Input processing method, apparatus and device for artificial intelligence model

Abstract

The application discloses an input processing method, device and equipment of an artificial intelligence model, and belongs to the field of communication. The input processing method of the artificial intelligence model of the embodiment comprises the following steps: a first device determines input information of an artificial intelligence model; wherein the artificial intelligence model is used for a beam-related function, and the input information comprises expected information and at least one of the following: beam quality-related information, first beam-related information and time-related information.

Description

Technical Field

[0001] This application belongs to the field of communication technology, and specifically relates to an input processing method, apparatus and device for an artificial intelligence model. Background Technology

[0002] Artificial intelligence (AI) has been widely applied in various fields, and therefore, a solution using AI for beam prediction has also been proposed in the field of communication technology. For example... Figure 1 As shown, the Reference Signal Received Power (RSRP) of a portion of the beam pairs is used as input, and the output of the AI ​​model is the RSRP result for all beam pairs. A beam pair consists of a transmit beam and a receive beam.

[0003] The number of inputs to the AI ​​model is related to the number of selected beam pairs; that is, the number of inputs to the AI ​​model is fixed. The number of outputs of the AI ​​model equals the total number of beam pairs, which in turn equals the number of transmitted beams multiplied by the number of received beams. If the model is sent from the network side to the terminal (i.e., the model is on the terminal side), the number of transmitted beams corresponds to the number of transmitted beams on the network side, while the number of received beams corresponds to the number of received beams on the terminal side.

[0004] However, considering generalization and practical feasibility, typically only one AI model is used for beam prediction within a single cell, meaning that this AI model must be applicable to all users within the cell. However, since different terminals have different capabilities, the number of beams received by each terminal also varies, meaning the total number of beam pairs differs depending on the capabilities of different terminals. Therefore, this limits the widespread application of the AI ​​model. Summary of the Invention

[0005] This application provides an input processing method, apparatus, and device for an artificial intelligence model, which can solve the problem that the number of AI model outputs cannot be widely used.

[0006] Firstly, an input processing method for an artificial intelligence model is provided, the method comprising:

[0007] The first device determines the input information of the artificial intelligence model; wherein the artificial intelligence model is used for beam prediction related functions, and the input information includes expected information and at least one of the following:

[0008] Beam quality related information;

[0009] First beam association information;

[0010] Time-related information.

[0011] Secondly, an input processing device for an artificial intelligence model is provided, the device comprising:

[0012] A first determining module is configured to determine the input information of an artificial intelligence model via a first device; wherein the artificial intelligence model is used for beam correlation functions, and the input information includes expected information and at least one of the following:

[0013] Beam quality related information;

[0014] First beam association information;

[0015] Time-related information.

[0016] Thirdly, an input processing device for an artificial intelligence model is provided. The terminal includes a processor and a memory, the memory storing a program or instructions that can run on the processor, the program or instructions being executed by the processor to implement the steps of the method described in the first aspect.

[0017] Fourthly, a communication device is provided, including a processor and a communication interface, wherein the processor is used to determine input information of an artificial intelligence model; wherein the artificial intelligence model is used for beam correlation functions, and the input information includes expected information and at least one of the following:

[0018] Beam quality related information;

[0019] First beam association information;

[0020] Time-related information.

[0021] Fifthly, an input processing system for an artificial intelligence model is provided, including a communication device that can be used to perform the steps of the method described in the first aspect. Sixthly, a readable storage medium is provided, on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described in the first aspect.

[0022] In a seventh aspect, a chip is provided, the chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run programs or instructions to implement the method as described in the first aspect.

[0023] Eighthly, a computer program / program product is provided, which is stored in a storage medium and is executed by at least one processor to implement the steps of the input processing method for the artificial intelligence model as described in the first aspect.

[0024] In this embodiment, a first device determines the input information of an artificial intelligence (AI) model. The AI ​​model is used for beam prediction-related functions, and the input information includes desired information and at least one of the following: beam quality-related information; first beam association information; and time-related information. Thus, the solution of this application is not limited by the capabilities of the first device; it can obtain desired output information through the AI ​​model of the first device. Furthermore, the number of outputs from the AI ​​model is fixed and independent of the number or angle of the received beams of the terminal device. This solves the problem that the number of AI model outputs cannot be widely applied due to differences in the capabilities of terminal devices, thereby increasing the practicality of the AI ​​model. Attached Figure Description

[0025] Figure 1 This is a schematic diagram of beam prediction using an artificial intelligence model in existing technology;

[0026] Figure 2 This is a block diagram of a wireless communication system to which this application embodiment can be applied.

[0027] Figure 3 This is a schematic diagram illustrating the steps of the input processing method for the artificial intelligence model according to an embodiment of this application;

[0028] Figure 4 This is a schematic diagram of the input processing system of the artificial intelligence model according to an embodiment of this application;

[0029] Figure 5 This is a schematic diagram of the structure of the input processing device for the artificial intelligence model according to an embodiment of this application;

[0030] Figure 6 This is a schematic diagram of the structure of the input processing device for the artificial intelligence model according to an embodiment of this application;

[0031] Figure 7 This is a schematic diagram of the structure of a communication device according to an embodiment of this application. Detailed Implementation

[0032] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0033] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same class, not limited in number; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0034] It is worth noting that the technologies described in this application are not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency Division Multiple Access (SC-FDMA), and other systems. The terms "system" and "network" in this application are often used interchangeably, and the described technologies can be used with the systems and radio technologies mentioned above, as well as with other systems and radio technologies. The following description describes New Radio (NR) systems for illustrative purposes, and NR terminology is used in most of the following description; however, these technologies can also be applied to applications beyond NR systems, such as 6th generation (6G) radio systems. th Generation 6G communication system.

[0035] Figure 2This diagram illustrates a block diagram of a wireless communication system applicable to embodiments of this application. The wireless communication system includes a terminal 11 and a network-side device 12. Terminal 11 can be a mobile phone, tablet computer, laptop computer, personal digital assistant (PDA), handheld computer, netbook, ultra-mobile personal computer (UMPC), mobile internet device (MID), augmented reality (AR) / virtual reality (VR) device, robot, wearable device, vehicle-mounted device (VUE), pedestrian terminal (PUE), smart home (home devices with wireless communication capabilities, such as refrigerators, televisions, washing machines, or furniture), game console, personal computer (PC), ATM or self-service machine, etc. Wearable devices include: smartwatches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart chains, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. It should be noted that the specific type of terminal 11 is not limited in this application embodiment. The network-side device 12 may include access network equipment or core network equipment. The access network equipment 12 may also be referred to as radio access network equipment, radio access network (RAN), radio access network function, or radio access network unit. The access network equipment 12 may include base stations, WLAN access points, or WiFi nodes, etc. The base station may be referred to as Node B, evolved Node B (eNB), access point, base transceiver station (BTS), radio base station, radio transceiver, basic service set (BSS), extended service set (ESS), home B node, home evolved B node, transmitting and receiving point (TRP), or any other suitable term in the field. As long as the same technical effect is achieved, the base station is not limited to specific technical terms. It should be noted that this application embodiment only uses a base station in an NR system as an example for introduction and does not limit the specific type of base station.

[0036] The input processing of the artificial intelligence model provided in this application will be described in detail below with reference to the accompanying drawings, through some embodiments and application scenarios.

[0037] like Figure 3 As shown in the figure, this application embodiment provides an input processing method for an artificial intelligence model, including the following steps:

[0038] Step 301, the first device determines the input information of the artificial intelligence model; wherein the artificial intelligence model is used for beam correlation function, and the input information includes expected information and at least one of the following:

[0039] Beam quality related information;

[0040] First beam association information;

[0041] Time-related information.

