Information processing method and device, communication equipment and storage medium

Abstract

The embodiment of the invention provides an information processing method and device, communication equipment and a storage medium. The information processing method executed by a base station may include determining whether a terminal supports channel state information-reference signal (CSI-RS) feedback information compression of at least one artificial intelligence (AI) model; and configuring a CSI-RS according to whether the terminal supports CSI-RS feedback information compression of at least one AI model or not.

Description

[0001] This application is filed on March 14, 2022, with application number 202280000750.1 and invention name “Information processing method and device,

[0002] A divisional application for the invention patent application for "communication device and storage medium". Technical Field

[0003] The present disclosure relates to the field of wireless communication technology but is not limited to the field of wireless communication technology, and in particular to an information processing method and apparatus, a communication device and a storage medium. Background Art

[0004] Channel state information can describe the current channel environment. In a mobile communication network, the base station transmits a channel state information-reference signal (CSI-RS), and the terminal evaluates the channel state information and feeds it back to the base station in a quantitative manner. By introducing channel state information (CSI) feedback information, the base station side can make timely adjustments when sending the channel state information reference signal, thereby reducing the bit error rate at the terminal and obtaining the optimal received signal. Summary of the invention

[0005] Embodiments of the present disclosure provide an information processing method and apparatus, a communication device, and a storage medium.

[0006] A first aspect of the present disclosure provides an information processing method, which is executed by a base station. The method includes:

[0007] Determining whether the terminal supports CSI-RS feedback information compression of at least one artificial intelligence (AI) model;

[0008] The CSI-RS is configured according to whether the terminal supports CSI-RS feedback information compression of at least one AI model.

[0009] A second aspect of the present disclosure provides an information processing method, which is executed by a terminal. The method includes:

[0010] Send second information, wherein the second information is used for the base station to determine whether the terminal supports compression of CSI-RS feedback information by at least one AI model.

[0011] A third aspect of the embodiments of the present disclosure provides an information processing device, wherein the method includes:

[0012] A determination module, used to determine whether the terminal supports channel state information-reference signal CSI-RS feedback information compression of at least one artificial intelligence AI model;

[0013] A configuration module is used to configure CSI-RS according to whether the terminal supports CSI-RS feedback information compression of at least one AI model.

[0014] A fourth aspect of the present disclosure provides an information processing device, the device comprising:

[0015] The sending module is configured to send second information, wherein the second information is used for the base station to determine whether the terminal supports compression of CSI-RS feedback information by at least one AI model.

[0016] A fifth aspect of an embodiment of the present disclosure provides a communication device, comprising a processor, a transceiver, a memory, and an executable program stored in the memory and capable of being run by the processor, wherein the processor executes the information processing method provided in the first aspect or the second aspect when running the executable program.

[0017] A sixth aspect of the embodiments of the present disclosure provides a computer storage medium, which stores an executable program; after the executable program is executed by a processor, it can implement the information processing method provided in the first aspect or the second aspect.

[0018] In the technical solution provided by the embodiment of the present disclosure, the base station will configure the CSI-RS for the corresponding terminal according to whether the terminal supports at least one AI model to compress the CSI-RS feedback information. In this way, the generated CSI-RS configuration is adapted to the AI ​​capability of the terminal, thereby reducing the UE measurement anomaly caused by the incompatible CSI-RS configuration. It should be understood that the above general description and the detailed description below are only exemplary and explanatory, and cannot limit the embodiments of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present invention and, together with the description, serve to explain the principles of the embodiments of the present invention.

[0020] Figure 1 is a schematic structural diagram of a wireless communication system according to an exemplary embodiment;

[0021] Figure 2 is a flowchart of an information processing method according to an exemplary embodiment;

[0022] Figure 3 is a flowchart of an information processing method according to an exemplary embodiment;

[0023] Figure 4 is a flowchart of an information processing method according to an exemplary embodiment;

[0024] Figure 5 is a flowchart of an information processing method according to an exemplary embodiment;

[0025] Figure 6 is a flowchart of an information processing method according to an exemplary embodiment;

[0026] Fig. 7A is a flowchart of an information processing method according to an exemplary embodiment;

[0027] Figure 7B is a flowchart of an information processing method according to an exemplary embodiment

[0028] Figure 8 is a flowchart of an information processing method according to an exemplary embodiment;

[0029] Fig. 9 is a flowchart of an information processing method according to an exemplary embodiment;

[0030] Fig.10 is a flowchart of an information processing method according to an exemplary embodiment;

[0031] Fig.11 is a flowchart of an information processing method according to an exemplary embodiment;

[0032] Fig.12 is a flowchart of an information processing method according to an exemplary embodiment;

[0033] Fig.13 is a flowchart of an information processing method according to an exemplary embodiment;

[0034] Fig.14 is a flowchart of an information processing method according to an exemplary embodiment;

[0035] Fig.15 is a schematic structural diagram of an information processing device according to an exemplary embodiment;

[0036] Fig.16 is a schematic structural diagram of an information processing device according to an exemplary embodiment;

[0037] Fig.17 is a schematic diagram of the structure of a terminal according to an exemplary embodiment;

[0038] Fig.18 The diagram is a schematic structural diagram of a communication device according to an exemplary embodiment. DETAILED DESCRIPTION

[0039] Here, exemplary embodiments will be described in detail, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the embodiments of the present invention. Instead, they are only examples of devices and methods consistent with some aspects of the embodiments of the present invention.

[0040] The terms used in the embodiments of the present disclosure are only for the purpose of describing specific embodiments and are not intended to limit the embodiments of the present disclosure. The singular forms of "a", "an", "the" and "the" used in the present disclosure are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in this article refers to and includes any or all possible combinations of one or more associated listed items.

[0041] It should be understood that although the terms first, second, third, etc. may be used to describe various information in the disclosed embodiments, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the disclosed embodiments, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0042] Please refer to Figure 1 , which shows a schematic diagram of the structure of a wireless communication system provided by an embodiment of the present disclosure. Figure 1 As shown, the wireless communication system is a communication system based on cellular mobile communication technology, and the wireless communication system may include: a plurality of terminals 11 and a plurality of access devices 12 .

[0043] Among them, the terminal 11 can be a device that provides voice and / or data connectivity to the user. The terminal 11 can communicate with one or more core networks via a radio access network (RAN). The terminal 11 can be an Internet of Things terminal, such as a sensor device, a mobile phone (or a "cellular" phone), and a computer with an Internet of Things terminal. For example, it can be a fixed, portable, pocket-sized, handheld, computer-built-in or vehicle-mounted device. For example, a station (STA), a subscriber unit, a subscriber station, a mobile station, a mobile station, a remote station, an access point, a remote terminal, an access terminal, a user terminal, a user agent, a user device, or a user terminal (user equipment, terminal). Alternatively, the terminal 11 can also be a device of an unmanned aerial vehicle. Alternatively, the terminal 11 can also be a vehicle-mounted device, for example, it can be a driving computer with wireless communication function, or a wireless communication device connected to an external driving computer. Alternatively, the terminal 11 may also be a roadside device, for example, a street lamp, a signal lamp or other roadside device with a wireless communication function.

[0044] The access device 12 may be a network-side device in a wireless communication system. The wireless communication system may be a fourth generation mobile communication technology (4G) system, also known as a long term evolution (LTE) system; or, the wireless communication system may be a 5G system, also known as a new radio (NR) system or a 5G NR system. Alternatively, the wireless communication system may be the next generation system of the 5G system. The access network in the 5G system may be referred to as NG-RAN (New Generation-Radio Access Network). Alternatively, an MTC system.

[0045] Among them, the access device 12 can be an evolved access device (eNB) adopted in a 4G system. Alternatively, the access device 12 can also be an access device (gNB) adopting a centralized distributed architecture in a 5G system. When the access device 12 adopts a centralized distributed architecture, it usually includes a centralized unit (CU) and at least two distributed units (DU). The centralized unit is provided with a protocol stack of a packet data convergence protocol (PDCP) layer, a radio link layer control protocol (RLC) layer, and a media access control (MAC) layer; the distributed unit is provided with a physical (Physical, PHY) layer protocol stack. The specific implementation method of the access device 12 is not limited in the embodiment of the present disclosure.

[0046] A wireless connection can be established between the access device 12 and the terminal 11 through 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, for example, the wireless air interface is a new air interface; or, the wireless air interface can also be a wireless air interface based on the next generation mobile communication network technology standard of 5G.

[0047] like Figure 2 As shown, an embodiment of the present disclosure provides an information processing method, which is executed by a network side device, and the method includes:

[0048] S110: Determine whether the terminal supports channel state information-reference signal CSI-RS feedback information processing based on at least one artificial intelligence AI model;

[0049] S120: Configure a CSI-RS for the terminal according to whether the terminal supports CSI-RS feedback information processing based on at least one AI model.

[0050] In the embodiments of the present disclosure, the network side device may be a base station, which may be an evolved base station (eNB) and / or a next generation base station (gNB), or a base station of any generation of communication system. Of course, the network side device is not limited to a base station, but may also be any device in the network, which is not limited here.

[0051] The base station transmits CSI-RS, the terminal receives CSI-RS, and the terminal generates CSI-RS feedback information according to its reception status of CSI-RS. That is, the CSI-RS feedback information can be used by the network side device to determine the reception status of the CSI-RS of the terminal, for example, whether the CSI-RS on the corresponding transmission resource block is received and / or the reception power of the CSI-RS by the terminal, etc.

