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

Abstract

The embodiment of the disclosure provides an information processing method and device, a communication device and a storage medium. The information processing method comprises the following steps: sending configuration information, wherein the configuration information comprises: RB indication information, which indicates the number of RBs with the same precoding of a UE; and the number of RBs are used for the UE to determine a channel estimation of an AI model.

Description

Technical Field

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

[0002] In traditional channel estimation, modulation and demodulation reference signals (DMRS) from multiple resource blocks (RBs) are jointly used for channel estimation. When using DMRS from different numbers of RBs for channel estimation, the required AI model will differ depending on the dimension of the input data. For example, if different numbers of RBs' DMRS are input into the AI ​​model of an Artificial Intelligence (AI) method, the required AI model will also be different.

[0003] In New Radio (NR), the concept of Physical Resource Block Bundling (PRB bundling) is introduced. This PRB bundling configuration can involve specifying that several consecutive Resource Blocks (RBs) in the frequency domain use the same precoding rules. If, after introducing PRB bundling, the dimensionality of the DMRS (Digital Resource Blocks) with different numbers of RBs does not match the dimensionality of the input data for a single AI model, it may lead to the failure of the AI ​​method and its inability to adapt to changes in channel estimation with different numbers of RBs after PRB bundling configuration. Summary of the Invention

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

[0005] According to a first aspect of this disclosure, an information processing method is provided, executed by a base station, comprising:

[0006] Send configuration information, which includes: RB indication information, indicating that the UE has the same number of RBs with the same precoding; the number of RBs is used by the UE to determine the AI ​​model for channel estimation.

[0007] According to a second aspect of this disclosure, an information processing method is provided, executed by a UE, comprising:

[0008] Receive configuration information, including: RB indication information, indicating that the UE has the same number of precoded RBs;

[0009] Based on the number of RBs, an AI model is determined for channel estimation.

[0010] According to a third aspect of this disclosure, an information processing apparatus is provided, applied to a base station, comprising:

[0011] The first transmitting module is configured to transmit configuration information, which includes: RB indication information, indicating that the UE has the same number of precoded RBs, and the number of RBs is used by the UE to determine the AI ​​model for channel estimation.

[0012] According to a fourth aspect of this disclosure, a processing apparatus is provided for use in a UE, comprising:

[0013] The second receiving module is configured to receive configuration information, wherein the configuration information includes: resource block (RB) indication information, indicating that the UE has the same number of precoded RBs;

[0014] The second processing module is configured to determine the AI ​​model for channel estimation based on the number of RBs.

[0015] According to a fifth aspect of this disclosure, a communication device is provided, wherein the communication device includes:

[0016] processor;

[0017] Memory used to store processor-executable instructions;

[0018] The processor is configured to implement the information processing method of any embodiment of this disclosure when running executable instructions.

[0019] According to a sixth aspect of this disclosure, a computer storage medium is provided, wherein the computer storage medium stores a computer executable program, which, when executed by a processor, implements the information processing method of any embodiment of this disclosure.

[0020] The technical solutions provided in this disclosure may have the following beneficial effects:

[0021] In this embodiment, configuration information can be transmitted via the base station. This configuration information includes RB indication information, indicating that the UE has the same number of precoded RBs. The number of RBs is used by the UE to determine the AI ​​model for channel estimation. This allows the UE to use an appropriate AI model for channel estimation with the same number of precoded RBs after introducing PRB bundling configuration. This allows for channel estimation variations using DMRS with different numbers of RBs after PRB bundling configuration, improving the scalability of the AI ​​method in the channel estimation field. Furthermore, since DMRS with the same number of precoded RBs can be used as joint input data into the AI ​​model, the efficiency and performance of the AI ​​method in the channel estimation field can also be improved.

[0022] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the embodiments of this disclosure. Attached Figure Description

[0023] Figure 1 This is a schematic diagram of the structure of a wireless communication system.

[0024] Figure 2 This is a flowchart illustrating an information processing method according to an exemplary embodiment of the present disclosure.

[0025] Figure 3 This is a flowchart illustrating an information processing method according to an exemplary embodiment of the present disclosure.

[0026] Figure 4 This is a flowchart illustrating an information processing method according to an exemplary embodiment of the present disclosure.

[0027] Figure 5 This is a flowchart illustrating an information processing method according to an exemplary embodiment of the present disclosure.

[0028] Figure 6 This is a flowchart illustrating an information processing method according to an exemplary embodiment of the present disclosure.

[0029] Figure 7 This is a flowchart illustrating an information processing method according to an exemplary embodiment of the present disclosure.

[0030] Figure 8 This is a flowchart illustrating an information processing method according to an exemplary embodiment of the present disclosure.

[0031] Figure 9 This is a block diagram illustrating an information processing apparatus according to an exemplary embodiment of the present disclosure.

[0032] Figure 10 This is a block diagram illustrating an information processing apparatus according to an exemplary embodiment of the present disclosure.

[0033] Figure 11 This is a block diagram illustrating a UE according to an exemplary embodiment.

[0034] Figure 12 This is a block diagram illustrating a base station according to an exemplary embodiment. Detailed Implementation

[0035] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of embodiments of this disclosure.

[0036] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the embodiments of this disclosure. The singular forms “a” and “the” as used in this disclosure are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0037] It should be understood that although the terms first, second, third, etc., may be used to describe various information in embodiments of this disclosure, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, first information may also be referred to as second information without departing from the scope of embodiments of this disclosure, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to a determination."

[0038] Please refer to Figure 1 This illustration shows a schematic diagram of the structure of a wireless communication system provided in an embodiment of this disclosure. Figure 1 As shown, the wireless communication system is a communication system based on cellular mobile communication technology. The wireless communication system may include: several user equipment 110 and several base stations 120.

[0039] User equipment 110 can be a device that provides voice and / or data connectivity to a user. User equipment 110 can communicate with one or more core networks via a Radio Access Network (RAN). User equipment 110 can be an Internet of Things (IoT) user equipment, such as sensor devices, mobile phones (or "cellular" phones), and computers with IoT user equipment capabilities. For example, it can be a fixed, portable, pocket-sized, handheld, computer-embedded, or vehicle-mounted device. Examples include a station (STA), subscriber unit, subscriber station, mobile station, mobile station, remote station, access point, remote terminal, access terminal, user terminal, user agent, user device, or user equipment. Alternatively, user equipment 110 can also be a device from an unmanned aerial vehicle (UAV). Alternatively, user equipment 110 can also be a vehicle-mounted device, such as a vehicle computer with wireless communication capabilities, or a wireless user equipment connected to an external vehicle computer. Alternatively, user equipment 110 can also be a roadside device, such as a street light, traffic light, or other roadside device with wireless communication capabilities.

[0040] Base station 120 can be a network-side device in a wireless communication system. This wireless communication system can be a 4G system (also known as Long Term Evolution, LTE); or it can be a 5G system (also known as a New Radio, 5G NR, or 5G NR system). Alternatively, it can be the next generation after 5G. In this case, the access network in the 5G system can be called a New Generation-Radio Access Network (NG-RAN).

[0041] The base station 120 can be an evolved NB (eNB) used in a 4G system. Alternatively, the base station 120 can also be a gNB (gNB) using a centralized-distributed architecture in a 5G system. When the base station 120 adopts a centralized-distributed architecture, it typically includes a central unit (CU) and at least two distributed units (DUs). The central unit is equipped with a protocol stack of the Packet Data Convergence Protocol (PDCP) layer, the Radio Link Control (RLC) layer, and the Medium Access Control (MAC) layer; the distributed units are equipped with a physical (PHY) layer protocol stack. This disclosure does not limit the specific implementation of the base station 120.

[0042] Base station 120 and user equipment 110 can establish a wireless connection via a wireless air interface. In different implementations, the wireless air interface is a wireless air interface based on the fourth-generation mobile communication network technology (4G) standard; or, the wireless air interface is a wireless air interface based on the fifth-generation mobile communication network technology (5G) standard, such as a new air interface; or, the wireless air interface can also be a wireless air interface based on a next-generation mobile communication network technology standard based on 5G.

[0043] In some embodiments, user equipment 110 can also establish E2E (End to End) connections. Examples include vehicle-to-vehicle (V2V) communication, vehicle-to-infrastructure (V2I) communication, and vehicle-to-pedestrian (V2P) communication in vehicle-to-everything (V2X) communication.

[0044] Here, the user equipment mentioned above can be considered as the terminal equipment in the following embodiments.

[0045] In some embodiments, the wireless communication system described above may further include a network management device 130.

[0046] Several base stations 120 are connected to network management device 130. Network management device 130 can be a core network device in a wireless communication system, such as a Mobility Management Entity (MME) in an Evolved Packet Core (EPC). Alternatively, it can be other core network devices, such as a Serving Gateway (SGW), a Public Data Network Gateway (PGW), a Policy and Charging Rules Function (PCRF), or a Home Subscriber Server (HSS). The implementation of network management device 130 is not limited in this embodiment.

[0047] To facilitate understanding by those skilled in the art, this disclosure provides multiple embodiments to clearly illustrate the technical solutions of the embodiments of this disclosure. Of course, those skilled in the art will understand that the multiple embodiments provided in this disclosure can be executed individually, or in combination with the methods of other embodiments in this disclosure, or individually or in combination with some methods in other related technologies; this disclosure does not limit these aspects.

