minimum confidence level of the AI ​​function within the second time period;

[0055] The third indication is used to indicate that the built-in confidence level of the AI ​​function remains above the seventh threshold for a second duration.

[0056] The sixth confidence level is the minimum confidence level of the most recent M consecutive outputs of the AI ​​function;

[0057] The fourth indicator is used to indicate that the confidence level of the AI ​​function in the most recent M consecutive outputs is higher than the eighth threshold;

[0058] The third resource information is used to indicate the resource location of the third prediction result, which is the prediction result output by the AI ​​function and related to the fourth information.

[0059] The above embodiments provide various information contents of the fourth information to facilitate flexible selection during specific implementation.

[0060] A second aspect provides a method for determining artificial intelligence parameters, wherein the method is executed by a network device, the method comprising:

[0061] Send first information to the terminal, the first information being used by the terminal to determine whether to use the first prediction result as an input parameter for an artificial intelligence (AI) function, the AI ​​function being used to output a prediction result for wireless measurement; the first prediction result is the output parameter of the AI ​​function.

[0062] In some embodiments of the second aspect, the first information includes at least one of the following:

[0063] The output performance metrics of the AI ​​function;

[0064] A first indication is provided to indicate whether the first prediction result can be used as an input parameter for the AI ​​function.

[0065] In some embodiments of the second aspect, the output performance metrics include one or more of the following:

[0066] The first confidence level is used to indicate the accuracy of the AI ​​function;

[0067] The first difference is used to indicate the difference between the first prediction result and the actual measurement result;

[0068] The second confidence level is used to indicate the accuracy of the first prediction result.

[0069] In some embodiments of the second aspect, the first prediction result includes multiple prediction results, and the method further includes:

[0070] The system receives second information sent by the terminal, the second information including information about a second prediction result; the second prediction result is the prediction result among the plurality of prediction results that serves as the input parameter for the AI ​​function.

[0071] In some embodiments of the second aspect, the second information is used to indicate one or more of the following:

[0072] The number of the second prediction results;

[0073] The resource location corresponding to the second prediction result includes one or more of the first time domain location and the first frequency domain location.

[0074] In some embodiments of the second aspect, any two prediction results among the plurality of prediction results are of the same type, and any two prediction results are associated with different resource locations; or, any two prediction results among the plurality of prediction results are of different types.

[0075] In some embodiments of the second aspect, the method further includes:

[0076] A third message sent to the terminal; the third message includes at least the first message, and further includes at least one of the following:

[0077] The second quantity is used to determine the number of first prediction results that the AI ​​function can use for a single input;

[0078] The second resource information is used by the terminal to determine the resource location that is allowed as the first prediction result input to the AI ​​function.

[0079] In some embodiments of the second aspect, the method further includes:

[0080] The network device receives a fourth message sent by the terminal, the fourth message being used to determine whether the first prediction result can be used as an input parameter for the AI ​​function.

[0081] In some embodiments of the second aspect, the fourth information includes one or more of the following:

[0082] The third confidence level is used to indicate the accuracy of the AI ​​function;

[0083] The second indicator is used to indicate that the third confidence level is higher than the sixth threshold;

[0084] The fourth confidence level is the minimum confidence level of the AI ​​function within the second time period;

[0085] The third indication is used to indicate that the built-in confidence level of the AI ​​function remains above the seventh threshold for a second duration.

[0086] The sixth confidence level is the minimum confidence level of the most recent M consecutive outputs of the AI ​​function;

[0087] The fourth indicator is used to indicate that the confidence level of the AI ​​function in the most recent M consecutive outputs is higher than the eighth threshold;

[0088] The third resource information is used to indicate the resource location of the third prediction result, which is the prediction result output by the AI ​​function and related to the fourth information.

[0089] A third aspect provides a parameter determining apparatus, wherein the parameter determining apparatus includes:

[0090] The processing module is configured to determine, based on first information, whether to use the first prediction result as an input parameter for an artificial intelligence (AI) function, wherein the AI ​​function is used to output a prediction result for wireless measurement, and the first prediction result is an output parameter of the AI ​​function.

[0091] In some embodiments of the third aspect, the processing module is configured to determine, when the first information satisfies a first condition, to use the first prediction result as input to the AI ​​function.

[0092] In some embodiments of the third aspect, the first information satisfying the first condition includes one or more of the following:

[0093] The first confidence level is higher than the first threshold;

[0094] The first confidence level remains higher than the second threshold within the first time period;

[0095] The AI ​​function has N consecutive first confidence levels that are higher than the third threshold; where N is a positive integer greater than or equal to 2.

[0096] The first difference is less than the fourth threshold;

[0097] The second confidence level is higher than the fifth threshold.

[0098] In some embodiments of the third aspect, the first prediction result includes multiple prediction results, and the processing module is configured to determine, based on the first information, whether to use the multiple prediction results as input parameters for the AI ​​function; the parameter determination device further includes:

[0099] The sending module is configured to send second information to the network device, the second information including information of a second prediction result; the second prediction result is the prediction result among the plurality of prediction results that serves as the input parameter of the AI ​​function.

[0100] In some embodiments of the third aspect, the apparatus further includes:

[0101] The sending module is configured to send fourth information to the network device, the fourth information being used by the network device to determine whether the first prediction result can be used as an input parameter for the AI ​​function.

[0102] A fourth aspect provides a parameter determining apparatus, wherein the apparatus includes:

[0103] The sending module is configured to send first information to the terminal, the first information being used by the terminal to determine whether to use the first prediction result as an input parameter for an artificial intelligence (AI) function, the AI ​​function being used to output a prediction result for wireless measurement; the first prediction result is the output parameter of the AI ​​function.

[0104] In some embodiments of the fourth aspect, the first prediction result includes multiple prediction results, and the apparatus further includes:

[0105] The receiving module is configured to receive second information sent by the terminal, the second information including information of a second prediction result; the second prediction result is the prediction result among the plurality of prediction results that serves as the input parameter of the AI ​​function.

[0106] In some embodiments of the fourth aspect, the apparatus further includes:

[0107] A sending module is configured to send third information to the terminal; the third information includes at least the first information, and further includes at least one of the following:

[0108] The second quantity is used to determine the number of first prediction results that the AI ​​function can use for a single input;

[0109] The second resource information is used by the terminal to determine the resource location that is allowed as the first prediction result input to the AI ​​function.

[0110] In some embodiments of the fourth aspect, the apparatus further includes:

[0111] The sending module is configured to receive fourth information sent by the terminal, the fourth information being used by the network device to determine whether the first prediction result can be used as an input parameter for the AI ​​function.

[0112] The fifth aspect provides a communication system, wherein the communication system includes: a terminal configured to perform the method provided by any technical solution of the first aspect; and a network device configured to perform the method provided by any technical solution of the second aspect.

[0113] In a sixth aspect, embodiments of this disclosure provide a program product, wherein the program product includes a computer program, which, when executed by a communication device, enables the communication device to perform the methods described in the optional implementations of the first to second aspects.

[0114] In a seventh aspect, embodiments of this disclosure provide a computer program that, when run on a computer, causes the computer to execute the artificial intelligence parameter determination method described in the optional implementations of the first to second aspects.

[0115] It is understood that the aforementioned first device, network device, communication system, program product, and computer program are all used to execute the methods provided in the embodiments of this disclosure. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0116] This disclosure provides a method for determining artificial intelligence parameters, a communication device, a communication system, and a storage medium. This disclosure is not exhaustive, but merely illustrative of some embodiments, and is not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, removing some steps from a particular embodiment can also be implemented as an independent embodiment, and the order of steps in a particular embodiment can be arbitrarily interchanged. Furthermore, the optional implementations in a particular embodiment can be arbitrarily combined; moreover, the embodiments can be arbitrarily combined, for example, some or all steps of different embodiments can be arbitrarily combined, and a particular embodiment can be arbitrarily combined with optional implementations of other embodiments.