[0052] In some embodiments, the data volume of the CSI-RS feedback information may be relatively large. In some cases, the terminal may only send part of the CSI-RS feedback information to the network side device. In some cases, the terminal may use an AI model to process the CSI-RS feedback information, and the terminal reports the processed CSI-RS feedback information. After the processed CSI-RS feedback information is processed accordingly by the network side device (such as a base station), the complete CSI-RS feedback information of the terminal can be obtained.

[0053] In one implementation, the processing of CSI-RS feedback information using the AI ​​model may be: the terminal compresses the CSI-RS feedback information using the AI ​​model. Based on this, the terminal reports the compressed CSI-RS feedback information, and the compressed CSI-RS feedback information is decompressed by the base station accordingly to obtain the complete CSI-RS feedback information of the terminal.

[0054] However, using AI models to process CSI-RS feedback information usually requires at least the terminal to have AI computing capabilities. For example, if the terminal includes an AI chip, then the terminal has AI computing capabilities. Different AI chips have different AI computing capabilities, and different AI models have different computing capability requirements. Therefore, some terminals may support processing CSI-RS feedback information through all AI models, some terminals may only support processing CSI-RS information through some AI models, and some terminals do not support the use of AI models to process CSI-RS feedback information at all.

[0055] In the following examples, the use of the AI ​​model to compress CSI-RS feedback information is used as an example, but those skilled in the art can understand that the use of the AI ​​model to process CSI-RS feedback information may also include other operations, which will not be repeated here.

[0056] In the disclosed embodiment, the base station and other network-side devices will first determine whether the terminal supports CSI-RS feedback information processing based on at least one AI model. Based on the determination result, a CSI-RS configuration for the UE is generated, so that the generated CSI-RS configuration can be ensured to be compatible with whether the UE supports the compression of CSI-RS feedback information by the AI ​​model, thereby reducing UE measurement anomalies caused by incompatible CSI-RS configurations.

[0057] The generated CSI-RS configuration may be sent to the terminal via an RRC message or a MAC CE.

[0058] The present disclosure provides an information processing method, which is executed by a network side device, and the method includes:

[0059] In response to determining that the terminal supports CSI-RS feedback information processing based on the AI ​​model, a CSI-RS used by the terminal is determined, wherein the CSI-RS corresponds to the AI ​​model supported by the terminal.

[0060] like Figure 3 As shown, an embodiment of the present disclosure provides an information processing method, which is executed by a network side device, and the method includes:

[0061] S310: Sending complexity information of the AI ​​model to the terminal;

[0062] S320: Receive first information provided by the terminal according to the complexity information;

[0063] S330: Determine, according to the first information, whether the terminal supports CSI-RS feedback information processing based on at least one AI model;

[0064] S340: Configure the CSI-RS according to whether the terminal processes CSI-RS feedback information based on support for at least one AI model.

[0065] In one implementation, the processing of CSI-RS feedback information using the AI ​​model may be: the terminal compresses the CSI-RS feedback information using the AI ​​model. Based on this, the terminal reports compressed CSI-RS feedback information, and the compressed CSI-RS feedback information is decompressed by the network side device (such as a base station) to obtain the complete CSI-RS feedback information of the terminal. In the following examples, the compression of CSI-RS feedback information using the AI ​​model is used as an example, but those skilled in the art can understand that the processing of CSI-RS feedback information using the AI ​​model may also include other operations, which will not be repeated here.

[0066] In the disclosed embodiment, the network side device will send the complexity information of the AI ​​model to the terminal. After the complexity information is sent to the terminal, the terminal can determine whether to support the compression of CSI-RS feedback information using the corresponding AI model based on its own AI capabilities. Of course, the network side device and the terminal can also determine the candidate AI model determined by the communication protocol, which will not be repeated here.

[0067] The complexity information may be sent by the base station to the terminal through an RRC message or a MAC CE.

[0068] The first information may be various information used by network-side devices (such as base stations) to determine whether the terminal supports AI model compression of CSI-RS feedback information, or the first information may be used by the terminal to determine which AI model compression CSI-RS feedback information.

[0069] In this way, it is actually up to the terminal to determine whether to support AI model compression of CSI-RS feedback information and inform the base station.

[0070] In some embodiments, the first information may explicitly indicate whether the terminal supports AI model compression of CSI-RS feedback information or which AI model compression of CSI-RS feedback information is supported.

[0071] In some other embodiments, the first information may also implicitly indicate whether the terminal supports AI model compression of CSI-RS feedback information and / or which AI model compression of CSI-RS feedback information is supported.

[0072] In some embodiments, the first information indicating that the terminal supports CSI-RS feedback information compression of at least one AI model includes at least one of the following parameters:

[0073] A model identifier, indicating the AI ​​model supported by the terminal for CSI-RS feedback information compression;

[0074] The CSI calculation duration indicates the duration required for the terminal to compress the CSI-RS feedback information using the AI ​​model identified by the model.

[0075] Of course, the CSI calculation duration can be the duration itself or a parameter used to determine the CSI calculation duration; for example, it can be the computing power of the AI ​​model or the computing power of the terminal, etc. In the embodiment of the present disclosure, the model identifier refers to the AI ​​model supported by the terminal.

[0076] In other embodiments, the model identifier may also indicate an AI model that is not supported by the terminal.

[0077] The CSI calculation duration can be: the duration required for the terminal to compress the CSI-RS feedback information using the corresponding AI model. If the CSI calculation duration is greater than the maximum duration allowed by the base station, even if the terminal supports the AI ​​model, the network-side device may not configure the terminal to use the AI ​​model to compress the CSI-RS feedback information due to timeout.

[0078] In the disclosed embodiment, the first information is equivalent to implicitly indicating whether the terminal supports AI model compression of CSI-RS feedback information. If the first information does not carry any model identifier or the terminal does not send the first information, it is equivalent to indicating that the terminal does not support any AI model compression of CSI-RS feedback information. If the first information carries at least one model identifier, it means that the terminal supports at least one AI model compression of CSI-RS feedback information.

[0079] In some embodiments, the first information indicating that the terminal does not support at least one AI model for compression of CSI-RS information feedback indicates that: CSI-RS feedback information adopts a partial reporting method.

[0080] If the first information indicates that the terminal will send CSI-RS feedback information to the base station by partially reporting the CSI-RS feedback information, it is equivalent to implicitly indicating that the terminal does not support AI model compression of CSI-RS feedback information or the terminal does not expect to use AI model compression of CSI-RS feedback information.

[0081] In some other embodiments, the first information may include: a bit specifically indicating whether the terminal supports AI model compression of CSI-RS feedback information.

[0082] In some other embodiments, the first information may include a bit map, which may include N bits, N≥1, and each bit corresponds to an AI model; wherein one bit in the bit map is used to indicate whether the terminal supports the corresponding AI model to compress CSI-RS feedback information.

[0083] In some other embodiments, the first information may include a bit map, the bits of the bit map may correspond to 2N values, and each value corresponds to an AI model.

[0084] In some embodiments, the complexity information indicates at least one of the following:

[0085] The total number of floating-point operations corresponding to the AI ​​model, wherein the total number of floating-point operations and the maximum allowed value of the CSI calculation duration are used together by the terminal to determine whether to support CSI-RS feedback information compression of the corresponding AI model;

[0086] A first ratio of the complexity of the corresponding AI model to the complexity of the baseline AI model, wherein the first ratio is used for the terminal to determine whether to support CSI-RS feedback information compression of the corresponding AI model in combination with the terminal AI capability and the complexity of the baseline AI model.

[0087] The baseline AI model here may be any one of a plurality of AI models for CSI-RS feedback information compression, for example, an AI model specified by a base station or a terminal. The complexity of the baseline AI model may be an AI model known to both the base station and the UE.

[0088] In some embodiments, the baseline AI model may be the AI ​​model with the lowest complexity or the highest complexity among multiple AI models supporting CSI-RS feedback information compression. In this way, the value range of the first ratio can be limited to a specific range, thereby reducing the bit overhead of indicating the first ratio.

[0089] In some embodiments, the complexity information can directly indicate the total number of floating-point operations of the corresponding AI model. After receiving it, the terminal can determine whether it supports the use of the corresponding AI model to compress CSI-RS feedback information based on the maximum allowable value of the CSI calculation time configured by the base station or the maximum allowable value agreed upon by the protocol.

[0090] In other embodiments, in order to reduce signaling overhead, the complexity information is represented by a ratio between the complexity of the corresponding AI model and the baseline AI model. The terminal indicates the total number of floating-point operations of the baseline AI model in advance, so after receiving the first ratio, the terminal can also determine whether it supports the corresponding AI model to compress the CSI-RS feedback information.

[0091] like Figure 4 As shown, the embodiment of the present disclosure provides an information processing method, which is executed by a network side device, and the method includes:

[0092] S410: Receive AI capability information sent by the terminal;

[0093] S420: Determine, according to the AI ​​capability information, whether the terminal supports CSI-RS feedback information compression of at least one AI model.

[0094] S430: Configure the CSI-RS according to whether the terminal supports CSI-RS feedback information compression of at least one AI model.