[0042] Optionally, the beam-related functions include, but are not limited to, beam prediction, beam indication, beam recovery, and beam training, that is, the artificial intelligence model has at least one of the following functions: beam prediction, beam indication, beam recovery, and beam training.

[0043] In this embodiment, a first device determines the input information of an artificial intelligence model. The artificial intelligence model is used for beam prediction-related functions, and the input information includes expected information and at least one of the following: beam quality-related information; first beam association information; and time-related information. Thus, the solution of this application is not limited by the capabilities of the first device, and can obtain the expected output information through the AI ​​model of the first device. Furthermore, the number of outputs from the artificial intelligence model is fixed and independent of the number or angle of the received beams of the terminal device. This solves the problem that the number of outputs from the artificial intelligence model cannot be widely applied due to differences in the capabilities of terminal devices, thereby increasing the practicality of the artificial intelligence model.

[0044] It should be noted that the first device and the second device can be various combinations of base station side, terminal side, and auxiliary network central unit; for example: the first device is terminal side and the second device is network side; or, the first device is network side and the second device is terminal side; or, both the first device and the second device are network side; or, both the first device and the second device are terminal side; or the first device is auxiliary network central unit and the second device is network side, etc., or the first device and the second device interact through auxiliary network central unit; wherein, the auxiliary network central unit is a unit used for information interaction. That is, both the first device and the second device can be a transmitting end device or a receiving end device. In one embodiment of this application, the first device is a receiving end device.

[0045] Optionally, the expected information includes at least one of the following:

[0046] Second beam association information;

[0047] Information related to prediction time.

[0048] The first beam association information may include at least one of transmit beam association information, receive beam association information, and beam pair association information. Similarly, the second beam association information may include at least one of transmit beam association information, receive beam association information, and beam pair association information. For example, when a first device receives a first reference signal transmitted by a second device, the first beam association information includes at least one of the second device transmit beam association information, the first device receive beam association information, and beam pair association information of the second device transmit beam and the first device receive beam. The second beam association information includes at least one of the second device transmit beam association information expected by the first device, the first device receive beam association information expected by the first device, and beam pair association information of the second device transmit beam and the first device receive beam expected by the first device.

[0049] Optionally, the input processing method of the artificial intelligence model in this application embodiment can determine the beam pair association information expected by the first device (receiving device), the beam association information received by the receiving device expected by the receiving device, and the beam association information transmitted by the second device (transmitting device) expected by the receiving device through the first device. It is possible to obtain the beam association information of all beams through the first device.

[0050] Optionally, the beam quality-related information includes at least one of the following: signal-to-noise ratio, received power, and received quality;

[0051] The first beam association information is used to characterize the association information corresponding to the first beam when the input of the artificial intelligence model is selected as the first beam; wherein, the first beam association information includes at least one of the following: beam identification related information, beam angle related information, beam gain related information, and beamwidth related information.

[0052] The time-related information is used to characterize the time corresponding to the beam quality-related information, and / or the time relationship between multiple beam quality-related information.

[0053] Among them, beam quality-related information refers to information that can characterize beam quality, including but not limited to at least one of the following: Layer 1 signal-to-noise ratio (L1-SINR), Layer 1 reference signal received power (L1-RSRP), Layer 1 reference signal received quality (L1-RSRQ), Layer 3 signal-to-noise ratio (L3-SINR), Layer 3 reference signal received power (L3-RSRP), Layer 3 reference signal received quality (L3-RSRQ), etc.

[0054] In one embodiment of this application, the beam identifier related information is also beam identity related information, which is used to characterize the identity recognition information of the beam, including but not limited to at least one of the following: transmitting beam identifier (ID), receiving beam identifier, beam pair identifier, reference signal set identifier corresponding to the beam, reference signal resource identifier corresponding to the beam, random identifier of unique identifier, encoded value after processing by additional AI model (or AI network), and beam angle related information.

[0055] The beam angle-related information is used to characterize the angle-related information corresponding to the beam, including but not limited to at least one of the following: beam pair angle-related information, transmitted angle-related information, and received angle-related information; wherein, the angle-related information is information used to characterize the angle, such as angle, radian, indexed encoding value, and encoded value after additional AI network processing;

[0056] Optionally, angle-related information can be determined based on a global coordinate system (GLS) or a local coordinate system (LCS). Optionally, if it is a local coordinate system, the origin of the coordinate system can be the first device or the second device, determined through network configuration, protocol agreement or reporting method.

[0057] The beam gain-related information is used to characterize the gain-related information of the beam and / or antenna, including but not limited to at least one of the following: antenna relative gain (in dBi), effective isotropic radiated power (EIRP) beam angle gain, beam angle gain spectrum (i.e., the gain of a beam relative to different angles, including complete or partial gain spectrum information), EIRP corresponding to each beam angle, main lobe angle, sidelobe angle, number of sidelobes, sidelobe distribution, number of antennas, horizontal coverage of beam scanning, vertical coverage of beam scanning, 3dB width, 6dB width, etc.

[0058] Optionally, at least one of the beam angle-related information and beam identification-related information can be described by two-dimensional components (which can be horizontal-vertical components) or determined by higher-dimensional component information.

[0059] In one embodiment of this application, the time-related information is used to characterize the time corresponding to the beam quality-related information, and / or the time relationship between multiple beam quality-related information. For example, three sets of beam quality-related information are input, corresponding to information received at the first, second, and third cycles prior to the current time.

[0060] The input processing method for the artificial intelligence model in this application embodiment can obtain beam quality-related information, including signal-to-noise ratio, received power, and received quality, the association information corresponding to the first beam, and the time-related information representing the time relationship between the beam quality-related information and / or the time relationship between multiple beam quality-related information, through a first device, thereby determining the input information of the artificial intelligence model.

[0061] Optionally, the second beam association information is used to characterize the association information corresponding to the desired second beam; wherein the second beam association information includes at least one of the following:

[0062] Beam identification information, beam angle information, beam gain information, beamwidth information;

[0063] The prediction time-related information is used to characterize the time-related information associated with the output information of the artificial intelligence model.

[0064] In one embodiment of this application, the prediction time-related information used to characterize the time-related information associated with the output information of the artificial intelligence model can be understood as follows: the prediction time-related information can indicate the time-related information associated with the output result of the AI ​​model, and the prediction time-related information includes, but is not limited to, at least one of the following: a reference time + z time units, a system frame number, and the prediction period; wherein, the reference time and z can be determined by the interaction between the first device and the second device, and the unit of the time unit can be a unit representing time, a symbol, a time slot, a frame number, a microsecond, a millisecond, or a second.

[0065] The input processing method of the artificial intelligence model in this application embodiment can determine the associated information corresponding to the desired second beam and the time-related information associated with the output information of the artificial intelligence model.

[0066] Optionally, the input information, for the same input type, includes at least one piece of time-related information.

[0067] Optionally, the information corresponding to the same input type can be understood as:

[0068] The desired information and at least one of the following: beam quality related information, beam association information, beam association information transmitted by the transmitting end, and beam association information received by the receiving end;

[0069] The desired information includes at least one of the following:

[0070] The beam association information desired by the receiving device;

[0071] The receiving device expects the receiving device to receive beam association information;

[0072] The receiving device expects the transmitting device to send beam association information.

[0073] In one embodiment of this application, the expected information includes at least one of the following: the first device's expected first device receive beam association information, the first device's expected second device transmit beam association information, the first device's expected beam pair association information between the second device transmit beam and the first device receive beam, and expected prediction time related information.

