Information processing method and apparatus, communication device, and storage medium

Abstract

Embodiments of the present disclosure provide an information processing method and apparatus, a communication device and a storage medium. The information processing method can include determining occupancy information of a processing unit performing artificial intelligence (AI) and / or machine learning (ML) processing according to configuration information related to the AI / ML processing.

Description

Technical Field

[0001] This disclosure relates to, but is not limited to, the field of wireless communication technology, and particularly to an information processing method and apparatus, communication equipment and storage medium. Background Technology

[0002] With technological advancements, artificial intelligence (AI) and machine learning (ML) can be used to process data during wireless communication.

[0003] If wireless communication involves AI / ML processing, the user equipment (UE) has limited capabilities for AI / ML processing. Therefore, if the configuration information involves AI / ML processing, the occupancy of processing units needs to be considered. Summary of the Invention

[0004] This disclosure provides an information processing method and apparatus, a communication device and a storage medium.

[0005] The first aspect of this disclosure provides an information processing method, wherein the method includes:

[0006] Based on the configuration information related to AI / ML processing, the occupancy information of the processing unit that performs the AI / ML processing is determined.

[0007] A second aspect of this disclosure provides an information processing apparatus, wherein the apparatus includes:

[0008] The processing module is configured to determine the occupancy information of the processing unit that performs the AI / ML processing based on configuration information related to AI / ML processing.

[0009] A third aspect of this disclosure provides a communication device, including a processor, a transceiver, a memory, and an executable program stored in the memory and capable of being run by the processor, wherein the processor executes the information processing method as described in the first aspect above when running the executable program.

[0010] A fourth aspect of this disclosure provides a computer storage medium storing an executable program; the executable program, when executed by a processor, can implement the information processing method provided in the first aspect.

[0011] The technical solutions provided in the embodiments of this disclosure are as follows:

[0012] The terminal or network device will determine the occupancy information of the processing unit based on the configuration information. In this way, when the terminal's processing unit is insufficient to support the required unit, it is necessary to ignore part of the configuration information or re-request the configuration in a timely manner, thereby ensuring the high-quality execution of the configuration corresponding to the configuration information.

[0013] It should be understood that the technical solutions provided in the embodiments of this disclosure are exemplary and explanatory only, and are not intended to limit the embodiments of this disclosure. Attached Figure Description

[0014] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the embodiments of the invention.

[0015] Figure 1 This is a schematic diagram illustrating the structure of a wireless communication system according to an exemplary embodiment;

[0016] Figure 2A This is a flowchart illustrating an information processing method according to an exemplary embodiment;

[0017] Figure 2B This is a flowchart illustrating an information processing method according to an exemplary embodiment;

[0018] Figure 2C This is a flowchart illustrating an information processing method according to an exemplary embodiment;

[0019] Figure 2D This is a flowchart illustrating an information processing method according to an exemplary embodiment;

[0020] Figure 3 This is a schematic diagram of the structure of an information processing apparatus according to an exemplary embodiment;

[0021] Figure 4 This is a schematic diagram of the structure of a terminal according to an exemplary embodiment;

[0022] Figure 5 This is a schematic diagram of the structure of a network device according to an exemplary embodiment. Detailed Implementation

[0023] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of the present invention.

[0024] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the embodiments disclosed herein. The singular forms “a,” “the,” and “the” used herein are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0025] It should be understood that although the terms first, second, third, etc., may be used to describe various information in embodiments of this disclosure, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, first information may also be referred to as second information without departing from the scope of embodiments of this disclosure, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to a determination."

[0026] Please refer to Figure 1 This illustration shows a schematic diagram of the structure of a wireless communication system provided in an embodiment of this disclosure. Figure 1 As shown, the wireless communication system is a communication system based on cellular mobile communication technology. The wireless communication system may include: several UEs 11, several access devices 12, and several core network devices 13.

[0027] UE 11 can be a device that provides voice and / or data connectivity to a user. UE 11 can communicate with one or more core networks via a Radio Access Network (RAN). UE 11 can be an IoT UE, such as a sensor device, a mobile phone (or "cellular" phone), and a computer with an IoT UE. For example, it can be a fixed, portable, pocket-sized, handheld, computer-embedded, or vehicle-mounted device. Examples include a station (STA), subscriber unit, subscriber station, mobile station, mobile station, remote station, access point, remote terminal, access terminal, user terminal, user agent, user device, or user equipment (UE). Alternatively, UE 11 can also be a device in an unmanned aerial vehicle (UAV). Alternatively, UE 11 can also be a vehicle-mounted device, such as a vehicle computer with wireless communication capabilities, or a wireless communication device connected to an external vehicle computer. Alternatively, UE 11 can also be a roadside device, such as a street light, traffic light, or other roadside device with wireless communication capabilities.

[0028] Access device 12 can be a network-side device in a wireless communication system. This wireless communication system can be a 4G system (also known as Long Term Evolution, LTE); or it can be a 5G system (also known as a New Radio, NR, or 5G NR system). Alternatively, it can be the next generation after 5G. In this case, the access network in the 5G system can be called NG-RAN (New Generation-Radio Access Network). Alternatively, it can be an MTC system.

[0029] The access device 12 can be an evolved NB (eNB) used in a 4G system. Alternatively, the access device 12 can also be a gNB (gNB) using a centralized-distributed architecture in a 5G system. When the access device 12 adopts a centralized-distributed architecture, it typically includes a central unit (CU) and at least two distributed units (DUs). The central unit is equipped with a protocol stack of the Packet Data Convergence Protocol (PDCP) layer, the Radio Link Control (RLC) layer, and the Media Access Control (MAC) layer; the distributed units are equipped with a physical (PHY) layer protocol stack. This disclosure does not limit the specific implementation of the access device 12.

[0030] Access device 12 and UE 11 can establish a wireless connection via a wireless air interface. In different implementations, the wireless air interface is a wireless air interface based on the fourth-generation mobile communication network technology (4G) standard; or, the wireless air interface is a wireless air interface based on the fifth-generation mobile communication network technology (5G) standard, such as a new air interface; or, the wireless air interface can also be a wireless air interface based on a next-generation mobile communication network technology standard based on 5G.

[0031] Typical core network equipment includes, but is not limited to: Access Management Function (AMF) and / or Policy Control Function (PCF).

[0032] like Figure 2A As shown in the embodiments of this disclosure, an information processing method is provided, which may include:

[0033] S1110: Determine the occupancy information of the processing unit that performs AI / ML processing based on the configuration information related to AI / ML processing.

[0034] This information processing method can be executed by a terminal or network device. The network device may include access network devices, including but not limited to base stations.

[0035] This configuration information can be any network-side configuration information used during terminal use of AI / ML processing. Here, "AI / ML" means "AI and / or ML".

[0036] This configuration information may include, but is not limited to, RRC configuration information.

[0037] This configuration information may include: configuration information related to measurement, and / or configuration information related to reporting.

[0038] The measurement-related configuration information may include: measurements related to Layer 1, and / or measurements related to Layer 3.

