Prediction processing method and apparatus, and readable storage medium

Abstract

The present disclosure relates to the technical field of communications. Disclosed are a prediction processing method and apparatus, and a readable storage medium, which are used for reducing the measurement of signal resources by a terminal. The method comprises: acquiring prediction information; and on the basis of the prediction information, executing prediction by means of an AI / ML model, wherein the prediction information comprises one or more of the following: time domain information; frequency domain information; reference signal information; frequency information; and beam information. The embodiments of the present disclosure can achieve the effect of automatic prediction of signal resources by a terminal.

Description

A predictive processing method, apparatus, and readable storage medium

[0001] This disclosure claims priority to Chinese Patent Application No. 202411590945.3, filed on November 8, 2024, entitled “A Predictive Processing Method, Apparatus and Readable Storage Medium”, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This disclosure relates to the field of communication technology, and in particular to a predictive processing method, apparatus and readable storage medium. Background Technology

[0003] Artificial intelligence (AI) technology has been increasingly widely applied in modern society. In the medical field, AI can be used for medical image analysis, diagnosis, and prediction; in the financial field, it can be used for risk management, fraud detection, and credit assessment; and in manufacturing, it can be used for intelligent manufacturing and intelligent management. Furthermore, many other fields are also applying AI technology, such as autonomous driving, smart homes, game development, and education.

[0004] In related technologies, terminals can perform measurements on SSB and CSI-RS. For SSB measurements, network devices can configure the resource locations for SSB measurements, such as frequency information, period, and the starting position within the period. The terminal performs the measurement based on this SSB configuration information. For CSI-RS measurements, the network side configures the frequency domain location, period, etc., of the CSI-RS, and the terminal performs CSI-RS measurements based on this configuration information.

[0005] Traditional measurements require the network side to configure corresponding reference signals at the corresponding locations, such as SSB and CSI-RS, and the terminal to perform the measurement at the resource location indicated by the network side, resulting in high power consumption. Some technologies even require the terminal to stop some DL reception / UL transmission before performing the corresponding measurement, which will also cause problems such as reduced system throughput. Summary of the Invention

[0006] This disclosure provides a predictive processing method, apparatus, and readable storage medium to reduce the terminal's measurement of signal resources.

[0007] In a first aspect, embodiments of this disclosure provide a prediction processing method applied to a terminal, comprising:

[0008] Obtain prediction information and perform predictions using AI / ML models based on that information;

[0009] The predictive information includes one or more of the following:

[0010] Time domain information; frequency domain information; reference signal information; frequency information; beam information.

[0011] In some embodiments, the time-domain information described above includes one or more of the following:

[0012] Periodic information and first time offset; second time offset; bit mapping information; measurement reduction rate.

[0013] In some embodiments, the prediction information may further include one or more of the following: the prediction object; the index number of the prediction object; and the reporting information of the prediction result.

[0014] In some embodiments, the prediction information is included within the first information, and the prediction is performed based on the first information, which further includes:

[0015] Measurement information, which is used to indicate the information measured by the terminal.

[0016] In some embodiments, performing a prediction based on first information includes:

[0017] Based on the above measurement information and time domain information, the prediction time is determined; wherein, the time domain information is the above periodic information and the first time offset.

[0018] In some embodiments, performing a prediction based on first information includes:

[0019] Based on the above measurement information and the above second time offset, the predicted time is determined; wherein, the second time offset represents the time offset between the first measurement time and the predicted time in the measurement information.

[0020] In some embodiments, performing a prediction based on first information includes:

[0021] The prediction time is determined based on the second measurement time and the bit mapping information mentioned above.

[0022] In some embodiments, performing a prediction based on first information includes:

[0023] The prediction time is determined based on the second measurement time and the aforementioned measurement reduction rate.

[0024] In some embodiments, performing a prediction based on first information includes:

[0025] The predicted time is determined based on the second measurement time and the aforementioned beam information.

[0026] In some embodiments, the second measurement time described above is configured on the network side.

[0027] In some embodiments, performing predictions via an AI / ML model includes:

[0028] AI predictions are performed using AI / ML models to obtain the predicted measurement results.

[0029] Secondly, embodiments of this disclosure also provide a prediction processing method applied to a network device, comprising:

[0030] Send prediction information, which is used to perform predictions through AI / ML models;

[0031] The predictive information includes one or more of the following:

[0032] Time domain information; frequency domain information; reference signal information; frequency information; beam information.

[0033] In some embodiments, the time-domain information described above includes one or more of the following: periodic information and a first time offset; a second time offset; bit mapping information; and a measurement reduction rate.

[0034] In some embodiments, the prediction information may further include one or more of the following: the prediction object; the index number of the prediction object; and the reporting information of the prediction result.

[0035] In some embodiments, the method further includes: sending measurement information, the measurement information being used to indicate information measured by the terminal; wherein the measurement information includes:

[0036] The first measurement time is used to indicate the measurement time in this measurement information;

[0037] The second measurement time is used to indicate the measurement time configured on the network side.

[0038] Thirdly, embodiments of this disclosure also provide a predictive processing apparatus, which is applied to a terminal and includes: a memory, a transceiver, and a processor.