[0095] In the disclosed embodiment, the base station and other network side devices receive the AI ​​capability information sent by the terminal. The base station and other network side devices combine the AI ​​capability information of the terminal and the complexity information of each AI model to determine whether the terminal supports the AI ​​model to compress the CSI-RS feedback information, or which AI model to compress the CSI-RS feedback information the terminal supports.

[0096] In some embodiments, the AI ​​capability information indicates at least one of the following:

[0097] Whether the terminal has AI capabilities;

[0098] performance parameters of the terminal.

[0099] The performance parameters of the terminal may include at least one of the following parameters:

[0100] the maximum AI capability of the terminal;

[0101] The terminal supports the number of floating-point operations per unit time (e.g., per second);

[0102] The processing capabilities supported by the terminal;

[0103] The number of floating-point operations supported by the terminal within the maximum allowed value of the CSI calculation duration;

[0104] The second ratio indicates a ratio between the complexity of the terminal AI capability and the baseline AI model.

[0105] Of course, the performance parameters can also be characterized by other parameters, which will not be elaborated here.

[0106] In some embodiments, the AI ​​capability information may at least indicate whether the terminal has AI capability. If the terminal does not have AI capability, the AI ​​capability information of the terminal will not carry the number of floating-point operations per unit time (e.g., per second) supported by the terminal, or the total number of floating-point operations that can be performed within the maximum allowed value of the CSI calculation duration.

[0107] In some embodiments, in order to reduce signaling bit overhead, the second ratio is used to indirectly indicate the AI ​​capability of the terminal. The larger the second ratio is, the stronger the AI ​​capability of the terminal is. If the second ratio is 0, it can be considered that the terminal does not have AI capability.

[0108] If the AI ​​capability information indicates that the number of floating-point operations supported by the terminal within the maximum allowed value of the CSI calculation duration is 0, it means that the terminal does not have AI capability. If the number of floating-point operations supported within the maximum allowed value of the CSI calculation duration reported by the terminal is lower than the total number of floating-point operations of any AI model, it also means that the terminal does not support any AI model for compression of CSI-RS feedback information. If the number of floating-point operations supported within the maximum allowed value of the CSI calculation duration reported by the terminal is greater than or equal to the total number of floating-point operations of at least one AI model, it means that at least one AI model of the terminal compresses the CSI-RS feedback information.

[0109] When the base station receives the AI ​​capability information reported by the terminal, it will determine whether the corresponding terminal supports the AI ​​model to compress the CSI-RS feedback information.

[0110] In some embodiments, configuring the CSI-RS according to whether the terminal supports CSI-RS feedback information compression of at least one AI model includes:

[0111] According to whether the terminal supports CSI-RS feedback information compression of at least one AI model, configuring a type of CSI-RS feedback information reported by the terminal;

[0112] When the terminal supports CSI-RS feedback information compression based on at least one AI model, determine the CSI calculation duration when the CSI-RS feedback information is compressed using the AI ​​model supported by the terminal, and configure the period of the CSI-RS.

[0113] The types of CSI-RS feedback information reported here may include at least the following two types:

[0114] Report the compressed information of CSI-RS feedback information compressed by the AI ​​model;

[0115] Report the CSI-RS feedback information generated by the terminal.

[0116] Of course, the type of the reported CSI-RS feedback information may also be other types, which will not be listed here one by one.

[0117] If the terminal supports AI model compression of CSI-RS feedback information and the CSI calculation duration is less than the maximum allowed value, the network side device determines the CSI calculation duration required for the terminal to compress the CSI-RS feedback information using the corresponding AI model to configure the CSI-RS period.

[0118] Exemplarily, the CSI calculation duration is positively correlated with the period of the CSI-RS.

[0119] In some embodiments, the network side device may also determine the measurement duration of the CSI-RS according to the CSI calculation duration. The measurement duration may be the duration of measuring the CSI-RS in a CSI-RS cycle.

[0120] like Figure 5 As shown, the embodiment of the present disclosure provides an information processing method, which is executed by a terminal, and the method includes:

[0121] S510: Send second information, wherein the second information is used for the network side device to determine whether the terminal supports compression of CSI-RS feedback information based on at least one AI model.

[0122] In the disclosed embodiment, an information processing method is provided, in which a terminal sends a second information to a base station, and the second information can be used by a network side device to determine whether at least one AI model can be used to compress CSI-RS feedback information. In this way, the network side device can know whether the terminal supports the use of at least one AI model to compress CSI-RS feedback information, and then facilitate the network side device to configure CSI-RS for whether the terminal supports the use of an AI model or which AI model to use to compress CSI-RS feedback information, so that the CSI-RS configuration generated by the base station is more in line with the capabilities of the terminal.

[0123] like Figure 6 As shown, the embodiment of the present disclosure provides an information processing method, which is executed by a terminal, and the method includes:

[0124] S610: Sending AI capability information indicating the AI ​​capability of the terminal to a network side device.

[0125] In some embodiments, the AI ​​capability information may be a type of the aforementioned second information, or may be independent of the second information.

[0126] By reporting the AI ​​capability information of the terminal, the network-side device can determine whether the terminal supports the use of the AI ​​model to compress the CSI-RS feedback information, and then generate the CSI-RS configuration for the terminal.

[0127] Exemplarily, the AI ​​capability information indicates at least one of the following:

[0128] Whether the terminal has AI capabilities;

[0129] performance parameters of the terminal.

[0130] The performance parameters of the terminal may include at least one of the following parameters:

[0131] the maximum AI capability of the terminal;

[0132] The terminal supports the number of floating-point operations per unit time (e.g., per second);

[0133] The processing capabilities supported by the terminal;

[0134] The number of floating-point operations supported by the terminal within the maximum allowed value of the CSI calculation duration;

[0135] The second ratio indicates a ratio between the complexity of the terminal AI capability and the baseline AI model.

[0136] Of course, the performance parameters can also be characterized by other parameters, which will not be elaborated here.

[0137] In some embodiments, the AI ​​capability information may at least indicate whether the terminal has AI capability. If the terminal does not have AI capability, the AI ​​capability information of the terminal will not carry the number of floating-point operations per unit time (e.g., per second) supported by the terminal, or the total number of floating-point operations that can be performed within the maximum allowed value of the CSI calculation duration.

[0138] If the AI ​​capability information indicates that the number of floating-point operations supported by the terminal within the maximum allowed value of the CSI calculation duration is 0, it means that the terminal does not have AI capability. If the number of floating-point operations supported within the maximum allowed value of the CSI calculation duration reported by the terminal is lower than the total number of floating-point operations of any AI model, it also means that the terminal does not support any AI model for compression of CSI-RS feedback information. If the number of floating-point operations supported within the maximum allowed value of the CSI calculation duration reported by the terminal is greater than or equal to the total number of floating-point operations of at least one AI model, it means that at least one AI model of the terminal compresses the CSI-RS feedback information.

[0139] In some embodiments, in order to reduce signaling bit overhead, the second ratio is used to indirectly indicate the AI ​​capability of the terminal. The larger the second ratio is, the stronger the AI ​​capability of the terminal is. If the second ratio is 0, it can be considered that the terminal does not have AI capability.

[0140] When the base station receives the AI ​​capability information reported by the terminal, it will determine whether the corresponding terminal supports the AI ​​model to compress the CSI-RS feedback information.

[0141] like Fig. 7A As shown, the embodiment of the present disclosure provides an information processing method, which is executed by a terminal, and the method includes:

[0142] S710A: Send first information to the network side device, wherein the first information is used to indicate whether the terminal supports compression of CSI-RS feedback information based on at least one AI model.

[0143] The first information may be a type of the aforementioned second information.

[0144] The first information may be generated after the terminal determines whether it supports compression of CSI-RS feedback information based on any AI model according to its own AI capability and the complexity of each AI model.

[0145] The first information may be various information used by a network side device (eg, a base station) to determine whether the terminal supports AI model compression of CSI-RS feedback information, or the terminal determines which AI model compresses CSI-RS feedback information.

[0146] In some embodiments, the first information may explicitly or implicitly indicate whether the terminal supports AI model compression of CSI-RS feedback information or which AI model compression of CSI-RS feedback information is supported.

[0147] In some embodiments, the first information indicating that the terminal supports CSI-RS feedback information compression based on at least one AI model includes:

[0148] A model identifier, indicating the AI ​​model supported by the terminal for CSI-RS feedback information compression;

[0149] The CSI calculation duration indicates the duration required for the terminal to compress the CSI-RS feedback information using the AI ​​model identified by the model.

[0150] Of course, the CSI calculation duration can be the duration itself or a parameter used to determine the CSI calculation duration; for example, it can be the computing power of the AI ​​model or the computing power of the terminal.

[0151] In the embodiment of the present disclosure, the model identifier refers to the AI ​​model supported by the terminal.

[0152] In other embodiments, the model identifier may also indicate an AI model that is not supported by the terminal.

[0153] The CSI calculation duration is: the duration required for the terminal to compress the CSI-RS feedback information using the corresponding AI model. If the CSI calculation duration is greater than the maximum duration allowed by the base station, even if the terminal supports the AI ​​model, the base station may not configure the terminal to use the AI ​​model to compress the CSI-RS feedback information due to timeout.