[0048] like Figure 2 As shown, this disclosure provides an information processing method, executed by a base station, including:

[0049] Step S21: Send configuration information, wherein the configuration information includes: RB indication information, indicating that the UE has the same number of RBs with the same precoding; the number of RBs is used by the UE to determine the AI ​​model for channel estimation.

[0050] In one embodiment, the base station can be of various types. For example, the base station can be a 2G base station, a 3G base station, a 4G base station, a 5G base station, or other evolved base stations.

[0051] In one embodiment, the UE can be various terminals. For example, the UE can be, but is not limited to, a mobile phone, a computer, a server, a wearable device, a game control platform, or a multimedia device.

[0052] Step S21 can be: the base station sends configuration information to the UE.

[0053] In one embodiment, the number of identically precoded RBs includes: the number of consecutive RBs with the same precoding. For example, RB indication information indicates that the UE has a number of consecutive RBs with the same precoding.

[0054] In one embodiment, the DMRS of consecutive RB numbers is input as an input parameter to the AI ​​model; for example, the DMRS of consecutive RB numbers is input as joint data to the AI ​​model for channel estimation. Here, channel estimation can be: joint channel estimation.

[0055] In one embodiment, the number of RBs includes the number of PRBs. For example, RB indication information indicates that the UE has the same precoded consecutive number of PRBs.

[0056] In one embodiment, the configuration information includes: PRB bundling configuration information; the PRB bundling configuration information includes: RB indication information.

[0057] In other embodiments, the PRB bundling configuration information may include, but is not limited to, at least one of the following: type information indicating the type of PRB bundling configuration, and value information indicating the number of RBs in the PRB bundling configuration. This value information may include: first value information indicating that the number of RBs is a first type of value, or second value information indicating that the number of RBs is a second type of value.

[0058] In some embodiments, the configuration information includes: model indication information, wherein the model indication information indicates the AI ​​model adopted by the UE.

[0059] In one embodiment, the RB indicator information can be: RB_indicator; the model indicator information can be: Model_indicator.

[0060] In some embodiments, configuration information can be used by the UE to determine the AI ​​model for channel estimation. For example, the number of identical precoded RBs indicated by the RB indication information in the configuration information is used by the UE to determine the AI ​​model for channel estimation. As another example, the number of identical precoded RBs indicated by the RB indication information in the configuration information is used to determine the corresponding model indication information; the model indication information is used by the UE to determine the AI ​​model for channel estimation. Yet another example is that the model indication information in the configuration information is used by the UE to determine the AI ​​model for channel estimation.

[0061] In some embodiments, the number of RBs is used by the UE to determine the AI ​​model for channel estimation during PRB bundling configuration.

[0062] Here, PRB bundling configuration includes, but is not limited to, at least one of the following: semi-static PRB bundling configuration; dynamic PRB bundling configuration.

[0063] Here, semi-static PRB bundling configuration can be configuration based on Radio Resource Control (RRC) signaling. For example, the base station sends configuration information to the UE via RRC signaling.

[0064] Here, dynamic PRB bundling configuration can be based on the Physical Downlink Control Channel (PDCCH). For example, the base station sends configuration information to the UE via the PDCCH.

[0065] In one embodiment, the usage time corresponding to a semi-static PRB bundling configuration is greater than the usage time corresponding to a dynamic PRB bundling configuration. For example, when performing a semi-static PRB bundling configuration on a UE, the usage time corresponding to this semi-static PRB bundling configuration can be a first time; when performing a dynamic PRB bundling configuration on a UE, the usage time corresponding to this dynamic PRB bundling configuration can be a second time; the first time is greater than the second time.

[0066] In this embodiment, configuration information can be transmitted via the base station. This configuration information includes RB indication information, indicating that the UE has the same number of precoded RBs. The number of RBs is used by the UE to determine the AI ​​model for channel estimation. This allows the UE to use an appropriate AI model for channel estimation with the same number of precoded RBs after introducing PRB bundling configuration. This allows for channel estimation variations using DMRS with different numbers of RBs after PRB bundling configuration, improving the scalability of the AI ​​method in the channel estimation field. Furthermore, since DMRS with the same number of precoded RBs can be used as joint input data into the AI ​​model, the efficiency and performance of the AI ​​method in the channel estimation field can also be improved.

[0067] Step 21 includes:

[0068] In response to the UE's PRB bundling configuration being semi-static, a Radio Resource Control (RRC) signaling carrying configuration information is sent; or...

[0069] In response to the UE's PRB bundling configuration being dynamically configured, configuration information is sent via the Physical Downlink Control Channel (PDCCH).

[0070] This disclosure provides an information processing method executed by a base station, which may include: sending RRC signaling carrying configuration information in response to the UE's PRB bundling configuration being semi-static; or, sending configuration information via PDCCH in response to the UE's PRB bundling configuration being dynamic. Here, sending configuration information via PDCCH includes: sending configuration information on the PDCCH.

[0071] Thus, in one embodiment of this disclosure, when the UE is configured for semi-static PRB bundling, configuration information can be sent via RRC signaling. In another embodiment, when the UE is configured for dynamic PRB bundling, configuration information can be sent via PDCCH. Therefore, on the one hand, different PRB bundling configurations can be sent via different signaling or channels; on the other hand, sending configuration information via RRC signaling or based on PDCCH can improve the utilization rate of RRC signaling or PDCCH.

[0072] It should be noted that those skilled in the art will understand that the methods provided in the embodiments of this disclosure can be executed alone or together with some methods in the embodiments of this disclosure or some methods in related technologies.

[0073] like Figure 3 As shown, this disclosure provides an information processing method, executed by a base station, including:

[0074] Step S31: Determine the target number of RBs based on the number of RBs;

[0075] Step S32: Based on the target number of RBs, determine the AI ​​model corresponding to the target number of RBs.

[0076] Step S31 includes: determining the target number of RBs based on the number of RBs configured in the PRB bundling.

[0077] This disclosure provides an information processing method executed by a base station, which may include: determining a target number of RBs based on the number of RBs configured by PRB bundling; and determining an AI model corresponding to the target number of RBs based on the target number of RBs.

[0078] Step S31 includes at least one of the following steps:

[0079] In response to the number of RBs being of the first type, determine that the target number of RBs is equal to the number of RBs; or,

[0080] In response to the second type of RB number, the target RB number is determined based on at least one of the UE's computing power information, UE's storage capacity information, channel quality information, and UE's model deployment information.

[0081] In this embodiment of the disclosure, model deployment information is used to indicate the AI ​​models that the UE can use. This model deployment information can be an AI model already deployed in the UE, or an AI model that the UE can use according to communication protocols or other configuration information.

[0082] In some embodiments, model deployment information may include: the number of RBs and / or the AI ​​models corresponding to the number of RBs.

[0083] In this embodiment of the disclosure, the target number of RBs is the number of RBs corresponding to the channel estimation performed by the UE. The AI ​​model for channel estimation determined by the base station is the AI ​​model corresponding to the target number of RBs.

[0084] Here, the second type of value is greater than the first type of value. For example, the first type of value is {2, 4}; the second type of value is a value of the wideband that is greater than a predetermined value, such as 10 or the total number of RBs in a certain frequency domain.

[0085] Here, the first type of value can be a fixed value; for example, the first type of value can be {2, 4, 6, 8}. The second type of value is a non-fixed value; for example, the second type of value can be {wideband} or at least a portion of the total number of RBs in the frequency domain.

[0086] This disclosure provides an information processing method executed by a base station, comprising: determining that the number of RBs configured based on PRB bundling is a first type of value, and determining that the target number of RBs is equal to the number of RBs.

[0087] This disclosure also provides an information processing method executed by a base station, comprising: determining a target number of RBs based on the second type of value of the number of RBs configured by PRB bundling, and based on at least one of the UE's computing power information, UE's storage power information, channel quality information, and UE's model deployment information.

[0088] In some embodiments of this disclosure, the PRB bundling configuration is the same as the PRB bundling configuration described in the above embodiments; for example, the PRB bundling configuration includes: a semi-static PRB bundling configuration or a dynamic PRB bundling configuration.

[0089] Here, the number of RBs configured in PRB bundling is of the first type, including: the number of RBs configured in semi-static PRB bundling is of the first type, or the number of RBs configured in dynamic PRB bundling is of the first type. For example, the number of RBs configured in semi-static PRB bundling is "2" or 4; or the number of RBs configured in dynamic PRB bundling is "2" or "4".

[0090] Here, the number of RBs configured in PRB bundling is a second type of value, including: the number of RBs configured in semi-static PRB bundling is a second type of value, or the number of RBs configured in dynamic PRB bundling is a second type of value. For example, the number of RBs configured in dynamic PRB bundling is "wideband", or the number of RBs configured in dynamic PRB bundling is "wideband".