[0039] Memory is used to store computer programs; transceiver is used to send and receive data under the control of the processor; processor is used to read the computer programs from memory and perform the following operations:

[0040] Obtain prediction information and perform predictions using AI / ML models based on that information;

[0041] The prediction information includes one or more of the following: time domain information; frequency domain information; reference signal information; frequency information; beam information.

[0042] Fourthly, embodiments of this disclosure also provide a prediction processing apparatus applied to a network device, comprising: a memory, a transceiver, and a processor.

[0043] Memory is used to store computer programs; transceiver is used to send and receive data under the control of the processor; processor is used to read the computer programs from memory and perform the following operations:

[0044] Send prediction information, which is used to perform predictions through AI / ML models;

[0045] The prediction information includes one or more of the following: time domain information; frequency domain information; reference signal information; frequency information; beam information.

[0046] Fifthly, embodiments of this disclosure also provide a prediction processing apparatus applied to a terminal, comprising:

[0047] The first acquisition unit is used to acquire prediction information;

[0048] The first prediction unit is used to perform predictions using an AI / ML model based on the prediction information.

[0049] The prediction information includes one or more of the following: time domain information; frequency domain information; reference signal information; frequency information; beam information.

[0050] Sixthly, embodiments of this disclosure also provide a prediction processing apparatus applied to a network device, comprising:

[0051] The sending unit is used to send prediction information, which is used to perform predictions through an AI / ML model.

[0052] The prediction information includes one or more of the following: time domain information; frequency domain information; reference signal information; frequency information; beam information.

[0053] In a seventh aspect, embodiments of this disclosure also provide a processor-readable storage medium storing a computer program that, when executed by a processor, implements the steps in the first or second aspect.

[0054] In this embodiment of the disclosure, prediction is performed by an AI / ML model based on the prediction information, which can achieve the effect of automatic prediction of signal resources by the terminal. Attached Figure Description

[0055] Figure 1 is a flowchart of a prediction processing method provided in this disclosure;

[0056] Figure 2 is a schematic diagram of Embodiment 1 of the prediction processing method provided in this disclosure;

[0057] Figure 3 is a schematic diagram of Embodiment 2 of the prediction processing method provided in this disclosure;

[0058] Figure 4 is a schematic diagram of Embodiment 3 of the prediction processing method provided in this disclosure;

[0059] Figure 5 is a schematic diagram of Embodiment 4 of the prediction processing method provided in this disclosure;

[0060] Figure 6 is a schematic diagram of Embodiment 5 of the prediction processing method provided in this disclosure;

[0061] Figure 7 is a flowchart of another prediction processing method provided in this disclosure;

[0062] Figure 8 is a structural diagram of a predictive processing apparatus provided in an embodiment of this disclosure;

[0063] Figure 9 is a structural diagram of another predictive processing apparatus provided in an embodiment of this disclosure;

[0064] Figure 10 shows the internal structure of a predictive processing device provided in an embodiment of this disclosure. Detailed Implementation

[0065] In this disclosure, the term "and / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0066] In this disclosure, the term "multiple" refers to two or more, and other quantifiers are similar.

[0067] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this disclosure.

[0068] This disclosure provides a prediction processing method and apparatus, relating to the field of communication technology, to reduce the measurement of signal resources by a terminal. The method includes: acquiring prediction information; and performing prediction using an AI / ML model based on the prediction information; wherein the prediction information includes one or more of the following: time-domain information; frequency-domain information; reference signal information; frequency information; and beam information. This disclosure enables the terminal to automatically predict signal resources.

[0069] The method and apparatus are based on the same concept of the application. Since the methods and apparatus solve problems in similar ways, the implementation of the apparatus and methods can refer to each other, and the repeated parts will not be described again.

[0070] In related technology measurements, the terminal can perform measurements on SSB and CSI-RS.

[0071] For SSB measurements, the network side can configure the resource locations for SSB measurements, such as the period and the starting position within the period. The terminal performs the measurement based on this SSB configuration information.

[0072] For CSI-RS measurements, the network side configures the frequency domain location, period, etc. of CSI-RS, and the terminal performs CSI-RS measurements based on this configuration information.

[0073] Traditional measurements require the network side to configure corresponding reference signals at specific locations, such as SSB or CSI-RS, and the terminal to perform the measurement at the location indicated by the network side, resulting in high power consumption. Some measurements even require gap configuration, necessitating the terminal to stop some DL reception / UL transmission before performing the corresponding measurement, which also leads to a decrease in system throughput. In the embodiments adopted in this disclosure, artificial intelligence / machine learning (AI / ML) models are used to predict measurement results, thereby achieving automatic prediction of signal resources by the terminal.

[0074] Referring to Figure 1, which is a flowchart of a prediction processing method provided in an embodiment of this disclosure, the method includes the following steps:

[0075] Step 101: Obtain prediction information;

[0076] Step 102: Based on the prediction information, perform predictions using an AI / ML model.

[0077] The prediction information includes one or more of the following: time-domain information; frequency-domain information; reference signal information; frequency information; beam information. The prediction information also includes: the prediction object; the index number of the prediction object; and the reporting information of the prediction results.