[0154] In the disclosed embodiment, the first information is equivalent to implicitly indicating whether the terminal supports AI model compression of CSI-RS feedback information. If the first information does not carry any model identifier or the terminal does not send the first information, it is equivalent to indicating that the terminal does not support any AI model compression of CSI-RS feedback information. If the first information carries at least one model identifier, it means that the terminal supports at least one AI model compression of CSI-RS feedback information.

[0155] In some embodiments, it indicates that the terminal does not support the first information indication: CSI-RS feedback information adopts a partial reporting method.

[0156] If the first information indicates that the terminal will send CSI-RS feedback information to the base station by partially reporting the CSI-RS feedback information, it is equivalent to implicitly indicating that the terminal does not support AI model compression of CSI-RS feedback information or the terminal does not expect to use AI model compression of CSI-RS feedback information.

[0157] In some other embodiments, the first information may include: a bit specifically indicating whether the terminal supports AI model compression of CSI-RS feedback information. In some other embodiments, the first information may include a bitmap, the bitmap may include N bits, N≥1, each bit corresponds to an AI model; wherein one bit in the bitmap is used to indicate whether the terminal supports the corresponding AI model compression of CSI-RS feedback information. Or the first information may include a bitmap, the bits of which may correspond to 2 N Each value corresponds to an AI model.

[0158] In some embodiments, Figure 7B As shown, the method also includes:

[0159] S710B: receiving complexity information of the AI ​​model;

[0160] S720B: Send first information to a base station according to the complexity information of the AI ​​model and the AI ​​capability of the terminal.

[0161] In an embodiment of the present disclosure, the first information is determined based on complexity information of the AI ​​model received from the network side and its own AI capability.

[0162] In other embodiments, the complexity information of the AI ​​model may also be determined by the terminal according to a protocol agreement or other methods.

[0163] In summary, in the embodiments of the present disclosure, the first information is not directly the AI ​​capability information of the terminal's AI capability, but is generated based on the complexity information of the AI ​​model and the AI ​​capability of the terminal and sent to the base station.

[0164] In some embodiments, the sending the first information to the base station according to the complexity information of the AI ​​model and the AI ​​capability of the terminal includes at least one of the following:

[0165] When determining, according to the complexity information of the AI ​​model and the AI ​​capability of the terminal, that the terminal supports compression of the CSI-RS feedback information by an AI model, sending, to the base station, the first information indicating support for compression of the CSI-RS feedback information of at least one AI model;

[0166] When determining, according to the complexity information of the AI ​​model and the AI ​​capability of the terminal, that the terminal supports multiple AI models for compressing the CSI-RS feedback information, selecting an AI model supported by the terminal according to a resource scheduling situation of the terminal to indicate to the base station the first information supporting CSI-RS feedback information compression of an AI model;

[0167] When it is determined according to the complexity information of the AI ​​model and the AI ​​capability of the terminal that the terminal does not support the AI ​​model for compressing the CSI-RS feedback information, the first information indicating that the terminal does not support at least one AI model for compressing the CSI-RS information feedback is sent to the base station.

[0168] In some cases, the terminal sends first information indicating that the base station supports CSI-RS feedback information compression of at least one AI model based on the complexity information of the AI ​​model and the AI ​​capability of the terminal, without paying attention to which AI model the terminal specifically supports to compress the CSI-RS feedback information. In this case, the first information may not include the model identifier of the AI ​​model supported by the terminal, but the base station may consider that the terminal at least supports the baseline AI model. Therefore, when configuring CSI-RS for the terminal, the CIS-RS may be configured based on at least the complexity of the baseline AI model or the required CSI calculation duration.

[0169] If the terminal not only determines whether the terminal supports compression of CSI-RS feedback information by at least one AI model based on the complexity information and AI capabilities of each AI model, but also determines which AI model is supported for compression of CSI-RS feedback information, and carries the model identifier of the AI ​​model supported by the terminal for compression of CSI-RS feedback information or the reference information of the AI ​​model in the first information sent to the terminal, then the base station not only knows that the terminal supports compression of CSI-RS feedback information by at least one AI model, but also knows which AI model is specifically supported for compression of CSI-RS feedback information.

[0170] If the terminal does not have AI capability or does not support any AI model compression CSI-RS feedback information indicated by the base station, the terminal sends first information to the base station indicating that at least one AI model is not supported for CSI-RS feedback information. Exemplarily, the first information indicating that the terminal supports at least one AI model for CSI-RS feedback information compression includes:

[0171] A model identifier, indicating the AI ​​model supported by the terminal for CSI-RS feedback information compression;

[0172] The CSI calculation duration indicates the duration required for the terminal to compress the CSI-RS feedback information using the AI ​​model identified by the model.

[0173] Also exemplarily, the first information indicating that the terminal does not support compression of CSI-RS information feedback based on at least one AI model indicates that: CSI-RS feedback information adopts a partial reporting method.

[0174] In some embodiments, the complexity information indicates at least one of the following:

[0175] The total number of floating-point operations corresponding to the AI ​​model, wherein the total number of floating-point operations and the maximum allowed value of the CSI calculation duration are used together by the terminal to determine whether to support CSI-RS feedback information compression of the corresponding AI model;

[0176] A first ratio of the complexity of the corresponding AI model to the complexity of the baseline AI model, wherein the first ratio is used for the terminal to determine whether to support CSI-RS feedback information compression of the corresponding AI model in combination with the terminal AI capability and the complexity of the baseline AI model.

[0177] Exemplarily, the total number of floating-point operations of each AI model and the number of floating-point operations performed per unit time (for example, per second) supported by the terminal can obtain the actual calculation time required for the terminal to use the corresponding AI model to compress CSI-RS feedback information. If the actual calculation time is less than the CSI calculation time and less than or greater than the maximum allowed value, it can be determined whether the terminal supports CSI-RS feedback information compression of the corresponding AI model.

[0178] If the complexity information is: a first ratio; after receiving the first ratio, the terminal first calculates a third ratio between the number of floating-point operations that can be performed by itself in the maximum allowed value of the CSI calculation duration and the number of floating-point operations required by the baseline AI model, and then compares the third ratio with the first ratio. If the third ratio is greater than or equal to the first ratio, it can be considered that the terminal supports the corresponding AI model compression of CSI-RS feedback information compression; if the third ratio is less than the first ratio, it can be considered that the terminal does not support the corresponding AI model compression of CSI-RS feedback information compression.

[0179] In an embodiment of the present disclosure, if the terminal does not support the AI ​​chip or does not have AI capability, after receiving the complexity information of the AI ​​model sent by the base station, the terminal can directly report the first information indicating that the AI ​​model does not support compression of the CSI-RS feedback information.

[0180] The disclosed embodiment provides a method for defining CSI calculation duration based on AI-based CSI-RS feedback information compression, aiming to solve the problem of how to estimate the CSI calculation duration on the terminal side when an AI model is introduced to compress CSI-RS feedback information. When an AI model is introduced to compress CSI-RS feedback information, the main factors affecting the CSI calculation duration are the AI ​​processing capability of the terminal hardware and the complexity of the AI ​​model used.

[0181] The method provided by the embodiment of the present disclosure comprehensively considers the impact of these two aspects and estimates the CSI calculation time after the introduction of the AI ​​model, thereby providing strong support for judging whether the terminal computing power is sufficient to support the use of the AI ​​model. At the same time, the base station side can configure the CSI-RS according to the estimated CSI calculation time.

[0182] The CSI calculation duration may include: the duration required to compress CSI-RS feedback information using the AI ​​model.

[0183] Of course, the CSI calculation duration can be the duration itself or a parameter used to determine the CSI calculation duration; for example, it can be the computing power of the AI ​​model or the computing power of the terminal, etc.

[0184] The present disclosure provides a method for defining CSI calculation duration for CSI-RS feedback information compression based on AI, the method comprising:

[0185] The network side equipment (the base station is used as an example below) has the complexity information of the available AI model, and the terminal side has its own hardware computing capability information. The base station can decide to estimate the CSI calculation duration of AI-based CSI-RS feedback information compression on the terminal side or the base station side. The specific CSI calculation duration definition methods include the definition method based on the terminal processing time and the definition method based on the model complexity.

[0186] When the method based on terminal processing time is used to estimate the CSI calculation duration, the terminal side has its own hardware processing capability information, such as the number of floating-point operations that can be performed per second, etc. By processing the AI ​​model complexity and the terminal processing capability per unit time (for example, per second), the CSI calculation duration under the AI ​​model can be obtained.

[0187] When the CSI calculation time is estimated using a method based on model complexity, the terminal side may have the CSI calculation time used to process the baseline AI model or store the processing time of preset AI models of various complexities. If the terminal side has the CSI calculation time used to process the baseline AI model, the CSI calculation time under the selected AI model can be obtained based on the relationship between the complexity of the AI ​​model selected by the base station and the complexity of the baseline AI model; if the terminal side has the processing time of preset AI models of various complexities, the complexity of the AI ​​model selected by the base station is matched with the complexity of the preset model, and the CSI calculation time under the selected AI model can be obtained.

[0188] When estimating the CSI calculation time on the terminal side, the base station first sends the complexity information and maximum calculation time requirement of one or a group of available AI models to the terminal. The terminal uses the complexity information of the AI ​​model sent by the base station, combined with its own hardware computing power, and adopts a method based on terminal processing time or model complexity to estimate the CSI calculation time under the corresponding model.