[0091] For example, the network device configures PRB bundling for the UE; if the number of RBs configured in the PRB bundling is 2, then the target number of RBs is 2; the base station then indicates that the number of RBs is 2 through RB indication information and determines the AI ​​model corresponding to the number of RBs being 2 for the UE. Here, if the UE receives the RB indication information and determines that the number of RBs is 2 based on the RB indication information, then the UE determines that the target number of RBs is 2, and the UE determines to use the AI ​​model corresponding to the number of RBs being 2 for channel estimation. Here, the PRB bundling configuration can be either semi-static or dynamic.

[0092] For example, the network device configures PRB bundling for the UE. If the number of RBs configured in the PRB bundling is "wideband", the base station can determine the target number of RBs based on at least one of the UE's computing power information, UE's storage capacity information, channel quality information, and UE's model deployment information. Here, if the UE receives RB indication information and determines that the number of RBs is "wideband" based on the RB indication information, the UE can determine the AI ​​model for channel estimation based on at least one of the UE's computing power information, UE's storage capacity information, channel quality information, and UE's model deployment information.

[0093] Here, the computing power indicated by the UE's computing power information is positively correlated with the number of RBs. That is, the stronger the UE's computing power, the larger the number of RBs determined; the weaker the UE's computing power, the smaller the number of RBs determined.

[0094] Here, the storage capacity indicated by the UE's storage capacity information is positively correlated with the number of Resource Blocks (RBs). That is, the larger the UE's storage capacity, the larger the number of RBs determined; the smaller the UE's storage capacity, the smaller the number of RBs determined.

[0095] Here, channel information quality indicates the quality of the channel environment and is positively correlated with the number of Reference Controllers (RBs). That is, the better the UE's channel environment, the larger the number of RBs determined; the worse the UE's channel environment, the smaller the number of RBs determined.

[0096] Here, determining the target number of Base Stations (RBs) based on the UE's model deployment information can be achieved by: determining the target number of RBs based on the AI ​​model within the UE's model deployment information. For example, the model deployment information includes an AI model; the base station can determine the target number of RBs based on the performance of the AI ​​model, such as the dimensionality of the AI ​​model's input data.

[0097] Thus, in this embodiment of the disclosure, if the PRB bundling configuration, such as the semi-static PRB bundling configuration or the dynamic PRB bundling configuration, is of the first type of value, then the number of target RBs for channel estimation that needs to be performed can be directly determined as the number of RBs of the first type of value; in this way, the appropriate number of RBs for joint channel estimation can be conveniently determined.

[0098] Alternatively, if the PRB bundling configuration, such as semi-static or dynamic PRB bundling, is of the second type, the base station can determine the target number of RBs requiring channel estimation based on at least one of the UE's computing power, storage capacity, channel quality, and model deployment information. In this way, the base station can freely select the number of RBs for joint channel estimation based on the UE's computing power, storage capacity, channel environment, and AI model within the UE, thereby maximizing resource utilization.

[0099] This disclosure provides an information processing method executed by a base station, comprising: determining the model deployment information of a UE; and storing the identification information of the UE and the corresponding model deployment information.

[0100] In one embodiment, model deployment information is used to indicate the correspondence between the number of Reference Builders (RBs) and the AI ​​model. For example, the model deployment information may be: when the number of RBs is 2, the corresponding AI model is the first AI model; when the number of RBs is 4, the corresponding AI model is the second AI model; and when the number of RBs is 6, the corresponding AI model is the third AI model.

[0101] In another embodiment, the model deployment information includes at least one of the following parameters: the AI ​​model that the UE can use, the number of RBs, and the AI ​​model corresponding to the number of RBs. For example, if the base station determines that the number of RBs is 2, the corresponding AI model is the first AI model; if the number of RBs is 4, the corresponding AI model is the second model; and if it also determines that the UE has a third AI model and a fourth AI model, and that the UE's corresponding PRB bundling configuration has a case where the number of RBs is 6; then the base station determines that the UE's model deployment information can include at least one of the following: 2 RBs and the corresponding first AI model, 4 RBs and the corresponding second AI model, the third AI model and the fourth AI model, and 6 RBs. That is, the model deployment information can identify the AI ​​models (first AI model, second AI model, third AI model, and fourth AI model) that the UE can use; it can also identify the number of RBs corresponding to the AI ​​models; and it can also identify the number of RBs corresponding to the UE. Of course, the above example includes all three parameters simultaneously, and those skilled in the art will understand that only one parameter may be included.

[0102] In some embodiments of this disclosure, the number of RBs is: the target number of RBs. For example, the model deployment information includes: at least one correspondence between the target number of RBs and the AI ​​model; or, the model deployment information includes: at least one target number of RBs and / or the AI ​​model corresponding to the target number of RBs.

[0103] This disclosure provides an information processing method executed by a base station, including: sending UE model deployment information to the UE.

[0104] Thus, in this embodiment of the disclosure, the model deployment information of the UE can be determined by the base station, which facilitates subsequent querying of whether the UE has an AI model corresponding to the number of RBs (or the target number of RBs). Furthermore, the base station can send the UE's model deployment information to the UE, enabling the UE to determine the AI ​​model corresponding to the number of RBs (or the target number of RBs) for channel estimation based on the RB indication information and / or AI model information in the received configuration information.

[0105] Step S21 includes: in response to determining that an AI model corresponding to the number of RBs exists in the UE based on the model deployment information, sending configuration information including RB indication information and model indication information.

[0106] Step S21 includes: in response to determining that there is no AI model in the UE corresponding to the number of RBs based on the model deployment information, sending configuration information including at least RB indication information.

[0107] In one embodiment, the number of RBs includes: the number of target RBs. Here, the RB indication information indicates the number of target RBs with the same precoding. Here, the number of target RBs with the same precoding can be: the number of consecutive target RBs with the same precoding.

[0108] Step S21 includes: in response to determining that there is an AI model in the UE corresponding to the target number of RBs based on the UE model deployment information, sending configuration information including RB indication information and model indication information.

[0109] Step S21 includes: in response to determining from the UE-based model deployment information that there is no AI model in the UE corresponding to the target number of RBs, sending configuration information including at least RB indication information.

[0110] It is understood that the above two steps can be performed individually or together; this disclosure does not limit this.

[0111] like Figure 4 As shown, this disclosure provides an information processing method, executed by a base station, including:

[0112] Step S41: In response to determining that there is an AI model in the UE corresponding to the target number of RBs based on the UE model deployment information, send configuration information including RB indication information and model indication information.

[0113] For example, if the number of RBs configured for the UE's PRB bundling by the network device is of the first type, then this number of RBs is the target number of RBs. The base station queries the UE's model deployment information. If an AI model corresponding to the number of RBs exists in the model deployment information, the base station sends configuration information to the UE. The configuration information includes: RB indication information indicating the same number of RBs in the precoding, and model indication information indicating the AI ​​model. When the UE receives the configuration information, it can directly perform channel estimation based on the AI ​​model indicated by the model indication information. Here, the UE's PRB bundling configuration can be a semi-static PRB bundling configuration or a dynamic PRB bundling configuration.

[0114] For example, if the number of RBs configured by the network device for the UE's PRB bundling is of the second type, the base station determines the target number of RBs based on one of the UE's computing power information, storage capacity information, channel quality information, and model deployment information. The base station queries the UE's model deployment information. If an AI model corresponding to the target number exists in the model deployment information, the base station sends configuration information to the UE. The configuration information includes RB indication information indicating the target number of RBs with the same precoding, and model indication information indicating the AI ​​model. When the UE receives the configuration information, it can directly perform channel estimation based on the AI ​​model indicated by the model indication information. Here, the UE's PRB bundling configuration can be a semi-static PRB bundling configuration or a dynamic PRB bundling configuration.

[0115] Thus, in this embodiment of the disclosure, if the UE's model deployment information contains an AI model corresponding to the number of RBs (or the target number of RBs), the base station can send configuration information including RB indication information and model indication information so that the UE can directly perform channel estimation based on the RB indication information and model indication information using the AI ​​model corresponding to the number of RBs (or the target number of RBs).

[0116] In some embodiments of this disclosure, if the base station determines that the UE's model deployment information contains an AI model corresponding to the target number of RBs, it may only send RB indication information, so that the UE can determine the target number of RBs based on the RB indication information, and then determine the AI ​​model corresponding to the target number of RBs based on the target number of RBs and the UE's model deployment information. For example, an embodiment of this disclosure provides an information method executed by a base station, including: determining that the UE contains an AI model corresponding to the target number of RBs based on the UE's model deployment information, and sending configuration information including RB indication information; wherein, the RB indication information is used for the UE to determine the target number of RBs; and the target number of RBs is used for the UE to determine the AI ​​model for channel estimation.

[0117] Here, the target number of Reference RBs (RBs) is used by the UE to determine the corresponding AI model for channel estimation based on the target number of RBs and model deployment information. The model deployment information includes the correspondence between the number of RBs and the AI ​​model.

[0118] For example, if the number of RBs configured by the network device for the UE's PRB bundling is of the first type, then this number of RBs is the target number of RBs. The base station queries the UE's model deployment information. If an AI model corresponding to the number of RBs exists in the model deployment information, the base station sends configuration information to the UE. The configuration information includes RB indication information indicating the number of RBs with the same precoding. When the UE receives the configuration information, it can determine the number of RBs based on the RB indication information, and determine the AI ​​model corresponding to the number of RBs for channel estimation based on the RB number and the UE's model deployment information. Here, the UE's model deployment information includes the correspondence between the number of RBs and the AI ​​model. Here, the UE's PRB bundling configuration can be a semi-static PRB bundling configuration or a dynamic PRB bundling configuration.