[0117] In each of the disclosed embodiments, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of the embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0118] The terminology used in the embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the scope of this disclosure.

[0119] In this embodiment of the disclosure, unless otherwise stated, elements expressed in the singular form, such as "a," "an," "the," "the aforementioned," "this," etc., can mean "one and only one," or "one or more," "at least one," etc. For example, when using articles such as "a," "an," "the," etc. in translation, the noun following the article can be understood as either a singular expression or a plural expression.

[0120] In the embodiments disclosed herein, "multiple" refers to two or more.

[0121] In some embodiments, the terms “at least one of”, “one or more”, “a plurality of”, “multiple”, etc., may be used interchangeably.

[0122] In some embodiments, the notation "at least one of A and B", "A and / or B", "A in one case, B in another", "A in one case, B in another", etc., may include the following technical methods depending on the situation: in some embodiments, A (A is executed regardless of B); in some embodiments, B (B is executed regardless of A); in some embodiments, execution is selected from A and B (A and B are selectively executed); in some embodiments, A and B (both A and B are executed). The same applies when there are more branches such as A, B, C, etc.

[0123] In some embodiments, the notation "A or B" may include the following technical approaches, depending on the circumstances: in some embodiments, A (execution of A regardless of B); in some embodiments, B (execution of B regardless of A); in some embodiments, selective execution from A and B (A and B are selectively executed). The same applies when there are more branches such as A, B, C, etc.

[0124] The prefixes "first," "second," etc., used in the embodiments of this disclosure are merely for distinguishing different descriptive objects and do not impose restrictions on the position, order, priority, quantity, or content of the descriptive objects. The description of the descriptive objects is found in the claims or the context of the embodiments, and the use of prefixes should not constitute unnecessary restrictions. For example, if the descriptive object is a "field," the ordinal numbers preceding "field" in "first field" and "second field" do not restrict the position or order of the "fields." "First" and "second" do not restrict whether the "fields" they modify are in the same message, nor do they restrict the order of "first field" and "second field." Similarly, if the descriptive object is a "level," the ordinal numbers preceding "level" in "first level" and "second level" do not restrict the priority between "levels." Furthermore, the number of descriptive objects is not limited by ordinal numbers and can be one or more. For example, in "first device," the number of "devices" can be one or more. Furthermore, the objects modified by different prefixes can be the same or different. For example, if the object being described is "device", then "first device" and "second device" can be the same device or different devices, and their types can be the same or different. As another example, if the object being described is "information", then "first type of information" and "second type of information" can be the same information or different information, and their content can be the same or different.

[0125] In some embodiments, “including A,” “containing A,” “for indicating A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.

[0126] In some embodiments, terms such as “…”, “determine…”, “in the case of…”, “when…”, “when…”, “if…”, etc. can be used interchangeably.

[0127] In some embodiments, the terms “greater than,” “greater than or equal to,” “not less than,” “more than,” “more than or equal to,” “not less than,” “higher than,” “higher than or equal to,” “not lower than,” and “above” can be used interchangeably, as can the terms “less than,” “less than or equal to,” “not greater than,” “less than,” “less than or equal to,” “not more than,” “lower than,” “lower than or equal to,” “not higher than,” and “below”.

[0128] In some embodiments, devices, etc., can be interpreted as physical or virtual, and their names are not limited to the names recorded in the embodiments. Terms such as “device”, “equipment”, “circuit”, “network element”, “node”, “function”, “unit”, “section”, “system”, “network”, “chip”, “chip system”, “entity”, and “subject” can be used interchangeably.

[0129] In some embodiments, "network" can be interpreted as network-side devices or network functions, such as access network devices and core network devices.

[0130] In some embodiments, the terms "access network device (AN device)," "radio access network device (RAN device)," "base station (BS)," "radio base station," "fixed station," "node," "access point," "transmission point (TP)," "reception point (RP)," "transmission / reception point (TRP)," "panel," "antenna panel," "antenna array," "cell," "macro cell," "small cell," "femto cell," "pico cell," "sector," "cell group," "serving node," "carrier," "component carrier," and "bandwidth part (BWP)" can be used interchangeably.

[0131] In some embodiments, the terms "UE (terminal)," "UE device (terminal device)," "user equipment (UE)," "user UE (user terminal)," "mobile station (MS)," "mobile UE (MT)," "subscriber station," "mobile unit," "subscriber unit," "wireless unit," "remote unit," "mobile device," "wireless device," "wireless communication device," "remote device," "mobile subscriber station," "access UE," "mobile UE," "wireless terminal," "remote UE," "handset," "user agent," "mobile client," and "client" can be used interchangeably.

[0132] In some embodiments, the access network device, core network device, or network device can be replaced by a UE. For example, embodiments of this disclosure can also be applied to structures where communication between the access network device, core network device, or network device and the UE is replaced by communication between multiple UEs (e.g., device-to-device (D2D), vehicle-to-everything (V2X), etc.). In this case, the UE can also be configured to have all or some of the functions of the access network device. Furthermore, terms such as "uplink" and "downlink" can be replaced with terms corresponding to communication between UEs (e.g., "sidelink"). For example, uplink channel, downlink channel, etc., can be replaced with sidelink channel, and uplink link, downlink, etc., can be replaced with sidelink link.

[0133] In some embodiments, the UE can be replaced by an access network device, a core network device, or a network device. In this case, it can also be configured such that the access network device, core network device, or network device has all or some of the functions of the UE.

[0134] In some embodiments, the acquisition of data, information, etc., may comply with the laws and regulations of the country where the location is situated.

[0135] In some embodiments, data, information, etc., may be obtained with the user's consent.

[0136] Furthermore, each element, each row, or each column in the table of this disclosure can be implemented as an independent embodiment, and any combination of any element, any row, or any column can also be implemented as an independent embodiment.

[0137] Figure 1A is a schematic diagram of the architecture of a communication system according to an embodiment of the present disclosure.

[0138] As shown in Figure 1A, the communication system 100 includes a terminal 101 and a network device 102. The network device 102 may include access network equipment and / or core network equipment. The terminal may also be referred to as a UE.

[0139] In some embodiments, terminal 101 includes, but is not limited to, at least one of the following: mobile phone, wearable device, Internet of Things device, car with communication function, smart car, tablet computer, computer with wireless transceiver function, virtual reality (VR) UE device, augmented reality (AR) UE device, wireless UE device in industrial control, wireless UE device in self-driving, wireless UE device in remote medical surgery, wireless UE device in smart grid, wireless UE device in transportation safety, wireless UE device in smart city, and wireless UE device in smart home.

[0140] In some embodiments, UE is also referred to as User Equipment (UE).

[0141] In some embodiments, the access network device may be a node or device that connects the UE to the wireless network. The access network device may include, but is not limited to, at least one of the following in a 5G communication system: evolved Node B (eNB), next generation eNB (ng-eNB), next generation Node B (gNB), node B (NB), home node B (HNB), home evolved node B (HeNB), radio backhaul device, radio network controller (RNC), base station controller (BSC), base transceiver station (BTS), base band unit (BBU), mobile switching center, base station in a 6G communication system, open RAN, cloud RAN, base station in other communication systems, and access node in a Wi-Fi system.

[0142] In some embodiments, the technical methods of this disclosure can be applied to the Open RAN architecture. In this case, the interfaces between or within access network devices involved in the embodiments of this disclosure can be transformed into internal interfaces of Open RAN. The processes and information interactions between these internal interfaces can be implemented by software or programs.

