Delay determination methods, device, system, storage medium and program product

Abstract

Provided in the embodiments of the present disclosure are delay determination methods, a device, a system, a storage medium and a program product. A delay determination method comprises: on the basis of the state of a model, determining a first delay, the model being used for determining channel state information (CSI), and the first delay being used for indicating a delay for determining the CSI on the basis of the model. In the method, when the model is in different states, delays for determining the CSI on the basis of the model are different and, on the basis of the state of the model, a terminal and a network device can determine the corresponding first delay, such that the network device can perform reasonable configuration, thus ensuring that the terminal can complete CSI processing or calculation within a sufficient delay, and improving the overall communication performance.

Description

Determine the latency method, device, system, storage medium, and program product. Technical Field

[0001] This disclosure relates to the field of communication technology, and in particular to a method, apparatus, system, storage medium, and program product for determining time delay. Background Technology

[0002] With the development of artificial intelligence (AI) technology, AI models are gradually being applied in the field of wireless communication, such as in the application scenario of calculating channel status information (CSI). Summary of the Invention

[0003] In scenarios where CSI is calculated based on AI models, ensuring consistent latency between the terminal and the network is a problem to be solved.

[0004] This disclosure provides a method, apparatus, system, storage medium, and program product for determining latency.

[0005] In a first aspect, embodiments of this disclosure provide a method for determining latency, executed by a terminal, the method comprising:

[0006] A first delay is determined based on the state of the model, wherein the model is used to determine channel state information (CSI), and the first delay is used to indicate the delay for determining CSI based on the model.

[0007] Secondly, embodiments of this disclosure provide a method for determining latency, executed by a network device, the method comprising:

[0008] A first delay is determined based on the state of the model, wherein the model is used to determine channel state information (CSI), and the first delay is used to indicate the delay for determining CSI based on the model.

[0009] Thirdly, embodiments of this disclosure provide a communication device, wherein the communication device is used to perform the method described in the first aspect or the second aspect.

[0010] Fourthly, embodiments of this disclosure provide a communication system, including a terminal and a network device, wherein,

[0011] The terminal is configured to implement the method as described in the first aspect;

[0012] The network device is configured to implement the method as described in the second aspect.

[0013] Fifthly, embodiments of this disclosure provide a storage medium storing instructions, wherein...

[0014] When the instructions are executed on the communication device, the communication device causes the communication device to perform the method as described in the first aspect or the second aspect.

[0015] In a sixth aspect, embodiments of this disclosure provide a program product, including at least one of a program and instructions, wherein when the program and instructions are executed by a communication device, they implement the method described in the first or second aspect.

[0016] In this embodiment of the disclosure, the latency for determining CSI based on the model varies depending on the model's state. The terminal and network device can determine the corresponding first latency according to the model's state, so that the network device can be configured reasonably to ensure that the terminal can complete CSI processing or calculation within a sufficient latency, thereby improving the overall communication performance. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings required for the description of the embodiments are introduced below. The following drawings are only some embodiments of this disclosure and do not impose specific limitations on the protection scope of this disclosure.

[0018] Figure 1A is an exemplary schematic diagram of the architecture of a communication system provided according to an embodiment of the present disclosure;

[0019] Figure 1B is a schematic diagram of CSI reporting based on channel prediction according to an embodiment of the present disclosure;

[0020] Figure 1C is a schematic diagram illustrating the CSI calculation time requirements according to an embodiment of the present disclosure;

[0021] Figures 2A and 2B are exemplary interactive schematic diagrams of the method provided according to embodiments of the present disclosure;

[0022] Figures 2C to 2G are schematic diagrams illustrating a second time delay according to embodiments of the present disclosure;

[0023] Figures 3A to 3D are exemplary interactive schematic diagrams of the method provided according to embodiments of the present disclosure;

[0024] Figure 4 is an exemplary interactive schematic diagram of the method provided according to an embodiment of the present disclosure;

[0025] Figure 5A is a schematic diagram of the structure of a terminal according to an embodiment of the present disclosure;

[0026] Figure 5B is a schematic diagram of the structure of a network device according to an embodiment of the present disclosure;

[0027] Figure 6A is a schematic diagram of a communication device according to an embodiment of the present disclosure;

[0028] Figure 6B is a schematic diagram of a communication device according to an embodiment of the present disclosure. Detailed Implementation

[0029] This disclosure provides a method, apparatus, system, storage medium, and program product for determining latency.

[0030] In a first aspect, embodiments of this disclosure provide a method for determining latency, executed by a terminal, the method comprising:

[0031] A first delay is determined based on the state of the model, wherein the model is used to determine channel state information (CSI), and the first delay is used to indicate the delay for determining CSI based on the model.

[0032] In the above embodiments, the delay for determining CSI based on the model varies when the model is in different states. The terminal and network device can determine the corresponding first delay according to the state of the model, so that the network device can be configured reasonably to ensure that the terminal can complete CSI processing or calculation within a sufficient delay, thereby improving the overall communication performance.

[0033] In conjunction with the embodiments of the first aspect, in some embodiments, the method further includes:

[0034] Send first information to the network device, the first information being used to indicate whether one or more models supported by the terminal are in a first state, the first state indicating that the model has been loaded into the processor from memory and is in an active state.

[0035] In the above embodiments, the terminal can inform the network device of the state of the model in the terminal through the first information, so that the terminal and the network device can determine the same first latency based on the same model state, thereby improving the rationality of the network device's latency configuration.

[0036] In conjunction with the embodiments of the first aspect, in some embodiments, the method further includes:

[0037] Receive second information sent by the network device, the second information being used to indicate the activation of one or more models or to indicate model parameters of one or more models;

[0038] After the first symbol following the second information reception time, and after a set time offset, the model is determined to be in a first state, wherein the first state indicates that the model has been loaded into the processor from the memory and is in an active state.

[0039] In the above embodiments, the state of the model can be determined by the second information sent by the network device, so that the terminal and the network device can determine the same first latency based on the same model state, thereby improving the rationality of the network device's latency configuration.

[0040] In conjunction with the embodiments of the first aspect, in some embodiments, the set duration is defined by a protocol, or the set duration is sent by the terminal to the network device.

[0041] In the above embodiments, the set duration can be reported to the network via a communication protocol or the terminal, thereby ensuring that the terminal and network devices have a consistent understanding of the first delay and guaranteeing the rationality of the network configuration.

[0042] In conjunction with the embodiments of the first aspect, in some embodiments, determining the first delay based on the state of the model includes one of the following:

[0043] The model is in a first state, and the first delay is determined to be a first value, where the first value represents the delay required by the terminal to determine the CSI based on the model.

[0044] The model is in a second state, and the first delay is determined to be the sum of a first value and a second value, where the second value represents the delay required for the model to be loaded from memory into the processor, and the second state indicates that the model has not been loaded from memory into the processor;

[0045] The model is in a third state, and the first delay is determined to be the sum of the first value and the third value. The third value represents the delay required for the model to transition from a dormant state to an active state. The third state indicates that the model has been loaded into the processor from the memory and is in a dormant state.

[0046] In the above embodiments, the value of the corresponding first delay can be determined according to different states of the model, thereby improving the rationality of network device configuration delay and ensuring that the terminal can report CSI within an appropriate time when the model is in different states.

[0047] In conjunction with the embodiments of the first aspect, in some embodiments, at least one of the first value, the second value, and the third value is defined by a protocol, or is sent by the terminal to the network device.

[0048] In the above embodiments, a relevant value for determining the first delay is reported to the network via a communication protocol or by the terminal, thereby ensuring that the terminal and network devices have a consistent understanding of the first delay.

[0049] In conjunction with the embodiments of the first aspect, in some embodiments, determining the first delay based on the state of the model includes:

[0050] Based on the state of the model, the first delay is determined as the fourth value, which includes the delay of the terminal determining CSI based on the model and the delay of processing the model;

[0051] The latency of the processing model includes the latency required for the model to be loaded from memory to the processor or the latency required for the model to transition from a sleep state to an active state.

[0052] In the above embodiments, the first latency can always be the fourth value to ensure that the terminal and network device have a consistent understanding of the first latency.

[0053] In conjunction with the embodiments of the first aspect, in some embodiments, the method further includes:

[0054] After determining the CSI based on the model in the first state, the model in the first state is removed by the processor or the model in the first state is converted to the third state.

[0055] In the above embodiments, the processing method of the model after determining the CSI based on the model is set, so that the accurate first latency can be determined based on the state of the model when the model is used again in the future, so as to ensure that the terminal and network device have a consistent understanding of the first latency.

[0056] In conjunction with the embodiments of the first aspect, in some embodiments, the method further includes:

[0057] The terminal receives third information sent by the network device, the third information being used to instruct the terminal to report the monitoring information;

[0058] Determine the second time delay corresponding to obtaining the monitoring information;

[0059] The monitoring information includes model performance index values ​​corresponding to one or more CSI times determined by the model.

[0060] In the above embodiments, when the terminal learns that monitoring information needs to be reported based on the third information, it can determine the second delay corresponding to the monitoring information. This can ensure that the terminal and the network device have a consistent understanding of the reporting time of the monitoring information, so that the terminal can report the monitoring information within an appropriate time. This facilitates the network device to evaluate the model that determines the CSI in the terminal in a timely manner and ensures communication performance.

[0061] In conjunction with the embodiments of the first aspect, in some embodiments, determining the second time delay corresponding to obtaining the monitoring information includes:

[0062] The second time delay is determined based on the number of times corresponding to the one or more times and the interval between different times.

[0063] In the above embodiments, the second delay can be determined based on the time of monitoring as needed and the interval between different times, so that the terminal and network device can determine a consistent second delay, thereby improving the rationality of network configuration.

[0064] In conjunction with the embodiments of the first aspect, in some embodiments,

[0065] The reception time of the third information is located before the first time of all the times among the one or more times. Determining the second delay based on the number of times corresponding to the one or more times and the interval between different times includes:

[0066] The second delay is determined based on the number of time points, the interval between adjacent time points, and the time delay required to determine the monitoring information for a given time point; wherein the third information indicates the reporting of performance index values ​​for all time points.

[0067] In the above embodiments, by combining the time to be monitored and the time domain location of the third information, the terminal and the network can determine a consistent second latency, thereby improving the rationality of the network configuration.

[0068] In conjunction with the embodiments of the first aspect, in some embodiments, the second delay is one of the following:

[0069] in, N4 represents the time delay required to determine the monitoring information at a given moment, d represents the interval between adjacent moments, and Ns represents the number of symbols in a time slot.

[0070] In the above embodiments, two methods for calculating the second delay are provided to facilitate flexible selection of the appropriate second delay under different circumstances.

[0071] In conjunction with the embodiments of the first aspect, in some embodiments,

[0072] Determining the second time delay based on the number of times corresponding to the one or more times and the interval between different times includes:

[0073] The second delay is determined based on the number of time points, the interval between different time points, the time delay required to determine the monitoring information of a time point, and the time index i.

[0074] Wherein, the third information indicates the reporting of performance index values ​​for a portion of the one or more time points, and the receiving time of the third information is before the i-th time point of all the one or more time points; or, the receiving time of the third information is before the first time point of the portion of time points, where i is the index of the first time point of the portion of time points in all the time points; where i≤N4;

[0075] The interval between the different times is the interval between adjacent times or the interval between the first and last times in the partial time.

[0076] In the above embodiments, based on the time-domain location of the third information, the second delay can be determined based on the index, so that the terminal and network device can determine the same second delay, thereby improving the rationality of network configuration.

[0077] In conjunction with the embodiments of the first aspect, in some embodiments,

[0078] The third information indicates that performance index values ​​for a portion of the one or more time points should be reported, and the second delay is: Where i∈{2,3,...,N4}; or,

[0079] The second delay is: or Where i∈{1,2,...,N4};

[0080] in, N4 represents the time delay required to determine the monitoring information at a given moment, d represents the interval between adjacent moments, δ represents the interval between the first and last moments in the given time period, and Ns represents the number of symbols in a time slot.