[0074] Optionally, for the input information, the temporal information can be information from a historical moment and / or information from the current moment.

[0075] Optionally, the first beam association information and / or the time-related information are associated with the beam quality-related information; and / or

[0076] The quantity of the first beam association information and / or the quantity of the time-related information are associated with the quantity of the beam quality-related information.

[0077] The relationships between the input information include the correlation between beam quality and the correlation between the number of beams.

[0078] In one embodiment of this application, the first device is a receiving device; the beam quality correlation can be understood as follows: the beam correlation information transmitted by the second device and the beam correlation information received by the first device are associated with the beam quality-related information; or, the time-related information is associated with the beam quality-related information; or, the beam correlation information transmitted by the second device, the beam correlation information received by the first device, and the time-related information are associated with the beam quality-related information; and / or

[0079] The correlation of beam count can be understood as follows: the number of beam association information transmitted by the second device and the number of beam association information received by the first device are related to the number of beam quality related information; or, the number of time related information is related to the number of beam quality related information; or, the number of beam association information transmitted by the second device, the number of beam association information received by the first device, and the number of time related information are related to the number of beam quality related information.

[0080] The input processing method of the artificial intelligence model in this application embodiment can determine the correlation between beam quality and beam quantity among the input information, thereby obtaining the detailed content of the input information.

[0081] Specifically, the first beam association information and / or the time-related information are associated with the beam quality-related information, including at least one of the following:

[0082] The beams corresponding to the beam quality-related information correspond one-to-one with the beams represented by the first beam association information.

[0083] The beams corresponding to the beam quality-related information correspond one-to-one with the beams characterized by the time-related information.

[0084] The beams corresponding to the beam quality-related information correspond one-to-one with the beams jointly characterized by the first beam association information and the time-related information.

[0085] Specifically, the quantity of the first beam association information and / or the quantity of the time-related information are associated with the quantity of the beam quality-related information, including at least one of the following:

[0086] The first beam association information includes at least one of beam pair association information, transmit beam association information, and receive beam association information, the number of which is equal to the number of beam quality related information.

[0087] The number of time-related information items is equal to the number of beam quality-related information items;

[0088] When the first beam association information includes transmitted beam association information and received beam association information, the product of the number of transmitted beam association information and the number of received beam association information is equal to the number of beam quality related information.

[0089] The product of the quantity of at least one of the beam pair association information, transmit beam association information, and receive beam association information included in the first beam association information and the quantity of the time-related information is equal to the quantity of the beam quality-related information.

[0090] When the first beam association information includes transmitted beam association information and received beam association information, the product of the number of transmitted beam association information and the number of time-related information is equal to the number of beam quality-related information.

[0091] When the first beam association information includes transmitted beam association information and received beam association information, the product of the number of received beam association information and the number of time-related information is equal to the number of beam quality-related information.

[0092] When the first beam association information includes transmitted beam association information and received beam association information, the product of the number of transmitted beam association information, the number of received beam association information, and the number of time-related information is equal to the number of beam quality-related information.

[0093] In one embodiment of this application, the number of transmitted beam association information, the number of received beam association information, and the number of time-related information can be determined through interaction between the first device and the second device.

[0094] In one embodiment of this application: the beams corresponding to the beam quality-related information correspond one-to-one with the beams characterized by the beam association information, and the remaining information is determined through interaction;

[0095] Specifically, the number of input information satisfies at least one of the following: a*b=y, a=b=y;

[0096] Where y represents beam quality-related information or beam pair association information; a represents beam association information transmitted by the transmitter; b represents beam association information received by the receiver; c represents beam pair association information desired by the receiver; d represents beam association information desired by the receiver; and e represents beam association information desired by the receiver.

[0097] In another embodiment of this application: the beams corresponding to the beam quality-related information correspond one-to-one with the beams characterized by the beam association information, and the remaining information is determined through interaction. At least one input information contains multiple temporal information.

[0098] Specifically, the number of input information satisfies at least one of the following: a*b=y, a=b=y;

[0099] Where y*t represents beam quality-related information; y*z*t or y*z represents beam pair association information; a*z*t or a*z represents transmit beam association information; b*z*t or b*z represents receive beam association information; c represents the receive beam pair association information desired by the receiver; d*z represents the receive beam association information desired by the receiver; and e*z represents the transmit beam association information desired by the receiver.

[0100] It should be noted that t represents the number of times the input information is received, one possibility being t-1 historical information plus the current information; z represents the number of component information representing beam association information. If two-dimensional component representation is used, z = 2 when only beam association information is used, and z = 1 when both transmit and receive beam association information are used; the number of c, d, and e is determined by interaction.

[0101] Optionally, the input processing method for the artificial intelligence model further includes:

[0102] The first device determines the output information of the artificial intelligence model; wherein the output information includes at least one of the following:

[0103] Under the first receiving beam, at least some beam quality-related information and / or optimal transmission beam-related information are transmitted;

[0104] Under the first transmitted beam, at least some of the received beam quality-related information and / or the optimal received beam-related information are received;

[0105] Under the second receiving beam and the second transmitting beam, the beam quality related information and / or the optimal beam related information of the corresponding beam pair;

[0106] Wherein, the first receiving beam and the second receiving beam are the receiving beams represented by the second beam association information; the first transmitting beam and the second transmitting beam are the transmitting beams represented by the second beam association information.

[0107] In one embodiment of this application, the output information includes at least one of the following:

[0108] Under the desired receive beam association information of the receiver, the receiver transmits beam quality-related information and / or optimal transmit beam-related information to all transmitters under that receive beam.

[0109] Under the beam association information expected by the transmitter, the receiver receives beam quality-related information and / or optimal reception beam-related information at all receivers of that transmitter beam.

[0110] Under the transmit beam association information and receive beam association information expected by the receiver, the receiver has beam quality related information and / or optimal beam related information for the beam pairs indicated by the transmit beam set and the receive beam set.

[0111] The transmit beam set is obtained based on the transmit beam association information desired by the receiver, and the receive beam set is obtained based on the receive beam association information desired by the receiver.

[0112] In one embodiment of this application, the first device is a receiving end, and the output information includes at least one of the following:

[0113] Under the desired received beam association information of the first device, the first device transmits beam quality related information and / or optimal transmitted beam related information to all second devices under the received beam.

[0114] Under the beam association information that the first device expects the second device to send, the first device receives beam quality information and / or optimal reception beam information for all first devices in the transmitted beam.

[0115] Under the condition that the first device expects the second device to send beam association information and the first device to receive beam association information, the first device sends beam quality-related information and / or optimal beam-related information of the beam pair indicated by the transmitted beam set and the received beam set;

[0116] The receiving beam set is obtained based on the first device's expected first device receiving beam association information, and the transmitting beam set is obtained based on the first device's expected second device transmitting beam association information.

[0117] Optionally, the optimal transmission-related information, optimal reception-related information, and optimal beam-related information refer to information that can characterize the optimal beam, including but not limited to: beam identification-related information and / or beam angle-related information; in addition, there can be multiple optimal beams.

[0118] Optionally, the output information, for the same output type, includes at least one piece of time-related information.

[0119] Optionally, the temporal information may be information about a future time and / or information about the current time.

[0120] It's important to note that information from historical moments and future moments is compared to information from the current moment in terms of time. Moments before the current moment are considered historical moments, and moments after the current moment are considered future moments. The current moment is related to the moment when the last quality-related information was obtained from the input beam quality-related information of the AI ​​model. This last obtained quality-related information is denoted as moment 's', so moment 's' is the current moment, or moment 's+x' is the current moment, where 'x' represents the time obtained interactively, which can be the processing time.