[0143] In some embodiments, the access network device may be composed of a central unit (CU) and a distributed unit (DU). The CU may also be called a control unit. The CU-DU structure can separate the protocol layer of the access network device. Some of the protocol layer functions are centrally controlled by the CU, while the remaining part or all of the protocol layer functions are distributed in the DU and centrally controlled by the CU. However, this is not the only possibility.

[0144] In some embodiments, the core network equipment can be a single device, including a first network element, or it can be multiple devices or a group of devices, each including a first network element. Network elements can be virtual or physical. The core network includes, for example, at least one of an Evolved Packet Core (EPC), a 5G Core Network (5GCN), and a Next Generation Core (NGC).

[0145] It is understood that the communication system described in this disclosure is for the purpose of more clearly illustrating the technical methods of this disclosure and does not constitute a limitation on the technical methods provided in this disclosure. As those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical methods provided in this disclosure are also applicable to similar technical problems.

[0146] The following embodiments of this disclosure can be applied to the communication system 100 shown in FIG1A, or to some of the main bodies, but are not limited thereto. The main bodies shown in FIG1A are illustrative. The communication system may include all or some of the main bodies in FIG1A, or it may include other main bodies outside of FIG1A. The number and form of each main body are arbitrary. The connection relationship between the main bodies is illustrative. The main bodies may not be connected or may be connected. The connection can be in any way, it can be a direct connection or an indirect connection, it can be a wired connection or a wireless connection.

[0147] The embodiments disclosed herein can be applied to Long Term Evolution (LTE), LTE-Advanced (LTE-A), LTE-Beyond (LTE-B), SUPER 3G, IMT-Advanced, 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 5G new radio (NR), Future Radio Access (FRA), New-Radio Access Technology (RAT), New Radio (NR), New radio access (NX), Future generation radio access (FX), Global System for Mobile communications (GSM), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), and IEEE 802.20, Ultra-Wideband (UWB), Bluetooth (a registered trademark), Public Land Mobile Network (PLMN) networks, Device-to-Device (D2D) systems, Machine-to-Machine (M2M) systems, Internet of Things (IoT) systems, Vehicle-to-Everything (V2X) systems, systems utilizing configuration methods of other resources, and next-generation systems extended from them, etc. Furthermore, multiple systems can be combined (e.g., LTE and NR can be combined).

[0148] Terminal wireless communication networks can use artificial intelligence (AI) for prediction and reasoning to improve system performance. Training AI models requires collecting a large amount of data, and the data required varies depending on the application scenario. Application scenarios can include mobile communication system processes such as beam management, channel state information (CSI) reporting, CSI compression, positioning, handover, mobility management, and radio resource management.

[0149] During mobility operations, a terminal can predict cell measurement results, handover target cells, or mobility events. Predicting future cell measurement results is called temporal prediction. Alternatively, predicting the measurement results of cells that have not yet been measured is called spatial prediction. Mobility events include met measurement reporting conditions, handover failures, cell dwell time, and radio link failures.

[0150] In communication systems based on related technologies, terminals need to receive and measure reference signals transmitted through the network at time-frequency locations, and then obtain the corresponding measurement results. This process consumes the terminal's power. AI models can predict future measurement results based on historical measurement results. At time-frequency locations where measurement results are obtained through prediction, the terminal can avoid performing measurements, thereby reducing energy consumption caused by measurement.

[0151] AI model prediction requires the terminal to perform measurements to obtain actual measurement results, which are then used as input to the AI ​​to predict future measurement results. (Refer to Figure 1B.)

[0152] First, the terminal performs measurements to obtain the actual measurement results. Then, these results are used as input to the AI ​​so that the AI ​​function can output a prediction result. This method can reduce the number of measurements performed by the terminal by one-third.

[0153] The inference results (i.e. prediction results) output by AI can be associated with an indicator that indicates the degree of certainty that the AI ​​model's inference results match the true values. This indicator can be confidence, accuracy, or probability.

[0154] It is necessary to monitor the performance of AI. If the performance degrades, the AI ​​function or AI model needs to be replaced or the AI ​​function needs to be deactivated.

[0155] In the process of AI predicting measurement results, the terminal needs to measure and predict the measurement results at the same time-frequency location, and calculate the difference. The difference can be used to monitor the performance of AI prediction.

[0156] If the terminal's prediction results can also be used as input parameters for the next prediction, then the terminal's measurements can be further reduced. Referring to Figure 1C, by using some or all of the prediction results as input parameters for the AI ​​function, the terminal's measurements can be reduced by half. However, prediction results contain errors, which may cause the AI ​​prediction results to also contain errors, and these errors may accumulate, leading to a decrease in prediction accuracy.

[0157] In view of this, as shown in FIG2A, this disclosure provides a method for using AI functions. This method can be executed by the communication system shown in FIG1A. The method may include:

[0158] S2101: The network device sends third-party information to the terminal.

[0159] In some embodiments, network devices broadcast, multicast, or unicast third-party information.

[0160] In some embodiments, the network device sends a Radio Resource Control (RRC) message, a Media Access Control (MAC) message, or Downlink Control Information (DCI) message to the terminal. The RRC message, MAC message, or DCI message contains third-party information.

[0161] In some embodiments, the third information includes at least the first information. In some embodiments, the first information is used by the terminal to determine whether to use the first prediction result as an input parameter for the AI ​​function.

[0162] In some embodiments, the third information may also include, but is not limited to, one or more of the following:

[0163] The second quantity is used to determine the number of first prediction results that the AI ​​function can use for a single input;

[0164] The second resource information is used by the terminal to determine the resource location that is allowed as the first prediction result input to the AI ​​function.

[0165] In some embodiments, one input to the AI ​​function requires X inputs, and a second quantity may indicate the number of first predictions allowed in one input to the AI ​​function. For example, the second quantity may be Y, which may be a natural number or a positive integer. Exemplarily, Y may be less than or equal to X.

[0166] In some embodiments, the second resource information is used to indicate a second resource location. This second resource location includes, but is not limited to, frequency domain resources and / or time domain resources.

[0167] In some embodiments, the second resource information is used by the terminal to determine resource locations that are allowed as first prediction results input to the AI ​​function.

[0168] For example, if the second resource information can indicate that the first prediction result corresponding to Z resource locations is used as the input parameter of the AI ​​function, then in this case, other time-domain locations besides the Z resource locations, even if the prediction result is highly accurate, cannot be used as the input parameter of the AI ​​function.

[0169] For example, the second resource information may also indicate that the first prediction results corresponding to the L resource locations are prohibited from being used as input parameters for the AI ​​function. In this case, the other first prediction results besides these L resource locations can satisfy the conditions required for other input parameters of the AI ​​function.

[0170] In some embodiments, the first prediction result can be any prediction result previously obtained and required by the AI ​​function. For example, the terminal inputs the prediction result at a second time step into the AI ​​function at a first time step; in this case, the prediction result at the second time step is one type of the first prediction result, and the second time step may be later than the first time step. For example, the first prediction result can be a prediction result output by the AI ​​function at a historical time step.

[0171] In some embodiments, the AI ​​functionality may be the ability to perform predictions of wireless measurements using one or more AI models.

[0172] In some embodiments, the AI ​​function is used to output predictions for wireless measurements.

[0173] In some embodiments, wireless measurement includes, but is not limited to, various measurements of wireless signals. Exemplarily, the wireless measurement may include, but is not limited to, one or more of the following: beam measurement; cell measurement; positioning reference signal measurement.

[0174] In some embodiments, beam measurement can be used by the terminal to determine a good beam for communication with network devices based on the measurement results. Here, a good beam refers to a beam with signal quality above a threshold or optimal.