[0189] The terminal then compares the estimated CSI calculation time with the maximum calculation time requirement. If the requirement is met, it means that the terminal computing power can support the use of the AI ​​model to compress the CSI-RS feedback information. The terminal reports the adopted model and the estimated CSI calculation time to the base station, and the base station configures the CSI-RS according to the terminal reporting situation. If the maximum calculation time requirement is not met, it means that the terminal computing power does not support the use of the AI ​​model to compress the CSI-RS feedback information. The terminal does not report information related to AI and uses the traditional algorithm for CSI feedback.

[0190] When estimating the CSI calculation duration on the base station side, the terminal first reports the computing power of its own terminal to the base station. The base station estimates the CSI calculation duration under the corresponding model based on the terminal computing power and the complexity information of the available AI model, using a method based on terminal processing time or model complexity. The base station then compares the estimated CSI calculation duration with the maximum calculation duration requirement. If the requirement is met, the AI ​​model is used to compress the CSI-RS feedback information. The base station configures the CSI-RS according to the estimated CSI calculation duration, and sends the selected AI model parameters to the terminal; if the maximum calculation duration requirement is not met, the traditional method is used for CSI feedback. It should be noted that the aforementioned embodiment is described by taking the base station as an example. Of course, those skilled in the art understand that the network side device in all embodiments of the present disclosure may be a base station or any other device, which will not be repeated here.

[0191] refer to Figure 8 As shown, a method for determining the CSI calculation duration of CSI-RS feedback information compression based on AI provided in an embodiment of the present disclosure may include:

[0192] The network side device (hereinafter taking the base station as an example) determines the definition method of the CSI calculation duration, and sets the definition method to be defined based on the terminal processing time or based on the complexity of the AI ​​model for compressing the CSI-RS feedback information. For example, according to the protocol agreement or its own computing load, it is determined that the base station or the terminal determines the CSI calculation duration of the terminal.

[0193] According to the set CSI calculation duration definition method, the CSI calculation duration is estimated on the base station side or the terminal side. Specifically, it can be divided into defining the CSI calculation duration based on the terminal processing time on the terminal side, defining the CSI calculation duration based on the terminal processing time on the base station side, defining the CSI calculation duration based on the model complexity on the terminal side, and defining the CSI calculation duration based on the model complexity on the base station side.

[0194] The base station side configures the CSI-RS according to the estimated CSI calculation duration.

[0195] It should be noted that the above embodiments are described by taking a base station as an example. Of course, those skilled in the art will understand that the network side device in all embodiments of the present disclosure may be a base station or any other device, which will not be described in detail here. It should be noted that the method may be implemented in combination with other embodiments of the present disclosure, or may be implemented independently, which will not be described in detail here.

[0196] refer to Fig. 9, which is a flowchart of defining the CSI calculation duration based on the terminal processing time on the terminal side in the CSI calculation duration definition method for AI-based CSI-RS feedback information compression provided by an embodiment of the present disclosure, may include:

[0197] The network side device (eg, base station) sets the CSI calculation duration definition method to be based on the terminal processing time definition, and determines to estimate the CSI calculation duration on the terminal side.

[0198] The network-side device sends the complexity information of the AI ​​model required for CSI-RS feedback information compression to the terminal, and at the same time sends the maximum calculation time requirement to the terminal. In one embodiment, the complexity information of the AI ​​model can be defined by the floating-point operations per second (FLOPs) of the AI ​​model. The floating-point operation is the total number of additions or multiplications required when calculating using the AI ​​model; the maximum calculation time requirement makes requirements on the CSI calculation time, and the CSI calculation time using the AI ​​model must be within the maximum calculation time requirement.

[0199] The terminal side estimates the CSI calculation time based on its own hardware computing capabilities and the complexity information of the AI ​​model sent by the base station.

[0200] In one embodiment, the computing capability of the terminal's own hardware can be defined by the number of floating point operations per unit time (eg, per second) FLOPS. The number of floating point operations per second is the total number of additions or multiplications that the hardware can perform per second.

[0201] In one embodiment, the CSI calculation time can be defined by the ratio of the AI ​​model complexity to the terminal hardware computing power, that is, CSI calculation time = FLOPs / FLOPS. The total number of addition or multiplication operations required by the model is divided by the number of addition or multiplication operations that the hardware can perform per second to obtain the calculation time required under the AI ​​model.

[0202] In one embodiment, the base station side only sends down the complexity information of a single AI model I, and the terminal can obtain the CSI calculation time T corresponding to the model I.

[0203] In one embodiment, the base station side sends down a group of complexity information of AI models Ii (i=1, 2, 3...), and the terminal can obtain the CSI calculation duration Ti (i=1, 2, 3...) corresponding to the group of models.

[0204] The terminal side determines whether the estimated CSI calculation duration meets the maximum calculation duration requirement. If so, the terminal can use the AI ​​model to compress the CSI-RS feedback information and report the model information of the AI ​​model used and the estimated CSI calculation duration to the base station; if not, the terminal uses the traditional mode to feedback CSI-RS information.

[0205] In one embodiment, among all the models sent by the base station, if no model meets the maximum calculation time requirement, the terminal uses a traditional algorithm to report CSI-RS feedback information, and does not report the estimated CSI calculation time or reports that there is no AI model or reports that the AI ​​model is not used to process the CSI-RS feedback information.

[0206] In one embodiment, among all AI models sent by the base station, only one AI model meets the maximum calculation time requirement, and the terminal reports the model information of the AI ​​model and the corresponding CSI calculation time to the base station.

[0207] In one embodiment, among all the models sent by the base station, there are multiple models that meet the maximum calculation time requirement. The terminal selects the optimal model according to its own characteristics and hardware resource allocation, and reports the optimal model information and the corresponding CSI calculation time to the base station; or the terminal reports two or more models with better performance; or the terminal reports a list of all available models and their priorities.

[0208] The base station configures the CSI-RS according to the information reported by the terminal.

[0209] In one embodiment, the terminal reports to the base station that a traditional mode is used for CSI feedback, and the base station side obtains the CSI calculation duration according to a traditional algorithm and configures the CSI-RS.

[0210] In one embodiment, the terminal reports the AI ​​model information used and the estimated CSI calculation duration to the base station. After the base station receives the CSI-RS feedback information compressed using the AI ​​model, it can use the corresponding decompression model to obtain the restored CSI-RS feedback information. When configuring the CSI-RS, the CSI-RS can be configured according to the estimated CSI calculation duration.

[0211] It should be noted that the above embodiments are described by taking a base station as an example. Of course, those skilled in the art will understand that the network side device in all embodiments of the present disclosure may be a base station or any other device, which will not be described in detail here. It should be noted that the method may be implemented in combination with other embodiments of the present disclosure, or may be implemented independently, which will not be described in detail here.

[0212] refer to Fig.10, which is a flow chart of defining the CSI calculation duration based on the terminal processing time at the base station side in the CSI calculation duration definition method for AI-based CSI-RS feedback information compression provided by an embodiment of the present disclosure. The specific process is as follows:

[0213] The base station side sets the CSI calculation duration definition mode to be defined based on the terminal processing time according to preset conditions, and determines to estimate the CSI calculation duration on the base station side.

[0214] The terminal reports its own hardware computing capabilities to the base station.

[0215] In one embodiment, the computing capability of the terminal's own hardware can be defined by the number of floating point operations per second (FLOPS), which is the total number of additions or multiplications that the hardware can perform per second.

[0216] The base station estimates the CSI calculation time based on the terminal hardware computing capability and the complexity of the AI ​​model used.

[0217] In one embodiment, the complexity information of the AI ​​model can be defined by the floating-point operation number FLOPs of the AI ​​model. The floating-point operation number is the total number of additions or multiplications required when using the AI ​​model for calculation. The CSI calculation time can be defined by the ratio of the complexity of the AI ​​model to the computing power of the terminal hardware, that is, CSI calculation time = FLOPs / FLOPS. The total number of additions or multiplications required by the model is divided by the number of additions or multiplications that the hardware can perform per second to obtain the calculation time required under the AI ​​model.

[0218] In one embodiment, only one model I is available, and the base station can obtain the corresponding CSI calculation duration T according to the complexity information of the model I.

[0219] In one embodiment, there is a group of models Ii (i=1, 2, 3...) available, and the base station can obtain the CSI calculation duration Ti (i=1, 2, 3...) corresponding to the group of models according to the complexity information of the group of models.

[0220] The base station determines whether the estimated CSI calculation time meets the maximum calculation time requirement. If so, the AI ​​model can be used in the terminal to compress the CSI-RS feedback information, and the base station uses the corresponding decompression model to decompress it after receiving it; if not, the traditional mode is used for CSI feedback.

[0221] In one embodiment, among all available models, no AI model meets the maximum computing time requirement, and the terminal side uses a traditional algorithm to report CSI-RS feedback information. The traditional algorithm for reporting CS feedback information here may at least include: reporting part of CSI-RS feedback information.

[0222] In one embodiment, among all available models, only one model meets the maximum calculation time requirement, then the base station configures the CSI-RS according to the estimated CSI calculation time, and sends the corresponding AI model information to the terminal.