[0078] The time-domain information further includes one or more of the following: periodic information and a first time offset; a second time offset; bit mapping information; measurement reduction rate, and other types of information. The first measurement time is used to represent the measurement time in the measurement information; the second measurement time is used to represent the measurement time configured on the network side.

[0079] In addition, in the embodiments of this disclosure, prediction can also be performed based on the first information (including measurement information and prediction information), whereby the measurement information is used to indicate the information measured by the terminal.

[0080] Example 1:

[0081] In embodiments of this disclosure, the prediction information may indicate the prediction period and a first time offset, thereby performing prediction through an artificial intelligence / machine learning (AI / ML) model to obtain the prediction time. The steps include:

[0082] Step 1-1: The terminal obtains the first information. This first information may be configuration information sent by the network side, such as through RRC (Radio Resource Control) reconfiguration, RRCSetup (RRC establishment), or RRCResume (RRC recovery) messages.

[0083] Step 1-2: The terminal obtains the prediction information through the first information.

[0084] The terminal can obtain prediction information through the first information in one of the following two ways:

[0085] Method 1: The first information includes measurement object information, which may include measurement information and prediction information.

[0086] Method 2: The first information includes prediction information, which includes the index information of the measurement object.

[0087] 6

[0088] In some embodiments, the measurement object is indicated by measurement object information, whereby the first information indicates the measurement object information. In some embodiments, the measurement object is used to indicate same-frequency or different-frequency measurements applied to a reference signal, which may be SSB, CSI-RS, PSS / SSS, CRS, etc., and is not limited here.

[0089] In this embodiment, the measurement information may include the time-domain and / or frequency-domain location of the measurement, such as indicating the measurement period and / or time-domain offset, and may also include the measurement reporting period, which is not limited here. The measurement information is the information actually used in the measurement, including the reference signal location, such as the period and time offset; the notification method can be SMTC, for example, the following execution code:

[0090] As described above, the period and offset can be notified via periodicityAndOffset; and the position of CSI-RS can be notified via information such as slotConfig in SI-RS-Resource-Mobility.

[0091] Figure 2 is a schematic diagram of a first embodiment of the prediction processing method provided in this disclosure. Referring to Figure 2, in some embodiments of this disclosure, the prediction information is information predicted by an AI / ML model, including: the period and / or a first offset predicted by the AI / ML model. As illustrated in Figure 2, assuming the measurement information indicates: the period is 20 time units and the offset is 5 time units, the time units can be time slots, subframes, milliseconds, seconds, etc., without limitation. It should be noted that the time units for the period and offset in Figure 2 can be the same or different, without limitation.

[0092] As shown in Figure 2, the prediction information can indicate periodicity and the first time offset. For example, the periodicity is 20 time units, and the first time offset is 15 time units.

[0093] Alternatively, it can be implemented as follows:

[0094] In this configuration, the terminal needs to perform measurements based on the resource location indicated by the measurement information, obtain the measurement results, and output the results predicted by the AI / ML model at the location indicated by the prediction information, based on the measurement results.

[0095] Steps 1-3: The terminal can predict the results based on the actual measurement results using AI / ML models, perform subsequent operations, and determine whether the measurement event is triggered or the measurement results are reported.

[0096] In this step, the measurement events may include one or more of the following events, without limitation:

[0097] A1 event: The signal quality of the serving cell is below the specified threshold;

[0098] A2 event: The signal quality of the serving cell is below the specified threshold.

[0099] A3 event: The neighboring cell signal quality is higher than SpCell by a specified offset;

[0100] A4 event: The signal quality of the neighboring cell is higher than the specified threshold;

[0101] 8

[0102] A5 event: SpCell's signal quality is below a certain threshold, while neighboring cells are above another threshold;

[0103] A6 event: The signal quality of the neighboring cell is higher than that of the SCell by a specified offset;

[0104] B1: Inter RAT neighbor cell signal quality is higher than a specified threshold;

[0105] B2: The signal quality of PCell is below a certain threshold, while the Inter RAT neighbor cell is above another threshold;

[0106] I1: Interference exceeds a specified threshold;

[0107] And V2X-related events, etc.

[0108] In Embodiment 1 of this disclosure, the prediction information may indicate the period and / or first time offset of the AI ​​prediction, thereby performing the prediction through an artificial intelligence / machine learning AI / ML model, obtaining the prediction time of the prediction result, and obtaining the prediction result.

[0109] Example 2:

[0110] In embodiments of this disclosure, the prediction information may indicate a second time offset between the predicted time position and the first measurement time.

[0111] Step 2-1: The terminal obtains the first information. This first information can be configuration information sent by the network side, such as through RRC reconfiguration, RRCSetup, or RRCResume messages.

[0112] Step 2-2: The terminal obtains the prediction information through the first information.

[0113] The terminal can obtain prediction information through the first information in one of the following two ways:

[0114] Method 1: The first information includes measurement object information, which includes measurement information and prediction information;

[0115] Method 2: The first information includes prediction information, which contains index information of the measurement object. In some embodiments, the measurement object is indicated by measurement object information, and the first information indicates the measurement object information. In some embodiments, the measurement object is used to indicate same-frequency or different-frequency measurements applied to a reference signal. The reference signal can be SSB, CSI-RS, PSS / SSS, CRS, etc., which are not limited here. The measurement information can include the time-domain and / or frequency-domain location of the measurement, such as indicating the measurement period and / or time offset, and can also include the measurement reporting period, which are not limited here either.