[0175] In some embodiments, cell measurement can be used to determine the serving cell or alternative serving cells based on the measurement results. For example, during cell handover or cell reselection, the measurement results of cell measurement can be used by network devices to select a target cell for cell handover or cell reselection for the terminal.

[0176] In some embodiments, in carrier aggregation or multi-connectivity (e.g., dual-connectivity) scenarios, cell measurements can also be used to determine the terminal's primary cell, secondary cell, or alternative cell. The alternative cell can subsequently be changed to the terminal's primary or secondary cell depending on the terminal's movement or the change in the wireless environment.

[0177] In some embodiments, the results of the wireless measurement can be used for Radio Resource Management (RRM). The results of the wireless measurement can be used for Radio Link Management (RLM).

[0178] In some embodiments, when a network device sends first information, the terminal receives the first information accordingly. For example, the terminal receives an RRC message, a MAC message, or a DCI message. The first information may be included in the RRC message, MAC message, or DCI message.

[0179] In some embodiments, the terminal receives first information broadcast, multicast, or unicast by the network device.

[0180] In some embodiments, the first information includes at least one of the following: the output performance metric of the AI ​​function; and a first indication, which indicates whether the first prediction result can be used as an input parameter of the AI ​​function.

[0181] In some embodiments, the output performance metric is used to describe or indicate the performance of the AI ​​function. If the AI ​​function performs well, it means that the prediction results output by the AI ​​function are good. In this case, using the first prediction result as the input parameter of the AI ​​function means that even if the first prediction result accumulates some prediction errors, its impact on the next prediction result is not significant, or the next prediction result is still good.

[0182] In some embodiments, the output performance metrics include one or more of the following: a first confidence level, used to indicate the accuracy of the AI ​​function; a first difference, used to indicate the difference between the first prediction result and the actual measurement result; and a second confidence level, used to indicate the accuracy of the first prediction result.

[0183] For example, the first confidence level is the overall accuracy of the AI ​​function; for instance, the first confidence level could be the average accuracy or the lowest pre-accuracy of the AI ​​function over a period of time.

[0184] In some embodiments, the first prediction result is the output parameter of the AI ​​function.

[0185] For example, the first prediction result can be a specific prediction result, such as a prediction result at a specific time or a prediction result of a prediction output of an AI function. In this case, the difference between the prediction result and the actual measurement result can be clearly determined. At this time, the magnitude of the first difference can also indicate the output performance of the AI ​​function, that is, the first difference can also be used as one of the output performance indicators of the AI ​​function.

[0186] In some embodiments, the second confidence level indicates the accuracy of the first prediction result. In some embodiments, for example, based on long-term statistical data, the AI ​​function has an average confidence level, but the actual confidence level of the AI ​​function fluctuates to some extent at different times and / or under different circumstances. Therefore, the confidence level (i.e., the second confidence level) of the first prediction result prepared as input to the AI ​​function can be statistically calculated. In this case, the second confidence level indicates the confidence level of the first prediction result.

[0187] In some embodiments, the network device may send a first indication to the terminal based on the output performance metrics of the AI ​​function. The first indication may be an explicit indication of whether a first prediction result can be used as input for the AI ​​function.

[0188] In some embodiments, the network device may generate a first indication based on the output performance metrics of the AI ​​function, and may also combine the current load status of the terminal and / or the network environment status.

[0189] For example, the first indication may be one or more bits. For instance, if the first indication has a first value, it means that the network device instructs the terminal to use the first prediction result as an input parameter for the AI ​​function. As another example, if the first indication has a second value, it means that the network device cannot use the first prediction result as an input parameter for the AI ​​function.

[0190] In some embodiments, after receiving the first information, the terminal can determine whether to use the first prediction result as the input parameter of the AI ​​function based on the first information.

[0191] It is worth noting that step S2101 can be optional. The reason is that in some cases, the terminal can generate the first information based on the usage of its own AI functions, or the terminal can receive the first information from the application server via WiFi or a wired network. Therefore, there are multiple ways for the terminal to obtain the first information, not limited to receiving it from network devices such as base stations based on wireless communication technology (mobile communication technology).

[0192] S2102: The terminal determines whether to use the first prediction result as an input parameter for the AI ​​function.

[0193] In some embodiments, the input parameters of the terminal AI function are determined based on the first information to determine whether to use the first prediction result as the input parameter of the AI ​​function.

[0194] In some embodiments, the first information satisfying the first condition includes one or more of the following: the first confidence level is higher than a first threshold; the first confidence level is continuously higher than a second threshold within a first time period; the first confidence level of the AI ​​function is higher than a third threshold for N consecutive times; N is a positive integer greater than or equal to 2; the first difference is less than a fourth threshold; and the second confidence level is higher than a fifth threshold.

[0195] In some embodiments, the values ​​of the first threshold, the second threshold, the third threshold, and the fifth threshold may be the same or different.

[0196] In some embodiments, considering that the first confidence level indicates the overall accuracy of the AI ​​function, or the minimum accuracy of the AI ​​function as indicated by the first confidence level, the first threshold may be slightly lower than the fifth threshold, etc. Of course, this is just an example, and the actual implementation is not limited to this example.

[0197] In some embodiments, the AI ​​function has multiple first confidence levels within a first time period. If all of these first confidence levels are higher than a second threshold within the first time period, it indicates that the AI ​​function has high accuracy during this period. This embodiment considers whether the first confidence levels remain higher than the second threshold within the first time period. In this case, the second threshold may be equal to or slightly lower than the first threshold.

[0198] In summary, the values ​​of the first threshold, the second threshold, the third threshold, and the fifth threshold can be the same or different.

[0199] The fourth threshold is the difference threshold. For example, the fourth threshold can be understood as the maximum difference that the first prediction result is allowed as the input of the AI ​​function. If the first difference is less than the fourth threshold, it means that the output performance of the AI ​​function in the current time period is good, and it can be considered to meet the first condition.

[0200] In some instances, the output performance metrics of an AI function can be used to determine whether the conditions for serving as input parameters for an AI function are met; however, examples of the first condition are not limited to any of the conditions mentioned above.

[0201] In some embodiments, if an AI function output includes a set of prediction results, and the set of prediction results may include multiple first prediction results, then the first condition for whether a certain first prediction result can be used as an input parameter of the AI ​​function may be: the accuracy or confidence of each first prediction result in the set of prediction results is greater than a threshold.

[0202] In some embodiments, if the terminal determines that the first prediction result is allowed to be used as the input parameter of the AI ​​function, the terminal will use the corresponding first prediction result as the input parameter of the AI ​​function, thereby reducing the probability that the terminal obtains the actual measurement result through actual wireless measurement as the input of the AI ​​function, thereby reducing the number of wireless measurements and / or the power consumption of wireless measurement, etc.

[0203] In some embodiments, if the terminal determines that the first prediction result is not allowed to be used as the input parameter of the AI ​​function, the terminal does not use the corresponding first prediction result as the input parameter of the AI ​​function, thereby reducing the problem of poor accuracy of the AI ​​function output caused by inappropriate prediction results as input parameters of the AI ​​function, and thus poor communication quality of the terminal.

[0204] In some embodiments, if the terminal determines that the first prediction result is not allowed to be used as the input parameter of the AI ​​function, in order to reduce the actual measurement in the next time period, the terminal can perform wireless measurement in the current time period, so that the actual measurement result can be used as the input parameter of the AI ​​function, thereby reducing the actual wireless measurement in the next time period.

[0205] S2103: The terminal sends a second message to the network device.

[0206] In some embodiments, the terminal sends a Radio Resource Control (RRC) message, a Media Access Control (MAC) message, or Uplink Control Information (UCI) to the network device. The RRC message, MAC message, or UCI includes second information.

[0207] In some embodiments, the second information includes information about the second prediction result. In some embodiments, the second prediction result is the prediction result among the plurality of prediction results that serves as input parameters for the AI ​​function.