[0081] In the above embodiments, a suitable second delay can be flexibly determined.

[0082] Secondly, embodiments of this disclosure provide a method for determining latency, executed by a network device, the method comprising:

[0083] A first delay is determined based on the state of the model, wherein the model is used to determine channel state information (CSI), and the first delay is used to indicate the delay for determining CSI based on the model.

[0084] In the above embodiments, the latency for determining CSI based on the model varies depending on the model's state. Network devices and terminals can determine the corresponding first latency based on the model's state, thereby allowing network devices to be configured reasonably to ensure that the terminal can complete CSI processing or calculation within a sufficient latency, thus improving overall communication performance.

[0085] In conjunction with the embodiments of the second aspect, in some embodiments, the method further includes:

[0086] The receiving terminal sends first information, which indicates whether one or more models supported by the terminal are in a first state, whereby the first state indicates that the model has been loaded into the processor from the memory and is in an active state.

[0087] In conjunction with the embodiments of the second aspect, in some embodiments, the method further includes:

[0088] Send a second message to the terminal, the second message being used to indicate the activation of one or more models or to indicate model parameters of one or more models;

[0089] After the first symbol following the second information transmission time, and after a set time offset, the model is determined to be in a first state, wherein the first state indicates that the model has been loaded from memory into the processor and is in an active state.

[0090] In conjunction with the embodiments of the second aspect, in some embodiments,

[0091] The set duration is defined by the protocol, or the set duration is sent by the terminal to the network device.

[0092] In conjunction with the embodiments of the second aspect, in some embodiments, determining the first delay based on the state of the model includes one of the following:

[0093] The model is in a first state, and the first delay is determined to be a first value, where the first value represents the delay required by the terminal to determine the CSI based on the model.

[0094] The model is in a second state, and the first delay is determined to be the sum of a first value and a second value, where the second value represents the delay required for the model to be loaded from memory into the processor, and the second state indicates that the model has not been loaded from memory into the processor;

[0095] The model is in a third state, and the first delay is determined to be the sum of the first value and the third value. The third value represents the delay required for the model to transition from a dormant state to an active state. The third state indicates that the model has been loaded into the processor from the memory and is in a dormant state.

[0096] In conjunction with the embodiments of the second aspect, in some embodiments,

[0097] At least one of the first value, the second value, and the third value is defined by the protocol or is sent by the terminal to the network device.

[0098] In conjunction with the embodiments of the second aspect, in some embodiments, determining the first delay based on the state of the model includes:

[0099] Based on the state of the model, the first delay is determined as the fourth value, which includes the delay of the terminal determining CSI based on the model and the delay of processing the model;

[0100] The latency of the processing model includes the latency required for the model to be loaded from memory to the processor or the latency required for the model to transition from a sleep state to an active state.

[0101] In conjunction with the embodiments of the second aspect, in some embodiments, the method further includes:

[0102] Send a third message to the terminal, the third message being used to instruct the terminal to report the monitoring information;

[0103] Determine the second time delay corresponding to obtaining the monitoring information;

[0104] The monitoring information includes model performance index values ​​corresponding to one or more CSI times determined by the model.

[0105] In conjunction with the embodiments of the second aspect, in some embodiments, the second delay is determined based on the number of times corresponding to the one or more times and the interval between different times.

[0106] In conjunction with the embodiments of the second aspect, in some embodiments,

[0107] The receiving time of the third information is located before the first time of all the times in the one or more times, and the second delay is determined based on the number of times, the interval between adjacent times, and the delay required to determine the monitoring information of a time; wherein, the third information indicates the reporting of the performance index values ​​of all the times.

[0108] In conjunction with the embodiments of the second aspect, in some embodiments, the second delay is one of the following:

[0109] in, N4 represents the time delay required to determine the monitoring information at a given moment, d represents the interval between adjacent moments, and Ns represents the number of symbols in a time slot.

[0110] In conjunction with the embodiments of the second aspect, in some embodiments,

[0111] The second delay is determined based on the number of time points, the interval between different time points, the delay required to determine the monitoring information for a given time point, and the time index i.

[0112] The third information indicates the reporting of performance index values ​​for a portion of the one or more time points, and the receiving time of the third information is before the i-th time point of all the one or more time points.

[0113] Alternatively, the time of receiving the third information is before the first time in the partial time, where i is the index of the first time in the partial time within the total time; where i ≤ N4;

[0114] The interval between the different times is the interval between adjacent times or the interval between the first and last times in the partial time.

[0115] In conjunction with the embodiments of the second aspect, in some embodiments,

[0116] The third information indicates that performance index values ​​for a portion of the one or more time points should be reported, and the second delay is: Where i∈{2,3,...,N4}; or,

[0117] The second delay is: or Where i∈{1,2,...,N4};

[0118] in, N4 represents the time delay required to determine the monitoring information at a given moment, d represents the interval between adjacent moments, δ represents the interval between the first and last moments in the given time period, and Ns represents the number of symbols in a time slot.

[0119] Thirdly, embodiments of this disclosure provide a communication device, wherein the communication device is used to perform the method described in the first aspect or the second aspect.

[0120] Fourthly, embodiments of this disclosure provide a communication system, including a terminal and a network device, wherein,

[0121] The terminal is configured to implement the method as described in the first aspect;

[0122] The network device is configured to implement the method as described in the second aspect.

[0123] Fifthly, embodiments of this disclosure provide a storage medium storing instructions, wherein...

[0124] When the instructions are executed on the communication device, the communication device causes the communication device to perform the method as described in the first aspect or the second aspect.

[0125] In a sixth aspect, embodiments of this disclosure provide a program product, including at least one of a program and instructions, wherein when the program and instructions are executed by a communication device, they implement the method described in the first or second aspect.

[0126] It is understood that the aforementioned communication equipment, communication system, storage medium, and program product are all used to execute the methods proposed in the embodiments of this disclosure. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0127] 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, a solution after removing some steps in a particular embodiment can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment can be arbitrarily interchanged. Furthermore, the optional implementation methods 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 the optional implementation methods of other embodiments. In all embodiments of this disclosure, unless otherwise specified or logically conflicting, the terminology and / or descriptions between the embodiments are consistent and can be mutually referenced. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0128] 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.

[0129] In this embodiment of the disclosure, unless otherwise stated, elements expressed in the singular form, such as "a," "an," "the," "the," "the," "the," "the," "the," "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.

[0130] In the embodiments disclosed herein, "multiple" refers to two or more.

[0131] In some embodiments, the terms “at least one of A or B, at least one of A and B”, “one or more”, “a plurality of”, “multiple”, etc., may be used interchangeably.

[0132] In some embodiments, the notation "at least one of A and B", "A and / or B", "A in one case, B in another", "in response to one case A, in response to another case B", etc., may include the following technical solutions depending on the situation: in some embodiments, A (execute A regardless of whether there is a branch B); in some embodiments, B (execute B regardless of whether there is a branch A); in some embodiments, execution is selected from A and B (A and B are selectively executed); in some embodiments, both A and B are executed. The same applies when there are more branches such as A, B, C, etc.

[0133] In some embodiments, the notation "A or B" may include the following technical solutions, depending on the situation: in some embodiments, A (execute A regardless of whether a branch B exists); in some embodiments, B (execute B regardless of whether a branch A exists); in some embodiments, execution is selected from A and B (A and B are selectively executed). The same applies when there are more branches such as A, B, and C.

[0134] 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. Similarly, if the object being described is "information", then "first information" and "second information" can be the same information or different information, and their content can be the same or different.

[0135] In some embodiments, “including A,” “containing A,” “for indicating A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.

[0136] In some embodiments, terms such as "time / frequency" and "time-frequency domain" refer to the time domain and / or frequency domain.

[0137] In some embodiments, terms such as “in response to…”, “in response to determining…”, “in the case of…”, “when…”, “when…”, “if…”, etc. can be used interchangeably. These descriptions all refer to the device making a corresponding action under certain objective circumstances. They do not necessarily limit the time, nor do they require the device to make a judgment action when implementing it, nor do they mean that there must be other limitations.

[0138] 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”.

[0139] In some embodiments, devices, etc., may be interpreted as physical or virtual, and their names are not limited to those described in the embodiments. Terms such as “device,” “equipment,” “circuit,” “network element,” “network function,” “network device,” “function,” “node,” “unit,” “section,” “system,” “network,” “chip,” “chip system,” “entity,” and “subject” are interchangeable.

[0140] In some embodiments, "network" can be interpreted as devices included in a network (e.g., access network devices, core network devices, etc.).

[0141] 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 cell," "carrier," "component carrier," and "bandwidth part (BWP)" can be used interchangeably.

[0142] In some embodiments, the terms "terminal", "terminal device", "user equipment (UE)", "user terminal", "mobile station (MS)", "mobile terminal (MT)", "subscriber station", "mobile unit", "subscriber unit", "wireless unit", "remote unit", "mobile device", "wireless device", "wireless communication device", "remote device", "mobile subscriber station", "access terminal", "mobile terminal", "wireless terminal", "remote terminal", "handset", "user agent", "mobile client", and "client" can be used interchangeably.

[0143] In some embodiments, access network devices, core network devices, or network devices can be replaced by terminals. For example, embodiments of this disclosure can also be applied to structures where communication between access network devices, core network devices, or network devices and terminals is replaced by communication between multiple terminals (e.g., device-to-device (D2D), vehicle-to-everything (V2X), etc.). In this case, the structure can also be configured such that the terminal has all or part of the functions of the access network device. Furthermore, terms such as "uplink" and "downlink" can be replaced with terms corresponding to communication between terminals (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.

[0144] In some embodiments, the terminal may be replaced by an access network device, a core network device, or a network device. In this case, the access network device, core network device, or network device may also be configured to have all or some of the functions of the terminal.

[0145] In some embodiments, the acquisition of data, information, etc., may comply with the laws and regulations of the country where the location is situated.

[0146] In some embodiments, data, information, etc., may be obtained with the user's consent.

[0147] 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.

[0148] Figure 1A is a schematic diagram of the architecture of a communication system according to an embodiment of the present disclosure.

[0149] As shown in Figure 1A, the communication system 100 includes a terminal 101 and a network device 102.

[0150] In some embodiments, terminal 101 includes, for example, 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) terminal device, augmented reality (AR) terminal device, wireless terminal device in industrial control, wireless terminal device in self-driving, wireless terminal device in remote medical surgery, wireless terminal device in smart grid, wireless terminal device in transportation safety, wireless terminal device in smart city, and wireless terminal device in smart home, but is not limited thereto.

[0151] In some embodiments, network device 102 may be at least one of access network device and core network device.

[0152] In some embodiments, the access network device is, for example, a node or device that connects a terminal to a wireless network. The access network device may include 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, but is not limited thereto.

[0153] In some embodiments, the technical solutions 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.

[0154] 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.

[0155] In some embodiments, a core network device may be a single device comprising one or more network elements, or it may be multiple devices or a group of devices, each comprising all or part of one or more network elements. Network elements may be virtual or physical. The core network may include, for example, at least one of the following: Evolved Packet Core (EPC), 5G Core Network (5GCN), and Next Generation Core (NGC).

[0156] In some embodiments, core network equipment includes network elements with specific functions, such as Access Management Function (AMF) and Service Management Function (SMF).

[0157] It is understood that the communication system described in this disclosure is for the purpose of more clearly illustrating the technical solutions of this disclosure, and does not constitute a limitation on the technical solutions proposed 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 solutions proposed in this disclosure are also applicable to similar technical problems.

[0158] 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. Each main body may be physical or virtual. 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.

[0159] 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 other communication methods, and next-generation systems built upon them, etc. Furthermore, multiple systems can be combined (e.g., a combination of LTE or LTE-A with 5G).