[0121] Optionally, the amount of output information is associated with the second beam association information and / or the prediction time-related information.

[0122] Optionally, the quantity of the output information is associated with the second beam association information and / or the prediction time-related information, including:

[0123] When the output information includes the optimal transmit beam information, the quantity of the output information is at least one of the following: the optimal number of beams, the product of the optimal number of beams and the number of predictions; or,

[0124] When the output information includes the optimal received beam information, the quantity of the output information is at least one of the following: the optimal number of beams, the product of the optimal number of beams and the number of predictions; or,

[0125] When the output information includes quality-related information of all transmitted beams under the first received beam, the quantity of the output information is at least one of the following: the quantity of at least some transmitted beams, the product of the quantity of at least some transmitted beams and the number of predictions;

[0126] When the output information includes quality-related information of all received beams under the first transmitted beam, the quantity of the output information is at least one of the following: the quantity of at least some received beams, the product of the quantity of at least some received beams and the number of predictions;

[0127] When the output information includes the second received beam and the second transmitted beam, and the beam quality related information and / or the optimal beam related information of the corresponding beam pair, the quantity of the output information is at least one of the following: the number of beam pairs corresponding to the second received beam and the second transmitted beam, and the product of the number of beam pairs and the number of predictions.

[0128] The number of predictions is indicated by the prediction time-related information, or determined by the artificial intelligence model, or obtained through interaction with the second device.

[0129] The correlation between the quantity of output information and the second beam association information and / or the prediction time related information can be understood as follows: the quantity of information output by the AI ​​model is related to at least one of the following: the beam pair association information expected by the receiver, the beam association information expected by the receiver to receive, the beam association information expected by the receiver to transmit, the expected prediction time related information, and their respective quantities.

[0130] In one embodiment of this application, when the AI ​​model outputs optimal transmit beam information, the number of outputs from the AI ​​model is the optimal beam number, or equal to the optimal beam number multiplied by the expected prediction time information indicating the number of predictions; the optimal beam includes: the optimal beam, the optimal transmit beam, and the optimal receive beam; or...

[0131] When the AI ​​model outputs information related to the optimal receive beam, the number of outputs from the AI ​​model is the number of optimal beams, or equal to the number of optimal beams multiplied by the expected number of predictions indicated by the prediction time-related information; the optimal beams include: the optimal beam, the optimal transmit beam, and the optimal receive beam; or...

[0132] When the AI ​​model outputs information related to the quality of all transmitting beams under the desired receiving beam association information at the receiver, the number of AI model outputs equals the number of all transmitting beams at the transmitter or the number of all transmitting beams at the transmitter multiplied by the number of predictions indicated by the desired prediction time-related information; or...

[0133] When the AI ​​model outputs information about the beam quality of all receivers receiving a given beam at the receiver, under the desired beam association information transmitted at the transmitter, the number of AI model outputs equals the number of all receiver beams or the number of all receiver beams multiplied by the number of predictions indicated by the desired prediction time information; or...

[0134] When the AI ​​model outputs the beam quality-related information and / or optimal beam-related information of the beam pairs indicated by the transmitted beam association information and received beam association information as expected at the receiver, the number of AI model outputs is equal to the number of beam pairs indicated by the transmitted beam set and received beam set or the number of beam pairs indicated by the transmitted beam set and received beam set multiplied by the number of predictions indicated by the expected prediction time-related information.

[0135] Optionally, the optimal beam includes: an optimal beam, an optimal transmit beam, and an optimal receive beam;

[0136] Optimal beam-related information, optimal transmit-related information, and optimal receive-related information refer to information that can characterize the optimal beam, including but not limited to: beam identification-related information and / or beam angle-related information; in addition, there can be multiple optimal beams.

[0137] Optionally, the input processing of the artificial intelligence model further includes:

[0138] The first device determines auxiliary information for the artificial intelligence model; wherein the auxiliary information is used to assist the first device in determining the input information and / or output information of the artificial intelligence model; the auxiliary information includes at least one of the following:

[0139] The order of the input information;

[0140] The order of the output information;

[0141] The way the artificial intelligence model processes input information;

[0142] The way the artificial intelligence model processes the output information;

[0143] The number of beam identification related information;

[0144] The amount of information related to beam angle;

[0145] Maximum beam correlation capability supported by the device;

[0146] The number of times the transmitted beam is repeated;

[0147] The number of loop iterations for outputting information;

[0148] Information related to the prediction time;

[0149] Third beam association information.

[0150] Optionally, the order of the input information is the order in which the information is input into the AI ​​model; the order of the output information is the order in which the information is output from the AI ​​model.

[0151] In one embodiment of this application, the order of the input information and the order of the output information can be a defined order according to certain rules, or a specified order. For example, when the input information includes desired information, beam quality-related information, first beam association information, and time-related information, the order of the input information is specified according to the information type, and the beam quality-related information, first beam association information, time-related information, and desired information are input sequentially.

[0152] Optionally, the number of beam identification related information includes:

[0153] The number of related information pairs for beam identifiers at the transmitting and receiving ends;

[0154] The number of transmit beam identifier related information at the transmitting end;

[0155] The number of transmit beam identifier related information at the receiving end;

[0156] The number of received beam identifier related information at the transmitting end;

[0157] The number of receiver beam identifier related information at the receiving end.

[0158] In one embodiment of this application, the first device is a receiving device, then the number of beam identifier related information includes:

[0159] The number of beam pairs identifying relevant information for the second and first devices;

[0160] The number of beam identifier related information transmitted by the second device;

[0161] The number of beam identifier related information transmitted by the first device;

[0162] The number of received beam identifier related information of the second device;

[0163] The number of received beam identifier related information of the first device.

[0164] Optionally, the number of beam angle-related information items includes:

[0165] The number of beam angle-related information transmitted by the transmitting end;

[0166] The number of beam angle-related information transmitted by the receiving end;

[0167] The number of beam angle-related information received by the transmitting end;

[0168] The number of beam angle-related information received at the receiving end.

[0169] In one embodiment of this application, the first device is a receiving device, then the quantity of beam angle-related information includes:

[0170] The second device sends the number of beam angle related information items;

[0171] The first device sends the number of beam angle related information items;

[0172] The second device receives a quantity of beam angle-related information.

[0173] The first device receives a quantity of information related to the beam angle.

[0174] Optionally, the maximum beam-related capability supported by the device includes: the maximum capability of beam identification and the maximum capability of beam angle supported by the device;

[0175] The maximum beamforming capability supported by the device includes:

[0176] The maximum amount of beam identifier-related information at the transmitting and receiving ends;

[0177] The maximum number of beam identifier related information transmitted by the transmitting end;

[0178] The maximum number of beam identifier related information transmitted by the receiving end;

[0179] The maximum value of the received beam identifier information at the transmitting end;

[0180] The maximum value of the receiver beam identifier related information at the receiving end;

[0181] The maximum beam angle capability supported by the device includes:

[0182] The maximum number of beam angle-related information items that the transmitting end can send;

[0183] The maximum number of beam angle-related information items that the receiving end can transmit;

[0184] The maximum number of beam angle-related information items received by the transmitting end;

[0185] The maximum amount of beam angle-related information received by the receiver.