[0208] In some embodiments, the second information is used to indicate one or more of the following:

[0209] The number of the second prediction results;

[0210] The resource location corresponding to the second prediction result.

[0211] In some embodiments, the second prediction result is the prediction result among M first prediction results in a single output of the AI ​​function that satisfies the condition of being usable as input to the AI ​​function, where M is a positive integer.

[0212] In some embodiments, any two of the M first prediction results are of the same type, and any two of the first prediction results are associated with different resource locations.

[0213] For example, the AI ​​function outputs five prediction results at once. These five prediction results can be of the same type, such as beam quality or cell quality, but the resource locations associated with these five prediction results are different. The resource locations here can include frequency domain locations and / or time domain locations.

[0214] In some embodiments, any two of the M first prediction results are of different types.

[0215] For example, during beam measurement, the AI ​​function may output multiple first prediction results, and these first prediction results are of different types, such as corresponding measurement quantities or measurement indicators failing to meet standards. These multiple first prediction results may include one or more of the following: signal-to-interference-plus-noise ratio (SINR), reference signal reception quality, and / or angle of arrival. In this case, any two first prediction results will be of different types.

[0216] It is worth noting that in some embodiments, S2103 is an optional step. For example, the terminal itself only needs to determine whether it can determine which first prediction results can be used as input parameters for the AI ​​function, and it is not necessary to tell the network device. If the terminal sends the second prediction results to the network device through the second information, then after receiving the second information, the network device can more objectively evaluate the accuracy of the third prediction result output by the AI ​​function when the second prediction results are used as input parameters for the AI ​​function, and / or the impact of the second prediction results as input parameters for the AI ​​function on the output performance of the AI ​​function. That is, the second information can be used by the network device to determine the third information to be sent to the terminal at the next moment.

[0217] The corresponding network device is able to receive the second information sent by the terminal. For example, the network device receives an RRC message, MAC message, or UCI message sent by the terminal. This RRC message, MAC message, or UCI message includes the second information.

[0218] In some embodiments, the third information provides a range of first prediction results that can be used as input parameters for AI functions. In this case, the second prediction result may be one or more of the first prediction results indicated by the third information. By sending the second information, the terminal can inform the network device which specific first prediction results the terminal used as input parameters for the AI ​​functions.

[0219] S2104: The terminal sends the fourth information to the network device.

[0220] In some embodiments, the fourth information is used by the network device to determine whether the first prediction result can be used as an input parameter for the AI ​​function.

[0221] In some embodiments, the RRC message, MAC message, or UCI sent by the terminal to the network device may include fourth information.

[0222] In some embodiments, S2104 is an optional step. For example, the terminal may generate the first information itself or receive the first information from another device other than the network device, instead of receiving the first information from the network device. In this case, it is not necessary to provide the fourth information to the network device.

[0223] In other embodiments, the execution order of S2104 is not limited to after S2103. For example, if the terminal receives third information from the network device, S2104 can be executed before S2101, which facilitates the network device sending the third information to the terminal based on the fourth information. In some embodiments, S2014 can also be executed after S2103. The terminal receives the third information at time T0 and determines a first prediction result that can be used as input for the AI ​​function at time T1 based on the third information. The terminal can send the fourth information to the network device at any time after time T0, and this fourth information can serve as the basis for the network device to send the third information at time T2. Time T2 is later than time T1. For example, the third information reported at time T1 can be used by the network device to determine whether the third information sent at time T0 is appropriate, and / or whether it needs to optimize its subsequent generation of third information.

[0224] In some embodiments, the network device may generate the third information without referring to the fourth information. Instead, the network device may determine the third information by referring to the terminal's beam selection result, cell selection result, and / or RRM result. This again illustrates that sending the fourth information to the network device is an optional step. In summary, if the terminal sends the fourth information to the network device, it means that the network device will receive the fourth information.

[0225] In some embodiments, any one of S2101 to S2104 can be implemented individually or any two can be implemented in combination. In combined implementations, the order of execution steps of S2101 to S2104 can be changed as needed. In some embodiments, as shown in FIG2B, S2104 can be executed before S2101. As shown in FIG2C, the transmission of the second information and / or the fourth information of the terminal are optional steps.

[0226] This disclosure provides a parameter determination method aimed at reducing the decrease in accuracy caused by using AI predictions as input for the next prediction.

[0227] Option 1: The terminal determines whether the measurement results obtained from the prediction can be used as input for the next AI prediction based on the first information, and the AI ​​predicts the measurement results of the future time and frequency position.

[0228] For example, the measurement result can be a cell measurement result or a beam measurement result.

[0229] For example, the AI ​​predicts future measurement results. For example, the terminal does not perform a measurement at the predicted time-frequency location of the measurement result.

[0230] Option 2: The first information is the confidence level of the AI ​​output. If the confidence level of the AI ​​output meets at least one of the following conditions, then the AI ​​output can be used as input for the next AI prediction:

[0231] a. Higher than the first value;

[0232] b. Continuously exceeds the first value within the first time period;

[0233] c. The confidence level of the AI ​​output is higher than the first value for N consecutive times.

[0234] It is worth noting that the content of option 2 can serve as a further limitation on the first piece of information in option 1.

[0235] Option 3: The first value, the first duration, and / or the value of N can be specified by the protocol or sent to the terminal by the network. Option 3 can be a further limitation of Option 2.

[0236] Option 4: The first information can be a performance metric of the AI ​​prediction result. If the performance metric meets certain requirements, the AI ​​output can be used as input for the next AI prediction. For example, the performance metric can be the difference between the predicted result and the actual measurement result. If the difference is less than a second value, it is determined that the requirements are met. It is worth noting that Option 4 can be used in combination with Option 1, Option 2, and / or Option 3.

[0237] Option 5: The terminal sends a second message to the network. This second message can indicate whether the prediction result should be used as input for the next AI. It is worth noting that Option 5 can be used in combination with Options 1, 2, 3, and / or 4.

[0238] Option 6: The second information may also indicate any of the following:

[0239] a. The number of prediction results used as AI inputs. For example, if the AI ​​predicts two measurement results, and only the confidence level of the second output meets the requirements, then one prediction result can be used as the input for the next AI prediction.

[0240] b. The time-frequency location that can be used as AI input for predicted values. For example, if the AI ​​predicts and outputs 5 measurement results, and only the confidence level of the second output meets the requirements, then the time-frequency location corresponding to the measurement result of the second output is reported.

[0241] Option 6 can be used in combination with Option 1, Option 2, Option 3, Option 4 and / or Option 5.

[0242] Option 7: The first information is sent from the network to the terminal, indicating whether the terminal can use the prediction result as input for the next AI prediction. Option 7 can be used in combination with any of Options 1 through 6.

[0243] Option 8: The first information may indicate any of the following: a. the number of prediction results used as AI inputs; b. the time-frequency location of the prediction values ​​that can be used as AI inputs. Option 8 may be used in combination with any of Options 1 through 7.

[0244] Option 9: The terminal reports third information to the network, which may indicate any of the following:

[0245] a. The AI's output is higher than the second value;

[0246] b. The AI's output remained higher than the second value throughout the second duration;

[0247] c. The confidence level of the AI ​​output is higher than the second value for M consecutive times;

[0248] d. The time-frequency position of the AI ​​output described in a, b, and c above.

[0249] Option 9 can be used in combination with any one of options 1 through 8.

[0250] Option 10: The second value, the second duration, and the value of M can be specified by the protocol or sent to the terminal by the network. Option 10 can be used in combination with any of options 1 through 9.