[0039] The measurement-related configuration information may include configuration information related to the terminal's measurement of various reference signals. These reference signals include, but are not limited to: synchronization signal block (SSB), channel information state-reference signal (CSI-RS), and / or positioning reference signal (PRS), etc.

[0040] The measurement-related configuration information may include: configuration information related to reference signal and / or beam measurement.

[0041] The configuration information related to reporting may include: configuration information for reporting measurement data and / or measurement results obtained after measuring the reference signal, and measurement configuration information associated with reporting, such as the measurement configuration ID. The measurement results may be obtained based on the measurement data.

[0042] In this embodiment of the disclosure, "association" can be understood as "binding".

[0043] For example, taking CSI-RS as an example, the measurement data or results obtained by CSI-RS are sent to the network device through a CSI report. The configuration information of this CSI report can be one of the aforementioned configuration information. For example, when the CSI is compressed and / or quantized using an AI / ML model before being reported, this configuration information is the configuration information related to AI / ML processing.

[0044] For example, taking PRS as an example, the terminal measures the PRS sent by the base station and obtains measurement data. Finally, the terminal can obtain its own location information based on the measurement data and AI model. At this time, the terminal can report the measurement data and / or location information to the access network device and / or core network device.

[0045] For example, this AI / ML processing can be processing performed using AI models and / or ML models. The AI / ML models here can include various neural network models and / or machine learning models. The neural network models can include: Convolutional Neural Networks (CNNs) and / or Recurrent Neural Networks (RNNs), etc. The machine learning models can include: Random Forest models and / or Bayesian models, etc. Of course, the above is merely an example, and the actual implementation is not limited to this example.

[0046] The occupancy status of processing units (PUs) in AI / ML processing can be indicated by occupancy information. The occupied processing units may include the occupancy of a central processing unit (CPU), microprocessor (MCU), and / or graphics processing unit (GPU). This occupancy information may include, but is not limited to, occupancy time information and / or the number of processing units occupied.

[0047] For example, the processing unit can also be understood as the number of CSI processing units (CPUs), which can be called the number of AI processing units (APUs).

[0048] In some embodiments, the occupancy information may also include the load rate of a single processing unit.

[0049] In this embodiment, after receiving configuration information from the network device, the terminal can determine the occupancy information of the processing units based on the configuration information. If the number of PUs occupied by the configuration information is greater than the number of processing units that the terminal can provide, when there are multiple sets of configuration information to be executed, the terminal can prioritize discarding the configuration information with lower priority and execute the configuration information with higher priority according to the priority of each set of configuration information. This discarding can be agreed upon in advance between the network device and the terminal, so that the network device can stop receiving reports on the resources corresponding to the discarded configuration information based on the configuration information discarded by the terminal. The configuration information is configured through RRC signaling, activated / deactivated through MAC CE signaling, and triggered through DCI signaling. The priority of the configuration information can be calculated according to the protocol agreement. The following uses the priority calculation of CSI-related configuration information as an example for illustration:

[0050] Pri iCSI (y,k,c,s)=2·N cells ·M s ·y+N cells ·M s ·k+M s·c+s,

[0051] s is the CSI reporting identifier (ID);

[0052] c represents the serving cell index;

[0053] k=0 indicates the reporting of Layer 1 Channel State Information Received Power (L1-RSRP) or Layer 1 Signal to Interference plus Noise Ratio (L1-SINR), while k=1 indicates the reporting of other CSIs besides L1-RSRP or L1-SINR.

[0054] y=0 indicates aperiodic CSI reporting carried on PUSCH; y=1 indicates semi-persistent CSI reporting carried on PUSCH; y=2 indicates semi-persistent CSI reporting carried on PUCCH; y=3 indicates periodic CSI reporting carried on PUCCH.

[0055] M s Indicates the maximum number of CSI reports configured in the network; N cells This indicates the maximum number of serving cells configured in the network. Before sending configuration information to the terminal, the base station determines the processing unit (PU) occupancy information for the terminal to perform related operations based on this configuration information. If the number of PUs occupied by this configuration information exceeds the number of PUs that the terminal can provide, the base station can adaptively adjust the configuration information to ensure that the sent configuration information matches the terminal's capabilities.

[0056] In some embodiments, the method further includes:

[0057] Obtain configuration information related to AI / ML processing;

[0058] If the device executing the information processing method is a base station, the base station can generate configuration information related to AI / ML processing based on the current resource scheduling and / or the configuration requirements of the terminal.

[0059] If the device executing the information processing method is a terminal, then the terminal receives configuration information related to AI / ML processing sent by the network device.

[0060] That is, Figure 2D As shown, this disclosure provides an information processing method executed by a terminal, including:

[0061] S1410: Receive configuration information;

[0062] S1420: When AI / ML processing is associated with configuration information, determine the occupancy information of the processing unit that performs AI / ML processing;

[0063] S1430: When the occupancy information indicates that the processing unit of AI / ML processing has reached the preset condition, discard the low-priority configuration information associated with AI / ML processing.

[0064] For example, the occupancy information indicating that the processing units of AI / ML processing have reached a preset condition may include: the processing units occupied by all AI / ML processing indicated by the network device within the same symbol are greater than the number of processing units that the terminal can provide, and / or the occupancy of one or more processing units by AI / ML processing associated with multiple sets of configuration information conflicts.

[0065] like Figure 2B As shown in the embodiments of this disclosure, an information processing method is provided, wherein the method includes:

[0066] S1210: Determine the number of processing units required to perform AI / ML processing based on the configuration information related to AI / ML processing.

[0067] In this embodiment of the disclosure, the terminal or network device determines the number of processing units that perform AI / ML processing at a single moment based on the configuration information.

[0068] For example, S1210 may include: determining the number of processing units that perform AI / ML processing within a single time unit based on configuration information related to AI / ML processing. This time unit may include: a symbol, a micro-slot, or a time slot.

[0069] In some embodiments, the terminal or network device determines the number of threads required for a processing unit to perform AI / ML processing at a single moment based on configuration information.

[0070] like Figure 2C As shown in the embodiments of this disclosure, an information processing method is provided, wherein the method includes:

[0071] S1310: Determine the time taken by the processing unit to perform AI / ML processing based on the configuration information related to AI / ML processing.

[0072] In this embodiment, the terminal or network device determines the processing unit time (i.e., the time occupied) occupied by AI / ML processing based on the configuration information.

[0073] The occupancy time may include at least one of the following: the occupancy start time;

[0074] The time of termination of occupation;

[0075] Duration of time occupied.

[0076] In some embodiments, the occupancy information may include: the duration of AI / ML processing occupying X processing units. X can be any positive integer, and the time when AI / ML processing is started is taken as the start time of occupancy.

[0077] In one embodiment, if the configuration information involves multiple measurements and / or multiple reports, S1310 may include: determining the time taken by the processing unit to perform AI / ML processing for a single measurement or a single report based on the configuration information related to AI / ML processing.

[0078] In other embodiments, S1310 may also include: determining the duration of continuous use of the processing unit for performing AI / ML processing based on configuration information related to AI / ML model processing.