[0160] In some implementations, CSI processing guidelines are used to ensure that the terminal and network (NW) sides have a consistent understanding of the CSI processing procedure, so that the network side can provide reasonable CSI reporting parameter configurations. The CSI processing guidelines include the number of CPUs occupied by CSI processing, the duration of CPUs occupied by CSI processing, and the number of channel measurement resources such as Channel Status Information-Reference Signal (CSI-RS) resources activated during CSI processing.

[0161] In some implementations, for traditional non-artificial intelligence (non-AI) algorithms, the terminal reports the total number of CPUs (denoted as N) capable of simultaneously calculating multiple CSIs. CPU If the current terminal has already occupied L of the CPUs, then the number of remaining CPUs is N. CPU -L. At this point, if the terminal can still perform M CSI calculations simultaneously, let the number of CPUs required to calculate the nth CSI be... but If the terminal cannot perform calculations for M CSIs simultaneously, based on the priority of the M CSIs reported, lower-priority CSIs are not updated; only higher-priority CSIs are updated, ensuring that the sum of CPU usage by the higher-priority CSIs does not exceed N. CPU -L.

[0162] In some implementations, with the application of AI technology in the field of wireless communication, traditional non-AI algorithms will be replaced by AI model inference. In a CSI report, the CSI calculation can be obtained directly through AI model inference. The CSI calculation can also include both traditional non-AI algorithms and calculations based on AI model inference, or the CSI calculation can be obtained based on multiple AI model inferences.

[0163] For non-AI algorithm methods, such as CSI feedback reporting based on the Type II Doppler codebook of Release 18 (Rel-18), CSI calculation includes at least CSI prediction and CSI measurement. CSI prediction refers to the terminal first obtaining downlink channel information within the measurement window based on the channel measurement resources configured by the network, such as CSI-RS. Then, it calculates the channel information for the next N4 time steps in a prediction window using the traditional Linear Minimum Mean Square Error (LMMSE) algorithm. Finally, the terminal measures the CSI within the prediction window based on the predicted channel information for the N4 time steps and reports it to the network. CSI can include Precoding Matrix Indication (PMI), Channel Quality Indication (CQI), Rank Indication (RI), etc. For example, Figure 1B is a schematic diagram of CSI reporting based on channel prediction according to an embodiment of this disclosure. As shown in Figure 1B, the black-filled box in the measurement window indicates the CSI measured by the terminal within a slot, which can be called the measured CSI; the gray-filled box in the prediction window indicates the CSI predicted by the terminal for a slot, which can be called the predicted CSI. The CSI may include the corresponding downlink channel information, and the DCI is used to trigger the terminal to report the CSI, such as reporting the predicted CSI.

[0164] For the AI ​​model approach, the traditional algorithm for predicting channel information at N4 future time points can be replaced by an AI model for CSI prediction to further improve the accuracy of the predicted channel information, while CSI measurement still uses the traditional non-AI algorithm. Optionally, CSI measurement can also be performed using an AI model instead of the traditional non-AI algorithm. Therefore, a single CSI report can include one or more AI models.

[0165] In some implementations, traditional CSI processing requires a certain CSI calculation time. This CSI calculation time requirement also necessitates a consistent understanding between the terminal and the network to ensure the network configures a reasonable CSI reporting time so that the terminal can report accurate and reliable CSI. Figure 1C is a schematic diagram illustrating the CSI calculation time requirement in traditional CSI processing according to an embodiment of this disclosure. As shown in Figure 1C, TA represents Timing Advance (TA). CSI, such as Aperiodic CSI Reporting (AP-CSI), can be reported through the Physical Uplink Shared Channel (PUSCH). Referring to Figure 1C, one type of CSI calculation time requirement is the minimum delay (T) required from the triggering of measurement resources on the Physical Downlink Control Channel (PDCCH) to CSI reporting. proc,CSI Another approach is to determine the minimum time delay (T′) required from receiving the most recent CSI-RS or Channel State Information-Interference Measurement (CSI-IM) measurement resources to reporting to CSI. proc,CSI ), where: T proc,CSI = (Z)(2048+144)×k×2 -μ ×T c +T switch T′ proc,CSI = (Z′)(2048+144)×k×2 -μ ×T c

[0166] Where k represents the time slot offset, used to define the time slot interval between PDCCH scheduling and PUSCH transmission, and is a scaling factor used to adjust the processing time; μ represents the exponent of sub-carrier spacing (SCS), for example, μ = 0 corresponds to a sub-carrier spacing of 15 kHz; T c The time unit representing the subcarrier interval, used to convert processing time from sample count to actual time units; T switch Z represents the time required for the terminal to switch between different operating modes; Z and Z′ represent the CSI computation delay requirement, and the values ​​of Z and Z′ are determined according to Table 1 or Table 2 as shown below. The unit of Z and Z′ is symbol:

[0167] Table 1 CSI Calculation Latency Requirements 1

[0168] Table 2 CSI Calculation Delay Requirements 2

[0169] In some implementations, during a CSI report, when a traditional algorithm is replaced by an AI model, the multiple possible states of the model can affect the CSI computation time. For example, before model inference, additional time may be needed to load the AI ​​model into the AI ​​model processor; if the AI ​​model has already been deployed to the AI ​​model processor, this additional loading time is no longer required. Therefore, the CSI computation time is related to whether the AI ​​model has been loaded.

[0170] Furthermore, for AI models deployed on the terminal, the network cannot determine whether the AI ​​model has been deployed to the AI ​​model processor. Therefore, how to enable the network to determine the status of the AI ​​model on the terminal and ensure that the network and the terminal have a consistent understanding of CSI calculation latency is a problem to be solved.

[0171] Figure 2A is an interactive schematic diagram illustrating a delay determination method according to an embodiment of the present disclosure. As shown in Figure 2A, the present disclosure relates to a delay determination method, which includes:

[0172] In step S2101, network device 102 sends second information to terminal 101.

[0173] In some embodiments, terminal 101 receives second information.

[0174] In some embodiments, terminal 101 may support at least one or more models, or terminal 101 may store at least one or more models.

[0175] Optionally, the model is an AI model or AI function used for beam prediction, or for determining the predicted CSI or the second CSI in the embodiments described below. For example, in conjunction with the description of steps S2105 to S2108, the model is used to predict the channel information at least one future moment based on the channel information obtained from the first measurement resource or the first CSI; or the model is used to calculate the second CSI based on the channel information at least one future moment, such as calculating PMI, CQI, and RI based on the channel matrix; or the model is used in both of the above processes; or the model is used to predict the second CSI based on the channel information obtained from the first measurement resource or the first CSI.

[0176] Optionally, for models deployed on the terminal side, the models are stored by default in the terminal's memory, such as the AI ​​model memory. The method of determining the second CSI based on the model needs to be executed in the terminal's processor, such as the AI ​​model processor. Therefore, before determining the second CSI based on the model, the model needs to be loaded from memory into the processor, that is, the model deployment needs to be completed first.

[0177] Optionally, the model's state includes an active state and a dormant state. A model in an active state can be used to determine the second CSI, while a model in a dormant state needs to be converted to an active state before it can be used to determine the second CSI. The dormant state can also be referred to as an inactive state.

[0178] In some embodiments, the second information is used to indicate the activation of one or more models or to indicate model parameters of one or more models.

[0179] Optionally, the second information may indicate some or all of the multiple models supported by the active terminal 101, that is, the second information indicates the active model, and the terminal 101 needs to load the model from memory into the processor, or needs to put the model into an active state.

[0180] Optionally, model parameters are used to determine a specific model, and model parameters may include at least one of input information, output information, and model dimensions. For example, when a model is used to predict channel information at a future time based on channel information at four historical measurement times, the input information is the channel information at the four historical measurement times, and the output information is the channel information at the future time.

[0181] In some embodiments, the second information may also be referred to as activation indication information, configuration information, or configuration parameters.

[0182] In some embodiments, after learning all the models supported by terminal 101, network device 102 sends second information to terminal 101.

[0183] Optionally, network device 102 selects from all models supported by terminal 101 to determine the model available for the second CSI, and activates one or more available models or indicates the model parameters of one or more available models through the second information.

[0184] Optionally, the network device 102 may learn about the models supported by the terminal 101 in the following way:

[0185] In the first example: Network device 102 sends a capability query command (UECapabilityEnquiry) to terminal 101. After receiving the capability query command, terminal 101 sends capability information (UECapabilityInformation) to network device 102. The capability information includes all models supported by terminal 101. In this example, the capability query command and capability information can be sent before step S2101.

[0186] In the second example: Terminal 101 actively sends capability information to network device 102, which includes all models supported by terminal 101. In this example, the capability information can be sent before step S2101.

[0187] In the third example, network device 102 sends configuration information (such as RRCReconfiguration) to terminal 101, configuring model parameters. Terminal 101, based on this configuration information and its supported AI models, determines the available AI models and sends an applicable functionality reporting message to network device 102, indicating the available AI models. After receiving the reporting message, network device 102 can also send other model configuration parameters (such as resending RRCReconfiguration) to allow the terminal to better adapt to the available models. In this example, the second information in step S2101 can be either one of the two configuration messages sent by network device 102. Optionally, when this example is combined with the first example, the capability query command and capability information can be sent before network device 102 sends the configuration information for the first time.

[0188] Alternatively, the above three examples can also be combined with the description of the embodiment in Figure 4.

[0189] In some embodiments, the names of information, etc., are not limited to the names described in the embodiments. Terms such as "information", "message", "signal", "signaling", "report", "configuration", "indication", "instruction", "command", "channel", "parameter", "domain", "field", "symbol", "symbol", "codebook", "codeword", "codepoint", "bit", "data", "program", and "chip" can be used interchangeably.

[0190] In some embodiments, terms such as “send,” “transmit,” “report,” “distribute,” “transfer,” “bidirectional transmission,” “send and / or receive” can be used interchangeably.

[0191] In some embodiments, "acquire," "get," "obtain," "receive," "transmit," "bidirectional transmission," and "send and / or receive" can be used interchangeably and can be interpreted as receiving from other entities, acquiring from protocols, acquiring from higher layers, obtaining through self-processing, or autonomous implementation. Protocols include, for example, at least one of the 3GPP protocol, Wi-Fi protocol, and audio and / or video protocols.

[0192] In some embodiments, terms such as “moment,” “point in time,” “time,” and “time location” can be used interchangeably, as can terms such as “duration,” “segment,” “time window,” “window,” and “time.”

[0193] In step S2102, terminal 101 sends first information to network device 102.

[0194] In some embodiments, network device 102 receives first information.

[0195] In some embodiments, the first information is used to indicate whether one or more models supported by the terminal 101 are in a first state, the first state indicating that the model has been loaded into the processor from the memory and is in an active state.

[0196] Optionally, the first information may occupy one or more bits, each bit corresponding to a model, and the value of each bit is used to indicate whether its corresponding model is in the first state or not. For example, a bit value of 0 indicates that the corresponding model is in the first state, and a bit value of 1 indicates that the corresponding model is not in the first state.

[0197] Optionally, the state of the model is the state of the model that needs to be determined by terminal 101 based on the CSI.

[0198] Optionally, the first information can be instruction information.

[0199] Optionally, in conjunction with the three examples of step S2101, the first information can be sent via the terminal's capability information or reporting information.

[0200] In some embodiments, the first information is used to indicate that one or more models supported by the terminal 101 are in a first state, a second state, or a third state, wherein if a model is in a second state or a third state, it indicates that the model is not in the first state.

[0201] Optionally, the second state indicates that the model has not been loaded from memory into the processor.

[0202] Optionally, the third state indicates that the model has been loaded into the processor from memory and is in a dormant state.

[0203] Optionally, the first information may occupy one or more bits, with one model corresponding to two bits. The value of these two bits is used to indicate whether the corresponding model is in a first state, a second state, or a third state. For example, a bit value of 10 indicates that the corresponding model is in the first state, a bit value of 11 indicates that the corresponding model is in the second state, and a bit value of 01 indicates that the corresponding model is in the third state.

[0204] In some embodiments, one or more models supported by terminal 101 represent available models, such as models that can be used to determine the second CSI.