[0251] This disclosure also provides apparatus for implementing any of the above methods. For example, an apparatus is provided that includes units or modules for implementing the steps performed by the UE in any of the above methods. Alternatively, another apparatus is provided that includes units or modules for implementing the steps performed by a network device (e.g., an access network device, or a core network device) in any of the above methods.

[0252] It should be understood that the division of units or modules in the above device is only a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, the units or modules in the device can be implemented by a processor calling software: for example, the device includes a processor connected to a memory containing instructions. The processor calls the instructions stored in the memory to implement any of the above methods or to implement the functions of the units or modules in the above device. The processor can be, for example, a general-purpose processor, such as a Central Processing Unit (CPU) or a microprocessor, and the memory can be internal or external to the device. Alternatively, the units or modules in the device can be implemented in the form of hardware circuits. The functionality of some or all of the units or modules can be achieved through the design of these hardware circuits, which can be understood as one or more processors. For example, in one implementation, the hardware circuit is an application-specific integrated circuit (ASIC). The functionality of some or all of the units or modules is achieved through the design of the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented using a programmable logic device (PLD). Taking a field-programmable gate array (FPGA) as an example, it can include a large number of logic gates. The connection relationships between the logic gates are configured through a configuration file, thereby achieving the functionality of some or all of the units or modules. All units or modules of the above device can be implemented entirely through processor-called software, entirely through hardware circuits, or partially through processor-called software with the remaining parts implemented through hardware circuits.

[0253] In this disclosure, the processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a Central Processing Unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a type of microprocessor), or a digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. The logical relationships of the aforementioned hardware circuits are fixed or reconfigurable. For example, the processor is a hardware circuit implemented as an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units or modules. Furthermore, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a Neural Network Processing Unit (NPU), a Tensor Processing Unit (TPU), or a Deep Learning Processing Unit (DPU). Unit, DPU, etc.

[0254] As shown in Figure 3A, this embodiment of the present disclosure provides a parameter determination device, wherein the terminal includes:

[0255] The processing module 3101 is configured to determine, based on the first information, whether to use the first prediction result as an input parameter for an artificial intelligence (AI) function, wherein the AI ​​function is used to output the prediction result of wireless measurement, and the first prediction result is the output parameter of the AI ​​function.

[0256] In some embodiments, the terminal further includes a transmitting module and / or a receiving module.

[0257] In some embodiments, the transmitting module and / or receiving module may correspond to the network interface and / or transceiver antenna of the terminal.

[0258] In some embodiments, the processing module can be used by the terminal to execute information processing-related steps in any artificial intelligence parameter determination method.

[0259] In some embodiments, the sending module can be used by the terminal to execute information sending-related steps in any artificial intelligence parameter determination method.

[0260] In some embodiments, the receiving module can be used by the terminal to perform information transmission-related steps in any artificial intelligence parameter determination method.

[0261] In some embodiments, the first information includes at least one of the following:

[0262] The output performance metrics of the AI ​​function;

[0263] A first indication is provided to indicate whether the first prediction result can be used as an input parameter for the AI ​​function.

[0264] In some embodiments, the output performance metrics include one or more of the following:

[0265] The first confidence level is used to indicate the accuracy of the AI ​​function;

[0266] The first difference is used to indicate the difference between the first prediction result and the actual measurement result;

[0267] The second confidence level is used to indicate the accuracy of the first prediction result.

[0268] In some embodiments, determining whether to use the first prediction result as an input parameter for the AI ​​function based on the first information includes:

[0269] If the first information satisfies the first condition, it is determined that the first prediction result will be used as the input of the AI ​​function.

[0270] In some embodiments, the first information satisfies a first condition, including one or more of the following:

[0271] The first confidence level is higher than the first threshold;

[0272] The first confidence level remains higher than the second threshold within the first time period;

[0273] The AI ​​function has N consecutive first confidence levels that are higher than the third threshold; where N is a positive integer greater than or equal to 2.

[0274] The first difference is less than the fourth threshold;

[0275] The second confidence level is higher than the fifth threshold.

[0276] In some embodiments, the sending module is configured to send second information to a network device, the second information including information of a second prediction result; the second prediction result is the prediction result among the plurality of prediction results that serves as the input parameter of the AI ​​function.

[0277] In some embodiments, the second information is used to indicate one or more of the following:

[0278] The number of the second prediction results;

[0279] The resource location corresponding to the second prediction result.

[0280] In some embodiments, any two prediction results among the plurality of prediction results are of the same type and are associated with different resource locations; or, any two prediction results among the plurality of prediction results are of different types.

[0281] In some embodiments, the receiving module is configured to receive third information sent by a network device; the third information includes at least the first information.

[0282] In some embodiments, the third information further includes one or more of the following;

[0283] The second quantity is used to determine the number of first prediction results that the AI ​​function can use for a single input;

[0284] The second resource information is used by the terminal to determine the resource location that is allowed as the first prediction result input to the AI ​​function.

[0285] In some embodiments, the sending module is configured to send fourth information to a network device, the fourth information being used by the network device to determine whether the first prediction result can be used as an input parameter for an AI function.

[0286] In some embodiments, the fourth information includes one or more of the following:

[0287] The third confidence level is used to indicate the accuracy of the AI ​​function;

[0288] The second indicator is used to indicate that the third confidence level is higher than the sixth threshold;

[0289] The fourth confidence level is the minimum confidence level of the AI ​​function within the second time period;

[0290] The third indication is used to indicate that the built-in confidence level of the AI ​​function remains above the seventh threshold for a second duration.

[0291] The sixth confidence level is the minimum confidence level of the most recent M consecutive outputs of the AI ​​function;

[0292] The fourth indicator is used to indicate that the confidence level of the AI ​​function in the most recent M consecutive outputs is higher than the eighth threshold;

[0293] The third resource information is used to indicate the resource location of the third prediction result, which is the prediction result output by the AI ​​function and related to the fourth information.

[0294] As shown in Figure 3B, this embodiment of the present disclosure provides a parameter determination device, which may include:

[0295] The sending module 3201 is configured as a sending module and is configured to send first information to the terminal. The first information is used by the terminal to determine whether to use the first prediction result as an input parameter of the artificial intelligence (AI) function. The AI ​​function is used to output the prediction result of the wireless measurement. The first prediction result is the output parameter of the AI ​​function.

[0296] In some embodiments, the parameter determination device may further include a processing module and / or a receiving module. In some embodiments, the transmitting module and / or receiving module may correspond to a network interface and / or transceiver antenna of the parameter determination device. In some embodiments, the processing module may be used by the parameter determination device to perform information processing-related steps in any artificial intelligence parameter determination method. In some embodiments, the transmitting module may be used by the parameter determination device to perform information transmission-related steps in any artificial intelligence parameter determination method. In some embodiments, the receiving module may be used by a network device to perform information transmission-related steps in any artificial intelligence parameter determination method.

[0297] In some embodiments, the first information includes at least one of the following:

[0298] The output performance metrics of the AI ​​function;

[0299] A first indication is provided to indicate whether the first prediction result can be used as an input parameter for the AI ​​function.

[0300] In some embodiments, the output performance metrics include one or more of the following:

[0301] The first confidence level is used to indicate the accuracy of the AI ​​function;

[0302] The first difference is used to indicate the difference between the first prediction result and the actual measurement result;

[0303] The second confidence level is used to indicate the accuracy of the first prediction result.

[0304] In some embodiments, the receiving module is configured to receive second information sent by the terminal, the second information including information of a second prediction result; the second prediction result is the prediction result among the plurality of prediction results that serves as the input parameter of the AI ​​function.

[0305] In some embodiments, the second information is used to indicate one or more of the following:

[0306] The number of the second prediction results;

[0307] The resource location corresponding to the second prediction result includes one or more of the first time domain location and the first frequency domain location.