[0079] In some embodiments, determining the number of processing units used to perform AI / ML processing based on configuration information related to AI / ML processing includes:

[0080] Based on the reported volume associated with the configuration information, determine the number of processing units required to perform AI / ML processing;

[0081] Based on the reported time-frequency domain characteristics associated with the configuration information, determine the number of processing units required to perform AI / ML processing;

[0082] The number of processing units required to perform AI / ML processing is determined based on at least one of the following: the AI / ML model associated with the configuration information, the features involved in AI / ML processing, the functions associated with the AI / ML model, and the complexity level of the AI / ML model.

[0083] Based on the frequency domain characteristics of the reported resources associated with the configuration information, determine the number of processing units required to perform AI / ML processing;

[0084] Based on the time-frequency domain characteristics of the measurement resources associated with the configuration information, determine the number of processing units required to perform AI / ML processing;

[0085] Based on the frequency domain characteristics of the control signaling that triggers the configuration information, determine the number of processing units that will be used to perform AI / ML processing;

[0086] The reported time-frequency domain characteristics may include: the reported time-domain characteristics and / or the reported time-frequency domain characteristics may include the reported frequency-domain characteristics.

[0087] The reported time-domain characteristics include at least one of the following:

[0088] Periodic reporting;

[0089] Semi-static reporting;

[0090] Non-periodic triggering of reports.

[0091] Periodic reporting can be performed according to the period indicated by the configuration information, which can be a statically configured period.

[0092] Semi-static reporting can be semi-static periodic reporting as indicated by semi-static configuration information. Semi-static reporting is different from periodic reporting. The first semi-static reporting needs to be triggered by control signaling from the network device.

[0093] Non-periodic triggering of reporting can also be understood as dynamic reporting. This dynamic reporting can be triggered by control signaling dynamically sent by network devices or by pre-configured triggering conditions.

[0094] In some embodiments, the reported time-frequency domain characteristics include the frequency domain characteristics and frequency domain characteristics of the reported resources.

[0095] The time-domain characteristics reported may include: the distribution density of reported resources in the time domain, the distribution period, the reporting triggering method, and / or the time-domain resources occupied by a single report.

[0096] The frequency domain characteristics of the reported resources may include: the distribution location of the reported resources in the frequency domain, the subcarrier space (SCS) of the channel where the reported frequency domain resources are located, and / or the number of carriers of the reported frequency domain resources.

[0097] For example, the frequency domain characteristics of the reported resources include the subcarrier spacing (SCS) of the reported resources.

[0098] In some embodiments, the measured time-frequency domain characteristics include at least one of the following:

[0099] The number of associated measurement resources;

[0100] Frequency domain distribution density of the reference signal to be measured;

[0101] The number of antenna ports of the reference signal to be measured;

[0102] The subcarrier space (SCS) associated with the configuration information.

[0103] Time-frequency domain characteristics may include: the time-domain characteristics of time-frequency domain resources associated with the configuration information.

[0104] For example, the number of associated measurement resources may include: the number of associated time-domain resources, the number of associated frequency-domain resources, the number of associated resource elements (REs), and the number of associated resource blocks (RBs).

[0105] For example, the amount of measurement resources can be positively correlated with the number of processing units occupied by AI / ML processing.

[0106] For example, the amount of measurement resources can be positively correlated with the duration of AI / ML processing in the processing unit.

[0107] The measurements associated with the aforementioned configuration information can be periodic measurements, semi-periodic measurements, or one or more measurements triggered by a single event.

[0108] The reference signal can be a variety of physical layer signals, such as SSB, CSI-RS, and / or PRS.

[0109] A terminal can be configured with one or more antenna ports. A single measurement can utilize one or more antenna ports of the terminal. Generally, the more antenna ports associated with a single measurement, the more measurement data is generated, and the more data is processed by AI / ML. Consequently, the number of processing units occupied by AI / ML processing may increase, or the processing time may lengthen. That is, the number of antenna ports occupied is positively correlated with the number of processing units occupied by AI / ML processing, and / or, the number of antenna ports occupied is positively correlated with the processing time occupied by AI / ML processing units.

[0110] The optional SCS for communication between the terminal and network devices may include values ​​such as 15KHz, 30KHz, 45KHz, 60KHz, 120KHz, or 240KHz.

[0111] A larger SCS results in a shorter duration for a single symbol. With the same number of time-domain units, the EU (Extreme Estimation Unit) will have more measurement data within a given time range, potentially requiring more measurement values ​​to be processed, thus necessitating more processing units. In some scenarios, the size of the SCS is positively correlated with the number of processing units required.

[0112] In some embodiments, when SCS is less than or equal to 120KHz, the number of APUs occupied is the same, that is, when SCS = 15KHz, 30KHz, 45KHz, 60KHz, and 120KHz, the number of APUs occupied is X; when SCS is greater than 120KHz, the number of APUs occupied is Y, and Y > X.

[0113] In some embodiments, the SCS associated with the configuration information may include: the SCS of the measurement resource associated with the configuration information, and / or the SCS of the reporting resource associated with the configuration information.

[0114] In other embodiments, if the configuration information is associated with semi-static reporting and / or non-periodic triggered reporting, the configuration information associated SCS may further include: an SCS for the transmission channel of control signaling that triggers the configuration information associated with measurement and / or reporting. This transmission channel may include, but is not limited to, various downlink channels, such as the PDCCH channel.

[0115] In some embodiments, the frequency domain characteristics of the control signaling that triggers the configuration information include: the SCS of the channel in which the control signaling that triggers the configuration information resides.

[0116] If the configuration information is associated with non-periodic measurements and / or reporting, then control signaling is required to trigger the measurement and / or reporting. In this case, the network device will send control signaling, and the terminal will receive the control signaling.

[0117] If the configuration information is associated with semi-static measurement and / or reporting, then control signaling is required to trigger the semi-static measurement and / or reporting for the first time. In this case, the network device will send control signaling, and the terminal will receive the control signaling.

[0118] The aforementioned control signaling may include, but is not limited to, Downlink Control Information (DCI) and / or Media Access Control (MAC) Control Element (CE).

[0119] For example, if the control signaling is DCI, then the frequency domain characteristics of the control signaling that triggers the configuration information may include: the SCS of the Physical Downlink Control Channel (PDCCH) where the DCI is located.

[0120] In some embodiments, determining the time taken by the processing unit performing AI / ML processing based on configuration information related to AI / ML processing includes:

[0121] If the reported quantity associated with the configuration information is not empty, the time occupied by the processing unit performing AI / ML processing should be determined at least based on the reported resources associated with the configuration information.

[0122] If the reported quantity associated with the configuration information is empty, the time occupied by the processing unit performing AI / ML processing is determined based on the measurement resources associated with the configuration information.

[0123] The reported quantity can be measurement parameters and / or results that need to be sent to network devices. For example, the reported quantity may include at least one of the following:

[0124] Reference Signal Received Power (RSRP); such as the layer 1 reference signal received power (L1-RSRP) of the AI-predicted beam.