[0205] In some embodiments, one of steps S2101 and S2102 is optional. For example, step S2101 may be performed without step S2102; or step S2102 may be performed without step S2101. Step S2101 or S2102 is used to determine the state of the model in the terminal.

[0206] In some embodiments, both steps S2101 and S2102 are performed, and they can be based on the current order or in an interchangeable order.

[0207] Optionally, step S2101 is performed before S2102. The terminal 101 selects an available model from all models supported by the terminal 101 according to the received second information, and indicates whether the available model is in a first state through the first information.

[0208] Optionally, step S2102 is performed before S2101. The network device 102 selects one or more available models from the models supported by the terminal 101 according to the first information, and instructs to activate one or more available models or instructs the model parameters of one or more available models through the second information.

[0209] In step S2103, terminal 101 and network device 102 determine the state of the model.

[0210] Optionally, the model is the one available when determining the second CSI.

[0211] In the first embodiment, it is determined whether the model is in the first state based on the second information.

[0212] In this embodiment, step S2102 can be omitted.

[0213] In this embodiment, after the first symbol following the second information reception time and after a set time offset, the terminal 101 determines that the model is in the first state; or after the first symbol following the second information transmission time and after a set time offset, the network device 102 determines that the model is in the first state.

[0214] Optionally, the second information reception time refers to the time slot in which the terminal 101 receives the second information, and the second information transmission time refers to the time slot in which the network device 102 transmits the second information. Each time slot includes multiple symbols, for example, each time slot includes 14 symbols.

[0215] Optionally, the set duration offset is a set number of symbols, such as 6 symbols. The set duration offset from the first symbol means that the set number of symbols are offset backward from the first symbol. For example, after the 6th symbol after the second information reception time, the terminal 101 determines that the model is in the first state.

[0216] Optionally, the duration offset can be set to the protocol definition.

[0217] Optionally, the duration offset is set by the terminal 101 to the network device 102, for example, by sending the duration offset via separate signaling, or by including it in the capability information or first information sent by the terminal 101 to the network device 102.

[0218] Optionally, after a set time offset, the terminal 101 or network device 102 determines that the model is in a first state, that is, it has been loaded into the processor of the terminal 101 and is in an active state.

[0219] In the second embodiment, it is determined whether the model is in the first state based on the first information.

[0220] In this embodiment, step S2101 can be omitted.

[0221] Optionally, the first information is used to indicate that when the model is in the first state, the terminal 101 determines that the model is in the first state at the time the first information is sent, or the network device 102 determines that the model is in the first state at the time the first information is received.

[0222] Optionally, the first information transmission time refers to the time slot in which the terminal 101 sends the first information, and the first information reception time refers to the time slot in which the network device 102 receives the first information.

[0223] In step S2104, network device 102 sends the first measurement resource to terminal 101.

[0224] In some embodiments, terminal 101 receives a first measurement resource.

[0225] In some embodiments, network device 102 transmits first measurement resources in multiple time slots respectively.

[0226] Optionally, multiple time slots can be located in a measurement window, and the multiple time slots in the measurement window can also be referred to as multiple historical moments. For example, network device 102 sends the first measurement resource in the time slot corresponding to the black filled box shown in Figure 1B.

[0227] In some embodiments, the first measurement resource is used to measure and obtain channel information such as a channel matrix at a historical time, and then calculate the CSI at the historical time based on the measured channel information; or the first measurement resource is used to measure and obtain the CSI at a historical time.

[0228] Optionally, the first measurement resource is at least one of a reference signal, such as CSI-RS or CSI-IM.

[0229] In some embodiments, the terms “frame”, “radio frame”, “subframe”, “slot”, “sub-slot”, “mini-slot”, “symbol”, “symbol”, and “transmission time interval (TTI)” can be used interchangeably.

[0230] In some embodiments, the terms "synchronization signal (SS)," "synchronization signal block (SSB)," "reference signal (RS)," "pilot," and "pilot signal" can be used interchangeably.

[0231] In step S2105, terminal 101 determines the first CSI based on the first measurement resource.

[0232] Optionally, the first CSI may also be referred to as the measurement CSI.

[0233] Optionally, terminal 101 measures CSI-RS to obtain channel information, and then measures the channel information to calculate the first CSI; or terminal 101 measures CSI-RS to obtain the first CSI.

[0234] Optionally, the first CSI includes at least one of PMI, CQI, and RI.

[0235] Optionally, terminal 101 can determine the first CSI corresponding to multiple time slots or multiple historical moments of the measurement window.

[0236] In step S2106, network device 102 sends a trigger command to terminal 101.

[0237] In some embodiments, terminal 101 receives a trigger command.

[0238] In some embodiments, the trigger command is used to instruct terminal 101 to report CSI, such as reporting CSI determined based on a model.

[0239] Optionally, the CSI determined based on the model can be referred to as the predicted CSI or the second CSI. For ease of distinction from the CSI determined based on the first measurement resource, the CSI determined based on the model will be referred to as the second CSI below.

[0240] Optionally, the second CSI includes predicted CSIs for one or more time points. These one or more time points may be located within a prediction window, and these time points within the prediction window may be one or more time slots, or referred to as one or more future time points. See the gray-filled box in Figure 1B.

[0241] In some embodiments, network device 102 sends trigger commands via DCI, which can be carried by PDCCH.

[0242] In some embodiments, the terms “downlink control information (DCI),” “downlink (DL) assignment,” “DL DCI,” “uplink (UL) grant,” and “UL DCI” can be used interchangeably.

[0243] In step S2107, terminal 101 and network device 102 determine the first delay based on the state of the model.

[0244] Optionally, the model is the one available when determining the second CSI.

[0245] In some embodiments, the first delay is used to indicate the delay for determining the second CSI based on the model.

[0246] Optionally, the start time of the first delay is the time when the trigger command is sent or received, such as the start time of the first delay being the time slot when terminal 101 receives the trigger command.

[0247] Optionally, the first delay represents the minimum interval between the time slot in which the terminal 101 receives the trigger command and the time slot in which the terminal reports the second CSI to the network device 102, that is, the minimum interval between the time of receiving the trigger command and the time of sending the second CSI.

[0248] Optionally, the first latency may include only the latency required to obtain the second CSI based on model inference, or the first latency may also include the latency required for the model to be loaded from memory into the processor, or the first latency may also include the latency required for the model to transition from a dormant state to an active state.

[0249] In some embodiments, a first delay is determined based on the state of the model.

[0250] Optionally, the network device 102 or the terminal 101 determines the state of the model based on the first information or the second information; or determines the state of the model based on the processing method of the model after the second CSI was determined last time, such as removing the model from the processor or converting the model to the third state.

[0251] In some embodiments, determining the first delay based on the state of the model includes one of the following:

[0252] The model is in the first state, and the first delay is determined as the first value. The first value represents the delay required by terminal 101 to determine CSI based on the model.

[0253] The model is in the second state, and the first delay is determined to be the sum of the first value and the second value, where the second value represents the delay required for the model to be loaded from memory to the processor.

[0254] The model is in the third state. The first delay is determined to be the sum of the first value and the third value. The third value represents the delay required for the model to transition from the dormant state to the active state.

[0255] Optionally, the delay required for terminal 101 to determine CSI based on the model represents the delay required for model inference, such as the delay required to determine the second CSI in step S2108; or, the delay required for determining CSI based on the model represents the delay of terminal 101 measuring or calculating CSI; or, the delay required for determining CSI based on the model represents the delay from obtaining model input through measurement to obtaining predicted CSI through model inference.

[0256] Optionally, at least one of the first, second, and third values ​​is defined by the protocol.

[0257] Optionally, at least one of the first value, the second value, and the third value is sent by the terminal 101 to the network device 102. For example, at least one of the first value, the second value, and the third value is sent through separate signaling, or is included in the capability information or first information sent by the terminal 101 to the network device 102.

[0258] Optionally, the time units for the first, second, and third values ​​are Orthogonal Frequency Division Multiplexing (OFDM) symbols.

[0259] Optionally, the first value can be defined based on the possible values ​​in Table 1 or Table 2 of the foregoing embodiments. Optionally, the latency required to determine CSI based on the model is defined according to the predefined latency value used for AI model inference, that is, for different values ​​of μ, the first value is defined respectively.

[0260] In one example, the first value is denoted as The second value is denoted as D1, the third value as D2, and the model's state is determined to be [value missing] when it has been loaded from memory into the processor and is in an active state. When the model's state is not loaded from memory into the processor, the first delay is determined to be... When the model's state has been loaded from memory into the processor and is in a sleep state, the first latency is determined to be...

[0261] In some embodiments, the first delay is determined as a fourth value based on the state of the model. The fourth value includes the delay of the terminal 101 in determining the second CSI based on the model and the delay in processing the model.

[0262] Optionally, the fourth value can be defined by the protocol or determined by the terminal. If determined by the terminal, the terminal can report the value to the network.

[0263] Optionally, the latency of processing the model includes the latency required for the model to be loaded from memory into the processor or the latency required for the model to transition from a dormant state to an active state.

[0264] In one example, the delay of terminal 101 in determining the second CSI based on the model is denoted as... Let D be the time delay of the processing model, and determine the fourth value. If the processing latency of the model includes the latency D1 required for the model to be loaded from memory to the processor, and if the model's state is the second state, then D = D1, and the fourth value is determined. If the processing delay of the model includes the delay D2 required for the model to transition from a dormant state to an active state, and if the model's state is the third state, then D = D2, and the fourth value is determined.

[0265] In step S2108, terminal 101 determines the second CSI based on the model in the first state.

[0266] Alternatively, this step can also be referred to as the model reasoning process.

[0267] In some embodiments, the terminal 101 uses the channel information or the first CSI obtained from the first measurement resource as input to the model, and determines the second CSI based on the output of the model, or the model directly outputs the second CSI based on the input.

[0268] Optionally, the channel information obtained from the first measurement resource is input into the model, and the channel information or second CSI at least one future time is output. The channel information at least one future time is such as the channel matrix, and the second CSI, such as PMI, CQI or RI, is calculated based on the channel matrix.

[0269] Optionally, the first CSI is input into the model, and the second CSI is output at least one future time.

[0270] It is understood that the model training process is not described in the embodiments of this disclosure. In the model inference stage, the model used is a trained and converged model.

[0271] In step S2109, terminal 101 sends a second CSI to network device 102.

[0272] Optionally, terminal 101 sends a second CSI to network device 102 after the first delay.

[0273] Alternatively, after the terminal 101 and the network device 102 determine the first delay based on the protocol definition, the network device 102 configures the CSI reporting time for the terminal. If the CSI reporting time is greater than or equal to the first delay, the terminal 101 sends the second CSI to the network device 102 within the CSI reporting time.

[0274] In some embodiments, network device 102 receives a second CSI.

[0275] Optionally, network device 102 receives the second CSI based on the first delay or the reporting time.

[0276] In some embodiments, terminal 101 sends a second CSI via PUSCH.

[0277] In some embodiments, after determining the second CSI based on the model in the first state, for example, after the terminal 101 reports the second CSI, the terminal 101 may remove the model in the first state from the processor or switch the model in the first state to the third state.

[0278] Optionally, the model in the first state can be removed from the processor, and it needs to be reloaded from memory to the processor when the model is used again.

[0279] Optionally, the model in the first state is switched to the third state, that is, the model is still loaded in the processor, the model's state is changed from active state to dormant state, and the model needs to be switched from dormant state to active state when it is used again.

[0280] In some embodiments, after determining the second CSI based on the model in the first state, the model in the first state remains in the first state, that is, it is always active in the processor, and model inference can be performed directly when the model is used again.

[0281] In some embodiments, terms such as "physical uplink shared channel (PUSCH)" and "UL data" can be used interchangeably.

[0282] The communication method involved in the embodiments of this disclosure may include at least one of steps S2101 to S2109. For example, step S2107 may be implemented as a standalone embodiment, but is not limited thereto.

[0283] In some embodiments, one of steps S2101 and S2102 is optional, or the order of steps S2101 and S2102 can be interchanged.