[0116] The measurement information is the information actually used in the measurement, including the first measurement time and / or pilot information, the first measurement time indicating the measurement period, and the time offset, etc. The notification method can be SMTC, for example, the following executed code:

[0117] As described above, the period and offset of the first measurement moment can be notified via periodicityAndOffset; and the position of CSI-RS can be notified via information such as slotConfig in SI-RS-Resource-Mobility.

[0118] Figure 3 is a schematic diagram of Embodiment 2 of the prediction processing method provided in this disclosure. Referring to Figure 3, in some embodiments of this disclosure, the prediction information is the information predicted by the AI / ML model, including: the time position (prediction time) predicted by the AI / ML model and the second time offset between the first measurement time; the measurement information is the information actually measured, including the first measurement time and / or pilot position, such as the first measurement time, period and time offset, etc., and the notification method can be the same as the above-described SMTC method.

[0119] As shown in Figure 3, for example, the second time offset is 10 time units, which means the offset is 10 time units away from the first measurement time.

[0120] The notification method can be:

[0121] SSB-MTC::= SEQUENCE{

[0122] Offset INTEGER(0..159)

[0123] }

[0124] In embodiments of this disclosure, the terminal performs a measurement based on a first measurement time indicated by the measurement information, and performs a prediction using an AI / ML model based on a second time offset.

[0125] Steps 2-3: Based on the actual measurement results, the terminal can use the AI / ML model to predict the results and perform subsequent operations to determine whether the measurement event is triggered or the measurement results are reported. The other steps in this process are the same as in steps 1-3 and will not be repeated here.

[0126] Example 3:

[0127] In embodiments of this disclosure, the prediction information may indicate bit mapping information and a second period, which may be an AI prediction period and / or an actual measurement period.

[0128] Step 3-1: The terminal obtains the first information. This first information may be configuration information sent by the network-side device, such as through RRC reconfiguration, RRCSetup, or RRCResume messages.

[0129] Step 3-2: The terminal obtains the prediction information through the first information.

[0130] The terminal can obtain prediction information through the first information in one of the following two ways:

[0131] Method 1: The first information includes measurement object information, which may include measurement information and prediction information.

[0132] Method 2: The first information includes prediction information, which includes the index information of the measurement object.

[0133] In some embodiments, the measurement object is indicated by measurement object information, whereby the first information indicates the measurement object information. The measurement object is used to indicate a measurement applied to a reference signal at the same frequency or a different frequency. The reference signal may be SSB, CSI-RS, PSS / SSS, CRS, etc., and is not limited here.

[0134] Measurement information may include the time-domain and / or frequency-domain position of the reference signal, such as the period and / or time offset of the reference signal, and may also include the measurement reporting period, which is not limited here.

[0135] The measurement information is the information actually used in the measurement, including pilot positions, such as period and time offset. Notification can be sent via SMTC, for example, through the following executed code:

[0136] As described above, the period and offset can be notified via periodicityAndOffset; and the position of CSI-RS can be notified via information such as slotConfig in SI-RS-Resource-Mobility.

[0137] Figure 4 is a schematic diagram of Embodiment 3 of the prediction processing method provided in this disclosure. Referring to Figure 4, in some embodiments of this disclosure, the prediction information is information predicted by an AI / ML model, including: bit mapping information and / or a second period, where the second period can be an AI prediction period and / or an actual measurement period. In this step, the terminal obtains information about performing measurements and performing AI / ML model predictions based on the second measurement time indicated by the measurement information (which represents the actual measurement time configured on the network side) and the bit mapping information.

[0138] As shown in Figure 4, the measurement information notification period and / or offset allow the terminal to perform measurements. The prediction information notification includes a bitmap, which can be in bitmap form. The terminal can calculate the resource locations predicted by the AI / ML model using the bitmap. For example, if the measurement information notification period is 50ms and the bitmap length is 4 (assumed to be 0111), in some embodiments, the network side can notify the AI ​​prediction period, which is 10ms in this embodiment. Thus, the terminal can assume that there are 5 points within 50ms, of which 2 are the actual measured points and 3 are locations that need to be predicted by the AI ​​(= bitmap length - 1). Therefore, the terminal can obtain the AI / ML model predicted locations.

[0139] Step 3-3: Based on the actual measurement results, the terminal can predict the results using an AI / ML model, execute subsequent operations, and determine whether the measurement event is triggered or the measurement results are reported. The other steps in this process are the same as in steps 1-3 and will not be repeated here.

[0140] Example 4:

[0141] In embodiments of this disclosure, the prediction information may indicate the time-domain measurement reduction rate and a third period, which may be the AI ​​prediction period and / or the actual measurement period.

[0142] Step 4-1: The terminal obtains the first information. This first information can be configuration information sent by the network side, such as through RRC reconfiguration, RRCSetup, or RRCResume messages.

[0143] Step 4-2: The terminal obtains the prediction information through the first information.

[0144] The terminal can obtain prediction information through the first information in one of the following two ways:

[0145] Method 1: The first information includes measurement object information, which may include measurement information and prediction information.