[0125] Signal-to-noise ratio (SINR); such as the AI-predicted SINR; Channel state information (CSI), such as the AI-predicted Channel Quality Indication (CQI), Rank Indication (RI), Precoding Matrix Indicator (PMI), etc.

[0126] Compressed CSI, such as AI-compressed feature vectors, etc.

[0127] Beam identifiers, such as AI-predicted beam identifiers, channel resource indexes (CRIs), and / or synchronization signal block indexes (SSB-indexes);

[0128] Reference Signal Received Quality (RSRQ), such as the beam quality predicted by AI. This beam quality may include, but is not limited to, L1-RSRQ.

[0129] In some embodiments, the reported quantities may be state quantities (or measured parameters) processed by an AI / ML model.

[0130] If the reported quantity is not empty, it means that the terminal needs to send the reported quantity to the network device. At this time, the processing unit time required to perform AI / ML processing will be determined according to the reported resources associated with the configuration information.

[0131] This reporting resource can be used by the terminal to report measurement and / or calculation values ​​related to the reported quantity to the network device.

[0132] For example, a terminal can report the execution result of sending configuration information to a network device. This reporting resource can be used by the terminal to send reports to the network device. In this case, the end time of the AI / M processing occupying the processing unit can be related to the end time of the reporting resource.

[0133] If the reported data is empty, it means that the terminal can currently perform relevant operations based on the configuration information, such as performing measurement operations, but does not need to send a report to the network device. In this case, the time occupied by the AI / ML processing unit depends more on the measurement resources associated with the configuration information. These measurement resources include at least the time resources for measurements performed based on the configuration information. In this situation, the end time of the AI / ML processing unit can be related to the end time of the measurement resources.

[0134] In this embodiment of the disclosure, the time required for AI / ML processing is determined based on whether the reported quantity is empty or not. This can more accurately reflect the time required for the terminal to perform operations related to configuration information using the AI / ML model.

[0135] In some embodiments, when the reported quantity associated with the configuration information is not empty, the time taken by the processing unit performing AI / ML processing is determined at least based on the reported resources associated with the configuration information, including:

[0136] If the reported quantity associated with the configuration information is not empty, the processing time occupied by the processing unit for executing AI / ML processing is determined based on the reported type associated with the configuration information and the reported resources associated with the configuration information.

[0137] In this embodiment of the disclosure, when the reported quantity associated with the configuration information is not empty, the time required for the processing unit to perform AI / ML processing is determined based on the reporting type and the reporting resources associated with the configuration information. Different reporting types require different processing times for AI / ML; therefore, distinguishing between different reporting types and determining the processing unit's time for performing AI / ML processing makes the determined time more accurate.

[0138] In some embodiments, when the configuration information associated reporting quantity is not empty, the time occupied by the processing unit performing AI / ML processing is determined based on the reporting type associated with the configuration information and the reporting resources associated with the configuration information, including at least one of the following:

[0139] In the case of configuration information associated reporting and the reporting of configuration information associated with periodic or semi-static reporting, the time period between the first symbol of the measurement resource associated with the configuration information and the last symbol of the reported resource is determined as the time occupied by the AI / ML processing unit.

[0140] In the case where configuration information is associated with reporting and the reporting of configuration information is triggered non-periodicly, the time period from the first symbol after the end of the transmission of the trigger reporting instruction to the last symbol of the reported resource is determined as the time occupied by the AI / ML processing unit.

[0141] The symbol here is an abbreviation for Orthogonal Frequency Division Multiplexing (OFDM).

[0142] Periodic reporting can be performed according to the period configured in the configuration information, including periodic measurement and / or periodic reporting.

[0143] The starting time for AI / ML processing to occupy the processing unit within each cycle can be determined from the starting time of the measured resource and end with the last symbol (i.e., the last symbol) of the reported resource.

[0144] Semi-static reporting can refer to the period from the start of execution of semi-static configuration information triggered by control commands to the end of the execution period, during which measurement and / or reporting are performed according to a semi-static cycle. Therefore, in some embodiments, based on the semi-static configuration information, for all semi-static measurements and / or semi-static reporting, the time occupied by a processing unit for one AI / ML process within a semi-static cycle can be determined from the start symbol (i.e., the first symbol) of the measured resource to the end symbol of the reported resource within each cycle.

[0145] In some embodiments, since the first execution of semi-static measurement and / or semi-static reporting is triggered by control signaling, the time period from the first symbol after the end of transmission to the last symbol of the reported resource can be determined as the time occupied by the AI / ML processing unit for the first execution of semi-static measurement and / or semi-static reporting.

[0146] In some embodiments, non-periodic triggering of reporting can be understood as dynamic reporting. Dynamic reporting can be configured by control instructions. Control instructions can be the aforementioned DCI and / or MAC CE, etc. Since dynamic reporting involves control instructions, in order to accurately determine the time occupied by the AI / ML processing in the processing unit in this embodiment of the disclosure, the time occupied is determined based on the first symbol after the end of the control instruction transmission and the last symbol of the reported resource.

[0147] In some embodiments, when the reported quantity associated with the configuration information is empty, the time taken by the processing unit performing AI / ML processing is determined based on the measurement resources associated with the configuration information, including:

[0148] If the reported quantity associated with the configuration information is empty, the time occupied by the processing unit performing AI / ML processing is determined based on the measurement resources associated with the configuration information and the processing latency.

[0149] In this embodiment of the disclosure, if the reported quantity associated with the configuration information is empty, it indicates that no reporting is required. In this case, the measurement resources associated with the configuration information and the processing latency will be used together to determine the occupancy time of the processing unit required for AI / ML processing.

[0150] Measurements are performed at the terminal within the measurement resource to obtain measurement values. After obtaining the measurement values, the AI / ML model may perform relevant processing on the measurement values, such as outlier removal, calculation of measurement results based on the measurement values, and / or quantization and / or compression of the measurement values. In this case, the AI / ML model requires a certain amount of latency. This latency, which is required for the AI / ML model to perform related operations after the measurement is completed, is the aforementioned processing latency.

[0151] In this embodiment of the disclosure, in order to accurately determine the occupancy time, the occupancy time of the processing unit for AI1 / ML processing is determined by combining the measurement resources and the processing latency.

[0152] In some embodiments, when configuration information is not reported, the occupancy time of the processing unit performing AI / ML processing is determined based on the measurement resources associated with the configuration information and the processing latency, including at least one of the following:

[0153] If the reported quantity associated with the configuration information is empty, and the reported quantity associated with the configuration information is periodic or semi-static, the time period between the first symbol of the measurement resource associated with the configuration information and the X symbols after the last symbol of the measurement resource is determined as the processing unit occupancy time of AI / ML processing; X is a positive integer.

[0154] If the reported quantity associated with the configuration information is empty and the reported quantity associated with the configuration information is a non-periodic trigger report, the first symbol after the end of the trigger command transmission is determined as the starting symbol of the occupied time, and the latter of the M symbols after the end of the trigger command and the N symbols after the last symbol of the measurement resource is determined as the ending symbol of the occupied time; M and N are both positive integers.