[0284] In some embodiments, steps S2107 and S2108 may be performed in an alternate order or simultaneously.

[0285] In some embodiments, steps S2101 to S2106 and steps S2108 to S2109 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0286] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0287] Figure 2B is an interactive schematic diagram illustrating a delay determination method according to an embodiment of the present disclosure. As shown in Figure 2B, the present disclosure relates to a delay determination method, which includes:

[0288] In step S2201, network device 102 sends second information to terminal 101.

[0289] In some embodiments, the implementation of step S2201 can be referred to the implementation of step S2101 in FIG2A, and will not be repeated here.

[0290] In step S2202, terminal 101 sends first information to network device 102.

[0291] In some embodiments, the implementation of step S2202 can be referred to the implementation of step S2102 in FIG2A, and will not be repeated here.

[0292] In step S2203, terminal 101 and network device 102 determine the state of the model.

[0293] In some embodiments, the implementation of step S2203 can be referred to the implementation of step S2103 in FIG2A, and will not be repeated here.

[0294] In step S2204, network device 102 sends the first measurement resource to terminal 101.

[0295] In some embodiments, the implementation of step S2204 can be referred to the implementation of step S2104 in FIG2A, and will not be repeated here.

[0296] In step S2205, terminal 101 determines the first CSI based on the first measurement resource.

[0297] In some embodiments, the implementation of step S2205 can be referred to the implementation of step S2105 in FIG2A, and will not be repeated here.

[0298] In step S2206, network device 102 sends a trigger command to terminal 101.

[0299] In some embodiments, the implementation of step S2206 can be found in the implementation of step S2106 in FIG2A, and will not be repeated here.

[0300] In step S2207, terminal 101 and network device 102 determine the first delay based on the state of the model.

[0301] In some embodiments, the implementation of step S2207 can be found in the implementation of step S2107 in FIG2A, and will not be repeated here.

[0302] In step S2208, terminal 101 determines the second CSI based on the model in the first state.

[0303] In some embodiments, the implementation of step S2208 can be referred to the implementation of step S2108 in FIG2A, and will not be repeated here.

[0304] In step S2209, terminal 101 sends a second CSI to network device 102 based on the first delay.

[0305] In some embodiments, the implementation of step S2209 can be referred to the implementation of step S2109 in FIG2A, and will not be repeated here.

[0306] In step S2210, network device 102 sends third information to terminal 101.

[0307] In some embodiments, terminal 101 receives third information.

[0308] In some embodiments, the third information is used to instruct the terminal 101 to report monitoring information, which includes model performance index values ​​corresponding to one or more time-based CSI values ​​determined by the model.

[0309] Optionally, the model performance metric values ​​include at least one of the Square of Generalized Cosine Similarity (SGCS) and the Normalized Mean Squared Error (NMSE).

[0310] Optionally, network device 102 may send the third information before all times corresponding to the second CSI, or before any time among all times corresponding to the second CSI.

[0311] Optionally, network device 102 may send third information after terminal 101 completes one or more CSI reports, the third information indicating that performance monitoring should be performed in the CSI prediction after the one or more CSI reports.

[0312] In some embodiments, the third information is used to instruct the terminal 101 to report monitoring information for all or part of the CSI based on the model after the third information is received.

[0313] In one example, the predicted CSI is determined based on the model for four time points (e.g., four slots) in the prediction window. The third information is used to instruct the terminal 101 to report the monitoring information for the four time points, or to instruct the terminal 101 to report the monitoring information for some of the four time points, such as the monitoring information for the first and last time points.

[0314] Optionally, the third information may also be called indication information or a command that triggers the reporting of monitoring information.

[0315] In some embodiments, network device 102 sends third information via DCI or PDCCH.

[0316] Optionally, network device 102 uses different DCIs to send the third information and the trigger command in step S2206.

[0317] Optionally, network device 102 uses the same DCI to send the third information and the trigger command in step S2206.

[0318] In step S2211, network device 102 sends the second measurement resource to terminal 101.

[0319] In some embodiments, terminal 101 receives a second measurement resource.

[0320] In some embodiments, network device 102 transmits the second measurement resource at one or more times after the third information transmission time.

[0321] Optionally, the transmission time of the second measurement resource corresponds one-to-one with the time related to the monitoring information.

[0322] Optionally, when the third information instructs terminal 101 to report monitoring information for all times after the third information reception time based on model-determined CSI, network device 102 sends the second measurement resources for all times after the third information transmission time. For example, when determining CSI for four times based on model, and the third information is used to instruct terminal 101 to report monitoring information for four times, network device 102 sends the second measurement resources in the time slots corresponding to all gray-filled boxes as shown in Figure 1B.

[0323] Optionally, when the third information instructs terminal 101 to report monitoring information for a portion of the CSI determined by the model after the third information reception time, network device 102 sends the second measurement resource at a portion of the time after the third information transmission time. For example, when the CSI is determined based on the model for four times, and the third information is used to instruct terminal 101 to report monitoring information for the first and last times of the four times, network device 102 sends the second measurement resource in the time slots corresponding to the first and fourth gray-filled boxes as shown in Figure 1B.

[0324] In some embodiments, network device 102 sends a second measurement resource at a corresponding time.

[0325] In some embodiments, the second measurement resource is used to measure and obtain channel information such as a channel matrix at one or more times, and then calculate and obtain the CSI at one or more times based on the measured channel matrix; or the second measurement resource is used to measure and obtain the CSI at one or more times.

[0326] Optionally, a second measurement resource such as at least one of CSI-RS and CSI-IM.

[0327] In step S2212, terminal 101 determines monitoring information based on the second measurement resource.

[0328] In some embodiments, terminal 101 obtains channel information such as a channel matrix at one or more times based on the second measurement resource, and then calculates the CSI at one or more times based on the measured channel matrix, or obtains the CSI at one or more times based on the second measurement resource.

[0329] Optionally, the CSI at one or more times determined based on the second measurement resource can also be referred to as the third CSI. The third CSI serves as the true value of the model and is used to evaluate the predicted CSI, i.e., the second CSI.

[0330] In some embodiments, terminal 101 calculates model performance index values ​​based on one or more time-based CSIs, such as second CSIs, determined based on the model, and one or more time-based CSIs, such as third CSIs, determined based on second measurement resources, and uses the model performance index values ​​as monitoring information to evaluate the performance of model predictions.

[0331] In step S2213, terminal 101 and network device 102 determine the second delay corresponding to the obtained monitoring information.

[0332] Optionally, in this embodiment of the disclosure, terminal 101 is used as an example, and the implementation of network device 102 can refer to the behavior of terminal 101.

[0333] In some embodiments, the start time of the second delay may be the time slot in which the third information is received.

[0334] In some embodiments, a second time delay is determined based on the number of times corresponding to one or more times and the interval between different times.

[0335] Optionally, the one or more times are the times in the prediction window, and the number of times is the number of times (e.g., slots) corresponding to the predicted CSI in the prediction window.

[0336] Optionally, at least one of the number of times corresponding to one or more times and the interval between different times is defined by the protocol.

[0337] Optionally, at least one of the number of times corresponding to one or more times and the interval between different times is sent by the network device 102 to the terminal 101, for example, by a separate signaling, or included in a triggering instruction or third information sent by the network device 102 to the terminal 101.

[0338] Optionally, the time unit for the interval between adjacent moments is an OFDM symbol or a time slot.

[0339] In one example, the number of time points corresponding to one or more time points is 4, the number of time points corresponding to the predicted CSI in the prediction window is 4, and the interval between adjacent time points is 1 time slot.

[0340] In some embodiments, the second delay represents the interval between the time slot in which the terminal 101 receives the third information and the time slot in which the terminal 101 sends the monitoring information to the network device 102, that is, the interval between the time when the third information is received and the time when the monitoring information is sent.

[0341] In some embodiments, determining the second delay based on the number of times corresponding to one or more times and the interval between different times includes any of the following embodiments:

[0342] In the first embodiment, when the time of receiving the third information is before the first time of all times in one or more times, the second delay is determined based on the number of times, the interval between adjacent times, and the time delay required to determine the monitoring information of a time.

[0343] Optionally, the third information is used to indicate the reporting of performance index values ​​for all time points. For example, if the total number of time points is 4, the third information is used to indicate the reporting of performance index values ​​for 4 time points.

[0344] Optionally, the time unit for determining the time delay required for monitoring information at a given moment is an OFDM symbol.

[0345] Optionally, the value of the time delay required to determine the monitoring information at a certain moment can be defined with reference to Table 1 or Table 2 in the aforementioned embodiments.

[0346] In one example, when the reception time of the third information is before the first of all times in one or more times, the second delay is one of the following:

[0347] in, This represents the time delay required to determine the monitoring information at a given moment. N4 represents the number of moments, d represents the interval between adjacent moments, and Ns represents the number of symbols in a time slot. For example, Ns is 14.

[0348] For example, Figures 2C to 2D are schematic diagrams of the second time delay according to embodiments of the present disclosure. As shown, the black filled box in the measurement window refers to the CSI measured by the terminal in one time slot (i.e., measured CSI), the gray filled box in the prediction window refers to the CSI predicted by the terminal in one time slot (i.e., predicted CSI), and the white unfilled box refers to the interval between adjacent time moments. PDCCH is used to trigger the reporting of monitoring information, such as third information, and PUSCH is used to report monitoring information.

[0349] Optionally, As shown in Figure 2C, the end position of the prediction window is at the time slot where the last predicted CSI is located. If the prediction window includes 1 time point and the number of intervals between adjacent time points is 0, the second delay... If the prediction window includes 2 time points and the interval between adjacent time points is 1, the second time delay... When the number of time points is 2, compared to when the number of time points is 1, the second delay adds the time delay required to determine the monitoring information of a time point and an interval between adjacent time points.

[0350] Optionally, the second delay As shown in Figure 2D, the end position of the prediction window is the time slot after the last predicted CSI. If the prediction window includes 1 time point and the number of intervals between adjacent time points is 0, the second delay... If the prediction window includes 2 time points and the interval between adjacent time points is 2, the second time delay... When the number of time points is 2, compared to when the number of time points is 1, the second delay increases the time required to determine the monitoring information of a time point and the interval between two adjacent time points.

[0351] In the second embodiment, when the time of receiving the third information is before the i-th time among all the times in one or more times, the second delay is determined based on the number of times, the interval between different times, the time delay required to determine the monitoring information of a time, and the time index i.

[0352] Optionally, i ≤ N4, where N4 represents the number of time points, and optionally, i ∈ {2, 3, ..., N4}.

[0353] Optionally, the third information indicates the reporting of performance index values ​​for a portion of one or more time points.

[0354] Optionally, the third information indicates the performance index value for the remaining time after the third information reception time.

[0355] Optionally, the interval between different times is the interval between adjacent times.

[0356] In one example, the second delay is:

[0357] in, N4 represents the time delay required to determine the monitoring information at a given moment, d represents the interval between adjacent moments, and Ns represents the number of symbols in a time slot.

[0358] In one example, when N4 = 4 and i = 3, as shown in Figure 2E, if Ns is 14, the second time delay T proc,CSI for The monitoring information includes performance index values ​​for the two time slots following PDCCH.

[0359] In the third embodiment, when the time of receiving the third information is before the first time in a subset of one or more times, the second delay is determined based on the number of times, the interval between different times, the delay required to determine the monitoring information of a time, and the time index i.

[0360] Optionally, the third information indicates the reporting of performance index values ​​for a portion of one or more time points.

[0361] Optionally, the third information indicates the performance index values ​​for a portion of the time after the third information is received.

[0362] Optionally, i is the index of the first time point in the partial time frame within all time frames, and optionally, i ∈ {1, 2, ..., N4}. For example, the first time point in the partial time frame is time i = 3, which is the 3rd time point in the prediction window.

[0363] Optionally, the interval between different times can be the interval between adjacent times or the interval between the first and last times in a set of times.