[0223] In one embodiment, among all available AI models, there are multiple AI models that meet the maximum computing time requirement. The base station selects the optimal model according to its own characteristics and computing resource allocation, configures the CSI-RS according to the CSI calculation time of the optimal model, and sends the optimal model information to the terminal.

[0224] It should be noted that the above embodiments are described by taking a base station as an example. Of course, those skilled in the art will understand that the network side device in all embodiments of the present disclosure may be a base station or any other device, which will not be described in detail here. It should be noted that the method may be implemented in combination with other embodiments of the present disclosure, or may be implemented independently, which will not be described in detail here.

[0225] refer to Fig.11 , which is a flow chart of defining the CSI calculation duration based on model complexity on the terminal side in the CSI calculation duration definition method for AI-based CSI-RS feedback information compression provided in an embodiment of the present disclosure. The specific process is as follows:

[0226] The base station side sets the CSI calculation duration definition method to be based on model complexity definition according to preset conditions, and determines to estimate the CSI calculation duration on the terminal side.

[0227] The base station side sends the complexity information of the AI ​​model required for CSI-RS feedback information compression to the terminal, and also sends the maximum calculation time requirement to the terminal.

[0228] The terminal side calculates information based on the preset model complexity and estimates the CSI calculation time required under the AI ​​model used.

[0229] In one embodiment, the terminal side presets calculation duration information for different complexity models. The terminal matches the complexity information of the AI ​​model sent by the base station with the preset information to obtain the corresponding CSI calculation duration.

[0230] In one embodiment, the terminal side is preset with baseline CSI calculation duration information corresponding to a baseline model. The complexity information of the AI ​​model sent by the terminal to the base station is related to the complexity of the baseline AI model. After scaling the CSI calculation duration of the baseline AI model, the CSI calculation duration of the AI ​​model used can be obtained.

[0231] In one embodiment, the base station side only sends down the complexity information of a single AI model I, and the terminal can obtain the CSI calculation time T corresponding to the model I.

[0232] In one embodiment, the base station side sends down a group of complexity information of AI models Ii (i=1, 2, 3...), and the terminal can obtain the CSI calculation duration Ti (i=1, 2, 3...) corresponding to the group of models.

[0233] The terminal side determines whether the estimated CSI calculation duration meets the maximum calculation duration requirement. If so, the terminal can use the AI ​​model to compress the CSI-RS feedback information and report the AI ​​model information and the estimated CSI calculation duration to the base station; if not, the terminal uses the traditional mode for CSI feedback.

[0234] In one embodiment, among all the models sent by the base station, if no model meets the maximum calculation duration requirement, the terminal uses a traditional algorithm to report CSI-RS feedback information and does not report the estimated CSI calculation duration.

[0235] In one embodiment, among all the models sent by the base station, only one model meets the maximum calculation duration requirement, and the terminal reports the model information, ie, the corresponding CSI calculation duration, to the base station.

[0236] In one embodiment, among all the models sent by the base station, there are multiple models that meet the maximum calculation time requirement. The terminal selects the optimal model according to its own characteristics and hardware resource allocation, and reports the optimal model information and the corresponding CSI calculation time to the base station.

[0237] The base station configures the CSI-RS according to the information reported by the terminal.

[0238] In one embodiment, the terminal reports to the base station that a traditional mode is used for CSI feedback, and the base station side obtains the CSI calculation duration according to a traditional algorithm and configures the CSI-RS.

[0239] In one embodiment, the terminal reports the AI ​​model information used and the estimated CSI calculation duration to the base station. After the base station receives the CSI-RS feedback information compressed using the AI ​​model, it can use the corresponding decompression model to obtain the restored CSI-RS feedback information. When configuring the CSI-RS, the CSI-RS can be configured according to the estimated CSI calculation duration.

[0240] It should be noted that the above embodiments are described by taking a base station as an example. Of course, those skilled in the art will understand that the network side device in all embodiments of the present disclosure may be a base station or any other device, which will not be described in detail here. It should be noted that the method may be implemented in combination with other embodiments of the present disclosure, or may be implemented independently, which will not be described in detail here.

[0241] refer to Fig.12, a flowchart of defining the CSI calculation duration based on model complexity on the base station side in the CSI calculation duration definition method for AI-based CSI-RS feedback information compression provided by an embodiment of the present disclosure, the specific process is as follows:

[0242] The base station side sets the CSI calculation duration definition mode to be based on model complexity definition according to preset conditions, and determines to estimate the CSI calculation duration on the base station side.

[0243] The terminal reports the preset model complexity calculation information to the base station.

[0244] In one embodiment, the terminal side presets calculation duration information for different complexity models.

[0245] In one embodiment, the terminal side presets and processes the baseline CSI calculation duration information corresponding to a certain baseline model.

[0246] The base station estimates the CSI calculation time based on the complexity calculation information of the terminal preset model and the complexity information of the AI ​​model used.

[0247] In one embodiment, the terminal side presets calculation duration information for different complexity models. The terminal matches the complexity information of the AI ​​model sent by the base station with the preset information to obtain the corresponding CSI calculation duration.

[0248] In one embodiment, the terminal side stores the baseline CSI calculation duration information corresponding to a baseline model. The complexity information of the AI ​​model sent by the terminal to the base station is related to the complexity of the baseline model. After scaling the CSI calculation duration of the baseline model, the CSI calculation duration of the AI ​​model used can be obtained.

[0249] In one embodiment, only one model I is available, and the base station can obtain the corresponding CSI calculation duration T according to the complexity information of the model I.

[0250] In one embodiment, there is a group of models Ii (i=1, 2, 3...) available, and the base station can obtain the CSI calculation duration Ti (i=1, 2, 3...) corresponding to the group of models according to the complexity information of the group of models.

[0251] The base station determines whether the estimated CSI calculation time meets the maximum calculation time requirement. If so, the AI ​​model can be used in the terminal to compress the CSI-RS feedback information, and the base station uses the corresponding decompression model to decompress it after receiving it; if not, the traditional mode is used for CSI feedback.

[0252] In one embodiment, if no AI model among all available AI models meets the maximum computing time requirement, a traditional algorithm is used to report CSI-RS feedback information.

[0253] In one embodiment, among all available models, only one model meets the maximum calculation time requirement, then the base station configures the CSI-RS according to the estimated CSI calculation time, and sends the corresponding AI model information to the terminal.

[0254] In one embodiment, among all available models, there are multiple models that meet the maximum calculation time requirement. The base station selects the optimal model according to its own characteristics and computing resource allocation, configures the CSI-RS according to the CSI calculation time of the optimal model, and sends the optimal model information to the terminal.

[0255] It should be noted that the above embodiments are described by taking a base station as an example. Of course, those skilled in the art will understand that the network side device in all embodiments of the present disclosure may be a base station or any other device, which will not be described in detail here. It should be noted that the method may be implemented in combination with other embodiments of the present disclosure, or may be implemented independently, which will not be described in detail here.

[0256] refer to Fig.13 , a signaling interaction diagram for calculating the CSI calculation duration on the terminal side in the CSI calculation duration definition method for AI-based CSI-RS feedback information compression provided by an embodiment of the present disclosure is as follows:

[0257] The base station sends an AI baseline model determination (AI-based CSIDelay Computation) message to the terminal, requiring the terminal to evaluate the CSI calculation duration.

[0258] The terminal sends a message indicating that the CSI calculation duration of the baseline AI model is complete (AI-basedCSIDelayComputationReady) to the base station, confirming that the evaluation of the CSI calculation duration has started.

[0259] The base station sends an AI capability request (AI Capability Requirement) to the terminal, which includes information such as the model complexity and maximum calculation time stored in the base station.

[0260] The terminal uses a method based on terminal processing time or model complexity to obtain the CSI calculation time, and determines whether to use the AI ​​mode based on the maximum calculation time.

[0261] The terminal sends the complexity information of the baseline AI model (AI-based CSIDelayComputationInformation) to the base station, reporting whether the AI ​​model is used for CSI-RS feedback information compression, the AI ​​model information used, and the corresponding CSI calculation duration.

[0262] The base station configures the CSI-RS according to the complexity information of the baseline AI model (AI-based CSIDelay ComputationInformation).

[0263] If the AI ​​mode is adopted, the base station will send the AI ​​model parameters used to the terminal.

[0264] refer to Fig.14 , a signaling interaction diagram for calculating the CSI calculation duration at the base station side in the CSI calculation duration definition method for AI-based CSI-RS feedback information compression provided by an embodiment of the present disclosure is as follows:

[0265] The base station sends a terminal capability inquiry (Capability Enquiry) to the terminal, requiring the terminal to report its own computing capability.

[0266] The terminal sends the terminal capability information (Capability Information) to the base station to report its own computing capability information. The capability information can at least indicate the AI ​​capability of the terminal.

[0267] The base station evaluates the AI ​​capability of the terminal based on the complexity information of the stored AI model and determines whether to adopt the AI ​​mode by using a method based on the terminal processing time or the model complexity.

[0268] The base station configures the CSI-RS according to the evaluation result.

[0269] If the AI ​​mode is adopted, the base station sends the model information of the AI ​​model used to the terminal.