[0308] In some embodiments, any two prediction results among the plurality of prediction results are of the same type, and the resource locations associated with any two prediction results are different; or, any two prediction results among the plurality of prediction results are of different types. In some embodiments, the sending module is configured to send third information to the terminal; the third information includes at least the first information, and the third information further includes at least one of the following:

[0309] The second quantity is used to determine the number of first prediction results that the AI ​​function can use for a single input;

[0310] The second resource information is used by the terminal to determine the resource location that is allowed as the first prediction result input to the AI ​​function.

[0311] In some embodiments, the receiving module is configured to receive fourth information sent by the terminal, the fourth information being used by the network device to determine whether the first prediction result can be used as an input parameter for the AI ​​function.

[0312] In some embodiments, the fourth information includes one or more of the following:

[0313] The third confidence level is used to indicate the accuracy of the AI ​​function;

[0314] The second indicator is used to indicate that the third confidence level is higher than the sixth threshold;

[0315] The fourth confidence level is the minimum confidence level of the AI ​​function within the second time period;

[0316] The third indication is used to indicate that the built-in confidence level of the AI ​​function remains above the seventh threshold for a second duration.

[0317] The sixth confidence level is the minimum confidence level of the most recent M consecutive outputs of the AI ​​function;

[0318] The fourth indicator is used to indicate that the confidence level of the AI ​​function in the most recent M consecutive outputs is higher than the eighth threshold;

[0319] The third resource information is used to indicate the resource location of the third prediction result, which is the prediction result output by the AI ​​function and related to the fourth information.

[0320] This disclosure also provides a communication device, which may include one or more processors; wherein the processors are configured to invoke instructions to cause the communication device to execute an artificial intelligence parameter determination method and / or an artificial intelligence parameter determination method achievable in any of the foregoing embodiments.

[0321] In some embodiments, as shown in FIG4A and / or FIG4B, the communication device 8100 further includes one or more memories 8102 for storing instructions. Optionally, all or part of the memories 8102 may also be located outside the communication device 8100.

[0322] The communication device may be the aforementioned UE or network device. In some embodiments, the network device may be a primary node and / or a secondary node.

[0323] In some embodiments, the communication device 8100 further includes one or more transceivers 8103. When the communication device 8100 includes one or more transceivers 8103, the communication steps such as sending and receiving in the above method are performed by the transceivers 8103, and other steps are performed by the processor 8101.

[0324] In some embodiments, a transceiver may include a receiver and a transmitter, which may be separate or integrated. Optionally, the terms transceiver, transceiver unit, transceiver, transceiver circuit, etc., may be used interchangeably; the terms transmitter, transmitting unit, transmitter, transmitting circuit, etc., may be used interchangeably; and the terms receiver, receiving unit, receiver, receiving circuit, etc., may be used interchangeably.

[0325] Optionally, the communication device 8100 further includes one or more interface circuits 8104, which are connected to the memory 8102. The interface circuits 8104 can be used to receive signals from the memory 8102 or other devices, and can be used to send signals to the memory 8102 or other devices. For example, the interface circuits 8104 can read instructions stored in the memory 8102 and send the instructions to the processor 8101.

[0326] The communication device 8100 described in the above embodiments may be a network device or a UE, but the scope of the communication device 8100 described in this disclosure is not limited thereto, and the structure of the communication device 8100 may not be limited by FIG. 4A. The communication device may be a standalone device or may be part of a larger device. For example, the communication device may be: (1) a standalone integrated circuit IC, or chip, or chip system or subsystem; (2) a collection of one or more ICs, optionally, the IC collection may also include storage components for storing data and programs; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a receiver, UE device, smart UE device, cellular phone, wireless device, handheld device, mobile unit, vehicle device, network device, cloud device, artificial intelligence device, etc.; (6) others, etc.

[0327] Figure 4B is a schematic diagram of the structure of chip 8200 provided in an embodiment of this disclosure. For cases where the communication device 8100 can be a chip or a chip system, please refer to the schematic diagram of chip 8200 shown in Figure 4B, but it is not limited thereto.

[0328] Chip 8200 includes one or more processors 8201, which are used to invoke instructions to cause chip 8200 to execute any of the above artificial intelligence parameter determination methods.

[0329] In some embodiments, chip 8200 further includes one or more interface circuits 8202 connected to memory 8203. Interface circuits 8202 can be used to receive signals from memory 8203 or other devices, and can also be used to send signals to memory 8203 or other devices. For example, interface circuit 8202 can read instructions stored in memory 8203 and send those instructions to processor 8201. Optionally, terms such as interface circuit, interface, transceiver pin, and transceiver can be used interchangeably.

[0330] In some embodiments, chip 8200 further includes one or more memories 8203 for storing instructions. Optionally, all or part of the memories 8203 may be located outside of chip 8200.

[0331] This disclosure also provides a storage medium storing instructions that, when executed on a communication device 8100, cause the communication device 8100 to perform any of the methods described above. Optionally, the storage medium is an electronic storage medium. Optionally, the storage medium is a computer-readable storage medium, but it can also be a storage medium readable by other devices. Optionally, the storage medium can be a non-transitory storage medium, but it can also be a temporary storage medium.

[0332] This disclosure also provides a program product, which, when executed by a communication device 8100, causes the communication device 8100 to execute any of the above-mentioned artificial intelligence parameter determination methods. Optionally, the program product is a computer program product.

[0333] This disclosure also provides a computer program that, when run on a computer, causes the computer to execute any of the above-described artificial intelligence parameter determination methods.

[0334] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the embodiments of this disclosure that follow the general principles of the embodiments of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the embodiments of this disclosure are indicated by the following claims.

[0335] It should be understood that the embodiments disclosed herein are not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from their scope. The scope of the embodiments disclosed herein is limited only by the appended claims.

Claims

1. A method for determining parameters, wherein, The method, executed by a terminal, includes: Based on the first information, it is determined whether to use the first prediction result as an input parameter for the artificial intelligence (AI) function, which is used to output the prediction result of wireless measurement, and the first prediction result is the output parameter of the AI ​​function.

2. The method according to claim 1, wherein, The first information includes at least one of the following: The output performance metrics of the AI ​​function; A first indication is provided to indicate whether the first prediction result can be used as an input parameter for the AI ​​function.

3. The method according to claim 2, wherein, The output performance metrics include one or more of the following: The first confidence level is used to indicate the accuracy of the AI ​​function; The first difference is used to indicate the difference between the first prediction result and the actual measurement result; The second confidence level is used to indicate the accuracy of the first prediction result.

4. The method according to any one of claims 1 to 3, wherein, The step of determining whether to use the first prediction result as an input parameter for the artificial intelligence (AI) function based on the first information includes: If the first information satisfies the first condition, it is determined that the first prediction result will be used as the input of the AI ​​function.

5. The method according to claim 4, wherein, The first information satisfies one or more of the following conditions: The first confidence level is higher than the first threshold; The first confidence level remains higher than the second threshold within the first time period; The AI ​​function has N consecutive first confidence levels that are higher than the third threshold; where N is a positive integer greater than or equal to 2. The first difference is less than the fourth threshold; The second confidence level is higher than the fifth threshold.

6. The method according to any one of claims 1 to 5, wherein, The first prediction result includes multiple prediction results, and the step of determining whether to use the first prediction result as an input parameter for the artificial intelligence (AI) function based on the first information includes: Based on the first information, determine whether to use the multiple prediction results as input parameters for the AI ​​function; The method further includes: Send a second message to the network device, the second message including information about a second prediction result; the second prediction result is the prediction result among the plurality of prediction results that serves as the input parameter for the AI ​​function.

7. The method according to claim 6, wherein, The second information is used to indicate one or more of the following: The number of the second prediction results; The resource location corresponding to the second prediction result.