[0155] Furthermore, in this embodiment of the disclosure, if the reported quantity associated with the configuration information is empty, and the time associated with the configuration information is periodic or semi-static, then the first symbol of the measurement resource can be determined as the start time of the occupancy time, and the X symbols after the last symbol after the measurement can be determined as the end time of the occupancy time. These X symbols can be the aforementioned processing delay. For example, the value of X can be any positive integer.

[0156] In some embodiments, the value of X may be related to the type of the reference signal being measured, the type of the measured value, the amount of data in the measured value, and / or the type of the AI / ML model and / or the number of processing units currently occupied. That is, in some embodiments, the method may further include determining the value of X based on the type of the reference signal being measured, the type of the measured value, the amount of data in the measured value, and / or the AI / ML model and / or the number of processing units currently occupied. Typically, the value of X is positively correlated with the amount of data in the measured value. The value of X is negatively correlated with the size of the AI / ML model.

[0157] In other embodiments, to simplify processing, the value of X can be predefined; for example, the value of X can be pre-agreed upon by a protocol.

[0158] In some embodiments, for the first report of non-periodic triggering or semi-static reporting, the first symbol after the end of the trigger instruction transmission can be determined as the starting symbol of the occupied time, and the latter of the M symbols after the end of the trigger instruction and the N symbols after the last symbol of the measurement resource can be determined as the ending symbol of the occupied time.

[0159] In this embodiment of the disclosure, it is further provided that when the reported quantity is empty, the time occupied by the AI / ML model to perform related operations (i.e., perform AI / ML processing) is determined based on the measurement resources and / or reporting resources associated with the configuration information.

[0160] In some embodiments, the configuration information includes at least one of the following:

[0161] CSI resource configuration information;

[0162] CSI report configuration information.

[0163] CSI resource configuration information can be used to configure measurement resources for CSI-related reference signals. For example, CSI resource configuration information may include at least one of the following:

[0164] Non-zero CSI-RS resource set, used for non-zero CSI-RS transmission for terminal beam measurement.

[0165] CSI-SSB resource set, for

[0166] Channel State Information-Interference Measurement (CSI-IM) is used for the transmission of CSI-IM for the terminal to perform interference measurements.

[0167] Of course, the above is just an example of CIS resource configuration information, and the actual implementation is not limited to this example.

[0168] CSI reported resource configuration information can be used for sending CSI reports. For example, CSI reported resource configuration information may include reported data based on AI / ML processing, such as AI / ML-based feature vector compression reporting, or AI / ML-based reporting of predicted CSI-RS resource indicators. These CSI-RS resource indicators may include, but are not limited to, beam identifiers.

[0169] Of course, the above is just an example of CSI reporting resource configuration information, and the actual implementation is not limited to this example.

[0170] In some embodiments, the configuration information may further include positioning signal configuration information. This positioning signal configuration information may include: resource configuration information for positioning signals and / or reporting configuration information for positioning measurement data and / or positioning measurement results.

[0171] In some embodiments, this disclosure provides an information processing method.

[0172] Define the number of processing units required for different AI processing methods.

[0173] When the AI ​​processes CSI, the reported data may include, but is not limited to, at least one of the following:

[0174] CSI reported data is compressed channel precoding information;

[0175] Predicted channel matrix information;

[0176] Compressed channel matrix information;

[0177] Predicted beam ID information;

[0178] Predicted beam L1-RSRP information.

[0179] The number of processing units here can also be understood as the number of CSI processing units (CPUs), which can be referred to as the number of AI processing units (APUs). For example, CPU will be used as a substitute below.

[0180] Different numbers of CPUs can be defined by at least one or a combination of the following aspects.

[0181] This is determined based on different reporting volumes and / or use cases. These different reporting volumes and / or use cases include, but are not limited to:

[0182] AI-based CSI compressed and quantized feature vector information / precoding matrix information;

[0183] Channel matrix information based on AI-driven CSI time-domain prediction;

[0184] The channel matrix of AI-based CSI time-domain prediction is processed and then subjected to AI-based CSI compressed quantization of feature vector information / precoding matrix information.

[0185] AI-based beam ID and / or RSRP information in the temporal and / or spatial domains, and AI-based positioning information.

[0186] The time-domain characteristics are determined based on the reporting time-domain characteristics. These time-domain characteristics include periodic, semi-static, and aperiodic reporting. For example, for the same reporting volume, aperiodic reporting uses X CPUs, while periodic and semi-static reporting use Y CPUs.

[0187] The model ID, feature ID, or functionality ID is used to determine the model. Different features, such as CSI prediction and CSI compression, have different complexities and require different numbers of CPUs. Even for the same feature, different models, such as CNN and Transformer models used for CSI compression, generally have higher implementation complexity and require more CPUs than CNN models.

[0188] In particular, different model IDs, feature IDs, or functional IDs can also be assigned to a complexity class, and the number of CPUs used can be determined based on the complexity class.

[0189] Based on the uplink and downlink SCS, the processing complexity increases with the increase of SCS. Therefore, different CPU usage numbers are defined according to different SCS values. For aperiodic triggered reporting, the SCS is determined by the maximum SCS among PDCCH, CSI-RS, and PUSCH. For example, PDCCH can be the transmission channel for control signaling. CSI-RS can be the transmission resource for reference signals. PUSCH can be the reporting channel for CSI reports. That is, for aperiodic triggered reporting, the SCS used by the transmission channel for control signaling, the transmission resource for reference signals, and the reporting resource for the reporting quantity is used as a reference parameter to determine the number of processing units required for AI / ML processing.

[0190] The number of resources based on different reference signals.

[0191] The number of CPUs used is positively correlated with the number of resources for the measured reference signal; the larger the number of resources for the measured reference signal, the more CPUs are used. Alternatively, the number of CPUs can be understood as being determined based on the number of measurement resources.

[0192] The number of measurement resources is affected by the specific RS resource configuration, such as the number of antenna ports and frequency domain resource density.

[0193] The APU / CPU usage time for the AI ​​processing mentioned above can be determined as follows:

[0194] Generally, CSI and / or beamforming information is reported to the base station. Location results are reported to the core network. Location reporting can be periodic or aperiodic. CSI and beamforming measurement reporting can be periodic, semi-static, or aperiodic triggered reporting (referred to as aperiodic reporting).

[0195] For periodic and semi-static reporting (except for the first semi-static CSI report triggered by DCI), the CPU time consumed is from the first symbol of the measurement resource to the last symbol of the reporting resource. Here, the measurement resource refers to the last CSI-RS / CSI-IM / SSB no later than the CSI reference resource.

[0196] The measurement resource can be the transmission resource of the reference signal. This reference signal may include, but is not limited to, CSI-RS / CSI-IM / SSB.

[0197] CSI reference resources, unlike measurement resources, are used by the UE to determine measurement resources. CSI reference resources are generally set before reporting resources.

[0198] For non-periodic CSI reporting and the first semi-static CSI triggered by DCI, the CPU usage time starts from the first symbol after the PDCCH ends and continues until the last symbol of the reported resource.