[0270] The CSI calculation time for AI-based CSI compression is calculated on the terminal side or the base station side. When calculating on the terminal side, the base station sends down the complexity information of the AI ​​model, and the terminal estimates the CSI calculation time based on its own computing power; when calculating on the base station side, the terminal reports its own computing power information, and the base station estimates the CSI calculation time based on the stored complexity information of the AI ​​model.

[0271] In some embodiments, a CSI calculation time defined based on the terminal processing time is proposed. The base station side stores the complexity information of the AI ​​model, and the terminal side stores its own computing power information. The model complexity and the terminal's own computing power are processed to obtain the CSI calculation time.

[0272] In other embodiments, a CSI calculation time defined based on model complexity is proposed. When the terminal side has the CSI calculation time used to process the baseline AI model, the CSI calculation time under the selected AI model can be obtained according to the relationship between the complexity of the AI ​​model selected by the base station and the complexity of the baseline AI model; when the terminal side has the processing time for preset AI models of various complexities, the complexity of the AI ​​model selected by the base station is matched with the complexity of the preset model, and the CSI calculation time under the selected AI model can be obtained.

[0273] It should be noted that the above embodiments are described by taking a base station as an example. Of course, those skilled in the art will understand that the network side device in all embodiments of the present disclosure may be a base station or any other device, which will not be described in detail here. It should be noted that the method may be implemented in combination with other embodiments of the present disclosure, or may be implemented independently, which will not be described in detail here.

[0274] like Fig.15 As shown, an embodiment of the present disclosure provides an information processing device, wherein the method includes:

[0275] A determination module 110, configured to determine whether the terminal supports channel state information-reference signal CSI-RS feedback information compression of at least one AI model;

[0276] The configuration module 120 is used to configure the CSI-RS according to whether the terminal supports CSI-RS feedback information compression of at least one AI model.

[0277] The information processing device may be included in a terminal.

[0278] In some embodiments, the determination module 110 and the configuration module 120 may be program modules; after the program modules are executed by a processor, the above functions can be realized.

[0279] In other embodiments, the determination module 110 and the configuration module 120 may be a combination of soft and hard modules; the combination of soft and hard modules includes but is not limited to: a programmable array; the programmable array includes but is not limited to a field programmable array and / or a complex programmable array.

[0280] In some other embodiments, the determination module 110 and the configuration module 120 may be pure hardware modules; the pure hardware modules include but are not limited to: application specific integrated circuits.

[0281] In some embodiments, the determination module 110 is configured to send complexity information of the AI ​​model to the terminal; receive first information provided by the terminal based on the complexity information; and determine whether the terminal supports CSI-RS feedback information compression of at least one AI model based on the first information.

[0282] In some embodiments, the first information indicating that the terminal supports CSI-RS feedback information compression of at least one AI model includes:

[0283] A model identifier, indicating the AI ​​model supported by the terminal for CSI-RS feedback information compression;

[0284] The CSI calculation duration indicates the duration required for the terminal to compress the CSI-RS feedback information using the AI ​​model identified by the model.

[0285] In some embodiments, the first information indicating that the terminal does not support at least one AI model for compression of CSI-RS information feedback indicates that: CSI-RS feedback information adopts a partial reporting method.

[0286] In some embodiments, the complexity information indicates at least one of the following:

[0287] The total number of floating-point operations corresponding to the AI ​​model, wherein the total number of floating-point operations and the maximum allowed value of the CSI calculation duration are used together by the terminal to determine whether to support CSI-RS feedback information compression of the corresponding AI model;

[0288] A first ratio of the complexity of the corresponding AI model to the complexity of the baseline AI model, wherein the first ratio is used for the terminal to determine whether to support CSI-RS feedback information compression of the corresponding AI model in combination with the terminal AI capability and the complexity of the baseline AI model.

[0289] In some embodiments, the determination module 110 is configured to receive AI capability information sent by the terminal; and determine, based on the AI ​​capability information, whether the terminal supports CSI-RS feedback information compression of at least one AI model.

[0290] In some embodiments, the AI ​​capability information indicates at least one of the following:

[0291] Whether the terminal has AI capabilities;

[0292] The terminal supports the number of floating point operations per second;

[0293] The number of floating-point operations supported by the terminal within the maximum allowed value of the CSI calculation duration;

[0294] The second ratio indicates a ratio between the complexity of the terminal AI capability and the baseline AI model.

[0295] In some embodiments, the configuration module 120 is configured to configure the type of CSI-RS feedback information reported by the terminal according to whether the terminal supports CSI-RS feedback information compression of at least one AI model; when the terminal supports CSI-RS feedback information compression of at least one AI model, determine the CSI calculation duration when compressing the CSI-RS feedback information using the supported AI model, and configure the CSI-RS period.

[0296] like Fig.16 As shown, an embodiment of the present disclosure provides an information processing device, the device comprising:

[0297] The sending module 210 is configured to send second information, wherein the second information is used for the base station to determine whether the terminal supports compression of CSI-RS feedback information by at least one AI model.

[0298] The information processing device may be included in a terminal.

[0299] In some embodiments, the sending module 210 may be a program module; after the program module is executed by the processor, it can enable the base station to determine whether the terminal supports the compression of CSI-RS feedback information by the AI ​​model.

[0300] In some other embodiments, the sending module 210 may be a soft-hard combination module; the soft-hard combination module includes but is not limited to: a programmable array. The programmable array includes but is not limited to: a field programmable array and / or a complex programmable array.

[0301] In some other embodiments, the sending module 210 may be a pure hardware module; the pure hardware module includes but is not limited to: a dedicated integrated circuit.

[0302] In some embodiments, the second information includes:

[0303] AI capability information indicating the AI ​​capability of the terminal.

[0304] In some embodiments, the AI ​​capability information indicates at least one of the following:

[0305] Whether the terminal has AI capabilities;

[0306] The terminal supports the number of floating point operations per second;

[0307] The number of floating-point operations supported by the terminal within the maximum allowed value of the CSI calculation duration;

[0308] The second ratio indicates a ratio between the complexity of the terminal AI capability and the baseline AI model.

[0309] In some embodiments, the second information includes:

[0310] The first information is used to indicate whether the terminal supports compression of CSI-RS feedback information by at least one AI model.

[0311] In some embodiments, the first information indicating that the terminal supports CSI-RS feedback information compression of at least one AI model includes:

[0312] A model identifier, indicating the AI ​​model supported by the terminal for CSI-RS feedback information compression;

[0313] The CSI calculation duration indicates the duration required for the terminal to compress the CSI-RS feedback information using the AI ​​model identified by the model.

[0314] In some embodiments, it indicates that the terminal does not support the first information indication: CSI-RS feedback information adopts a partial reporting method.

[0315] In some embodiments, the apparatus further comprises:

[0316] A receiving module, configured to receive complexity information of the AI ​​model;

[0317] The sending module 210 is configured to send the first information to the base station according to the complexity information of the AI ​​model and the AI ​​capability of the terminal.

[0318] In some embodiments, the sending module 210 is further configured to perform at least one of the following:

[0319] When determining, according to the complexity information of the AI ​​model and the AI ​​capability of the terminal, that the terminal supports compression of the CSI-RS feedback information by an AI model, sending, to the base station, the first information indicating support for compression of the CSI-RS feedback information of at least one AI model;

[0320] When determining, according to the complexity information of the AI ​​model and the AI ​​capability of the terminal, that the terminal supports multiple AI models for compressing the CSI-RS feedback information, selecting an AI model supported by the terminal according to a resource scheduling situation of the terminal to indicate to the base station the first information supporting CSI-RS feedback information compression of an AI model;

[0321] When it is determined according to the complexity information of the AI ​​model and the AI ​​capability of the terminal that the terminal does not support the AI ​​model for compressing the CSI-RS feedback information, the first information indicating that the terminal does not support at least one AI model for compressing the CSI-RS information feedback is sent to the base station.

[0322] In some embodiments, the complexity information indicates at least one of the following:

[0323] The total number of floating-point operations corresponding to the AI ​​model, wherein the total number of floating-point operations and the maximum allowed value of the CSI calculation duration are used together by the terminal to determine whether to support CSI-RS feedback information compression of the corresponding AI model;

[0324] A first ratio of the complexity of the corresponding AI model to the complexity of the baseline AI model, wherein the first ratio is used for the terminal to determine whether to support CSI-RS feedback information compression of the corresponding AI model in combination with the terminal AI capability and the complexity of the baseline AI model.

[0325] The present disclosure provides a communication device, including:

[0326] a memory for storing processor-executable instructions;

[0327] Processor, respectively memory connection;

[0328] Among them, the processor is configured to execute the information processing method provided by any of the aforementioned technical solutions.

[0329] The processor may include various types of storage media, which are non-transitory computer storage media that can continue to retain information stored thereon after the communication device loses power.

[0330] Here, the communication device includes: a terminal or a network element, and the network element can be any one of the first network element to the fourth network element mentioned above.

[0331] The processor may be connected to the memory via a bus or the like, and is used to read an executable program stored in the memory, for example, Figures 2 to 14 At least one of the methods shown.

[0332] Fig.17 800 is a block diagram of a terminal 800 according to an exemplary embodiment. For example, the terminal 800 may be a mobile phone, a computer, a digital broadcast user device, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0333] Reference Fig.17 The terminal 800 may include one or more of the following components: a processing component 802 , a memory 804 , a power component 806 , a multimedia component 808 , an audio component 810 , an input / output (I / O) interface 812 , a sensor component 814 , and a communication component 816 .