[0119] For example, if the network device configures the number of RBs for the UE's PRB bundling to be of the second type, the base station determines the target number of RBs based on one of the UE's computing power information, storage capacity information, channel quality information, and model deployment information. The base station queries the UE's model deployment information. If an AI model corresponding to the target number exists in the model deployment information, the base station sends configuration information to the UE. The configuration information includes RB indication information indicating the target number of RBs with the same precoding. When the UE receives the configuration information, it can determine the target number of RBs based on the RB indication information and, based on the target number of RBs and the UE's model deployment information, determine the AI ​​model corresponding to the target number of RBs for channel estimation. Here, the UE's model deployment information includes the correspondence between the target number of RBs and the AI ​​model. Here, the UE's PRB bundling configuration can be a semi-static PRB bundling configuration or a dynamic PRB bundling configuration.

[0120] Thus, in this embodiment of the disclosure, configuration information including only RB indication information can be sent to the UE by the base station, thereby reducing the number of bits in the configuration information and saving transmission resources.

[0121] like Figure 5 As shown, this disclosure provides an information processing method, executed by a base station, including:

[0122] Step S51: In response to determining from the UE-based model deployment information that there is no AI model in the UE corresponding to the target number of RBs, send configuration information including at least RB indication information.

[0123] Here, the RB indication information is used by the UE to determine the target number of RBs; the target number of RBs is used by the UE to determine the channel estimation for the AI ​​model.

[0124] Here, the target number of RBs is used to enable the UE to determine the AI ​​model for channel estimation based on the UE's computing power information, storage capacity information, channel quality information, and model deployment information.

[0125] Here, the computing power information of the UE, the storage capacity information of the UE, and the channel quality information of the channel environment are all positively correlated with the performance of the AI ​​model. For example, they are positively correlated with the dimensionality of the input data of the AI ​​model or the amount of data processed by the AI ​​model. For instance, the stronger the UE's computing power, the larger the UE's storage capacity, and / or the better the UE's channel quality, the larger the dimensionality of the input data of the AI ​​model; conversely, the weaker the UE's computing power, the smaller the UE's storage capacity, and / or the worse the UE's channel quality, the smaller the dimensionality of the input data of the AI ​​model.

[0126] Here, determining the AI ​​model based on the UE's model deployment information can mean that the determined AI model belongs to the AI ​​models included in the model deployment information.

[0127] Here, sending configuration information that includes at least RB indication information can be: sending configuration information that includes RB indication information.

[0128] For example, if the number of RBs configured for the UE's PRB bundling by the network device is of the first type, then this number of RBs is the target number of RBs. The base station queries the UE's model deployment information. If there is no AI model corresponding to the number of RBs in the model deployment information, the base station sends configuration information to the UE. The configuration information includes RB indication information indicating the number of RBs with the same precoding. When the UE receives the RB indication information, it can determine the number of RBs based on the RB indication information; and based on the UE's computing power information, storage capacity information, channel quality information, and model deployment information, it determines the AI ​​model for channel estimation. Here, the UE's PRB bundling configuration can be a semi-static PRB bundling configuration or a dynamic PRB bundling configuration.

[0129] For example, if the number of RBs configured for the UE's PRB bundling by the network device is of the second type, the base station determines the target number of RBs based on one of the UE's computing power information, storage capacity information, channel quality information, and model deployment information. The base station queries the UE's model deployment information. If no AI model corresponding to the target number exists in the model deployment information, the base station sends configuration information to the UE. The configuration information includes RB indication information indicating the target number of RBs with the same precoding. When the UE receives the RB indication information, it can determine the target number of RBs based on the RB indication information; and based on the UE's computing power information, storage capacity information, channel quality information, and model deployment information, it determines the AI ​​model for channel estimation. Here, the UE's PRB bundling configuration can be a semi-static PRB bundling configuration or a dynamic PRB bundling configuration.

[0130] Here, sending configuration information that includes at least RB indication information can be: sending configuration information including RB indication information and model indication information indicating the AI ​​model. Alternatively, sending model indication information can instruct the UE to use the AI ​​model required for channel estimation.

[0131] Thus, in this embodiment, if the base station determines that there is no AI model corresponding to the number of RBs (or the target number of RBs) in the UE's model deployment information, it sends configuration information, including at least RB indication information, to the UE. This allows the UE to determine the number of RBs (or the target number of RBs) based on the RB indication information, and then determine the AI ​​model for channel estimation based on the UE's model deployment information, computing power information, storage capacity information, and channel quality information. This allows the UE to freely choose a suitable AI model for channel estimation, maximizing resource utilization. Furthermore, by sending configuration information including only RB indication information to the UE, the base station reduces the number of bits in the configuration information, thereby saving transmission resources.

[0132] Step 21 includes: in response to determining that the UE does not have an AI model corresponding to the target number of RBs based on the UE-based model deployment information, sending configuration information including RB indication information;

[0133] It also includes sending model information to the UE, wherein the model information includes AI models corresponding to the target number.

[0134] Here, sending configuration information including RB indication information can also be: sending configuration information including RB indication information and model indication information.

[0135] like Figure 6As shown, this disclosure provides an information processing method, executed by a base station, including:

[0136] Step S61: In response to determining from the UE-based model deployment information that there is no AI model in the UE corresponding to the target number of RBs, send model information to the UE, wherein the model information includes: the AI ​​model corresponding to the target number of RBs.

[0137] In one embodiment, model deployment information includes: model information.

[0138] In step S61, model information is sent to the UE, including:

[0139] Based on the semi-static PRB bundling configuration of the UE, RRC signaling carrying model information is discovered; or,

[0140] Based on the dynamic PRB bundling configuration of the UE, model information is sent through PDCCH.

[0141] This disclosure provides an information processing method executed by a base station, including: discovering RRC signaling carrying model information based on the PRB bundling configuration of the UE being semi-static; or, transmitting model information via PDCCH based on the PRB bundling configuration of the UE being dynamic.

[0142] Here, the AI ​​model included in the model information is the AI ​​model indicated by the model indication information.

[0143] For example, if the number of RBs configured for the UE's PRB bundling by the network device is of the first type, then this number of RBs is the target number of RBs. The base station queries the UE's model deployment information. If there is no AI model corresponding to the number of RBs in the model deployment information, the base station sends configuration information to the UE via RRC signaling. The configuration information includes: RB indication information indicating the same number of RBs with precoding and indication information indicating the AI ​​model. The base station also sends model information to the UE via RRC signaling, which includes the AI ​​model indicated by the model indication information. When the UE receives the RB indication information, model indication information, and AI model, it can determine the AI ​​model used by the UE for channel estimation. Here, the UE's PRB bundling configuration can be a semi-static PRB bundling configuration or a dynamic PRB bundling configuration.

[0144] For example, if the number of RBs configured by the network device for the UE's PRB bundling is of the second type, the base station determines the target number of RBs based on one of the UE's computing power information, storage capacity information, channel quality information, and model deployment information. The base station queries the UE's model deployment information. If no AI model corresponding to the target number exists in the model deployment information, the base station sends configuration information to the UE via PDCCH. The configuration information includes RB indication information indicating the target number of RBs with the same precoding and indication information indicating the AI ​​model. The base station also sends model information to the UE via PDCCH, which includes the AI ​​model indicated by the model indication information. When the UE receives the model indication information and the AI ​​model, it can determine the AI ​​model used by the UE for channel estimation. Here, the UE's PRB bundling configuration can be a semi-static PRB bundling configuration or a dynamic PRB bundling configuration.

[0145] Thus, in this embodiment of the disclosure, if the base station determines that there is no AI model corresponding to the number of RBs (target number of RBs) in the UE's model deployment information, it can directly send the AI ​​model to the UE; this allows the UE to subsequently perform channel estimation based on the AI ​​model.

[0146] Furthermore, AI models with different PRB bundling configuration types can be transmitted via different signaling or channels. For example, for UEs with semi-static PRB bundling configurations, AI models can be transmitted via RRC signaling, while for UEs with dynamic PRB bundling configurations, AI models can be transmitted via PDCCH. In this way, appropriate signaling or channels can be used for transmission based on UEs with different PRB bundling configurations, improving the success rate of UE receiving AI models.

[0147] This disclosure provides an information processing method, executed by a base station, which may include:

[0148] In response to the PRB bundling configuration of the UE being dynamically configured, the transmission time of the transmitted AI model is obtained;

[0149] The time slot offset between the PDCCH and the corresponding Physical Downlink Shared Channel (PDSCH) is adjusted and sent to the UE, wherein the time slot offset indicates a time longer than the transmission time.

[0150] Here, the time slot offset allows the UE to determine whether the AI ​​model can be used for channel estimation. For example, if the time slot offset is greater than or equal to the transmission time, the AI ​​model can be used for channel estimation; or if the time slot offset is less than the transmission time, the AI ​​model cannot be used for channel estimation.