[0146] Method 2: The first information includes prediction information, which includes the index information of the measurement object.

[0147] In some embodiments, the measurement object is indicated by measurement object information, whereby the first information indicates the measurement object information. In some embodiments, the measurement object is used to indicate same-frequency or different-frequency measurements applied to a reference signal, which may be SSB, CSI-RS, PSS / SSS, CRS, etc., and is not limited here.

[0148] Measurement information may include the time domain and / or frequency domain location of the measurement, such as the period and / or time offset of the measurement, and may also include the reporting period of the measurement, which is not limited here.

[0149] The measurement information is the information actually used in the measurement, including pilot positions, such as period and time offset. Notification can be sent via SMTC, for example, through the following executed code:

[0150] In the above description, the period and offset can be notified via periodicityAndOffset; and the position of CSI-RS can be notified via information such as slotConfig in SI-RS-Resource-Mobility. Figure 5 is a schematic diagram of Embodiment 4 of the prediction processing method provided by this disclosure. Referring to Figure 5, in some embodiments of this disclosure, the prediction information is information predicted by the AI / ML model, including: the prediction information notification time-domain measurement reduction rate, for example, 3 / 4, and / or the third period, which can be the AI ​​prediction period and / or the actual measurement period, for example, in this embodiment, it is the AI ​​prediction period, and its size is 10ms. As shown in the figure below, if the measurement information notification period is 50ms, the AI ​​prediction period is 10ms, which can be configured on the network side, and the measurement reduction rate is 3 / 4. The terminal can determine that through a measurement result (for example, the second measurement time, which represents a certain moment of the actual measurement configured on the network side), the terminal can predict 3 prediction results, and thus know the predicted position.

[0151] Step 4-3: Based on the actual measurement results, the terminal can predict the results using an AI / ML model, execute subsequent operations, and determine whether the measurement event is triggered or the measurement results are reported. The other steps in this process are the same as in steps 1-3 and will not be repeated here.

[0152] Example 5:

[0153] In embodiments of this disclosure, the prediction information may indicate beam information.

[0154] Step 5-1: The terminal obtains the first information. This first information can be configuration information sent by the network side, such as through RRC reconfiguration, RRCSetup, or RRCResume messages.

[0155] Step 5-2: The terminal obtains measurement prediction information through the first information.

[0156] The terminal can obtain prediction information through the first information in one of the following two ways:

[0157] Method 1: The first information includes object information, which may include measurement information and prediction information.

[0158] Method 2: The first information includes prediction information, which includes index information of the measurement object. In some embodiments, the first information indicates measurement object information. In some embodiments, the measurement object information is used to indicate the measurement object, which indicates a same-frequency or different-frequency measurement applied to a reference signal. The reference signal can be SSB, CSI-RS, PSS / SSS, CRS, etc., without limitation. The measurement information can include the time-domain and / or frequency-domain position of the reference signal, such as indicating the measurement period and / or time offset, and can also include the measurement reporting period, without limitation.

[0159] The measurement information refers to the information used in the actual measurement, including SSB beam information or CSI-RS beam information, such as a bitmap of the beam. The measurement information may also include a second measurement time, which represents a specific moment in the actual measurement configured on the network side.

[0160] Figure 6 is a schematic diagram of Embodiment 5 of the prediction processing method provided in this disclosure. Referring to Figure 6, in some embodiments of this disclosure, the prediction information is the information predicted by the AI / ML model, including: prediction information notification beam information, such as bitmap information. As shown in Figure 6, if the beam pattern of the measurement information notification is 10101010 (counter-clockwise rotation, the leftmost bit corresponds to the leftmost beam), and the beam information is 01010101 (counter-clockwise rotation, the leftmost bit corresponds to the leftmost beam), after mapping, it can be known that the measured beam is the beam with index 0, 2, 4, 6, while the predicted beam is the beam with index 1, 3, 5, 7, thereby obtaining the prediction result.

[0161] Step 4-3: Based on the actual measurement results, the terminal can predict the results using an AI / ML model, execute subsequent operations, and determine whether the measurement event is triggered or the measurement results are reported. The other steps in this process are the same as in steps 1-3 and will not be repeated here.

[0162] In embodiments of this disclosure, a prediction processing method is also provided. Figure 7 is a flowchart of another prediction processing method provided by this disclosure. As shown in Figure 7, it is applied to a network device and includes:

[0163] Step 701: Send prediction information, which is used to perform predictions through the AI / ML model;

[0164] The prediction information includes one or more of the following: time domain information; frequency domain information; reference signal information; frequency information; beam information.

[0165] The aforementioned time-domain information includes one or more of the following: periodic information and a first time offset; a second time offset; bit mapping information; and measurement reduction rate.

[0166] In some embodiments, the prediction information further includes: the prediction object; the index number of the prediction object; and the reporting information of the prediction result.

[0167] In some embodiments, the method further includes: sending measurement information, the measurement information being used to indicate information measured by the terminal; wherein the measurement information includes:

[0168] The first measurement time is used to indicate the measurement time in the measurement information;

[0169] The second measurement time is used to indicate the measurement time configured on the network side.