[0364] In one example, the second delay is: or

[0365] in, N4 represents the time delay required to determine the monitoring information at a given moment, d represents the interval between adjacent moments, δ represents the interval between the first and last moments in a subset of moments, and Ns represents the number of symbols in a time slot.

[0366] In one example, N4 = 4, i = 1, and the partial time points are the first and fourth time points, if Ns is 14, the second time delay is... Or the second delay is The monitoring information includes performance index values ​​for the two time slots following PDCCH.

[0367] In some embodiments, the second delay represents the interval between the time slot in which the terminal 101 receives the last second measurement resource and the time slot in which the terminal 101 sends the monitoring information to the network device 102, that is, the interval between the time when the last second measurement resource is received and the time when the monitoring information is sent.

[0368] In one example, referring to Figures 2F to 2G, the second delay is: T proc,CSI Z′ = Z′ + (d-1)*Ns, where Z′ and The relationship is shown in Table 1 or Table 2 as the relationship between Z′ and Z. The value of Z′ is defined or defined in Table 1 or Table 2 in the aforementioned embodiments. d represents the interval between adjacent times and Ns represents the number of symbols in a time slot, for example, Ns is 14.

[0369] Optionally, in this embodiment, the above three embodiments can refer to this second delay determination method.

[0370] In step S2214, terminal 101 sends monitoring information to network device 102 according to the second delay.

[0371] Optionally, terminal 101 sends monitoring information to network device 102 after the second delay.

[0372] Alternatively, after the terminal 101 and the network device 102 determine the second delay based on the protocol definition, the network device 102 configures the monitoring information reporting time for the terminal. If the monitoring information reporting time is greater than or equal to the second delay, the terminal 101 sends the monitoring information to the network device 102 within the monitoring information reporting time.

[0373] In some embodiments, network device 102 receives monitoring information.

[0374] Optionally, network device 102 receives monitoring information based on a second delay or the monitoring information reporting time.

[0375] In some embodiments, terminal 101 sends monitoring information via PUSCH.

[0376] Optionally, terminal 101 uses different PUSCH to send monitoring information and the second CSI in step S2209.

[0377] Optionally, terminal 101 uses the same PUSCH to send monitoring information and the second CSI in step S2209.

[0378] Optionally, during the process of reporting monitoring information, terminal 101 may simultaneously report the second CSI in the model monitoring performance.

[0379] The communication method involved in the embodiments of this disclosure may include at least one of steps S2201 to S2214. For example, step S2207 may be implemented as a standalone embodiment, steps S2210 and S2213 may be implemented as standalone embodiments, and steps S2207, S2210 and S2213 may be implemented as standalone embodiments, but are not limited thereto.

[0380] In some embodiments, one of steps S2201 and S2202 may be optional, or the order of steps S2101 and S2102 may be interchanged.

[0381] In some embodiments, steps S2207 and S2208 may be performed in an alternate order or simultaneously, and steps S2212 and S2213 may be performed in an alternate order or simultaneously.

[0382] In some embodiments, steps S2201 to S2206 and steps S2208 to S2214 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0383] In some embodiments, steps S2201 to S2209, S2211, S2212, and S2214 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0384] In some embodiments, steps S2201 to S2206, S2208 to S2209, S2211, S2212, and S2214 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0385] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0386] Figure 3A is an interactive schematic diagram illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 3A, the present disclosure relates to a communication method, which includes:

[0387] In step S3101, terminal 101 and network device 102 determine the first delay based on the state of the model.

[0388] In some embodiments, the implementation of step S3101 can be referred to the implementation of step S2107 in FIG2A, and will not be repeated here.

[0389] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0390] Figure 3B is an interactive schematic diagram illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 3B, the embodiments of the present disclosure relate to a communication method, which includes:

[0391] In step S3201, terminal 101 sends first information to network device 102.

[0392] In some embodiments, the implementation of step S3201 can be referred to the implementation of step S2102 in FIG2A, and will not be repeated here.

[0393] In step S3202, terminal 101 and network device 102 determine the first delay based on the state of the model.

[0394] In some embodiments, the implementation of step S3202 can be referred to the implementation of step S2107 in FIG2A, and will not be repeated here.

[0395] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0396] Figure 3C is an interactive schematic diagram illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 3C, the embodiments of the present disclosure relate to a communication method, which includes:

[0397] In step S3301, network device 102 sends second information to terminal 101.

[0398] In some embodiments, the implementation of step S3301 can be referred to the implementation of step S2101 in FIG2A, and will not be repeated here.

[0399] In step S3302, terminal 101 and network device 102 determine the first delay based on the state of the model.

[0400] In some embodiments, the implementation of step S3302 can be referred to the implementation of step S2107 in FIG2A, and will not be repeated here.

[0401] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0402] Figure 3D is an interactive schematic diagram illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 3D, the embodiments of the present disclosure relate to a communication method, which includes:

[0403] In step S3401, terminal 101 and network device 102 determine the first delay based on the state of the model.

[0404] In some embodiments, the implementation of step S3401 can be referred to the implementation of step S2107 in FIG2A, and will not be repeated here.

[0405] In step S3402, network device 102 sends third information to terminal 101.

[0406] In some embodiments, the implementation of step S3402 can be referred to the implementation of step S2110 in FIG2B, and will not be repeated here.

[0407] In step S3403, terminal 101 and network device 102 determine the second delay corresponding to the obtained monitoring information.

[0408] In some embodiments, the implementation of step S3403 can be referred to the implementation of step S2113 in FIG2B, and will not be repeated here.

[0409] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0410] This disclosure provides a communication method that calculates the latency requirements required for CSI or monitoring results when reporting CSI based on AI model inference and CSI based on AI model monitoring, so as to enable the network to configure a reasonable CSI reporting time.

[0411] To facilitate understanding of the embodiments of this disclosure, some embodiments are listed below:

[0412] In some embodiments, a method for determining whether an AI model is deployed in AI model processing and a method for processing the AI ​​model after AI model inference are provided. Based on the determination method and the processing method, the latency requirement used to calculate CSI during AI model inference is determined. For monitoring the AI ​​model performance at multiple time points, the latency requirement used to calculate the monitoring results shall at least include the interval between the multiple monitoring time points.

[0413] Example 1: Definition of timeline for AI model inference reporting.

[0414] Example 1.1: The network determines whether the terminal's AI model has been deployed to the AI ​​model processor in one of the following ways:

[0415] Method 1: The terminal reports indication information to indicate that the AI ​​models supported or available to the terminal have been deployed in the AI ​​model processor. Optionally, the indication information can be reported in the reporting information when reporting terminal capabilities or available AI models.

[0416] Optionally, the indication information corresponds to the first information in the foregoing embodiments.

[0417] Method 2: The terminal receives a signal from the network to activate the AI ​​model or AI function, or receives parameters configured by the network, and deploys the activated model to the AI ​​model processor. Optionally, the parameters configured by the network refer to the relevant parameters used to determine the input information, output information, and dimensions of the AI ​​model.

[0418] Optionally, the signaling or network configuration parameters for activating the AI ​​model or AI function via the network correspond to the second information in the aforementioned embodiments.

[0419] Example 1.2: How to define the calculation time of CSI.

[0420] In some embodiments, if the terminal and network have determined, according to method 1 or method 2 above, that the AI ​​model has been deployed to the AI ​​model processor and is in an active state before a CSI report is submitted, then the CSI calculation time is the measurement CSI time. This includes model inference time.

[0421] In some embodiments, if the terminal and network have determined, according to method 1 or method 2 above, that the AI ​​model has not been deployed to the AI ​​model processor before a CSI report is submitted, then the CSI calculation time is [time missing]. Where D1 is the time required for the AI ​​model to be loaded from the AI ​​model memory to the AI ​​model processor.

[0422] In some embodiments, after completing AI model inference, the AI ​​model is processed in one of the following two ways:

[0423] Method 1: The AI ​​model is in a dormant state;

[0424] Method 2: Remove the AI ​​model from the AI ​​model processor.

[0425] Optionally, the processing method of the AI ​​model can be determined by at least one of the following: predefined method, network instruction via signaling, or terminal instruction via message reporting.

[0426] In some embodiments, if the processing of the AI ​​model after AI model inference is performed using method 1 described above, then the computation time for CSI is... Where D2 is the latency required for the AI ​​model to transition from a dormant state to an active state.

[0427] In some embodiments, if the processing of the AI ​​model after AI model inference is performed using method 2 described above, then the computation time for CSI is... That is, before calculating CSI, the AI ​​model needs to be loaded from memory into the AI ​​model processor.

[0428] In some embodiments, the calculation time for CSI is determined to be... Where D represents the time required to load the model from memory into the processor (D1) or the time required for model activation (D2). This does not take into account the CSI computation latency requirements used for model loading or model activation.

[0429] Optionally, the values ​​of D1 and D2 mentioned above can be determined by terminal predefinition or terminal capability indication reporting.

[0430] Optionally, the above The time units D1 and D2 can be represented by OFDM symbols.

[0431] Optionally, D1 corresponds to the first value in the aforementioned embodiments, D2 corresponds to the second value in the aforementioned embodiments, and the calculation time of CSI corresponds to the first delay in the aforementioned embodiments.

[0432] Optionally, the above The value can be any of the possible values ​​of Z or Z′ in Table 1 or Table 2 of the aforementioned embodiments. Optionally, the latency used for calculating CSI during AI model inference is defined according to a predefined latency value, i.e., for different values ​​of μ.

[0433] Example 2: Timeline definition for AI model performance monitoring and reporting (assuming CSI at N4 time points during AI model inference).

[0434] Example 2.1: Monitoring the performance of the AI ​​model at all N4 time points.

[0435] Example 2.1.1: When the trigger command for monitoring information reporting occurs before the first time point within the prediction window, the latency required for monitoring information reporting by an AI model is expressed as a function of N₄ and d. For example, as shown in Figure 2C, the latency required for monitoring information reporting is calculated as follows: in, The time delay required to calculate the monitoring information when N4 = 1 is given by d, where d is the time interval between adjacent moments in the N4 time intervals. Alternatively, as shown in Figure 2D, the time delay required to calculate the monitoring information is...

[0436] Optionally, the trigger command corresponds to the third information in the aforementioned embodiments, 14 corresponds to Ns in the aforementioned embodiments, and the time delay T required to calculate the monitoring information is calculated. proc,CSI This corresponds to the second delay in the aforementioned embodiments.

[0437] Example 2.1.2: When the trigger command for monitoring information reporting occurs before the i-th time (i∈{2,3,…,N4}) of the predicted N4 time points, what is the latency T required for an AI model to report monitoring information? proc,CSI Represented as a function of N4-i and d, for example, the time delay required to calculate monitoring information is...

[0438] In some embodiments, the time delay T′ required for monitoring information is calculated by taking the time of the last channel measurement resource used for monitoring information as a reference. proc,CSI =Z′+d-1.

[0439] Example 2.2: Monitoring the AI ​​model performance at N′4 partial time points out of N4 time points, where N′4 <N4。

[0440] When the trigger command for monitoring information reporting occurs before the first of N′4 time points, the latency required for a monitoring AI model performance report is determined based on the first of N′4 time points and d. For example, the latency required to calculate the monitoring information is... Where i∈{1,…,N4} is the index of the first time point in the N4 time points. Optionally, the time delay T required for a monitoring information report is... proc,CSI It is at least a function of intervals δ and / or d, for example, the required delay is Where δ is the interval between the first and last time points in the reported time segment.

[0441] Alternatively, in Example 2, The value of Z is taken from the value of Z in Table 1 or Table 2 of the aforementioned embodiments, and the value of Z′ is taken from the value of Z′ in Table 1 or Table 2 of the aforementioned embodiments.

[0442] Example 3: Assuming the terminal memory includes an AI model (or AI function) for beam prediction or CSI prediction, Figure 4 is an interactive diagram illustrating the query of the available AI model on the terminal according to an embodiment of this disclosure. Based on the above embodiments, as shown in Figure 4, the method may include the following steps:

[0443] Step S4101: The network sends a capability query command (UECapabilityEnquiry) to the terminal.