[0151] Here, if the time slot offset indicates a time greater than the transmission time slot, it can be ensured that the UE has already received the AI ​​model when the PDSCH arrives at the UE; then the UE can perform channel estimation based on the AI ​​model.

[0152] In some embodiments, obtaining the transmission time of the transmitted AI model may include: obtaining the transmission time of the transmitted AI model based on at least one of the following: the amount of data processed by the AI ​​model, the transmission time of historical transmitted AI models, the number of RBs corresponding to the AI ​​model, and the number of bits occupied by the AI ​​model. Of course, the transmission time of the transmitted AI model can also be determined in any feasible manner, and there is no limitation here.

[0153] For example, the network device configures the UE's PRB bundling as a dynamic PRB bundling configuration. If the number of RBs in the dynamic PRB bundling configuration is a first-type value, then the number of RBs is the RB number. If the number of RBs in the dynamic PRB bundling configuration is a second-type value, then the base station determines the target number of RBs based on one of the UE's computing power information, UE's storage capacity information, channel quality information, and UE's model deployment information. The base station queries the UE's model deployment information. If there is no AI model corresponding to the target number in the model deployment information, then the base station determines the AI ​​model corresponding to the target number of RBs and determines the transmission time of the AI ​​model. The base station then sends configuration information, time slot offset, and model information to the UE through PDCCH. The configuration information includes: RB indication information indicating the target number of RBs with the same precoding and indication information indicating the AI ​​model; the model information includes the AI ​​model corresponding to the target number of RBs; the time slot offset indicates a time greater than the transmission time. When the UE receives the configuration information and the AI ​​model, it can determine the AI ​​model and determine whether the AI ​​model can be used for channel estimation based on the time slot offset.

[0154] Thus, in this embodiment of the disclosure, if the UE's PRB bundling configuration is dynamic, the base station will also obtain the transmission time of the AI ​​model and send a timeslot offset to the UE. The timeslot offset indicates a time greater than the transmission time. This can ensure that the UE has received the AI ​​model by the time the PDSCH reaches the UE, thereby improving the availability of the AI ​​model for channel estimation and enhancing the UE's ability to perform channel estimation based on the AI ​​model.

[0155] It should be noted that those skilled in the art will understand that the methods provided in the embodiments of this disclosure can be executed alone or together with some methods in the embodiments of this disclosure or some methods in related technologies.

[0156] like Figure 7 As shown, this disclosure provides an information processing method, executed by a base station, including:

[0157] Step S71: Receive suggestion information, wherein the suggestion information includes at least one of the following: UE computing power information, UE storage capacity information, and channel quality information;

[0158] Step S72: Based on the suggested information, determine the AI ​​model for the UE to perform channel estimation.

[0159] This step S71 can be: receiving suggestion information sent by the UE.

[0160] Here, the computing power information of the UE, the storage capacity information of the UE, and the channel quality information of the channel environment are all positively correlated with the performance of the AI ​​model. For example, they are positively correlated with the dimensionality of the input data of the AI ​​model or the amount of data processed by the AI ​​model. For instance, the stronger the UE's computing power, the larger the UE's storage capacity, and / or the better the UE's channel quality, the larger the dimensionality of the input data of the AI ​​model; conversely, the weaker the UE's computing power, the smaller the UE's storage capacity, and / or the worse the UE's channel quality, the smaller the dimensionality of the input data of the AI ​​model.

[0161] Here, the base station can determine the UE's AI model in advance based on the suggested information, or determine the UE's AI model based on the suggested information when no AI model corresponding to the target number of RBs is found in the UE's model deployment information.

[0162] Thus, this embodiment of the disclosure can determine a suitable AI model for the UE based on the suggestion information reported by the UE.

[0163] Here, step S71 can be: receiving suggestion information sent by a UE with semi-static PRB bundling configuration or receiving suggestion information sent by a UE with dynamic PRB bundling configuration.

[0164] In one embodiment, before step S71, the following steps are included: the base station sends request information to the UE, the request information being used to instruct the UE to send suggestion information.

[0165] Therefore, in this embodiment of the disclosure, the base station may only receive the suggestion information reported by the UE when it needs to request the UE to report suggestion information. This eliminates the need for the base station to receive suggestion information in real time to determine the AI ​​model for channel estimation by the UE, thereby saving transmission and processing resources.

[0166] It should be noted that those skilled in the art will understand that the methods provided in the embodiments of this disclosure can be executed alone or together with some methods in the embodiments of this disclosure or some methods in related technologies.

[0167] The following information processing method is executed by the UE and is similar to the information processing method executed by the base station described above. For technical details not disclosed in the embodiments of the information processing method executed by the UE, please refer to the description of the example of the information processing method executed by the base station, which will not be described in detail here.

[0168] This disclosure provides an information processing method executed by a UE, comprising: determining an AI model for channel estimation based on the number of RBs having the same precoding.

[0169] This disclosure provides an information processing method executed by a UE, which may include: determining an AI model for channel estimation based on the same number of precoded RBs during PRB bundling configuration.

[0170] like Figure 8 As shown, this disclosure provides an information processing method, executed by a UE, including:

[0171] Step S81: Receive configuration information, wherein the configuration information includes: RB indication information, indicating that the UE has the same number of precoded RBs;

[0172] Step S82: Based on the number of RBs, determine the AI ​​model for channel estimation.

[0173] This configuration information includes: model indication information.

[0174] This disclosure provides an information processing method executed by a UE, including: receiving configuration information, the configuration information including RB indication information and model indication information.

[0175] In some embodiments of this disclosure, the configuration information is the configuration information in step S21; the RB indication information is the RB indication information in step S21; the number of RBs is the number of RBs in step S21; the model indication information is the model indication information in the above embodiments; and the AI ​​model is the AI ​​model in the above embodiments.

[0176] Step S82 may include: determining the number of RBs in the PRB bundling configuration to perform channel estimation using the AI ​​model. Here, the PRB bundling configuration is the PRB bundling configuration in the above embodiments; for example, the PRB bundling configuration may be a semi-static PRB bundling configuration or a dynamic PRB bundling configuration.

[0177] This configuration information includes: model indication information, indicating the AI ​​model adopted by the UE;

[0178] This step S82 may include: determining the channel estimation based on the AI ​​model indicated by the model indication information corresponding to the number of RBs.

[0179] This disclosure provides an information processing method executed by a UE, comprising: receiving configuration information, the configuration information including: RB indication information, indicating that the UE has the same number of precoded RBs; and model indication information, indicating the AI ​​model adopted by the UE; and performing channel estimation based on the AI ​​model indicated by the model indication information corresponding to the number of RBs.

[0180] The number of RBs includes the target number of RBs.

[0181] This disclosure provides an information processing method executed by a UE, comprising: receiving configuration information, the configuration information including: RB indication information, indicating that the UE has the same number of target RBs with the same precoding; and model indication information, indicating the AI ​​model adopted by the UE; and performing channel estimation based on the AI ​​model indicated by the model indication information corresponding to the number of target RBs.

[0182] Step S82 may include: in response to the number of RBs being a first-type value, determining the AI ​​model corresponding to the number of RBs for channel estimation. Here, the number of RBs may include the number of RBs configured based on PRB bundling.

[0183] This disclosure provides an information processing method executed by a UE, comprising: receiving configuration information, the configuration information including RB indication information, indicating that the UE has the same number of precoded RBs; and, in response to the number of RBs being a first type of value, performing channel estimation based on an AI model corresponding to the number of RBs. Here, the UE performing channel estimation based on the AI ​​model corresponding to the number of RBs may be: the UE determines an AI model corresponding to the number of RBs based on the number of RBs and the UE's model deployment information; and performs channel estimation based on the AI ​​model.

[0184] Step S82 may include: in response to the number of RBs being a second type of value, determining the AI ​​model for channel estimation based on at least one of the UE's model deployment information, UE's computing power information, UE's storage capacity information, and channel quality information. Here, the number of RBs may include the number of RBs configured based on PRB bundling.

[0185] Here, the number of RBs includes the target number of RBs.

[0186] This disclosure provides a processing method executed by a UE, comprising: receiving configuration information, the configuration information including: RB indication information, indicating that the UE has the same precoded target RB number; in response to the target RB number being a second type value, determining an AI model for channel estimation based on at least one of the UE's model deployment information, the UE's computing power information, the UE's storage power information, and channel quality information.

[0187] The number of RBs may include: the target number of RBs; the method also includes:

[0188] The method may include: receiving model information, wherein the model information includes: an AI model corresponding to the target number of RBs;

[0189] Step S82 may include: determining an AI model corresponding to the target number of RBs for channel estimation.

[0190] This disclosure provides a processing method executed by a UE, comprising: receiving configuration information, the configuration information including: RB indication information, indicating that the UE has the same precoded target number of RBs; receiving model information, wherein the model information includes an AI model corresponding to the target number of RBs; and determining the AI ​​model corresponding to the target number of RBs for channel estimation.

[0191] This step S81 may include:

[0192] Receive RRC signaling carrying configuration information; wherein, the RRC signaling is sent by the base station when it determines that the PRB bundling configuration for the UE is a semi-static PRB bundling configuration, or,

[0193] Receive configuration information sent via PDCCH, wherein the configuration information is sent by the base station when it determines that the PRB bundling configuration for the UE is dynamic PRB bundling configuration.