[0334] The processing component 802 generally controls the overall operation of the terminal 800, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 802 may include one or more modules to facilitate the interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.

[0335] The memory 804 is configured to store various types of data to support operations at the terminal 800. Examples of such data include instructions for any application or method operating on the terminal 800, contact data, phone book data, messages, pictures, videos, etc. The memory 804 may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk, or an optical disk.

[0336] Power component 806 provides power to various components of terminal 800. Power component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to terminal 800.

[0337] The multimedia component 808 includes a screen that provides an output interface between the terminal 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and / or a rear camera. When the terminal 800 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and the rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0338] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC), and when the terminal 800 is in an operation mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 804 or sent via the communication component 816. In some embodiments, the audio component 810 also includes a speaker for outputting audio signals.

[0339] 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: a home button, a volume button, a start button, and a lock button.

[0340] The sensor assembly 814 includes one or more sensors for providing various aspects of status assessment for the terminal 800. For example, the sensor assembly 814 can detect the open / closed state of the device 800, the relative positioning of the components, such as the display and keypad of the terminal 800, and the sensor assembly 814 can also detect the position change of the terminal 800 or a component of the terminal 800, the presence or absence of contact between the user and the terminal 800, the orientation or acceleration / deceleration of the terminal 800 and the temperature change of the terminal 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor or a temperature sensor.

[0341] The communication component 816 is configured to facilitate wired or wireless communication between the terminal 800 and other devices. The terminal 800 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0342] In an exemplary embodiment, terminal 800 can 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 above methods.

[0343] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 804 including instructions, and the instructions can be executed by a processor 820 of the terminal 800 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0344] like Fig.18 As shown, an embodiment of the present disclosure shows a structure of an access device. For example, the communication device 900 can be provided as a network side device. The communication device can be the aforementioned terminal or base station.

[0345] Reference Fig.18 , the communication device 900 may be the aforementioned base station, and the communication device 900 may include a processing component 922, which further includes one or more processors, and a memory resource represented by a memory 932, for storing instructions that can be executed by the processing component 922, such as an application. The application stored in the memory 932 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 922 is configured to execute instructions to perform any of the aforementioned methods applied to the access device, such as Figures 4 to 9 Any of the methods shown.

[0346] The communication device 900 may also include a power supply component 926 configured to perform power management of the communication device 900, a wired or wireless network interface 950 configured to connect the communication device 900 to a network, and an input / output (I / O) interface 958. The communication device 900 may operate based on an operating system stored in the memory 932, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™ or the like.

[0347] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.

[0348] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. An information processing method, wherein: Executed by a base station, the method includes: Determine whether the terminal supports channel state information-reference signal CSI-RS feedback information compression of at least one artificial intelligence AI model; The CSI-RS is configured according to whether the terminal supports CSI-RS feedback information compression of at least one AI model.

2. The method according to claim 1, wherein: The determining whether the terminal supports CSI-RS feedback information compression of at least one artificial intelligence AI model includes: Sending complexity information of the AI ​​model to the terminal; receiving first information provided by the terminal according to the complexity information; According to the first information, determine whether the terminal supports CSI-RS feedback information compression of at least one AI model.

3. The method according to claim 2, wherein: The first information indicating that the terminal supports CSI-RS feedback information compression of at least one AI model includes: A model identifier, indicating the AI ​​model supported by the terminal for CSI-RS feedback information compression; The CSI calculation duration indicates the duration required for the terminal to compress the CSI-RS feedback information using the AI ​​model identified by the model.

4. The method according to claim 2, wherein: The first information indicating that the terminal does not support at least one AI model for compressing CSI-RS information feedback indicates that the CSI-RS feedback information adopts a partial reporting method.

5. The method according to claim 2, wherein: The complexity information indicates at least one of the following: The total number of floating-point operations corresponding to the AI ​​model, wherein the total number of floating-point operations and the maximum allowed value of the CSI calculation duration are used together by the terminal to determine whether to support CSI-RS feedback information compression of the corresponding AI model; A first ratio of the complexity of the corresponding AI model to the complexity of the baseline AI model, wherein the first ratio is used for the terminal to determine whether to support CSI-RS feedback information compression of the corresponding AI model in combination with the terminal AI capability and the complexity of the baseline AI model.

6. The method according to claim 1, wherein: The determining whether the terminal supports CSI-RS feedback information compression of at least one artificial intelligence AI model includes: Receiving AI capability information sent by the terminal; Determine, according to the AI ​​capability information, whether the terminal supports CSI-RS feedback information compression of at least one AI model.

7. The method according to claim 6, wherein: The AI ​​capability information indicates at least one of the following: Whether the terminal has AI capabilities; The terminal supports the number of floating point operations per second; The number of floating-point operations supported by the terminal within the maximum allowed value of the CSI calculation duration; The second ratio indicates a ratio between the complexity of the terminal AI capability and the baseline AI model.

8. The method according to any one of claims 1 to 7, wherein: The configuring the CSI-RS according to whether the terminal supports CSI-RS feedback information compression of at least one AI model includes: According to whether the terminal supports CSI-RS feedback information compression of at least one AI model, configuring a type of CSI-RS feedback information reported by the terminal; When the terminal supports CSI-RS feedback information compression of at least one AI model, determine the CSI calculation duration when the supported AI model is used to compress the CSI-RS feedback information, and configure the period of the CSI-RS.

9. An information processing method, executed by a terminal, the method comprising: Send second information, wherein the second information is used for the base station to determine whether the terminal supports compression of CSI-RS feedback information by at least one AI model.

10. The method according to claim 9, wherein: The second information includes: AI capability information indicating the AI ​​capability of the terminal.

11. The method according to claim 10, wherein: The AI ​​capability information indicates at least one of the following: Whether the terminal has AI capabilities; The terminal supports the number of floating point operations per second; The number of floating-point operations supported by the terminal within the maximum allowed value of the CSI calculation duration; The second ratio indicates a ratio between the complexity of the terminal AI capability and the baseline AI model.

12. The method according to claim 9, wherein: The second information includes: The first information is used to indicate whether the terminal supports compression of CSI-RS feedback information by at least one AI model.

13. The method according to claim 12, wherein: The first information indicating that the terminal supports CSI-RS feedback information compression of at least one AI model includes: A model identifier, indicating the AI ​​model supported by the terminal for CSI-RS feedback information compression; The CSI calculation duration indicates the duration required for the terminal to compress the CSI-RS feedback information using the AI ​​model identified by the model.

14. The method according to claim 12, wherein: It indicates that the terminal does not support the first information indication: CSI-RS feedback information adopts a partial reporting method.

15. The method according to claim 12, wherein: The method further comprises: Receive AI model complexity information; The sending of the second information comprises: The first information is sent to a base station according to the complexity information of the AI ​​model and the AI ​​capability of the terminal.

16. The method according to claim 15, wherein: The sending the first information to the base station according to the complexity information of the AI ​​model and the AI ​​capability of the terminal includes at least one of the following: When determining, according to the complexity information of the AI ​​model and the AI ​​capability of the terminal, that the terminal supports compression of the CSI-RS feedback information by an AI model, sending, to the base station, the first information indicating support for compression of the CSI-RS feedback information of at least one AI model; When determining, according to the complexity information of the AI ​​model and the AI ​​capability of the terminal, that the terminal supports multiple AI models for compressing the CSI-RS feedback information, selecting an AI model supported by the terminal according to a resource scheduling situation of the terminal to indicate to the base station the first information supporting CSI-RS feedback information compression of an AI model; When it is determined according to the complexity information of the AI ​​model and the AI ​​capability of the terminal that the terminal does not support the AI ​​model for compressing the CSI-RS feedback information, the first information indicating that the terminal does not support at least one AI model for compressing the CSI-RS information feedback is sent to the base station.

17. The method according to claim 15 or 16, wherein: The complexity information indicates at least one of the following: The total number of floating-point operations corresponding to the AI ​​model, wherein the total number of floating-point operations and the maximum allowed value of the CSI calculation duration are used together by the terminal to determine whether to support CSI-RS feedback information compression of the corresponding AI model; A first ratio of the complexity of the corresponding AI model to the complexity of the baseline AI model, wherein the first ratio is used for the terminal to determine whether to support CSI-RS feedback information compression of the corresponding AI model in combination with the terminal AI capability and the complexity of the baseline AI model.

18. An information processing device, wherein: The device comprises: A determination module, used to determine whether the terminal supports channel state information-reference signal CSI-RS feedback information compression of at least one artificial intelligence AI model; A configuration module is used to configure CSI-RS according to whether the terminal supports CSI-RS feedback information compression of at least one AI model.

19. An information processing device, the device comprising: The sending module is configured to send second information, wherein the second information is used for the base station to determine whether the terminal supports compression of CSI-RS feedback information by at least one AI model.

20. A communication device comprising a processor, a transceiver, a memory, and an executable program stored in the memory and capable of being run by the processor, wherein: When the processor runs the executable program, the method provided in any one of claims 1 to 8 or 9 to 17 is performed.

21. A computer storage medium storing an executable program; after the executable program is executed by a processor, it can implement the method provided in any one of claims 1 to 8 or 9 to 17.

Images