[0186] In one embodiment of this application, the first device is a receiving device, and the maximum beam correlation capability supported by the device includes:

[0187] The maximum capability of beam identification and the maximum capability of beam angle supported by the device;

[0188] The maximum beamforming capability supported by the device includes:

[0189] The maximum number of beam identification related information for the second and first devices;

[0190] The maximum number of beam identifier related information transmitted by the second device;

[0191] The maximum number of beam identifier related information transmitted by the first device;

[0192] The maximum number of beam identifier related information received by the second device;

[0193] The maximum number of beam identifier related information received by the first device;

[0194] The maximum beam angle capability supported by the device includes:

[0195] The maximum number of beam angle-related information transmitted by the second device;

[0196] The maximum number of beam angle-related information transmitted by the first device;

[0197] The maximum number of beam angle-related information items that the second device can receive;

[0198] The maximum number of beam angle-related information received by the first device.

[0199] Optionally, the number of repetitions of the transmitted beam includes:

[0200] The number of times the transmitting beam is repeated. During the repetition process, the receiving end can use different receiving beams under the same transmitting beam.

[0201] Optionally, the number of loops for outputting information includes:

[0202] The minimum number of cycles recommended by the transmitter to the receiver refers to the number of times the receiver changes the desired beam association information to obtain the AI ​​model output under different desired conditions.

[0203] It should be noted that this minimum number of times cannot exceed the number of beam identifiers or angle-related information received by the receiving end of the interaction, or its maximum capacity.

[0204] Optionally, the information related to the prediction time can be prediction time-related information, or information used to calculate the prediction time-related information, and may include the number of predicted cycles and the cycle length. For example, the number of predicted future cycles needs to be converted into corresponding times by the receiving end.

[0205] Optionally, the third beam association information includes: beam association information related to the AI ​​model input information suggested by the transmitter to the receiver, including at least one of the following: suggested beam pair information, suggested transmitter-transmitted beam identifier information, suggested transmitter-transmitted beam angle information, suggested receiver-received beam identifier information, and suggested receiver-received beam angle information. The suggested information is used by the transmitter to inform the receiver of the recommended beam identifier and / or angle combination for the AI ​​model input during AI model training.

[0206] In one embodiment of this application, the first device is a first device device, and the third beam association information includes: beam association information related to the AI ​​model input information suggested by the second device to the first device, including at least one of the following: suggested beam pair information, suggested beam identifier information sent by the second device, suggested beam angle information sent by the second device, suggested beam identifier information received by the first device, and suggested beam angle information received by the first device. The suggested information is used by the second device to inform the first device of the recommended beam identifier and / or angle combination for the AI ​​model input during AI model training.

[0207] Optionally, after the first device determines the output information of the artificial intelligence model, it further includes:

[0208] The first device selects at least one of the following from the output information:

[0209] Optimal transmission beam information;

[0210] Information related to the optimal receiving beam;

[0211] Optimal beam information.

[0212] It should be noted that the optimal transmit beam-related information, the optimal receive beam-related information, and the optimal beam-related information can all be one or more. The optimal beam-related information refers to the information of the optimal beam pair.

[0213] Optionally, when the artificial intelligence model is used for beam prediction related to the synchronization signal block SSB, and at least one SSB in the SSB burst set is disabled, the optimal beam association information is selected from the beam of the first SSB.

[0214] Wherein, the first SSB is the SSB to which the output information is associated, and the SSB burst-enabled;

[0215] The optimal beam includes at least one of the following:

[0216] The beam corresponding to the optimal transmission beam information;

[0217] The beam corresponding to the optimal receiving beam information shown;

[0218] The beam corresponding to the optimal beam information.

[0219] Optionally, in the SSB burst set, whether an SSB is enabled is determined by a bitmap indication; the optimal beam for interaction can only be selected from the SSBs that are enabled in the SSB burst set associated with the AI ​​model output.

[0220] Optionally, at least one of the input information, output information, and auxiliary information of the artificial intelligence model is determined by the first device through interaction with the second device;

[0221] The interaction methods include at least one of the following:

[0222] Send; report; instruct; configure; request; pre-agreed upon.

[0223] In one embodiment of this application, the first device is a receiving end and the second device is a sending end. In this case, at least one of the input information, output information, and auxiliary information of the artificial intelligence model can be sent from the first device to the second device; or...

[0224] If the first device is a base station and the second device is a terminal, then at least one of the input information, output information, and auxiliary information of the artificial intelligence model can be an instruction from the first device to the second device, a configuration from the first device to the second device, a report from the second device to the first device, or a request from the second device to the first device; or...

[0225] A pre-agreed agreement between the first device and the second device.

[0226] The input processing method of the artificial intelligence model in this application embodiment can be as follows: Figure 4 The input processing system implementation for the shown artificial intelligence model is as follows:

[0227] RSRP indicates that the input is RSRP information, angle information indicates that the input is the angle information of the beam corresponding to RSRP, and desired information indicates that the input is the desired angle information of the beam corresponding to RSRP. The desired information includes: desired receive angle information and / or desired transmit angle information.

[0228] Assume the transmitter has 32 transmit beams and the receiver has 8 receive beams:

[0229] In one embodiment of this application: if the input information of the AI ​​model contains only the desired receiving angle information, then:

[0230] AI model input: 8 RSRPs, 8 transmitting angle information corresponding to the 8 RSRPs, 8 receiving angle information corresponding to the 8 RSRPs, and 1 desired receiving angle information;

[0231] AI model output: The predicted RSRP of the 32 transmitting beams under the expected receiving angle information;

[0232] At this point, the receiver cycles 8 times, changing the desired receiving angle information, and can obtain RSRP information corresponding to a total of 32*8 beam pairs.

[0233] In another embodiment of this application: if the input information of the AI ​​model contains only the desired transmission angle information, then:

[0234] AI model input: 8 RSRPs, 8 transmitting angle information corresponding to the 8 RSRPs, 8 receiving angle information corresponding to the 8 RSRPs, and 1 desired transmitting angle information;

[0235] AI model output: The predicted RSRP of the 8 receiving beams at the receiving end under the expected transmission angle information;

[0236] At this point, the receiver cycles 32 times, changing the desired transmission angle information, and can obtain RSRP information corresponding to a total of 8*32 beam pairs.

[0237] In another embodiment of this application, the input information of the AI ​​model includes the desired transmission angle information and the desired reception angle information. Then:

[0238] AI model input: 8 RSRPs, 8 corresponding transmitter angle information, 8 corresponding receiver angle information, 1 desired transmitter angle information, and 1 desired receiver angle information.

[0239] AI model output: One corresponding RSRP predicted under the expected transmission angle information and the expected reception angle information;

[0240] At this point, the receiver cycles 256 times, changing the desired transmission angle and the desired reception angle information, and can obtain RSRP information corresponding to 1*256 beam pairs.

[0241] In another embodiment of this application, the input information of the AI ​​model includes desired transmission angle information and desired reception angle information, then:

[0242] AI model input: 8 RSRPs, 8 transmitting angle information corresponding to the 8 RSRPs, 8 receiving angle information corresponding to the 8 RSRPs, 1 expected transmitting angle information and 1 expected receiving angle information, which contains 8 expected transmitting angles and 2 expected receiving angles.

[0243] AI model output: The predicted RSRP of the 16 beam pairs under the expected transmit angle information and the expected receive angle information;

[0244] At this point, the receiver cycles 16 times, changing the desired transmission angle and the desired reception angle information, and can obtain RSRP information corresponding to a total of 16*16 beam pairs.

[0245] In another embodiment of this application, the input information of the AI ​​model includes desired transmission angle information and desired reception angle information, then:

[0246] AI model input: 8 RSRPs, 8 transmitting angle information corresponding to the 8 RSRPs, 8 receiving angle information corresponding to the 8 RSRPs, 8 expected transmitting angle information and 2 expected receiving angle information, each expected transmitting angle information and each expected receiving angle information contains 1 expected transmitting angle and 1 expected receiving angle.