[0194] This disclosure provides an information processing method executed by a UE, which may include: receiving RRC signaling carrying configuration information; wherein the RRC signaling is sent when the base station determines that the PRB bundling configuration for the UE is a semi-static PRB bundling configuration, or receiving configuration information sent via PDCCH, wherein the configuration information is sent when the base station determines that the PRB bundling configuration for the UE is a dynamic PRB bundling configuration.

[0195] This disclosure provides an information processing method, executed by a UE, which may include:

[0196] When the RPB bundling configuration is set to dynamic RPB bundling, the receive time slot offset is used, where the time slot offset is used to adjust the time slot between the PDCCH and the corresponding PDSCH; and the time indicated by the time slot offset is greater than the transmission time of the AI ​​model.

[0197] Based on the time slot offset, it is determined whether the received AI model can be used for channel estimation.

[0198] Here, if the time slot offset is greater than or equal to the transmission time of the AI ​​model, it is determined that the AI ​​model can be used for channel estimation; or if the time slot offset is less than the transmission time of the AI ​​model, it is determined that the AI ​​model cannot be used for channel estimation.

[0199] This disclosure provides an information processing method executed by a UE, which may include: sending suggestion information, wherein the suggestion information includes at least one of the UE's computing power information, the UE's storage capacity information, and channel quality information; wherein the suggestion information is used to enable a base station to determine an AI model for the UE to perform channel estimation.

[0200] This disclosure provides an information processing method, executed by a UE, which may include: receiving request information sent by a base station; and sending suggestion information determined based on the request information to the base station. Here, the request information is used to instruct the UE to send suggestion information.

[0201] The above implementation methods can be referred to the description on the base station side for details, and will not be repeated here.

[0202] It should be noted that those skilled in the art will understand that the methods provided in the embodiments of this disclosure can be executed alone or together with some methods in the embodiments of this disclosure or some methods in related technologies.

[0203] To further explain any embodiment of this disclosure, a specific embodiment is provided below.

[0204] This disclosure provides an information processing method, executed by a communication device, which includes a base station or a UE; the method may include the following steps:

[0205] Step S91: Deploy model deployment information, including the AI ​​model, using the following two methods:

[0206] Method 1: Deploy AI models in advance;

[0207] The UE sends at least one of its storage capacity information, computing capacity information, and channel quality information to the base station; the base station determines an AI model with at least one number of RBs based on the UE's storage capacity information, computing capacity information, and channel quality information; the base station stores the correspondence between an RB number and an AI model as model deployment information; and sends the model deployment information to the UE.

[0208] Method 2: Deploy AI models on demand;

[0209] When the base station performs PRB bundling configuration on the UE, it queries the UE's model deployment information. If the base station determines that there is no AI model corresponding to the number of RBs in the UE's model deployment information, it sends the AI ​​model corresponding to the number of RBs to the UE.

[0210] For semi-static PRB bundling configuration, model information can be sent via RRC signaling, where the model information includes the AI ​​model;

[0211] For dynamic PRB bundling configurations, model information, including AI models, can be sent via PDCCH.

[0212] Step S92: For the semi-static PRB bundling configuration, the channel estimation configuration is as follows:

[0213] Case A: The number of RBs configured in the semi-static PRB bundling is a first-type value, such as "2" or "4":

[0214] The base station determines the AI ​​model corresponding to the number of RBs based on the number of RBs with the same precoding configuration;

[0215] The base station sends configuration information via RRC signaling. The configuration information includes: RB indication information and model indication information; wherein, the RB indication information indicates the number of RBs with the same precoding; and the model indication information indicates the AI ​​model corresponding to the number of RBs.

[0216] The base station queries the UE's model deployment information; if it determines that there is no AI model corresponding to the number of RBs in the UE's model deployment information, it sends the AI ​​model to the UE via RRC signaling.

[0217] In one embodiment, the number of identically precoded RBs in this configuration can be: the number of identically precoded RBs in the most recently configured configuration.

[0218] Case B: The number of RBs configured in the semi-static PRB bundling is a second-type value, such as "wideband"; Case B can be configured in the following two ways:

[0219] Method B1: The base station queries the UE's model deployment information, determines the AI ​​model from the model deployment information, sets the RB indication information to the target number of RBs corresponding to the AI ​​model, and sends configuration information via RRC signaling, wherein the configuration information includes RB indication information and model indication information;

[0220] Here, determining the AI ​​model from the model deployment information in method B1 can be based on at least one of the UE's storage capacity information, UE's computing capacity information, and channel quality information.

[0221] Here, method B1 can also be: if the number of RBs configured in the semi-static PRB bundling is the second type of value, the target number of RBs is determined based on at least one of the UE's computing power information, UE's storage power information, and channel quality information; configuration information is sent through RRC signaling, the configuration information including RB indication information and model indication information; wherein, the RB indication information indicates the target number of RBs; and the model indication information indicates the AI ​​model corresponding to the target number of RBs.

[0222] Method B2: The base station sends PRB bundling configuration information to the UE, which includes type information and value information. Based on the type information and value information, the UE determines the number of RBs in its semi-static PRB bundling configuration to be the second type value "wideband". The UE determines the AI ​​model for channel estimation based on at least one of the following: the UE's storage capacity information, the UE's computing capacity information, and the channel quality information.

[0223] Step S93: For dynamic PRB bundling configuration, the channel estimation configuration is as follows:

[0224] Case C: The number of RBs configured in the dynamic PRB bundling is a first-type value, such as "2" or "4":

[0225] The base station determines the AI ​​model corresponding to the number of RBs based on the number of RBs with the same precoding configured.

[0226] The base station queries the UE's model deployment information:

[0227] If the UE's model deployment information contains an AI model corresponding to the number of RBs, configuration information is sent via PDCCH. The configuration information includes: RB indication information and model indication information. The RB indication information indicates the number of RBs with the same precoding, and the model indication information indicates the AI ​​model corresponding to the number of RBs.

[0228] If the UE's model deployment information does not contain an AI model corresponding to the number of RBs, the base station queries the transmission time k of the AI ​​model and sends the AI ​​model to the UE. The base station adjusts the time slot offset between the PDCC and the corresponding PDSCH. The time slot offset indicates a time greater than k, and the RB indication information, model indication information, and time slot offset are sent to the UE through the PDCCH.

[0229] Here, the time slot offset can be a type of information in the PRB bundling configuration information.

[0230] Case D: The number of RBs configured in the dynamic PRB bundling is a second-type value, such as "wideband"; Case B can be in the following three ways:

[0231] Method D1: The base station queries the UE's model deployment information, determines the AI ​​model from the model deployment information, sets the RB indication information to the target RB number corresponding to the AI ​​model, and sends configuration information via PDCCH, wherein the configuration information includes RB indication information and model indication information;

[0232] Here, determining the AI ​​model from the model deployment information in method D1 can be based on at least one of the UE's storage capacity information, UE's computing capacity information, and channel quality information.

[0233] Here, method D1 can also be: if the number of RBs configured in the dynamic PRB bundling is the second type of value, the target number of RBs is determined based on at least one of the UE's computing power information, UE's storage power information, and channel quality information; configuration information is sent through PDCCH signaling, and the configuration information includes RB indication information and model indication information; wherein, the RB indication information indicates the target number of RBs; and the model indication information indicates the AI ​​model corresponding to the target number of RBs.

[0234] Method D2: The base station sends PRB bundling configuration information to the UE, which includes type information and value information. Based on the type information and value information, the UE determines the number of RBs in the dynamic PRB bundling configuration to be the second type value "wideband". The UE determines the AI ​​model for channel estimation based on at least one of the following: the UE's storage capacity information, the UE's computing capacity information, and the channel quality information.

[0235] Method D3: The base station sends a request message; and the UE reports a suggestion message based on the request message, which includes at least one of the following: the UE's computing power information, the UE's storage power information, and the channel quality information; and the AI ​​model is determined based on the suggestion message.

[0236] The base station queries the UE's model deployment information:

[0237] If the AI ​​model exists in the UE's model deployment information, configuration information is sent via PDCCH; the configuration information includes: RB indication information and model indication information;

[0238] If the AI ​​model is not present in the UE's model deployment information, the base station queries the transmission time k of the AI ​​model and sends the AI ​​model to the UE. The base station adjusts the time slot offset between the PDCC and the corresponding PDSCH, and the time slot offset indicates a time greater than k. The base station then sends the RB indication information, model indication information, and time slot offset to the UE through the PDCCH.

[0239] It should be noted that those skilled in the art will understand that the methods provided in the embodiments of this disclosure can be executed alone or together with some methods in the embodiments of this disclosure or some methods in related technologies.

[0240] like Figure 9 As shown, this disclosure provides an information processing apparatus applied to a base station, comprising:

[0241] The first transmitting module 41 is configured to transmit configuration information, wherein the configuration information includes: RB indication information, indicating that the UE has the same number of precoded RBs, and the number of RBs is used by the UE to determine the AI ​​model for channel estimation.