8. The method according to claim 6 or 7, wherein, Any two of the multiple prediction results are of the same type, and any two prediction results are associated with different resource locations; or, Any two of the multiple prediction results are of different types.

9. The method according to any one of claims 1 to 8, wherein, The method further includes: Receive third information sent by a network device; the third information includes at least the first information, and the third information also includes one or more of the following: The second quantity is used to determine the number of first prediction results that the AI ​​function can use for a single input; The second resource information is used by the terminal to determine the resource location that is allowed as the first prediction result input to the AI ​​function.

10. The method according to any one of claims 1 to 9, wherein, The method further includes: A fourth message is sent to the network device, the fourth message being used by the network device to determine whether the first prediction result can be used as an input parameter for the AI ​​function.

11. The method according to claim 10, wherein, The fourth piece of information includes one or more of the following: The third confidence level is used to indicate the accuracy of the AI ​​function; The second indicator is used to indicate that the third confidence level is higher than the sixth threshold; The fourth confidence level is the minimum confidence level of the AI ​​function within the second time period; The third indication is used to indicate that the built-in confidence level of the AI ​​function remains above the seventh threshold for a second duration. The sixth confidence level is the minimum confidence level of the most recent M consecutive outputs of the AI ​​function; The fourth indicator is used to indicate that the confidence level of the AI ​​function in the most recent M consecutive outputs is higher than the eighth threshold; The third resource information is used to indicate the resource location of the third prediction result, which is the prediction result output by the AI ​​function and related to the fourth information.

12. A method for determining parameters, wherein, Performed by a network device, the method includes: Send first information to the terminal, the first information being used by the terminal to determine whether to use the first prediction result as an input parameter for an artificial intelligence (AI) function, the AI ​​function being used to output a prediction result for wireless measurement; the first prediction result is the output parameter of the AI ​​function.

13. The method according to claim 12, wherein, The first information includes at least one of the following: The output performance metrics of the AI ​​function; A first indication is provided to indicate whether the first prediction result can be used as an input parameter for the AI ​​function.

14. The method according to claim 13, wherein, The output performance metrics include one or more of the following: The first confidence level is used to indicate the accuracy of the AI ​​function; The first difference is used to indicate the difference between the first prediction result and the actual measurement result; The second confidence level is used to indicate the accuracy of the first prediction result.

15. The method according to any one of claims 12 to 14, wherein, The first prediction result includes multiple prediction results, and the method further includes: The system receives second information sent by the terminal, the second information including information about a second prediction result; the second prediction result is the prediction result among the plurality of prediction results that serves as the input parameter for the AI ​​function.

16. The method according to claim 15, wherein, The second information is used to indicate one or more of the following: The number of the second prediction results; The resource location corresponding to the second prediction result includes one or more of the first time domain location and the first frequency domain location.

17. The method according to claim 15 or 16, wherein, Any two of the multiple prediction results are of the same type, and any two prediction results are associated with different resource locations; or, Any two of the multiple prediction results are of different types.

18. The method according to any one of claims 12 to 17, wherein, The method further includes: A third message sent to the terminal; the third message includes at least the first message, and further includes at least one of the following: The second quantity is used to determine the number of first prediction results that the AI ​​function can use for a single input; The second resource information is used by the terminal to determine the resource location that is allowed as the first prediction result input to the AI ​​function.

19. The method according to any one of claims 12 to 18, wherein, The method further includes: The network device receives a fourth message sent by the terminal, the fourth message being used to determine whether the first prediction result can be used as an input parameter for the AI ​​function.

20. The method according to claim 19, wherein, The fourth piece of information includes one or more of the following: The third confidence level is used to indicate the accuracy of the AI ​​function; The second indicator is used to indicate that the third confidence level is higher than the sixth threshold; The fourth confidence level is the minimum confidence level of the AI ​​function within the second time period; The third indication is used to indicate that the built-in confidence level of the AI ​​function remains above the seventh threshold for a second duration. The sixth confidence level is the minimum confidence level of the most recent M consecutive outputs of the AI ​​function; The fourth indicator is used to indicate that the confidence level of the AI ​​function in the most recent M consecutive outputs is higher than the eighth threshold; The third resource information is used to indicate the resource location of the third prediction result, which is the prediction result output by the AI ​​function and related to the fourth information.

21. A parameter determining device, wherein, The parameter determination device includes: The processing module is configured to determine, based on first information, whether to use the first prediction result as an input parameter for an artificial intelligence (AI) function, wherein the AI ​​function is used to output a prediction result for wireless measurement, and the first prediction result is an output parameter of the AI ​​function.

22. The apparatus according to claim 21, wherein, The processing module is configured to determine, when the first information satisfies the first condition, to use the first prediction result as the input of the AI ​​function.

23. The apparatus according to claim 22, wherein, The first information satisfies one or more of the following conditions: The first confidence level is higher than the first threshold; The first confidence level remains higher than the second threshold within the first time period; The AI ​​function has N consecutive first confidence levels that are higher than the third threshold; where N is a positive integer greater than or equal to 2. The first difference is less than the fourth threshold; The second confidence level is higher than the fifth threshold.

24. The apparatus according to any one of claims 21 to 23, wherein, The first prediction result includes multiple prediction results, and the processing module is configured to determine whether to use the multiple prediction results as input parameters for the AI ​​function based on the first information; The parameter determination device further includes: The sending module is configured to send second information to a network device, the second information including information of the second prediction result; The second prediction result is the prediction result among the multiple prediction results that serves as the input parameter for the AI ​​function.

25. The apparatus according to any one of claims 21 to 24, wherein, The device further includes: The sending module is configured to send fourth information to the network device, the fourth information being used by the network device to determine whether the first prediction result can be used as an input parameter for the AI ​​function.

26. A parameter determining device, wherein, The device includes: The sending module is configured to send first information to the terminal, the first information being used by the terminal to determine whether to use the first prediction result as an input parameter for an artificial intelligence (AI) function, the AI ​​function being used to output a prediction result for wireless measurement; the first prediction result is the output parameter of the AI ​​function.

27. The apparatus according to claim 26, wherein, The first prediction result includes multiple prediction results, and the device further includes: The receiving module is configured to receive second information sent by the terminal, the second information including information of a second prediction result; the second prediction result is the prediction result among the plurality of prediction results that serves as the input parameter of the AI ​​function.

28. The apparatus according to claim 26 or 27, wherein, The device further includes: A sending module is configured to send third information to the terminal; the third information includes at least the first information, and further includes at least one of the following: The second quantity is used to determine the number of first prediction results that the AI ​​function can use for a single input; The second resource information is used by the terminal to determine the resource location that is allowed as the first prediction result input to the AI ​​function.

29. The apparatus according to any one of claims 26 to 28, wherein, The device further includes: The sending module is configured to receive fourth information sent by the terminal, the fourth information being used by the network device to determine whether the first prediction result can be used as an input parameter for the AI ​​function.

30. A communication system, wherein, The communication system includes: The user equipment (UE) is configured to perform the artificial intelligence parameter determination method according to any one of claims 1 to 11; A network device configured to perform the artificial intelligence parameter determination method according to any one of claims 12 to 20.

31. A communication device, wherein, The communication device includes: One or more processors; The processor is configured to invoke instructions to cause the communication device to perform the method according to any one of claims 1 to 11 or 12 to 20.

32. A storage medium, wherein, The storage medium stores instructions that, when executed on a communication device, cause the communication device to perform any one of the artificial intelligence parameter determination methods of claims 1 to 11 or 12 to 20.

33. A program product, wherein, The program product includes a computer program that, when executed by a communication device, enables the communication device to implement the method of any one of claims 1 to 11 or 12 to 20.

Images