[0247] AI model output: The predicted RSRP of the 16 beam pairs under the expected transmit angle information and the expected receive angle information;

[0248] At this point, the receiver cycles 16 times, changing the desired transmission angle and the desired reception angle information, thus obtaining RSRP information corresponding to 16*16 beam pairs.

[0249] In another embodiment of this application, the expected information in the AI ​​model input information includes expected receiving angle information and expected prediction time related information, then:

[0250] AI model input: 8 RSRPs, 8 transmitting angle information corresponding to the 8 RSRPs, 8 receiving angle information corresponding to the 8 RSRPs, 1 expected receiving angle information, and 1 expected prediction time-related information to indicate the information predicted to be 1 second after the reference time.

[0251] AI model output: Predict the RSRP of the 32 transmitting beams located 1 second after the reference time, based on the expected receiving angle information;

[0252] At this point, the receiver cycles 8 times, changing the desired receiving angle information, and can obtain RSRP information corresponding to 32*8 beam pairs located 1 second after the reference time.

[0253] like Figure 5 As shown in the figure, this application embodiment also provides an input processing device 500 for an artificial intelligence model, including:

[0254] The first determining module 501 is used to determine the input information of the artificial intelligence model through the first device; wherein the artificial intelligence model is used for beam prediction related functions, and the input information includes expected information and at least one of the following:

[0255] Beam quality related information;

[0256] First beam association information;

[0257] Time-related information.

[0258] In this embodiment, the input information of the artificial intelligence model is determined by the first determining module of the first device. The artificial intelligence model is used for beam prediction-related functions, and the input information includes expected information and at least one of the following: beam quality-related information; first beam association information; and time-related information. Thus, the solution of this application is not limited by the capabilities of the first device, and can obtain the expected output information through the AI ​​model of the first device. Furthermore, the number of outputs from the artificial intelligence model is fixed and independent of the number or angle of the received beams of the terminal device. This solves the problem that the number of outputs from the artificial intelligence model cannot be widely applied due to differences in the capabilities of terminal devices, thereby increasing the practicality of the artificial intelligence model.

[0259] Optionally, the input processing device for the artificial intelligence model further includes:

[0260] The second determining module is configured to determine the output information of the artificial intelligence model through the first device; wherein the output information includes at least one of the following:

[0261] Under the first receiving beam, at least some beam quality-related information and / or optimal transmission beam-related information are transmitted;

[0262] Under the first transmitted beam, at least some of the received beam quality-related information and / or the optimal received beam-related information are received;

[0263] Under the second receiving beam and the second transmitting beam, the beam quality related information and / or the optimal beam related information of the corresponding beam pair;

[0264] Wherein, the first receiving beam and the second receiving beam are the receiving beams represented by the second beam association information; the first transmitting beam and the second transmitting beam are the transmitting beams represented by the second beam association information.

[0265] In one embodiment of this application, the output information includes at least one of the following:

[0266] Under the desired receive beam association information of the receiver, the receiver transmits beam quality-related information and / or optimal transmit beam-related information to all transmitters under that receive beam.

[0267] Under the beam association information expected by the transmitter, the receiver receives beam quality-related information and / or optimal reception beam-related information at all receivers of that transmitter beam.

[0268] Under the transmit beam association information and receive beam association information expected by the receiver, the receiver has beam quality related information and / or optimal beam related information of the beam pair indicated by the transmit beam set and the receive beam set.

[0269] The first and second transmit beams are obtained based on the transmit beam association information desired by the receiver, and the first and second receive beams are obtained based on the receive beam association information desired by the receiver.

[0270] Optionally, the input processing device for the artificial intelligence model further includes:

[0271] The third determining module is used to determine auxiliary information of the artificial intelligence model through the first device; wherein the auxiliary information is used to assist the first device in determining the input information and / or output information of the artificial intelligence model; the auxiliary information includes at least one of the following:

[0272] The order of the input information;

[0273] The order of the output information;

[0274] The way the artificial intelligence model processes input information;

[0275] The way the artificial intelligence model processes the output information;

[0276] The number of beam identification related information;

[0277] The amount of information related to beam angle;

[0278] Maximum beam correlation capability supported by the device;

[0279] The number of times the transmitted beam is repeated;

[0280] The number of loop iterations for outputting information;

[0281] Information related to the prediction time;

[0282] Third beam association information.

[0283] Optionally, the order of the input information is the order in which the information is input into the AI ​​model; the order of the output information is the order in which the information is input from the AI ​​model.

[0284] In one embodiment of this application, the order of the input information and the order of the output information can be an order defined according to certain rules, or a specified order.

[0285] Optionally, the number of beam identification related information includes:

[0286] The number of beam identifier related information at the transmitting and receiving ends;

[0287] The number of transmit beam identifier related information at the transmitting end;

[0288] The number of transmit beam identifier related information at the receiving end;

[0289] The number of received beam identifier related information at the transmitting end;

[0290] The number of receiver beam identifier related information at the receiving end.

[0291] Optionally, the number of beam angle-related information items includes:

[0292] The number of beam angle-related information transmitted by the transmitting end;

[0293] The number of beam angle-related information transmitted by the receiving end;

[0294] The number of beam angle-related information received by the transmitting end;

[0295] The number of beam angle-related information received at the receiving end.

[0296] Optionally, the maximum beam-related capability supported by the device includes: the maximum capability of beam identification and the maximum capability of beam angle supported by the device;

[0297] The maximum beamforming capability supported by the device includes:

[0298] The number of beam identifier related information or the maximum supported capability at the transmitting and receiving ends;

[0299] The number of transmit beam identifier related information or the maximum supported capability at the transmitting end;

[0300] The number of transmit beam identifier related information or the maximum supported capability at the receiving end;

[0301] The number of received beam identifier related information or the maximum supported capability at the transmitting end;

[0302] The number of receiver beam identifier related information or the maximum supported capability at the receiver end;

[0303] The maximum beam angle capability supported by the device includes:

[0304] The number of beam angle-related information transmitted by the transmitting end or the maximum supported capability;

[0305] The number of beam angle-related information transmitted by the receiving end or the maximum supported capability;

[0306] The number of beam angle-related information received by the transmitting end or its maximum supported capability;

[0307] The number of beam angle-related information received by the receiver or the maximum supported capability.

[0308] Optionally, the number of repetitions of the transmitted beam includes:

[0309] The number of times the transmitting beam is repeated at the transmitting end is used to indicate to the receiving end that different receiving beams can be used under the same transmitting beam.

[0310] Optionally, the number of loops for outputting information includes:

[0311] The minimum number of loops recommended by the sender to the receiver refers to the number of times the receiver changes the desired correlation information to obtain the AI ​​model output under different desired conditions.

[0312] It should be noted that this minimum number of times cannot exceed the number of beam identifiers or angle-related information received by the receiving end of the interaction, or its maximum capacity.

[0313] Optionally, the input processing device for the artificial intelligence model further includes:

[0314] The selection module is configured to select at least one of the following from the output information via the first device:

[0315] Optimal transmission beam information;

[0316] Information related to the optimal receiving beam;

[0317] Optimal beam information.

[0318] It should be noted that the optimal transmit beam-related information, the optimal receive beam-related information, and the optimal beam-related information can all be one or more. The optimal beam-related information refers to the information related to the beam pair.

[0319] The input processing device for the artificial intelligence model in this application embodiment can be an electronic device, such as an electronic device with an operating system, or a component in an electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal, or other devices besides a terminal. For example, the terminal can include, but is not limited to, the type of terminal 11 listed above; other devices can be servers, Network Attached Storage (NAS), etc., and this application embodiment does not specifically limit the type.