[0199] In particular, there is a special case in beam processing where no data needs to be reported, and the beam selection is only performed on the terminal side. In this case, the time taken is determined as follows:

[0200] For semi-static reporting, except for the first semi-static CSI report triggered by DCI, the CPU usage time starts from the first symbol of the semi-static or periodic measurement resource and ends X symbols after the last symbol of the last measurement resource.

[0201] For aperiodic reporting, CPU usage time extends from the first symbol after the PDCCH that triggered the aperiodic reporting to a later position in M ​​and N. M and N correspond to the PDCCH end position X and the measurement resource end position Y, respectively.

[0202] X can be understood as measurement delay; Y can be understood as DCI processing delay.

[0203] In one embodiment, in the configuration for CSI reporting, the reported quantity includes the beam identifier (ID), reference signal resource ID, synchronization signal ID, RSRP, and / or SINR obtained by the terminal based on AI / ML processing. For example, the reported quantity can be set to include at least one of the following:

[0204] ai-cri-RSRP is used to instruct the terminal to report the Channel State Information Reference Signal Resource Index (CSI-RS resource index, CRI) and L1-RSRP based on AI prediction.

[0205] ai-ssb-Index-RSRP is used to instruct the terminal to report the SSB index and L1-RSRP based on AI prediction.

[0206] ai-cri-SINR is used to instruct the terminal to report CRI reports based on AI predictions and SINR.

[0207] ai-ssb-Index-SINR is used to instruct the terminal to report the SSB index and SINR based on AI prediction.

[0208] ai-cri-RSRP-Capability[Set]Index is used to indicate the terminal's AI-predicted CRI and L1-RSRP reporting, as well as the maximum number of Sounding Reference Signal (SRS) antenna ports supported by the UE.

[0209] ai-ssb-Index-RSRP-Capability[Set]Index is used to indicate the SSB index predicted by AI and the L1-RSRP reporting of the terminal, as well as the maximum number of SRS antenna ports supported by the UE.

[0210] ai-cri-SINR-Capability[Set]Index is used to instruct the terminal to report the CRI and SINR based on AI predictions, as well as the maximum number of SRS antenna ports supported by the UE.

[0211] ai-ssb-Index-SINR-Capability[Set]Index is used to instruct the terminal to report the SSB index based on AI prediction, as well as the SINR report and the maximum number of SRS antenna ports supported by the UE.

[0212] `ai-none` indicates that the reported data is empty. This situation, where the reported data is empty, can include scenarios where AI-predicted terminal communication uses beamforming.

[0213] If the CSI-RS resource set is not configured with higher-layer parameters to be transmitted, that is, if the reported quantity is empty, then the APU / CPU = 1.

[0214] In one embodiment, in the configuration for CSI reporting, the reported quantity includes compressed feature vectors, precoded vectors, or precoded matrix information obtained by the terminal based on AI / ML processing.

[0215] For example, the reporting volume is set to:

[0216] ai-cri-RI-PMI-CQI is used to instruct the terminal to report CRI, channel RI, channel PMI and CQI.

[0217] ai-cri-RI-x is used to instruct the terminal to report the CRI, the channel's RI, and x; here, x can be any amount of information that the network device requires the terminal to report. For example, x can refer to the PMI or a portion of the PMI used for beam selection.

[0218] ai-cri-RI-x-CQI is used to instruct the terminal to report the CRI, the RI, x and CQI of the channel;

[0219] Alternatively, ai-cri-RI-LI-PMI-CQI is used to instruct the terminal to report the CRI, the channel's RI, L1-RSRP, the first part of the channel's PMI, and the CQI.

[0220] If the report is not periodic, the number of CPUs used is equal to the CPU capacity reported by the terminal.

[0221] If it is semi-static or periodic reporting, the number of CPUs used is equal to the total number of measurement resources.

[0222] In one embodiment, when configuring CSI reports, the reported quantity includes compressed feature vectors, precoded vectors, and / or precoded matrix information obtained by the terminal based on AI / ML processing. For example, the reported quantity is set to ai-cri-RI-PMI-CQI, ai-cri-RI-x, ai-cri-RI-x-CQI, or ai-cri-RI-LI-PMI-CQI.

[0223] If the reporting is semi-static and periodic, and the AI ​​model complexity level is 1, then the number of CPUs used is X. If the AI ​​model complexity level is 2, then the number of CPUs used is Y.

[0224] In one embodiment, when a terminal sends an AI-based positioning result to the core network, the number of AI processing units it occupies is M when the function ID is 1, and the number of AI processing units it occupies is N when the function ID is 2.

[0225] like Figure 3 As shown, this disclosure provides an information processing apparatus, wherein the apparatus includes:

[0226] The processing module 110 is configured to determine the occupancy information of the processing unit that performs AI / ML processing based on the configuration information related to AI / ML processing.

[0227] The information processing device can be a terminal or a network device.

[0228] In some embodiments, the processing module 110 may include a program module; the program module, after being executed by the processor, is capable of performing the above operations.

[0229] In other embodiments, the processing module 110 may include a hardware-software hybrid module; the hardware-software hybrid module includes, but is not limited to, a programmable array. The programmable array includes, but is not limited to, field-programmable arrays and / or complex programmable arrays.

[0230] In some embodiments, the processing module 110 may include a pure hardware module. The pure hardware module includes, but is not limited to, an application-specific integrated circuit (ASIC).

[0231] In some embodiments, the processing module may further include a storage module, which can be connected to the processing module 110 and can be used to store the configuration information.

[0232] In other embodiments, the processing module may further include an acquisition module. This acquisition module can be used to acquire configuration information related to AI / ML processing.

[0233] Understandably, the processing module 110 is configured to determine the number of processing units that perform AI / ML processing based on configuration information related to AI / ML processing; and / or to determine the time that the processing units perform AI / ML processing are occupied based on configuration information related to AI / ML processing.

[0234] Understandably, processing module 110 is configured to perform at least one of the following:

[0235] Based on the reported volume associated with the configuration information, determine the number of processing units required to perform AI / ML processing;

[0236] Based on the reported time-frequency domain characteristics associated with the configuration information, determine the number of processing units required to perform AI / ML processing;

[0237] The number of processing units required to perform AI / ML processing is determined based on at least one of the following: the AI / ML model associated with the configuration information, the features involved in AI / ML processing, the functions associated with the AI / ML model, and the complexity level of the AI / ML model.

[0238] Based on the frequency domain characteristics of the reported resources associated with the configuration information, determine the number of processing units required to perform AI / ML processing;

[0239] Based on the time-frequency domain characteristics of the measurement resources associated with the configuration information, determine the number of processing units required to perform AI / ML processing;

[0240] Based on the frequency domain characteristics of the control signaling that triggers the configuration information, determine the number of processing units that will be used to perform AI / ML processing.

[0241] Understandably, the reported time-frequency domain characteristics include the reported time-domain characteristics; the reported time-domain characteristics include at least one of the following:

[0242] Periodic reporting;

[0243] Semi-static reporting;

[0244] Non-periodic triggering of reports.