[0170] In some embodiments, the second measurement time mentioned above includes: the Radio Resource Management (RRM) measurement time configured on the network side.

[0171] In the embodiments of this disclosure, the prediction information and measurement information may be configuration information sent by the network-side device, such as through RRC reconfiguration, RRCSetup (RRC establishment), and RRCResume (RRC recovery) messages.

[0172] The aforementioned prediction information can indicate various information for AI prediction, and through the first or second measurement time in the measurement information, the prediction is performed by the artificial intelligence / machine learning (AI / ML) model to obtain the prediction time of the prediction result.

[0173] The above embodiments describe the service performance monitoring method of this disclosure. The following embodiments will further describe the corresponding devices in conjunction with the accompanying drawings.

[0174] In an embodiment of this disclosure, FIG8 is a structural diagram of a prediction processing device provided in an embodiment of this disclosure. As shown in FIG8, an embodiment of this disclosure provides a prediction processing device 800, applied to a terminal, comprising:

[0175] The first acquisition unit 801 is used to acquire prediction information;

[0176] The first prediction unit 802 is used to perform predictions based on the prediction information using an artificial intelligence / machine learning (AI / ML) model.

[0177] The predictive information includes one or more of the following:

[0178] Time domain information;

[0179] Frequency domain information;

[0180] Reference signal information;

[0181] Frequency information;

[0182] Beam information.

[0183] In some embodiments, the time-domain information described above includes one or more of the following:

[0184] Periodic information and first time offset; second time offset; bit mapping information; measurement reduction rate.

[0185] In some embodiments, the prediction information may further include one or more of the following: the prediction object; the index number of the prediction object; and the reporting information of the prediction result.

[0186] In some embodiments, the prediction information is included in the first information, and the first prediction unit 802 is used to perform prediction based on the first information. The first information further includes measurement information, which is used to indicate information measured by the terminal.

[0187] In some embodiments, the first prediction unit 802 is used for:

[0188] Based on the above measurement information and time domain information, the prediction time is determined; wherein, the time domain information is the above periodic information and the first time offset.

[0189] In some embodiments, the first prediction unit 802 is used for:

[0190] Based on the above measurement information and the above second time offset, the predicted time is determined; wherein, the second time offset represents the time offset between the first measurement time and the predicted time in the measurement information.

[0191] In some embodiments, the first prediction unit 802 is used for:

[0192] The prediction time is determined based on the second measurement time and the bit mapping information mentioned above.

[0193] In some embodiments, the first prediction unit 802 is used for:

[0194] The prediction time is determined based on the second measurement time and the aforementioned measurement reduction rate.

[0195] In some embodiments, the first prediction unit 802 is used for:

[0196] The predicted time is determined based on the second measurement time and the aforementioned beam information.

[0197] In some embodiments, the second measurement time described above is configured on the network side.

[0198] In some embodiments, the first prediction unit 802 is used for:

[0199] AI predictions are performed using AI / ML models to obtain the predicted measurement results.

[0200] It should be noted that the apparatus provided in this embodiment can implement all the method steps implemented in the method embodiment applied to the terminal, and can achieve the same technical effect. Therefore, the parts and beneficial effects that are the same as those in the method embodiment will not be described again here.

[0201] In one embodiment of this disclosure, FIG9 is a structural diagram of another prediction processing apparatus provided by an embodiment of this disclosure. As shown in FIG9, an embodiment of this disclosure provides a prediction processing apparatus 900, applied to a network device, comprising:

[0202] The sending unit 901 is used to send prediction information, which is used to perform predictions through an artificial intelligence / machine learning (AI / ML) model.

[0203] The predictive information includes one or more of the following:

[0204] Time domain information; frequency domain information; reference signal information; frequency information; beam information.

[0205] In some embodiments, the time-domain information described above includes one or more of the following: periodic information and a first time offset; a second time offset; bit mapping information; and a measurement reduction rate.

[0206] In some embodiments, the prediction information may further include one or more of the following: the prediction object; the index number of the prediction object; and the reporting information of the prediction result.

[0207] In some embodiments, the sending unit 901 is further configured to: send measurement information, the measurement information being used to indicate information measured by the terminal; wherein the measurement information includes:

[0208] The first measurement time is used to indicate the measurement time in this measurement information;

[0209] The second measurement time is used to indicate the measurement time configured on the network side.

[0210] It should be noted that the apparatus provided in this embodiment can implement all the method steps implemented in the method embodiment applied to the first network element and can achieve the same technical effect. Therefore, the parts and beneficial effects that are the same as those in the method embodiment will not be described again here.

[0211] It should be noted that the division of units in the embodiments of this disclosure is illustrative and only represents one logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional units in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated units described above can be implemented in hardware or as software functional units.

[0212] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a processor-readable storage medium. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to related technologies, or all or part of the technical solution, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the various method embodiments of this disclosure. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, read-only memory (ROM), random access memory (RAM), a magnetic disk, or an optical disk.

[0213] This disclosure also provides a communication device, including: a memory, a processor, and a program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps in the above-described predictive processing method.