[0320] The input processing device for the artificial intelligence model provided in this application embodiment can achieve... Figure 3 The various processes implemented in the method embodiments achieve the same technical effect, and will not be described again here to avoid repetition.

[0321] Optional, such as Figure 6 As shown in the illustration, this application also provides an input processing device 600 for an artificial intelligence model, including a processor 601 and a memory 602. The memory 602 stores programs or instructions that can run on the processor 601. For example, when the communication device 600 is a terminal, the program or instructions executed by the processor 601 implement the various steps of the above-described input processing method embodiment for the artificial intelligence model, and achieve the same technical effect. When the input processing device 600 for the artificial intelligence model is a network-side device, the program or instructions executed by the processor 601 implement the various steps of the above-described input processing method embodiment for the artificial intelligence model, and achieve the same technical effect. To avoid repetition, further details are omitted here.

[0322] This application embodiment also provides a communication device, including a processor and a communication interface, wherein the processor is used to determine the input information of an artificial intelligence model through a first device;

[0323] The artificial intelligence model is used for beam correlation functions, and the input information includes expected information and at least one of the following: beam quality related information;

[0324] First beam association information;

[0325] Time-related information.

[0326] This communication device embodiment corresponds to the first device method embodiment described above. All implementation processes and methods of the above method embodiment can be applied to this terminal embodiment and achieve the same technical effect. Specifically, Figure 7 A schematic diagram of the hardware structure of the communication device used to implement the embodiments of this application.

[0327] The communication device 700 includes, but is not limited to, at least some of the following components: radio frequency unit 701, network module 702, audio output unit 703, input unit 704, sensor 705, display unit 706, user input unit 707, interface unit 708, memory 709, and processor 710.

[0328] Those skilled in the art will understand that the communication device 700 may also include a power supply (such as a battery) for supplying power to various components. The power supply may be logically connected to the processor 710 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system. Figure 7 The communication device structure shown does not constitute a limitation on the input processing of the artificial intelligence model. The communication device may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.

[0329] It should be understood that, in this embodiment, the input unit 704 may include a graphics processing unit (GPU) 7041 and a microphone 7042. The GPU 7041 processes image data of still images or videos obtained by an image capture device (such as a camera) in video capture mode or image capture mode. The display unit 706 may include a display panel 7061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, or the like. The user input unit 707 includes at least one of a touch panel 7071 and other input devices 7072. The touch panel 7071 is also called a touch screen. The touch panel 7071 may include a touch detection device and a touch controller. Other input devices 7072 may include, but are not limited to, a physical keyboard, function keys (such as volume control buttons, power buttons, etc.), a trackball, a mouse, and a joystick, which will not be described in detail here.

[0330] In this embodiment, after receiving downlink data from the network-side device, the radio frequency unit 701 can transmit it to the processor 710 for processing; in addition, the radio frequency unit 701 can send uplink data to the network-side device. Typically, the radio frequency unit 701 includes, but is not limited to, an antenna, amplifier, transceiver, coupler, low-noise amplifier, duplexer, etc.

[0331] The memory 709 can be used to store software programs or instructions, as well as various data. The memory 709 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, the memory 709 may include volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (Synchlink DRAM, SLDRAM), and direct memory bus RAM (DRRAM). The memory 709 in the embodiments of this application includes, but is not limited to, these and any other suitable types of memory.

[0332] Processor 710 may include one or more processing units; optionally, processor 710 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into processor 710.

[0333] The processor 710 is configured to determine input information for an artificial intelligence model via a first device; wherein the artificial intelligence model is used for beam correlation functions, and the input information includes expected information and at least one of the following:

[0334] Beam quality related information;

[0335] First beam association information;

[0336] Time-related information.

[0337] The processor 710 is further configured to determine the output information of the artificial intelligence model in the first device; wherein the output information includes at least one of the following:

[0338] Under the first receiving beam, at least some beam quality-related information and / or optimal transmission beam-related information are transmitted;

[0339] Under the first transmitted beam, at least some of the received beam quality-related information and / or the optimal received beam-related information are received;

[0340] Under the second receiving beam and the second transmitting beam, the beam quality related information and / or the optimal beam related information of the corresponding beam pair;

[0341] Wherein, the first receiving beam and the second receiving beam are the receiving beams represented by the second beam association information; the first transmitting beam and the second transmitting beam are the transmitting beams represented by the second beam association information.

[0342] The processor 710 is further configured to determine auxiliary information of the artificial intelligence model for the first device; wherein the auxiliary information is used to assist the first device in determining the input information and / or output information of the artificial intelligence model; the auxiliary information includes at least one of the following:

[0343] The order of the input information;

[0344] The order of the output information;

[0345] The way the artificial intelligence model processes input information;

[0346] The way the artificial intelligence model processes the output information;

[0347] The number of beam identification related information;

[0348] The amount of information related to beam angle;

[0349] Maximum beam correlation capability supported by the device;

[0350] The number of times the transmitted beam is repeated;

[0351] The number of loop iterations for outputting information;

[0352] Information related to the prediction time;

[0353] Third beam association information.

[0354] The processor 710 is further configured to select at least one of the following from the output information:

[0355] Optimal transmission beam information;

[0356] Information related to the optimal receiving beam;

[0357] Optimal beam information.

[0358] This application also provides a readable storage medium that stores programs or instructions. When the programs or instructions are executed by a processor, they implement various processes of the above-described artificial intelligence model input processing method and achieve the same technical effect. To avoid repetition, these will not be described again here.

[0359] The processor is the processor in the communication device described in the above embodiments. The readable storage medium includes a computer-readable storage medium, such as a computer-readable memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0360] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described artificial intelligence model input processing method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0361] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0362] This application also provides a computer program / program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the above-described artificial intelligence model input processing method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0363] This application embodiment also provides an input processing system for an artificial intelligence model, including: a communication device, which can be used to execute the input processing method for the artificial intelligence model as described above.

[0364] 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. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0365] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0366] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. An input processing method for an artificial intelligence model, characterized in that, include: The first device determines the input information of the artificial intelligence model; wherein the artificial intelligence model is used for beam prediction related functions, and the input information includes expected information and at least one of the following: Beam quality related information; First beam association information; Time-related information; The first beam association information is used to characterize the association information corresponding to the first beam when the input of the artificial intelligence model is selected as the first beam; The time-related information is used to characterize the time corresponding to the beam quality-related information, and / or the time relationship between multiple beam quality-related information; The desired information includes at least one of the following: second beam association information; prediction time-related information; The second beam association information is used to characterize the association information corresponding to the desired second beam; The method further includes: The first device determines the output information of the artificial intelligence model, and the quantity of the output information is associated with the second beam association information and / or the prediction time related information.

2. The method according to claim 1, characterized in that, The beam quality-related information includes at least one of the following: signal-to-noise ratio, received power, and received quality; The first beam association information includes at least one of the following: beam identification information, beam angle information, beam gain information, and beamwidth information.

3. The method according to claim 1, characterized in that, The second beam association information includes at least one of the following: Beam identification information, beam angle information, beam gain information, beamwidth information; The prediction time-related information is used to characterize the time-related information associated with the output information of the artificial intelligence model.

4. The method according to claim 1, characterized in that, The input information includes at least one time-related information for the same input type.

5. The method according to claim 1, characterized in that, The first beam association information and / or the time-related information are associated with the beam quality-related information; and / or The quantity of the first beam association information and / or the quantity of the time-related information are associated with the quantity of the beam quality-related information.