[0245] Understandably, the reported time-frequency domain characteristics include the frequency domain characteristics of the reported resources; wherein, the frequency domain characteristics of the reported resources include:

[0246] The subcarrier spacing (SCS) of the reported resources.

[0247] Understandably, the measured time-frequency domain characteristics include at least one of the following:

[0248] The number of associated measurement resources;

[0249] Frequency domain distribution density of the reference signal to be measured;

[0250] The number of antenna ports of the reference signal to be measured;

[0251] The subcarrier spacing (SCS) associated with the configuration information.

[0252] Understandably, the frequency domain characteristics of the control signaling that triggers the configuration information include: the SCS of the channel in which the control signaling that triggers the configuration information resides.

[0253] Understandably, processing module 110 is configured to perform at least one of the following:

[0254] If the reported quantity associated with the configuration information is not empty, the time occupied by the processing unit performing AI / ML processing should be determined at least based on the reported resources associated with the configuration information.

[0255] If the reported quantity associated with the configuration information is empty, the time occupied by the processing unit performing AI / ML processing is determined based on the measurement resources associated with the configuration information.

[0256] Understandably, the processing module 110 is configured to determine the time taken by the processing unit to perform AI / ML processing based on the reporting type associated with the configuration information and the reporting resources associated with the configuration information, when the reported quantity associated with the configuration information is not empty.

[0257] Understandably, processing module 110 is configured to perform at least one of the following:

[0258] In the case of configuration information associated reporting and the reporting of configuration information associated with periodic or semi-static reporting, the time period between the first symbol of the measurement resource associated with the configuration information and the last symbol of the reported resource is determined as the time occupied by the AI / ML processing unit.

[0259] In the case where configuration information is associated with reporting and the reporting of configuration information is triggered non-periodicly, the time period from the first symbol after the end of the transmission of the trigger reporting instruction to the last symbol of the reported resource is determined as the time occupied by the AI / ML processing unit.

[0260] Understandably, the processing module 110 is configured to determine the time occupied by the processing unit performing AI / ML processing based on the measurement resources associated with the configuration information and the processing latency when the reported quantity associated with the configuration information is empty.

[0261] Understandably, processing module 110 is configured to perform at least one of the following:

[0262] If the reported quantity associated with the configuration information is empty, and the reported quantity associated with the configuration information is periodic or semi-static, the time period between the first symbol of the measurement resource associated with the configuration information and the X symbols after the last symbol of the measurement resource is determined as the processing unit occupancy time of AI / ML processing; X is a positive integer.

[0263] If the reported quantity associated with the configuration information is empty and the reported quantity associated with the configuration information is a non-periodic trigger report, the first symbol after the end of the trigger command transmission is determined as the starting symbol of the occupied time, and the latter of the M symbols after the end of the trigger command and the N symbols after the last symbol of the measurement resource is determined as the ending symbol of the occupied time; M and N are both positive integers.

[0264] Understandably, the configuration information includes at least one of the following:

[0265] CSI resource configuration information;

[0266] CSI report configuration information.

[0267] This disclosure provides a communication device, including:

[0268] Memory used to store processor-executable instructions;

[0269] The processor is connected to the memory separately;

[0270] The processor is configured to execute the information processing method provided by any of the aforementioned technical solutions.

[0271] The processor may include various types of storage media, which are non-transitory computer storage media that can continue to store information after the communication device loses power.

[0272] Here, communication equipment includes: terminals and / or network equipment.

[0273] The processor can connect to memory via a bus or similar means to read executable programs stored in memory, for example... Figures 2A to 2D At least one of the methods shown.

[0274] Figure 4 This is a block diagram illustrating a terminal 800 according to an exemplary embodiment. For example, terminal 800 may be a mobile phone, computer, digital broadcast user equipment, messaging device, game console, tablet device, medical device, fitness equipment, personal digital assistant, etc.

[0275] Reference Figure 4 Terminal 800 may include one or more of the following components: processing component 802, memory 804, power supply component 806, multimedia component 808, audio component 810, input / output (I / O) interface 812, sensor component 814, and communication component 816.

[0276] Processing component 802 typically controls the overall operation of terminal 800, such as operations associated with display, telephone calls, data communication, camera operation, and recording. Processing component 802 may include one or more processors 820 to execute instructions to generate all or part of the steps of the methods described above. Furthermore, processing component 802 may include one or more modules to facilitate interaction between processing component 802 and other components. For example, processing component 802 may include a multimedia module to facilitate interaction between multimedia component 808 and processing component 802.

[0277] Memory 804 is configured to store various types of data to support operation on terminal 800. Examples of this data include instructions for any application or method operating on terminal 800, contact data, phonebook data, messages, pictures, videos, etc. Memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0278] Power supply component 806 provides power to various components of terminal 800. Power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to terminal 800.

[0279] Multimedia component 808 includes a screen that provides an output interface between terminal 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of touch or swipe actions but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 808 includes a front-facing camera and / or a rear-facing camera. When terminal 800 is in an operating mode, such as a shooting mode or video mode, the front-facing camera and / or rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0280] Audio component 810 is configured to output and / or input audio signals. For example, audio component 810 includes a microphone (MIC) configured to receive external audio signals when terminal 800 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 804 or transmitted via communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.

[0281] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0282] Sensor assembly 814 includes one or more sensors for providing state assessments of various aspects of terminal 800. For example, sensor assembly 814 can detect the on / off state of terminal 800, the relative positioning of components such as the display and keypad of terminal 800, changes in the position of terminal 800 or a component of terminal 800, the presence or absence of user contact with terminal 800, the orientation or acceleration / deceleration of terminal 800, and temperature changes of terminal 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 814 may also include an accelerometer, a gyroscope, a magnetometer, a pressure sensor, or a temperature sensor.

[0283] Communication component 816 is configured to facilitate wired or wireless communication between terminal 800 and other devices. Terminal 800 can access wireless networks based on communication standards, such as WiFi, 2G, or 3G, or combinations thereof. In one exemplary embodiment, communication component 816 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 816 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0284] In an exemplary embodiment, terminal 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the methods described above.

[0285] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 804 including instructions that can be executed by a processor 820 of a terminal 800 to generate the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0286] like Figure 5 As shown in the illustration, one embodiment of this disclosure illustrates the structure of an access device. For example, the communication device 900 can be provided as a network-side device. This communication device can be various network elements such as the aforementioned access network elements and / or network functions.

[0287] Reference Figure 5 The communication device 900 includes a processing component 922, which further includes one or more processors, and memory resources represented by a memory 932 for storing instructions executable by the processing component 922, such as application programs. The application programs stored in the memory 932 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processing component 922 is configured to execute instructions to perform any of the methods described above applied to the access device, such as... Figures 2A to 2D Any of the methods shown, exemplarily, performs as follows Figures 2A to 2D At least one of the methods shown.