[0214] In an exemplary embodiment, a predictive processing device is provided, which can be a terminal, and its internal structure can be as shown in Figure 10. The predictive processing device includes a processor 1000, a transceiver 1010, a memory 1010, and a bus interface. The processor 1000 and the memory 1010 are connected via the bus interface. The processor 1000 provides computational and control capabilities. The memory 1010 of the auxiliary positioning device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface of the auxiliary positioning device is used for exchanging information between the processor and external devices. The communication interface of the auxiliary positioning device is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a positioning method for a passive device. The display unit of the auxiliary positioning device is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the auxiliary positioning device can be a touch layer covering the display screen, or a button, trackball, or touchpad set on the housing of the auxiliary positioning device, or an external keyboard, touchpad, or mouse, etc.

[0215] The assisted positioning device involved in the embodiments of this disclosure can be a base station, which may include multiple cells providing services to terminals. Depending on the application, the base station may also be called an access point, or a device in the access network that communicates with the wireless terminal device through one or more sectors on the air interface, or other names. The network device can be used to exchange received air frames with Internet Protocol (IP) packets, acting as a router between the wireless terminal device and the rest of the access network, where the rest of the access network may include an Internet Protocol (IP) communication network. The network device can also coordinate the attribute management of the air interface. For example, the network device involved in the embodiments of this disclosure may be an evolved Node B (eNB or e-NodeB) in a long term evolution (LTE) system, a 5G base station (gNB) in a next generation system, or a Home evolved Node B (HeNB), relay node, femto, pico, network testing equipment, etc., and is not limited in the embodiments of this disclosure. In some network architectures, network devices may include centralized unit (CU) nodes and distributed unit (DU) nodes, which may also be geographically separated.

[0216] Those skilled in the art will understand that the structure shown in Figure 10 is merely a block diagram of a portion of the structure related to the present disclosure and does not constitute a limitation on the auxiliary positioning device to which the present disclosure is applied. The auxiliary positioning device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements. The present disclosure also provides a computer program product, including computer instructions, which, when executed by a processor, implement the various processes of the above-described predictive processing method embodiments and achieve the same technical effects. To avoid repetition, further details are omitted here.

[0217] This disclosure also provides a processor-readable storage medium storing a program. When executed by a processor, this program implements the various processes of the above-described predictive processing method embodiments and achieves the same technical effects. To avoid repetition, further details are omitted here. The readable storage medium can be any available medium or data storage device accessible to the processor, including but not limited to magnetic storage (e.g., floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (e.g., CDs, DVDs, BDs, HVDs, etc.), and semiconductor storage (e.g., ROMs, EPROMs, EEPROMs, non-volatile memory (NAND flash), solid-state drives (SSDs), etc.).

[0218] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, the terms are used in conjunction with the provided text.

[0219] The phrase “including one…” does not preclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0220] Those skilled in the art will understand that embodiments of this disclosure can be provided as methods, systems, or computer program products. Therefore, this disclosure can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this disclosure can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0221] This disclosure describes embodiments of methods, apparatus (systems), and computer program products according to embodiments of this disclosure with reference to flowchart illustrations and / or block diagrams. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-executable instructions. These computer-executable instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in one or more flowchart illustrations and / or one or more block diagrams.

[0222] These processor-executable instructions may also be stored in a processor-readable memory that can instruct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the processor-readable memory produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.

[0223] Obviously, those skilled in the art can make various modifications and variations to the embodiments of this disclosure without departing from the spirit and scope of the embodiments of this disclosure. Therefore, if these modifications and variations to the embodiments of this disclosure fall within the scope of the claims of the embodiments of this disclosure and their equivalents, then the embodiments of this disclosure are also intended to include these modifications and variations.

Claims

1. A predictive processing method, wherein, Applied to terminals, including: Obtain prediction information, and perform predictions based on the prediction information using artificial intelligence / machine learning (AI / ML) models; The prediction information includes one or more of the following: Time domain information; Frequency domain information; Reference signal information; Frequency information; Beam information.

2. The method according to claim 1, wherein, The time-domain information includes one or more of the following: Periodic information and first time offset; Second time offset; Bit mapping information Measure the reduction rate.

3. The method according to claim 1, wherein, The prediction information also includes one or more of the following: Predicted object; The index number of the predicted object; Information on reporting prediction results.

4. The method according to claim 1, wherein, The prediction information is included within the first information, and prediction is performed based on the first information, wherein the first information further includes: Measurement information, which is used to indicate information measured by the terminal.

5. The method according to claim 4, wherein, The step of performing prediction based on the first information includes: The prediction time is determined based on the measurement information and the time domain information; wherein, the time domain information is the period information and the first time offset.

6. The method according to claim 4, wherein, The step of performing prediction based on the first information includes: The predicted time is determined based on the measurement information and the second time offset; wherein the second time offset represents the time offset between the first measurement time and the predicted time in the measurement information.

7. The method according to claim 4, wherein, The step of performing prediction based on the first information includes: The predicted time is determined based on the second measurement time and the bit mapping information.

8. The method according to claim 4, wherein, The step of performing prediction based on the first information includes: The prediction time is determined based on the second measurement time and the measurement reduction rate.

9. The method according to claim 1, wherein, The step of performing prediction based on the first information includes: The predicted time is determined based on the second measurement time and the beam information.