[0242] This disclosure provides an information processing apparatus applied to a base station, which may include: a first transmitting module 41 configured to transmit configuration information; wherein the configuration information includes: RB indication information, indicating that the UE has the same precoded target RB number, the target RB number being used by the UE to determine the AI ​​model for channel estimation.

[0243] In some embodiments, the configuration information includes: model indication information, indicating the AI ​​model adopted by the UE.

[0244] This disclosure provides an information processing apparatus applied to a base station, which may include: a first transmitting module 41 configured to transmit configuration information, wherein the configuration information includes: RB indication information and model indication information.

[0245] This disclosure provides an information processing apparatus applied to a base station, which may include: a first processing module configured to determine a target number of base stations (RBs) based on the number of base stations (RBs); and to determine an AI model corresponding to the target number of RBs based on the target number of RBs.

[0246] This disclosure provides an information processing apparatus applied to a base station, which may include: a first processing module configured to determine a target number of RBs based on the number of RBs configured by PRB bundling; and to determine an AI model corresponding to the target number of RBs based on the target number of RBs.

[0247] This disclosure provides an information processing apparatus applied to a base station, which may include: a first processing module configured to determine that the target number of RBs is equal to the number of RBs in response to the number of RBs being a first type of value.

[0248] This disclosure provides an information processing apparatus applied to a base station, which may include: a first processing module configured to determine that the target number of RBs is equal to the number of RBs in response to the PRB bundling configuration being a first type of value.

[0249] This disclosure provides an information processing apparatus applied to a base station, which may include: a first processing module configured to determine a target number of RBs based on at least one of the following in response to the number of RBs being a second type of value: the computing power information of the UE, the storage capacity information of the UE, the channel quality information, and the model deployment information of the UE.

[0250] This disclosure provides an information processing apparatus applied to a base station, which may include: a first processing module configured to determine a target number of RBs based on at least one of the following: UE computing power information, UE storage power information, channel quality information, and UE model deployment information, in response to a second type of value being configured for PRB bundling.

[0251] This disclosure provides an information processing apparatus applied to a base station, which may include: a first sending module 41 configured to send RRC signaling carrying configuration information based on a semi-static PRB bundling configuration of the UE.

[0252] This disclosure provides an information processing apparatus applied to a base station, which may include: a first sending module 41 configured to send configuration information via PDCCH based on the PRB bundling configuration of the UE as a dynamic PRB bundling configuration.

[0253] This disclosure provides an information processing apparatus applied to a base station, which may include: a first sending module 41 configured to send configuration information including RB indication information and model indication information in response to determining that an AI model corresponding to the target number of RBs exists in the UE based on UE model deployment information.

[0254] This disclosure provides an information processing apparatus applied to a base station, which may include: a first sending module 41 configured to send configuration information including at least RB indication information in response to determining, based on UE-based model deployment information, that there is no AI model in the UE corresponding to the target number of RBs.

[0255] This disclosure provides an information processing apparatus applied to a base station, which may include: a first sending module 41 configured to send model information to the UE in response to determining, based on UE-based model deployment information, that there is no AI model in the UE corresponding to the target number of RBs, wherein the model information includes: an AI model corresponding to the target number of RBs.

[0256] This disclosure provides an information processing apparatus applied to a base station, which may include:

[0257] The first processing module is configured to obtain the transmission time of the transmitted AI model in response to the PRB bundling configuration of the UE as a dynamic PRB bundling configuration.

[0258] The first transmitting module 41 is configured to send the time slot offset between the adjusted PDCCH and the corresponding PDSCH to the UE, wherein the time slot offset indicates a time longer than the transmission time.

[0259] This disclosure provides an information processing apparatus applied to a base station, which may include:

[0260] The first receiving module is configured to receive suggestion information, wherein the suggestion information includes at least one of the following: UE computing power information, UE storage capacity information, and channel quality information;

[0261] The first processing module is configured to determine the AI ​​model for channel estimation by the UE based on the suggestion information.

[0262] like Figure 10 As shown, this disclosure provides an information processing apparatus applied to a UE, comprising:

[0263] The second receiving module 61 is configured to receive configuration information, wherein the configuration information includes: RB indication information, indicating that the UE has the same number of precoded RBs;

[0264] The second processing module 62 is configured to determine the AI ​​model for channel estimation based on the number of RBs.

[0265] In some embodiments, the configuration information includes: model indication information, indicating the AI ​​model adopted by the UE.

[0266] This disclosure provides an information processing apparatus for a UE, which may include a second processing module 62 configured to determine the number of RBs based on PRB bundling configuration and perform channel estimation using an AI model.

[0267] This disclosure provides an information processing apparatus for a UE, which may include a second processing module 62 configured to determine an AI model based on model indication information corresponding to the number of RBs for channel estimation.

[0268] This disclosure provides an information processing apparatus applied to a UE, which may include: a second processing module 62 configured to determine an AI model corresponding to the number of RBs for channel estimation in response to the number of RBs being a first type of value.

[0269] This disclosure provides an information processing apparatus applied to a UE, which may include: a second processing module 62 configured to determine an AI model corresponding to the number of RBs for channel estimation in response to the PRB bundling configuration being a first type of value.

[0270] This disclosure provides an information processing apparatus applied to a UE, which may include: a second processing module 62 configured to determine an AI model for channel estimation based on at least one of the following: the number of RBs being a second type of value, in response to the UE's model deployment information, the UE's computing power information, the UE's storage power information, and channel quality information.

[0271] This disclosure provides an information processing apparatus applied to a UE, which may include: a second processing module 62 configured to determine an AI model for channel estimation based on at least one of the following: the number of RBs configured in PRB bundling is a second type value; and the AI ​​model is used to perform channel estimation in response to at least one of the UE's model deployment information, the UE's computing power information, the UE's storage power information, and channel quality information.

[0272] In one embodiment, the number of RBs includes: the target number of RBs.

[0273] This disclosure provides an information processing apparatus, applied to a UE, which may include:

[0274] The second receiving module 61 is configured to receive model information, wherein the model information includes: an AI model corresponding to the target number of RBs;

[0275] The second processing module 62 is configured to determine the AI ​​model corresponding to the target number of RBs for channel estimation.

[0276] This disclosure provides an information processing apparatus applied to a UE, which may include: a second receiving module 61 configured to receive RRC signaling carrying configuration information; wherein, the RRC signaling is sent by the base station when it determines that the PRB bundling configuration for the UE is a semi-static PRB bundling configuration.

[0277] This disclosure provides an information processing apparatus applied to a UE, which may include: a second receiving module 61 configured to receive configuration information sent via PDCCH, wherein the configuration information is sent when the base station determines that the PRB bundling configuration for the UE is a dynamic PRB bundling configuration.

[0278] This disclosure provides an information processing apparatus, applied to a UE, which may include:

[0279] The second receiving module 61 is configured to receive a timeslot offset in a dynamic PRB bundling configuration, wherein the timeslot offset is an adjustment of the timeslot between the PDCCH and the corresponding PDSCH; wherein the time indicated by the timeslot offset is greater than the transmission time of the AI ​​model.

[0280] The second processing module 62 is configured to determine whether the received AI model can be used for channel estimation based on the time slot offset.

[0281] This disclosure provides an information processing apparatus applied to a UE, which may include: a second transmitting module configured to transmit suggestion information, wherein the suggestion information includes at least one of the UE's computing power information, the UE's storage capacity information, and channel quality information; wherein the suggestion information is used to enable a base station to determine an AI model for the UE to perform channel estimation.

[0282] It should be noted that those skilled in the art will understand that the apparatus provided in the embodiments of this disclosure can be executed alone or together with some apparatus in the embodiments of this disclosure or some apparatus in related technologies.

[0283] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0284] This disclosure provides a communication device, including:

[0285] processor;

[0286] Memory used to store processor-executable instructions;

[0287] The processor is configured to implement the information processing method of any embodiment of this disclosure when running executable instructions.

[0288] In one embodiment, the communication device may be a base station or a UE.

[0289] The processor may include various types of storage media, which are non-transitory computer storage media that can continue to store information after the user equipment loses power.

[0290] The processor can connect to memory via a bus or similar means to read executable programs stored in memory, for example... Figures 2 to 8 At least one of the methods shown.

[0291] This disclosure also provides a computer storage medium storing a computer-executable program, which, when executed by a processor, implements the information processing method of any embodiment of this disclosure. For example, such as... Figures 2 to 8 At least one of the methods shown.

[0292] Regarding the apparatus or storage medium in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0293] Figure 11 This is a block diagram illustrating a user equipment 800 according to an exemplary embodiment. For example, user equipment 800 may be a mobile phone, computer, digital broadcast user equipment, messaging device, game console, tablet device, medical device, fitness equipment, personal digital assistant, etc.

[0294] Reference Figure 11 User equipment 800 may include one or more of the following components: processing component 802, memory 804, power supply component 806, multimedia component 808, audio component 810, input / output (I / O) interface 812, sensor component 814, and communication component 816.

[0295] Processing component 802 typically controls the overall operation of user equipment 800, such as operations associated with display, telephone calls, data communication, camera operation, and recording. Processing component 802 may include one or more processors 820 to execute instructions to perform all or part of the steps of the methods described above. Furthermore, processing component 802 may include one or more modules to facilitate interaction between processing component 802 and other components. For example, processing component 802 may include a multimedia module to facilitate interaction between multimedia component 808 and processing component 802.