[0288] The communication device 900 may also include a power supply component 926 configured to perform power management of the communication device 900, a wired or wireless network interface 950 configured to connect the communication device 900 to a network, and an input / output (I / O) interface 958. The communication device 900 can operate on an operating system stored in memory 932, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, or similar.

[0289] Unless otherwise specified, each step in a particular implementation or embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, the solution after removing some steps in a particular implementation or embodiment can also be implemented as an independent embodiment, and the order of the steps in a particular implementation or embodiment can be arbitrarily interchanged. In addition, the optional methods or examples in a particular implementation or embodiment can be arbitrarily combined. Furthermore, the implementations or embodiments can be arbitrarily combined with each other. For example, some or all of the steps in different implementations or embodiments can be arbitrarily combined, and a particular implementation or embodiment can be arbitrarily combined with the optional methods or examples of other implementations or embodiments.

[0290] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the following claims.

[0291] It should be understood that the present invention is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. An information processing method, wherein, The method includes: Based on the configuration information related to artificial intelligence (AI) and / or machine learning (ML) processing, determine the occupancy information of the processing unit that performs the AI ​​and / or ML processing; The occupancy information includes: occupancy time; the determination of occupancy information of the processing unit executing the AI ​​and / or ML processing based on configuration information related to AI and / or ML processing includes: If the reported quantity associated with the configuration information is not empty, the time occupied by the processing unit that performs the AI ​​and / or ML processing is determined according to the reported type associated with the configuration information and the reported resources associated with the configuration information. If the reported quantity associated with the configuration information is empty, the time occupied by the processing unit performing the AI ​​and / or ML processing is determined based on the measurement resources associated with the configuration information.

2. The method according to claim 1, wherein, The step of determining the occupancy information of the processing unit executing the AI ​​and / or ML processing based on configuration information related to artificial intelligence (AI) / machine learning (ML) processing further includes: Based on the configuration information related to the AI / ML processing, determine the number of processing units required to perform the AI ​​and / or ML processing.

3. The method according to claim 2, wherein, The step of determining the number of processing units required to perform the AI ​​and / or ML processing based on configuration information related to the AI / ML processing includes: Based on the reported volume associated with the configuration information, determine the number of processing units required to perform the AI ​​and / or ML processing; Based on the reported time-frequency domain characteristics associated with the configuration information, determine the number of processing units required to perform the AI ​​and / or ML processing; The number of processing units required to perform the AI ​​and / or ML processing is determined based on at least one of the AI ​​and / or ML models associated with the configuration information, the features involved in the AI ​​and / or ML processing, the functions associated with the AI ​​and / or ML models, and the complexity level of the AI ​​and / or ML models. Based on the frequency domain characteristics of the reported resources associated with the configuration information, determine the number of processing units required to perform the AI ​​and / or ML processing; Based on the time-frequency domain characteristics of the measurement resources associated with the configuration information, determine the number of processing units required to perform the AI ​​and / or ML processing; Based on the frequency domain characteristics of the control signaling that triggers the configuration information, the number of processing units that perform the AI ​​and / or ML processing is determined.

4. The method according to claim 3, wherein, The reported time-frequency domain characteristics include the reported time-domain characteristics; the reported time-domain characteristics include at least one of the following: Periodic reporting; Semi-static reporting; Non-periodic triggering of reports.

5. The method according to claim 3, wherein, The reported time-frequency domain characteristics include the frequency domain characteristics of the reported resources; wherein, the frequency domain characteristics of the reported resources include: The subcarrier spacing (SCS) of the reported resources.

6. The method according to claim 3, wherein, The measured time-frequency domain characteristics include at least one of the following: The number of associated measurement resources; Frequency domain distribution density of the reference signal to be measured; The number of antenna ports of the reference signal to be measured; The subcarrier spacing (SCS) associated with the configuration information.

7. The method according to claim 3, wherein, The frequency domain characteristics of the control signaling that triggers the configuration information include: the SCS of the channel in which the control signaling that triggers the configuration information is located.

8. The method according to claim 1, wherein, When the reported quantity associated with the configuration information is not empty, the time occupied by the processing unit performing the AI ​​and / or ML processing is determined based on the reported type associated with the configuration information and the reported resources associated with the configuration information, including at least one of the following: In the case where the configuration information is associated with the report and the associated report is periodic or semi-static, the time period between the first symbol of the measurement resource associated with the configuration information and the last symbol of the reported resource is determined as the time occupied by the AI ​​and / or ML processing in the processing unit. In the case where the configuration information is associated with a report and the report associated with the configuration information is a non-periodic triggered report, the time period from the first symbol after the transmission of the trigger report instruction to the last symbol of the reported resource is determined as the time period occupied by the AI ​​and / or ML processing unit.

9. The method according to claim 1, wherein, When the reported quantity associated with the configuration information is empty, determining the time occupied by the processing unit performing the AI ​​and / or ML processing based on the measurement resources associated with the configuration information includes: If the reported quantity associated with the configuration information is empty, the time occupied by the processing unit performing the AI ​​and / or ML processing is determined based on the measurement resources associated with the configuration information and the processing latency.

10. The method according to claim 9, wherein, In the event that the configuration information association is not reported, the time occupied by the processing unit performing the AI ​​and / or ML processing is determined based on the measurement resources associated with the configuration information and the processing latency, including at least one of the following: If the reported quantity associated with the configuration information is empty, and the reported quantity associated with the configuration information is periodic or semi-static, the time period between the first symbol of the measurement resource associated with the configuration information and the X symbols after the last symbol of the measurement resource is determined as the occupancy time of the processing unit of the AI ​​and / or ML processing; where X is a positive integer. If the reported quantity associated with the configuration information is empty, and the reported quantity associated with the configuration information is a non-periodic triggered report, the first symbol after the end of the trigger instruction transmission is determined as the starting symbol of the occupied time, and the latter of the M symbols after the end of the trigger instruction and the N symbols after the last symbol of the measurement resource is determined as the ending symbol of the occupied time; M and N are both positive integers.

11. The method according to any one of claims 1 to 10, wherein, The configuration information includes at least one of the following: CSI resource configuration information; CSI report configuration information.

12. An information processing apparatus, wherein, The device includes: The processing module is configured to determine the occupancy information of the processing unit that performs the AI ​​and / or ML processing based on configuration information related to artificial intelligence (AI) / machine learning (ML) processing. The occupancy information includes: occupancy time; the processing module is configured as follows: If the reported quantity associated with the configuration information is not empty, the time occupied by the processing unit that performs the AI ​​and / or ML processing is determined according to the reported type associated with the configuration information and the reported resources associated with the configuration information. If the reported quantity associated with the configuration information is empty, the time occupied by the processing unit performing the AI ​​and / or ML processing is determined based on the measurement resources associated with the configuration information.

13. A communication device, comprising a processor, a transceiver, a memory, and an executable program stored in the memory and executable by the processor, wherein, When the processor runs the executable program, it performs the information processing method provided as claimed in any one of claims 1 to 11.

14. A computer storage medium storing an executable program; the executable program, when executed by a processor, is capable of implementing the information processing method provided in any one of claims 1 to 11.

Images