10. The method according to any one of claims 7 to 9, wherein, The second measurement time is configured on the network side.

11. The method according to claim 1, wherein, Performing predictions using artificial intelligence / machine learning (AI / ML) models includes: AI predictions are performed using artificial intelligence / machine learning (AI / ML) models to obtain predictive measurement results.

12. A predictive processing method, wherein, Applied to network devices, including: Send prediction information, which is used to perform predictions through artificial intelligence / machine learning (AI / ML) models; The prediction information includes one or more of the following: Time domain information; Frequency domain information; Reference signal information; Frequency information; Beam information.

13. The method according to claim 12, wherein, The time-domain information includes one or more of the following: Periodic information and first time offset; Second time offset; Bit mapping information; Measure the reduction rate.

14. The method according to claim 12, wherein, The prediction information also includes one or more of the following: Predicted object; The index number of the predicted object; Information on reporting prediction results.

15. The method according to claim 12, wherein, The method further includes: Sending measurement information, the measurement information being used to indicate information measured by the terminal; wherein, the measurement information includes: The first measurement time is used to represent the measurement time in the measurement information; The second measurement time is used to represent the measurement time configured on the network side.

16. A predictive processing apparatus, wherein, Applications in terminals include: memory, transceiver, and processor. A memory for storing computer programs; a transceiver for sending and receiving data under the control of the processor; and a processor for reading the computer programs from the memory and performing the following operations: Obtain prediction information, and perform predictions based on the prediction information using artificial intelligence / machine learning (AI / ML) models; The prediction information includes one or more of the following: Time domain information; Frequency domain information; Reference signal information; Frequency information; Beam information.

17. The apparatus according to claim 16, wherein, The time-domain information includes one or more of the following: Periodic information and first time offset; Second time offset; Bit mapping information; Measure the reduction rate.

18. The apparatus according to claim 16, wherein, The prediction information also includes one or more of the following: Predicted object; The index number of the predicted object; Information on reporting prediction results.

19. The apparatus according to claim 16, wherein, The prediction information is included within the first information, and prediction is performed based on the first information, wherein the first information further includes: Measurement information, which is used to indicate information measured by the terminal.

20. The apparatus according to claim 19, wherein, The step of performing prediction based on the first information includes: The prediction time is determined based on the measurement information and the time domain information; wherein, the time domain information is the period information and the first time offset.

21. The apparatus according to claim 19, wherein, The step of performing prediction based on the first information includes: The predicted time is determined based on the measurement information and the second time offset; wherein the second time offset represents the time offset between the first measurement time and the predicted time in the measurement information.

22. The apparatus according to claim 19, wherein, The step of performing prediction based on the first information includes: The second measurement time is used to determine the predicted time by mapping the bit information to the second measurement time.

23. The apparatus according to claim 19, wherein, The step of performing prediction based on the first information includes: The second measurement time and the measurement reduction rate are used to determine the prediction time.

24. The apparatus according to claim 16, wherein, The step of performing prediction based on the first information includes: The second measurement time and the beam information are used to determine the predicted time.

25. The method according to any one of claims 22 to 24, wherein, The second measurement time is configured on the network side.

26. The apparatus according to any one of claims 22 to 24, wherein, The second measurement time includes: The measurement time of the Radio Resource Management (RRM) configured on the network side.

27. The apparatus according to claim 16, wherein, Performing predictions using artificial intelligence / machine learning (AI / ML) models includes: AI predictions are performed using artificial intelligence / machine learning (AI / ML) models to obtain predictive measurement results.

28. A predictive processing apparatus, wherein, Applications in network devices, including: memory, transceivers, and processors. A memory for storing computer programs; a transceiver for sending and receiving data under the control of the processor; and a processor for reading the computer programs from the memory and performing the following operations: Send prediction information, which is used to perform predictions through artificial intelligence / machine learning (AI / ML) models; The prediction information includes one or more of the following: Time domain information; Frequency domain information; Reference signal information; Frequency information; Beam information.

29. The apparatus according to claim 28, wherein, The time-domain information includes one or more of the following: Periodic information and first time offset; Second time offset; Bit mapping information; Measure the reduction rate.

30. The apparatus according to claim 28, wherein, The method further includes: Sending measurement information, the measurement information being used to indicate information measured by the terminal; wherein, the measurement information includes: The first measurement time is used to represent the measurement time in the measurement information; The second measurement time is used to represent the measurement time configured on the network side.

31. A predictive processing apparatus, wherein, Applied to terminals, including: The first acquisition unit is used to acquire prediction information; The first prediction unit is used to perform predictions based on the prediction information using an artificial intelligence / machine learning (AI / ML) model. The prediction information includes one or more of the following: Time domain information; Frequency domain information; Reference signal information; Frequency information; Beam information.

32. A predictive processing apparatus, wherein, Applied to network devices, including: A sending unit is used to send prediction information, which is used to perform predictions through an artificial intelligence / machine learning (AI / ML) model. The prediction information includes one or more of the following: Time domain information; Frequency domain information; Reference signal information; Frequency information; Beam information.

33. A processor-readable storage medium, wherein, The processor-readable storage medium stores a program for causing the processor to perform the method as described in any one of claims 1 to 15.

Images