[0444] In some embodiments, the terminal receives a capability query command.

[0445] Step S4102: The terminal sends UECapabilityInformation to the network.

[0446] In some embodiments, network reception capability information.

[0447] Alternatively, capability information can also be referred to as capability reporting information.

[0448] In some embodiments, the capability information includes the AI ​​models supported by the terminal.

[0449] In some embodiments, the capability information includes or corresponds to the first information in the foregoing embodiments.

[0450] Step S4103: The network sends the first RRC configuration parameter (RRCReconfiguration) to the terminal.

[0451] In some embodiments, the terminal receives a first RRC configuration parameter.

[0452] In some embodiments, when the network wants the terminal to perform the inference function of the AI ​​model, it sends RRC configuration parameters to the terminal.

[0453] In some embodiments, the first RRC configuration parameter can be used to determine the input information, output information, and dimensions of the AI ​​model.

[0454] In some embodiments, the first RRC configuration parameter corresponds to the second information in the foregoing embodiments.

[0455] In step S4104, the terminal sends an indication message (Applicable functionality reporting) to the network.

[0456] In some embodiments, the indication message is used to indicate the available AI models.

[0457] In some embodiments, the terminal determines the available AI model based on the RRC configuration parameters and the AI ​​model or AI function supported by the terminal itself.

[0458] In some embodiments, the instruction message includes or corresponds to the first information in the foregoing embodiments.

[0459] In step S4105, the network sends the second RRC configuration parameter (RRCReconfiguration) to the terminal.

[0460] In some embodiments, the second RRC configuration parameter can be used to better adapt to the AI ​​models available on the terminal.

[0461] In some embodiments, step S4105 is optional.

[0462] In some embodiments, the second RRC configuration parameter corresponds to the second information in the foregoing embodiments.

[0463] Step S4106: AI model activation, deactivation, inference, and monitoring.

[0464] In some embodiments, the AI ​​model is activated in two ways, wherein activating the AI ​​model refers to loading the AI ​​model from memory such as ROM into the AI ​​model processor:

[0465] Method 1: The AI ​​model activation is completed after reporting the available AI model in step S4104 of Figure 4.

[0466] Method 2: After step S4103 or step S4105 in Figure 4, that is, after the terminal receives the network configuration to determine the AI ​​model input information, output information and dimension and other parameters.

[0467] For example, if the network instructs the terminal to execute an AI model for CSI prediction and provide CSI feedback, the network can configure Ks = 4 aperiodic CSI-RS resources to measure channel information at historical time points. The terminal uses the obtained historical channel information from these Ks time points as the input and output of the AI ​​model. The network also configures the terminal to predict channel information for the next N4 = 1 time points based on the AI ​​model. The terminal determines the output of the AI ​​model to be the channel information for N4 time points based on this configuration information. After receiving these configuration parameters, the terminal loads the corresponding AI model into the AI ​​model processor, activating the AI ​​model. The terminal can then perform inference based on the activated AI model to obtain CSI and report it to the network.

[0468] In some embodiments, after completing CSI reporting, the terminal may perform the following three operations:

[0469] The first method is to clear the AI ​​model from the AI ​​model processor;

[0470] The second scenario involves the AI ​​model still being processed by the AI ​​model processor, but the AI ​​model is in a dormant state, i.e., not activated.

[0471] The third type involves keeping the AI ​​model constantly active within the AI ​​model processor.

[0472] For the first scenario described above, if the AI ​​model is not in the AI ​​model processor, the terminal needs to load the AI ​​model from ROM into the AI ​​model processor before activating it the next time it performs AI model inference. In this case, the CSI calculation timeline includes both AI model inference and CSI measurement time requirements. In addition, it also includes the time D1 for loading the AI ​​model into the AI ​​model processor.

[0473] For the second scenario described above, the terminal needs to activate the AI ​​model from its dormant state before performing the next inference operation, and then proceed with inference and CSI measurement. In this case, the CSI calculation timeline includes not only the AI ​​model inference and CSI measurement time requirements, but also... In addition, it also includes the AI ​​model activation time D2.

[0474] For the third case mentioned above, the AI model is always activated and can be directly used for AI model inference. Therefore, calculating the CSI timeline only requires the time for AI model inference and CSI measurement

[0475] Optionally, the value of D1 or D2 may be indicated to the network when the terminal reports its capability.

[0476] Example 4: Performance monitoring timeline.

[0477] Assume that the AI model infers CSI at future N4=4 time instants based on CSI from 4 historical measurements, and the network triggers reporting of monitoring information by sending DCI signaling carried on PDCCH.

[0478] In some embodiments, the AI model performance at all N4 time instants is monitored, and the time instant where DCI is located is before the first predicted time slot (i.e., the aforementioned Example 2.1.1). Figure 2F is a schematic diagram of the latency requirement for calculating monitoring information shown according to embodiments of the present disclosure. As shown in Figure 2F, in order to calculate the monitoring information, the network needs to send CSI-RS in the 4 predicted time instants within the prediction window, that is, in the time slots where the gray positions are located, to obtain real channel information. The terminal calculates performance KPIs such as SGCS or NMSE using the obtained real channel information and the predicted channel information, as the to-be-reported monitoring information. The time for calculating the monitoring information wherein d=2 time slots (slots). Correspondingly, T' proc,CSI =Z'+(d-1)×14=Z'+14.

[0479] In some embodiments, the time instant where DCI is located is before the i-th ∈ {2,3,…,N4} time slot among the N4 predicted time instants, and the AI model performance at N4 time instants after DCI is monitored (i.e., the aforementioned Example 2.1.2). Assume i=3, as shown in Figure 2G, the time for calculating monitoring information wherein d=2 time slots. Correspondingly, T' proc,CSI =Z'+(d-1)×14=Z'+14.

[0480] In some embodiments, the AI model performance at N'4 partial time instants among the N4 time instants is monitored, where N'4 < N4. Assume N'4=2, for example, only the first time instant and the last time instant among the 4 predicted time instants are monitored. When the time when DCI triggers the reporting of monitoring information is before the first time instant of the prediction window (i.e., the aforementioned Example 2.2), then i=1, the time delay required for calculating monitoring information is wherein d=2 time slots. Correspondingly, T' proc,CSI =Z'+(d-1)×14=Z'+14.

[0481] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0482] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0483] This disclosure also proposes an apparatus (also referred to as a communication device, etc.) for implementing any of the above methods. For example, an apparatus is proposed that includes units or modules for implementing the steps performed by the terminal in any of the above methods. Furthermore, another apparatus is proposed that includes units or modules for implementing the steps performed by a network device (e.g., an access network device, a core network functional node, a core network device, etc.) in any of the above methods.

[0484] 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 configuration files, 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.

[0485] In this embodiment, 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 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 using 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).

[0486] Figure 5A is a schematic diagram of the structure of a terminal proposed in an embodiment of this disclosure. Terminal 5100 is used to execute any of the above methods. In some embodiments, as shown in Figure 5A, terminal 5100 may include at least one of a transceiver module 5101, a processing module 5102, etc. In some embodiments, the processing module 5102 is used to determine a first delay based on the state of a model, wherein the model is used to determine channel state information (CSI), and the first delay is used to indicate the delay for determining the CSI based on the model.

[0487] Optionally, the transceiver module 5101 is used to execute at least one of the communication steps (e.g., steps S2101, S2102, S2104, S2106, S2210, S2211, S2214, but not limited thereto) performed by the terminal 101 in any of the above methods, which will not be elaborated here. Optionally, the processing module 5102 is used to execute at least one of the other steps (e.g., steps S2103, S2105, S2108, S2212, S2213, but not limited thereto) performed by the terminal 101 in any of the above methods, which will not be elaborated here.

[0488] Figure 5B is a schematic diagram of the structure of a network device according to an embodiment of this disclosure. The network device 5200 is used to perform any of the above methods. In some embodiments, as shown in Figure 5B, the network device 5200 may include at least one of a transceiver module 5201, a processing module 5202, etc. In some embodiments, the processing module 5102 is used to determine a first delay based on the state of a model, wherein the model is used to determine channel state information (CSI), and the first delay is used to indicate the delay for determining the CSI based on the model.

[0489] Optionally, the transceiver module 5201 is used to perform at least one of the communication steps (e.g., steps S2101, S2102, S2104, S2106, S2210, S2211, S2214, but not limited thereto) performed by the network device 102 in any of the above methods, which will not be elaborated here. Optionally, the processing module 5202 is used to perform at least one of the other steps (e.g., steps S2103, S2107, S2213, but not limited thereto) performed by the network device 102 in any of the above methods, which will not be elaborated here.

[0490] In some embodiments, the transceiver module may include a transmitting module and / or a receiving module, which may be separate or integrated. Optionally, the transceiver module may be interchangeable with a transceiver.

[0491] In some embodiments, the processing module may be a single module or may include multiple sub-modules. Optionally, the multiple sub-modules may each perform all or part of the steps required by the processing module.

[0492] In some embodiments, the processing module can be replaced by the processor, and the transceiver module can be replaced by the transceiver.

[0493] Figure 6A is a schematic diagram of the structure of the communication device 6100 proposed in an embodiment of this disclosure. The communication device 6100 can be a network device (e.g., access network device, core network device, etc.), a terminal (e.g., user equipment, etc.), a chip, chip system, or processor that supports the network device in implementing any of the above methods, or a chip, chip system, or processor that supports the terminal in implementing any of the above methods. The communication device 6100 can be used to implement the methods described in the above method embodiments; for details, please refer to the descriptions in the above method embodiments.

[0494] As shown in Figure 6A, the communication device 6100 is used to execute any of the above methods. In some embodiments, the communication device 6100 includes one or more processors 6101. The processor 6101 may be a general-purpose processor or a special-purpose processor, such as a baseband processor or a central processing unit. The baseband processor may be used to process communication protocols and communication data, and the central processing unit may be used to control communication devices (e.g., base stations, baseband chips, terminal devices, terminal device chips, DUs or CUs, etc.), execute programs, and process program data. Optionally, the communication device 6100 is used to execute any of the above methods. Optionally, one or more processors 6101 are used to invoke instructions to cause the communication device 6100 to execute any of the above methods.

[0495] In some embodiments, the communication device 6100 further includes one or more transceivers 6102. When the communication device 6100 includes one or more transceivers 6102, the transceiver 6102 performs at least one of the communication steps such as sending and / or receiving in the above method (e.g., steps S2101, S2102, S2104, S2106, S2210, S2211, S2214, but not limited thereto), and the processor 6101 performs at least one of other steps (e.g., steps S2103, S2107, S2213, but not limited thereto). In optional embodiments, the transceiver may include a receiver and / or a transmitter, which may be separate or integrated. Optionally, the terms transceiver, transceiver unit, transceiver, transceiver circuit, interface circuit, interface, etc., can be used interchangeably; the terms transmitter, transmitting unit, transmitter, transmitting circuit, etc., can be used interchangeably; the terms receiver, receiving unit, receiver, receiving circuit, etc., can be used interchangeably.

[0496] In some embodiments, the communication device 6100 further includes one or more memories 6103 for storing data and / or instructions. Optionally, one or more processors 6101 are used to invoke instructions stored in the memory 6103 to cause the communication device 6100 to perform any of the above methods. Optionally, all or part of the memory 6103 may also be located outside the communication device 6100. In an optional embodiment, the communication device 6100 may include one or more interface circuits 6104. Optionally, the interface circuit 6104 is connected to the memory 6102 and can be used to receive data and / or instructions from the memory 6102 or other devices, and can be used to send data and / or instructions to the memory 6102 or other devices. For example, the interface circuit 6104 can read data and / or instructions stored in the memory 6102 and send the data and / or instructions to the processor 6101.