[0296] Memory 804 is configured to store various types of data to support the operation of user equipment 800. Examples of this data include instructions for any application or method operating on user equipment 800, contact data, phonebook data, messages, pictures, videos, etc. Memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0297] Power supply component 806 provides power to various components of user equipment 800. Power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to user equipment 800.

[0298] Multimedia component 808 includes a screen that provides an output interface between the user equipment 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of the touch or swipe action but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 808 includes a front-facing camera and / or a rear-facing camera. When the user equipment 800 is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or the rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0299] Audio component 810 is configured to output and / or input audio signals. For example, audio component 810 includes a microphone (MIC) configured to receive external audio signals when user equipment 800 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 804 or transmitted via communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.

[0300] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0301] Sensor assembly 814 includes one or more sensors for providing status assessments of various aspects of user equipment 800. For example, sensor assembly 814 may detect the on / off state of user equipment 800, the relative positioning of components such as the display and keypad of user equipment 800, changes in position of user equipment 800 or a component of user equipment 800, the presence or absence of user contact with user equipment 800, orientation or acceleration / deceleration of user equipment 800, and temperature changes of user equipment 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 814 may also include an accelerometer, gyroscope, magnetometer, pressure sensor, or temperature sensor.

[0302] Communication component 816 is configured to facilitate wired or wireless communication between user equipment 800 and other devices. User equipment 800 can access wireless networks based on communication standards, such as WiFi, 4G, or 5G, or combinations thereof. In one exemplary embodiment, communication component 816 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 816 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0303] In an exemplary embodiment, the user equipment 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the methods described above.

[0304] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 804 including instructions, which can be executed by a processor 820 of a user device 800 to perform the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0305] like Figure 12 As shown, one embodiment of this disclosure illustrates the structure of a base station. For example, base station 900 can be provided as a network-side device. (Refer to...) Figure 12 The base station 900 includes a processing component 922, which further includes one or more processors, and memory resources represented by a memory 932 for storing instructions, such as application programs, that can be executed by the processing component 922. The application programs stored in the memory 932 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processing component 922 is configured to execute instructions to perform any of the methods described above applied to the base station.

[0306] Base station 900 may also include a power supply component 926 configured to perform power management of base station 900, a wired or wireless network interface 950 configured to connect base station 900 to a network, and an input / output (I / O) interface 958. Base station 900 can operate on an operating system stored in memory 932, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, or similar.

[0307] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the following claims.

[0308] It should be understood that the present invention is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. An information processing method, wherein, Performed by the base station, including: The target number of resource blocks (RBs) is determined based on the number of RBs. This determination includes one of the following: in response to the RBs being a first-type value, the target number of RBs is determined to be equal to the number of RBs; in response to the RBs being a second-type value, the target number of RBs is determined based on at least one of the following: the user equipment (UE)'s computing power information, the UE's storage capacity information, channel quality information, and the UE's model deployment information. Send configuration information, wherein the configuration information includes: resource block (RB) indication information, indicating that the user equipment (UE) has the same precoded number of target RBs; the number of target RBs is used by the UE to determine the artificial intelligence (AI) model for channel estimation.

2. The method based on claim 1, wherein, The method includes: Based on the target number of RBs, determine the AI ​​model corresponding to the target number of RBs.

3. The method according to claim 2, wherein, The configuration information also includes: model indication information, indicating the AI ​​model adopted by the UE.

4. The method according to claim 2 or 3, wherein, The configuration information to be sent includes: In response to determining, based on the model deployment information of the UE, that there exists an AI model in the UE corresponding to the target number of RBs, the configuration information including the RB indication information and the model indication information is sent; or, In response to determining, based on the model deployment information of the UE, that there is no AI model in the UE corresponding to the target number of RBs, the configuration information including at least the RB indication information is sent.

5. The method according to claim 4, wherein, The method further includes: In response to determining, based on the model deployment information of the UE, that there is no AI model in the UE corresponding to the target number of RBs, model information is sent to the UE; wherein, the model information includes: the AI ​​model corresponding to the target number of RBs.

6. The method according to claim 5, wherein, The method further includes: In response to the PRB bundling configuration of the UE being set to dynamic PRB bundling configuration, the transmission time of the AI ​​model is obtained; The time slot offset between the adjusted PDCCH and the corresponding Physical Downlink Shared Channel (PDSCH) is sent to the UE, wherein the time slot offset indicates a time greater than the transmission time.

7. The method according to any one of claims 1 to 3, 5 to 6, wherein, The configuration information to be sent includes: Based on the PRB bundling configuration of the UE being semi-static, Radio Resource Control (RRC) signaling carrying the configuration information is sent. or, Based on the PRB bundling configuration of the UE being a dynamic PRB bundling configuration, the configuration information is sent through the Physical Downlink Control Channel (PDCCH).

8. The method according to claim 1, wherein, The method includes: Receive suggestion information, wherein the suggestion information includes at least one of the UE's computing power information, the UE's storage capacity information, and channel quality information; Based on the suggested information, the AI ​​model for the UE to perform channel estimation is determined.

9. An information processing method, wherein, Performed by the user equipment (UE), including: Receive configuration information, wherein the configuration information includes: resource block (RB) indication information, indicating that the UE has the same number of precoded target RBs; Based on the target number of Resource Blocks (RBs), an artificial intelligence (AI) model is determined for channel estimation; wherein, determining the AI ​​model for channel estimation based on the target number of RBs includes one of the following: in response to the target number of RBs being a first type of value, determining the AI ​​model corresponding to the target number of RBs for channel estimation; in response to the target number of RBs being a second type of value, determining the AI ​​model for channel estimation based on at least one of the UE's model deployment information, the UE's computing power information, the UE's storage power information, and channel quality information.

10. The method according to claim 9, wherein, The configuration information also includes: model indication information, indicating the AI ​​model adopted by the UE; The step of determining the AI ​​model for channel estimation based on the target number of RBs includes: Channel estimation is performed based on the AI ​​model indicated by the model indication information corresponding to the target number of RBs.

11. The method according to claim 9 or 10, wherein, The method further includes: Receive model information, wherein the model information includes: the AI ​​model corresponding to the target number of RBs.

12. The method according to claim 9 or 10, wherein, The received configuration information includes: The system receives Radio Resource Control (RRC) signaling carrying the configuration information; wherein the RRC signaling is sent by the base station when it determines that the PRB bundling configuration for the UE is a semi-static PRB bundling configuration. or, The configuration information is received via the Physical Downlink Control Channel (PDCCH), wherein the configuration information is sent by the base station when it determines that the PRB bundling configuration for the UE is a dynamic PRB bundling configuration.

13. The method according to claim 12, wherein, The method includes: When the RPB bundling configuration is set to dynamic RPB bundling, a timeslot offset is received, wherein the timeslot offset is used to adjust the timeslot between the PDCCH and the corresponding PDSCH; wherein the time indicated by the timeslot offset is greater than the transmission time of the AI ​​model. Based on the time slot offset, it is determined whether the received AI model can be used for channel estimation.

14. The method according to claim 9 or 10, wherein, The method includes: Sending suggestion information, wherein the suggestion information includes at least one of the UE's computing power information, the UE's storage capacity information, and channel quality information; wherein the suggestion information is used to enable the base station to determine the AI ​​model for the UE to perform channel estimation.

15. An information processing apparatus, wherein, Applied to base stations, including: The first processing module is configured to determine a target number of resource blocks (RBs) based on the number of RBs; wherein, the first processing module is specifically configured to: determine that the target number of RBs is equal to the number of RBs in response to the number of RBs being a first type of value; or determine the target number of RBs based on at least one of the following: the computing power information of the user equipment (UE), the storage capacity information of the UE, the channel quality information, and the model deployment information of the UE; The first transmitting module is configured to transmit configuration information, wherein the configuration information includes: resource block (RB) indication information, indicating that the user equipment (UE) has the same precoded number of target RBs, and the number of target RBs is used by the UE to determine the artificial intelligence (AI) model for channel estimation.

16. A processing apparatus, wherein, Applied to User Equipment (UE), including: The second receiving module is configured to receive configuration information, wherein the configuration information includes: resource block (RB) indication information, indicating that the UE has the same number of precoded target RBs; The second processing module is configured to determine an artificial intelligence (AI) model for channel estimation based on the target number of redundancies (RBs); specifically, the second processing module is configured to: determine the AI ​​model corresponding to the target number of RBs for channel estimation in response to the target number of RBs being a first type of value; or determine the AI ​​model for channel estimation based on at least one of the following: the model deployment information of the UE, the computing power information of the UE, the storage capacity information of the UE, and the channel quality information of the UE.

17. A communication device, wherein, The communication device includes: processor; Memory used to store the processor's executable instructions; The processor is configured to implement the information processing method according to any one of claims 1 to 8 or claims 9 to 14 when running the executable instructions.

18. A computer storage medium, wherein, The computer storage medium stores a computer-executable program, which, when executed by a processor, implements the information processing method according to any one of claims 1 to 8 or claims 9 to 14.

Images