6. The method according to claim 5, characterized in that, The first beam association information and / or the time-related information are associated with the beam quality-related information, including at least one of the following: The beams corresponding to the beam quality-related information correspond one-to-one with the beams represented by the first beam association information. The beams corresponding to the beam quality-related information correspond one-to-one with the beams characterized by the time-related information. The beams corresponding to the beam quality-related information correspond one-to-one with the beams jointly characterized by the first beam association information and the time-related information.

7. The method according to claim 5, characterized in that, The quantity of the first beam association information and / or the quantity of the time-related information are associated with the quantity of the beam quality-related information, and include at least one of the following: The first beam association information includes at least one of beam pair association information, transmit beam association information, and receive beam association information, the number of which is equal to the number of beam quality related information. The number of time-related information items is equal to the number of beam quality-related information items; When the first beam association information includes transmitted beam association information and received beam association information, the product of the number of transmitted beam association information and the number of received beam association information is equal to the number of beam quality related information. The product of the quantity of at least one of the beam pair association information, transmit beam association information, and receive beam association information included in the first beam association information and the quantity of the time-related information is equal to the quantity of the beam quality-related information. When the first beam association information includes transmitted beam association information and received beam association information, the product of the number of transmitted beam association information and the number of time-related information is equal to the number of beam quality-related information. When the first beam association information includes transmitted beam association information and received beam association information, the product of the number of received beam association information and the number of time-related information is equal to the number of beam quality-related information. When the first beam association information includes transmitted beam association information and received beam association information, the product of the number of transmitted beam association information, the number of received beam association information, and the number of time-related information is equal to the number of beam quality-related information.

8. The method according to claim 1, characterized in that, The output information includes at least one of the following: Under the first receiving beam, at least some beam quality-related information and / or optimal transmission beam-related information are transmitted; Under the first transmitted beam, at least some of the received beam quality-related information and / or the optimal received beam-related information are received; Under the second receiving beam and the second transmitting beam, the beam quality related information and / or the optimal beam related information of the corresponding beam pair; Wherein, the first receiving beam and the second receiving beam are the receiving beams represented by the second beam association information; the first transmitting beam and the second transmitting beam are the transmitting beams represented by the second beam association information.

9. The method according to claim 1 or 8, characterized in that, The output information includes at least one time-related information for each output type.

10. The method according to claim 8, characterized in that, The quantity of output information is associated with the second beam association information and / or the prediction time-related information, including: When the output information includes the optimal transmit beam information, the quantity of the output information is at least one of the following: the optimal number of beams, the product of the optimal number of beams and the number of predictions; or, When the output information includes the optimal received beam information, the quantity of the output information is at least one of the following: the optimal number of beams, the product of the optimal number of beams and the number of predictions; or, When the output information includes quality-related information of all transmitted beams under the first received beam, the quantity of the output information is at least one of the following: the quantity of at least some transmitted beams, the product of the quantity of at least some transmitted beams and the number of predictions; When the output information includes quality-related information of all received beams under the first transmitted beam, the quantity of the output information is at least one of the following: the quantity of at least some received beams, the product of the quantity of at least some received beams and the number of predictions; When the output information includes the second received beam and the second transmitted beam, and the beam quality related information and / or the optimal beam related information of the corresponding beam pair, the quantity of the output information is at least one of the following: the number of beam pairs corresponding to the second received beam and the second transmitted beam, and the product of the number of beam pairs and the number of predictions. The number of predictions is indicated by the prediction time-related information, or determined by the artificial intelligence model, or obtained through interaction with the second device.

11. The method according to claim 1, characterized in that, Also includes: The first device determines auxiliary information for the artificial intelligence model; wherein the auxiliary information is used to assist the first device in determining the input information and / or output information of the artificial intelligence model; the auxiliary information includes at least one of the following: The order of the input information; The order of the output information; The way the artificial intelligence model processes input information; The way the artificial intelligence model processes the output information; The number of beam identification related information; The amount of information related to beam angle; Maximum beam correlation capability supported by the device; The number of times the transmitted beam is repeated; The number of loop iterations for outputting information; Information related to the prediction time; Third beam association information.

12. The method according to claim 8, characterized in that, After the first device determines the output information of the artificial intelligence model, it also includes: The first device selects at least one of the following from the output information: Optimal transmission beam information; Information related to the optimal receiving beam; Optimal beam information.

13. The method according to claim 12, characterized in that, When the artificial intelligence model is used for beam prediction related to the synchronization signal block SSB, and at least one SSB in the SSB burst set is disabled, the optimal beam association information is selected from the beam of the first SSB. Wherein, the first SSB is the SSB to which the output information is associated, and the SSB burst-enabled; The optimal beam includes at least one of the following: The beam corresponding to the optimal transmission beam information; The beam corresponding to the optimal received beam information; The beam corresponding to the optimal beam information.

14. The method according to claim 1, characterized in that, At least one of the input information, output information, and auxiliary information of the artificial intelligence model is determined by the first device through interaction with the second device; The interaction methods include at least one of the following: Send; report; instruct; configure; request; pre-agreed upon.

15. An input processing device for an artificial intelligence model, characterized in that, include: A first determining module is configured to determine the input information of an artificial intelligence model via a first device; wherein the artificial intelligence model is used for beam prediction-related functions, and the input information includes expected information and at least one of the following: Beam quality related information; First beam association information; Time-related information; The first beam association information is used to characterize the association information corresponding to the first beam when the input of the artificial intelligence model is selected as the first beam; The time-related information is used to characterize the time corresponding to the beam quality-related information, and / or the time relationship between multiple beam quality-related information; The desired information includes at least one of the following: second beam association information; prediction time-related information; The second beam association information is used to characterize the association information corresponding to the desired second beam; The device further includes: The second determining module is used to determine the output information of the artificial intelligence model through the first device, wherein the quantity of the output information is associated with the second beam association information and / or the prediction time related information.

16. The apparatus according to claim 15, characterized in that, The output information includes at least one of the following: Under the first receiving beam, at least some beam quality-related information and / or optimal transmission beam-related information are transmitted; Under the first transmitted beam, at least some of the received beam quality-related information and / or the optimal received beam-related information are received; Under the second receiving beam and the second transmitting beam, the beam quality related information and / or the optimal beam related information of the corresponding beam pair; Wherein, the first receiving beam and the second receiving beam are receiving beams characterized by the second beam association information; the first transmitting beam and the second transmitting beam are transmitting beams characterized by the second beam association information.

17. The apparatus according to claim 15, characterized in that, Also includes: The third determining module is used to determine auxiliary information of the artificial intelligence model through the first device; wherein the auxiliary information is used to assist the first device in determining the input information and / or output information of the artificial intelligence model; the auxiliary information includes at least one of the following: The order of the input information; The order of the output information; The way the artificial intelligence model processes input information; The way the artificial intelligence model processes the output information; The number of beam identification related information; The amount of information related to beam angle; Maximum beam correlation capability supported by the device; The number of times the transmitted beam is repeated; The number of loop iterations for outputting information; Information related to the prediction time; Third beam association information.

18. The apparatus according to claim 15, characterized in that, Also includes: The selection module is configured to select at least one of the following from the output information via the first device: Optimal transmission beam information; Information related to the optimal receiving beam; Optimal beam information.

19. An input processing device for an artificial intelligence model, characterized in that, It includes a processor and a memory, the memory storing a program or instructions that can run on the processor, the program or instructions being executed by the processor to implement the steps of the input processing method of the artificial intelligence model as described in any one of claims 1 to 14.

20. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the input processing method for the artificial intelligence model as described in any one of claims 1 to 14.

Images