[0497] The communication device 6100 described in the above embodiments may be a network device or a terminal, but the scope of the communication device 6100 described in this disclosure is not limited thereto, and the structure of the communication device 6100 may not be limited by FIG. 6A. The communication device may be a standalone device or a 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, programs and / or instructions; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a receiver, terminal device, smart terminal device, cellular phone, wireless device, handheld device, mobile unit, vehicle device, network device, cloud device, artificial intelligence device, etc.; (6) others, etc.

[0498] Figure 6B is a schematic diagram of the structure of chip 6200 according to an embodiment of this disclosure. For cases where the communication device 6100 can be a chip or a chip system, please refer to the schematic diagram of chip 6200 shown in Figure 6B, but it is not limited thereto.

[0499] Chip 6200 includes one or more processors 6201. Chip 6200 is used to perform any of the methods described above.

[0500] In some embodiments, chip 6200 further includes one or more interface circuits 6202. Optionally, terms such as interface circuit, interface, and transceiver pin can be used interchangeably. In some embodiments, chip 6200 further includes one or more memories 6203 for storing data and / or instructions. Optionally, all or part of the memories 6203 may be located outside of chip 6200. Optionally, interface circuit 6202 is connected to memory 6203, and interface circuit 6202 can be used to receive data and / or instructions from memory 6203 or other devices, and interface circuit 6202 can be used to send data and / or instructions to memory 6203 or other devices. For example, interface circuit 6202 can read data and / or instructions stored in memory 6203 and send the data and / or instructions to processor 6201.

[0501] In some embodiments, the interface circuit 6202 performs at least one of the communication steps such as sending and / or receiving in the above-described method (e.g., steps S2101, S2102, S2104, S2106, S2210, S2211, and S2214, but not limited thereto). The interface circuit 6202 performing the communication steps such as sending and / or receiving in the above-described method refers, for example, to the interface circuit 6202 performing data and / or instruction interaction between the processor 6201, the chip 6200, the memory 6203, or the transceiver device. In some embodiments, the processor 6201 performs at least one of other steps (e.g., steps S2103, S2107, and S2213, but not limited thereto).

[0502] The modules and / or devices described in the various embodiments, such as virtual devices, physical devices, and chips, can be combined or separated arbitrarily as needed. Optionally, some or all steps can also be performed collaboratively by multiple modules and / or devices, which is not limited here.

[0503] This disclosure also proposes a storage medium storing instructions that, when executed on a communication device, cause the communication device to perform any of the above methods. Optionally, the storage medium is an electronic storage medium. Optionally, the storage medium is a computer-readable storage medium, but not limited thereto; it may also be a storage medium readable by other devices. Optionally, the storage medium may be a non-transitory storage medium, but not limited thereto; it may also be a temporary storage medium.

[0504] This disclosure also proposes a program product, including a program and / or instructions, which, when executed by a communication device, cause the communication device to perform any of the above methods. Optionally, the program product is a computer program product. Optionally, the program product is stored on the storage medium.

[0505] This disclosure also proposes a computer program that, when run on a computer, causes the computer to perform any of the above methods. Industrial applicability

[0506] The latency for determining CSI based on the model varies depending on the model's state. Terminals and network devices can determine the corresponding initial latency based on the model's state, allowing network devices to be configured appropriately to ensure that the terminal can complete CSI processing or calculation within a sufficient latency, thereby improving overall communication performance.

Claims

1. A method for determining latency, executed by a terminal, the method comprising: A first delay is determined based on the state of the model, wherein the model is used to determine channel state information (CSI), and the first delay is used to indicate the delay for determining CSI based on the model.

2. The method as described in claim 1, wherein, The method further includes: Send first information to the network device, the first information being used to indicate whether one or more models supported by the terminal are in a first state, the first state indicating that the model has been loaded into the processor from memory and is in an active state.

3. The method of claim 1, wherein, The method further includes: Receive second information sent by a network device, the second information being used to indicate the activation of one or more models or to indicate model parameters of one or more said models; After the first symbol following the second information reception time, and after a set time offset, the model is determined to be in a first state, wherein the first state indicates that the model has been loaded into the processor from the memory and is in an active state.

4. The method of claim 3, wherein, The set duration is defined by the protocol, or the set duration is sent by the terminal to the network device.

5. The method as described in any one of claims 2 to 4, wherein, Determining the first time delay based on the state of the model includes the following: The model is in a first state, and the first delay is determined to be a first value, where the first value represents the delay required by the terminal to determine the CSI based on the model. The model is in a second state, and the first delay is determined to be the sum of a first value and a second value, where the second value represents the delay required for the model to be loaded from memory into the processor, and the second state indicates that the model has not been loaded from memory into the processor; The model is in a third state, and the first delay is determined to be the sum of the first value and the third value. The third value represents the delay required for the model to transition from a dormant state to an active state. The third state indicates that the model has been loaded into the processor from the memory and is in a dormant state.

6. The method of claim 5, wherein, At least one of the first value, the second value, and the third value is defined by the protocol or is sent by the terminal to the network device.

7. The method of any one of claims 2 to 4, wherein, Determining the first delay based on the state of the model includes: Based on the state of the model, the first delay is determined as the fourth value, which includes the delay of the terminal determining CSI based on the model and the delay of processing the model; The latency of the processing model includes the latency required for the model to be loaded from memory to the processor or the latency required for the model to transition from a sleep state to an active state.

8. The method as claimed in any one of claims 2 to 7, wherein, The method further includes: After determining the CSI based on the model in the first state, the model in the first state is removed by the processor or the model in the first state is converted to the third state.

9. The method according to any one of claims 1 to 8, wherein, The method further includes: The terminal receives third information sent by the network device, the third information being used to instruct the terminal to report monitoring information; Determine the second time delay corresponding to obtaining the monitoring information; The monitoring information includes model performance index values ​​corresponding to one or more CSI times determined by the model.

10. The method of claim 9, wherein, Determining the second time delay corresponding to obtaining the monitoring information includes: The second time delay is determined based on the number of times corresponding to the one or more times and the interval between different times.

11. The method of claim 10, wherein, The reception time of the third information is located before the first time of all the one or more times. Determining the second delay based on the number of times corresponding to the one or more times and the interval between different times includes: The second delay is determined based on the number of time points, the interval between adjacent time points, and the time delay required to determine the monitoring information for a given time point; wherein the third information indicates the reporting of performance index values ​​for all time points.

12. The method of claim 11, wherein, The second delay is one of the following: in, N4 represents the time delay required to determine the monitoring information at a given moment, d represents the interval between adjacent moments, and Ns represents the number of symbols in a time slot.

13. The method of claim 10, wherein, Determining the second time delay based on the number of times corresponding to the one or more times and the interval between different times includes: The second delay is determined based on the number of time points, the interval between different time points, the time delay required to determine the monitoring information of a time point, and the time index i. Wherein, the third information indicates the reporting of performance index values ​​for a portion of the one or more time points, and the receiving time of the third information is before the i-th time point among all the one or more time points; or, the receiving time of the third information is before the first time point among the portion of time points, where i is the index of the first time point among the portion of time points in all the time points; where i≤N4; The interval between the different times is the interval between adjacent times or the interval between the first and last times in the partial time.

14. The method of claim 13, wherein, The third information indicates that performance index values ​​for a portion of the one or more time points should be reported, and the second delay is: Where i∈{2,3,...,N4}; or, The second delay is: or Where i∈{1,2,...,N4}; in, N4 represents the time delay required to determine the monitoring information at a given moment, d represents the interval between adjacent moments, δ represents the interval between the first and last moments in the given time period, and Ns represents the number of symbols in a time slot.

15. A method for determining latency, performed by a network device, the method comprising: A first delay is determined based on the state of the model, wherein the model is used to determine channel state information (CSI), and the first delay is used to indicate the delay for determining CSI based on the model.

16. The method of claim 15, wherein, The method further includes: The receiving terminal sends first information, which is used to indicate whether one or more models supported by the terminal are in a first state, the first state indicating that the model has been loaded into the processor from the memory and is in an active state.

17. The method of claim 15, wherein, The method further includes: Send a second message to the terminal, the second message being used to indicate the activation of one or more models or to indicate the model parameters of one or more of the models; After the first symbol following the second information transmission time, and after a set time offset, the model is determined to be in a first state, wherein the first state indicates that the model has been loaded from memory into the processor and is in an active state.

18. The method of claim 17, wherein, The set duration is defined by the protocol, or the set duration is sent by the terminal to the network device.

19. The method as claimed in any one of claims 16 to 18, wherein, Determining the first time delay based on the state of the model includes the following: The model is in a first state, and the first delay is determined to be a first value, where the first value represents the delay required by the terminal to determine the CSI based on the model. The model is in a second state, and the first delay is determined to be the sum of a first value and a second value, where the second value represents the delay required for the model to be loaded from memory into the processor, and the second state indicates that the model has not been loaded from memory into the processor; The model is in a third state, and the first delay is determined to be the sum of the first value and the third value. The third value represents the delay required for the model to transition from a dormant state to an active state. The third state indicates that the model has been loaded into the processor from the memory and is in a dormant state.

20. The method of claim 19, wherein, At least one of the first value, the second value, and the third value is defined by the protocol or is sent by the terminal to the network device.

21. The method as claimed in any one of claims 16 to 18, wherein, Determining the first delay based on the state of the model includes: Based on the state of the model, the first delay is determined as the fourth value, which includes the delay of the terminal determining CSI based on the model and the delay of processing the model; The latency of the processing model includes the latency required for the model to be loaded from memory to the processor or the latency required for the model to transition from a sleep state to an active state.

22. The method according to any one of claims 15 to 21, wherein, The method further includes: Send a third message to the terminal, the third message being used to instruct the terminal to report monitoring information; Determine the second time delay corresponding to obtaining the monitoring information; The monitoring information includes model performance index values ​​corresponding to one or more CSI times determined by the model.

23. The method of claim 22, wherein, The second time delay is determined based on the number of times corresponding to the one or more times and the interval between different times.

24. The method of claim 23, wherein, The receiving time of the third information is located before the first time of all the times in the one or more times, and the second delay is determined based on the number of times, the interval between adjacent times, and the delay required to determine the monitoring information of a time; wherein, the third information indicates the reporting of the performance index values ​​of all the times.

25. The method of claim 24, wherein, The second delay is one of the following: in, N4 represents the time delay required to determine the monitoring information at a given moment, d represents the interval between adjacent moments, and Ns represents the number of symbols in a time slot.

26. The method of claim 23, wherein, The second delay is determined based on the number of time points, the interval between different time points, the delay required to determine the monitoring information for a given time point, and the time index i. Wherein, the third information indicates the reporting of performance index values ​​for a portion of the one or more time points, and the receiving time of the third information is before the i-th time point of all the one or more time points; or, the receiving time of the third information is before the first time point of the portion of time points, where i is the index of the first time point of the portion of time points in all the time points; where i≤N4; The interval between the different times is the interval between adjacent times or the interval between the first and last times in the partial time.

27. The method of claim 26, wherein, The third information indicates that performance index values ​​for a portion of the one or more time points should be reported, and the second delay is: Where i∈{2,3,...,N4}; or, The second delay is: or Where i∈{1,2,...,N4}; in, N4 represents the time delay required to determine the monitoring information at a given moment, d represents the interval between adjacent moments, δ represents the interval between the first and last moments in the given time period, and Ns represents the number of symbols in a time slot.

28. A communication device, wherein, The communication device is used to perform the method according to any one of claims 1 to 14 or any one of claims 15 to 27.

29. A communication system comprising a terminal and network equipment, wherein, The terminal is configured to implement the method as described in any one of claims 1 to 14; The network device is configured to implement the method as described in any one of claims 15 to 27.

30. A storage medium storing instructions, wherein, When the instructions are executed on the communication device, the communication device performs the method as described in any one of claims 1 to 14 or any one of claims 15 to 27.

31. A program product comprising at least one of a program and instructions, wherein, When at least one of the programs or instructions is executed by a communication device, it implements the method as described in any one of claims 1 to 14 or any one of claims 15 to 27.

Images