Channel state information generation method and apparatus, channel state information configuration method and apparatus, and communication system

Abstract

Provided in the embodiments of the present application are a channel state information (CSI) generation method and apparatus, a CSI configuration method and apparatus, and a communication system. The CSI generation apparatus is applied to a terminal device. The apparatus comprises a first processing unit, wherein the first processing unit controls the terminal device, such that the terminal device executes the following operations: the terminal device receiving a first configuration from a network device, which first configuration is used for configuring the terminal device to send CSI to the network device, and comprises model information, and / or bit width information related to precoding matrix information; and the terminal device generating the CSI on the basis of a model, which model is determined at least on the basis of the first configuration, and which CSI at least comprises the precoding matrix information.

Description

Channel state information generation and configuration method, device and communication system Technical Field

[0001] The embodiments of the present application relate to the field of communication technologies. Background Art

[0002] Massive multiple-input multiple-output (MIMO) technology is one of the key technologies for 5G mobile communications. MIMO can provide higher channel capacity, but achieving these benefits depends on obtaining accurate channel state information.

[0003] In MIMO technology, terminal devices measure spatial channels and provide channel state information (CSI) back to the network. Based on this CSI, the network selects an appropriate precoding matrix for downlink transmission to the terminal, minimizing the probability of bit errors in the terminal's reception.

[0004] The channel state information generation and feedback process can be summarized as follows. The network device sends a channel state information reference signal (CSI-RS) to each terminal device. The terminal device estimates the channel using the received CSI-RS and obtains an estimate of the spatial channel matrix. The terminal device further uses the estimated spatial channel to obtain CSI. In new radio (NR) technology, CSI feedback is implicit. That is, the terminal device feeds back CSI in the form of recommended transmission parameters to the network device. These transmission parameters include the channel state information reference signal resource indicator (CQI), precoding matrix indicator (PMI), CSI-RS resource indicator (CRI), synchronization signal block resource indicator (SSBRI), layer indicator (LI), rank indicator (RI), and physical layer RSRP (L1-RSRP). The base station can directly use the parameters recommended by the terminal device for downlink transmission, or it can choose not to use the recommended parameters.

[0005] In frequency division duplex (FDD) systems, for the downlink, when network devices use downlink channel information for precoding, terminal devices are required to feed back downlink channel state information to the network devices via the uplink. However, because downlink channel information is proportional to the number of antennas on the network devices, in massive MIMO scenarios, the large number of network device antennas results in a very large amount of downlink channel state information feedback. The Third Generation Partnership Project (3GPP) has designed enhanced codebooks (e.g., the etype II codebook) for downlink feedback, reducing the amount of channel state information feedback through frequency domain compression. However, given the precious uplink resources, there is still a need to further reduce the amount of uplink feedback.

[0006] It should be noted that the above introduction to the technical background is merely intended to provide a clear and complete description of the technical solutions of this application and facilitate understanding by those skilled in the art. Simply because these solutions are described in the background technology section of this application, it should not be assumed that the above technical solutions are well known to those skilled in the art.

[0007] Summary of the Invention

[0008] With the development of artificial intelligence / machine learning (AI / ML) technology, applying AI / ML technology to the physical layer of wireless communications to solve the difficulties of traditional methods has become a current technical direction.

[0009] Figure 1 is a schematic diagram of AI / ML-based CSI feedback. The AI / ML module may include an AI / ML-based CSI generation component and an AI / ML-based CSI reconstruction component. The AI / ML-based CSI generation component includes an AI / ML model, which may include an AI / ML encoder and quantizer. In addition, the AI / ML model may also include a pre-processing module. The AI / ML-based CSI reconstruction component includes an AI / ML reconstruction model, which includes a dequantizer and an AI / ML decoder. In addition, the AI / ML reconstruction model may also include a post-processing module.

[0010] As shown in Figure 1, in operation 101, the terminal device side uses the AI / ML-based CSI generation part to process and obtain CSI; the network device receives the CSI through the air interface; in operation 102, the network device uses the AI / ML-based CSI reconstruction part to process the received CSI to obtain recovered CSI.

[0011] The inventors of this application discovered that the CSI reporting configuration in the prior art supports CSI generated based on a codebook, and the relevant information for configuring the CSI bit width is implicitly implemented through the codebook configuration. However, for the technical solution of generating CSI using an AI / ML model, how to perform CSI reporting configuration is a problem that needs to be solved.

[0012] In response to at least one of the above-mentioned problems or other similar problems, an embodiment of the present application provides a channel state information generation and configuration method, apparatus and communication system. In this method, a terminal device receives a first configuration corresponding to a model sent from a network device, thereby enabling the terminal device to be configured with respect to CSI reporting. In addition, the terminal device can generate CSI according to the model corresponding to the first configuration.

[0013] According to one aspect of an embodiment of the present application, a channel state information generating apparatus is provided, which is applied to a terminal device. The apparatus includes a first processing unit, which controls the terminal device to cause the terminal device to perform the following operations:

[0014] The terminal device receives a first configuration from a network device, where the first configuration is used to configure the terminal device to send channel state information (CSI) to the network device, where the first configuration includes model information and / or bit width information related to precoding matrix information; and

[0015] The terminal device generates the CSI based on a model, where the model is determined based on at least the first configuration, and the CSI includes at least the precoding matrix information.

[0016] According to another aspect of an embodiment of the present application, a channel state information configuration apparatus is provided, which is applied to a network device. The apparatus includes a second processing unit, which controls the network device to cause the network device to perform the following operations:

[0017] The network device sends a first configuration to the terminal device, where the first configuration is used to configure the terminal device to send channel state information (CSI) to the network device, and the first configuration includes model information and / or bit width information related to precoding matrix information; and

[0018] The CSI is generated by the terminal device based on a model, the model is determined based on at least the first configuration, and the CSI includes at least the precoding matrix information.

[0019] One of the beneficial effects of the embodiments of the present application is that: the terminal device receives a first configuration corresponding to a model sent from a network device, thereby enabling the terminal device to be configured with respect to CSI reporting. In addition, the terminal device can generate CSI according to the model corresponding to the first configuration.

[0020] With reference to the following description and accompanying drawings, specific embodiments of the present application are disclosed in detail, indicating the manner in which the principles of the present application can be employed. It should be understood that the embodiments of the present application are not limited in scope. Within the spirit and scope of the appended claims, the embodiments of the present application include many variations, modifications and equivalents.

[0021] Features described and / or illustrated with respect to one embodiment may be used in the same or similar manner in one or more other embodiments, combined with features in other embodiments, or substituted for features in other embodiments.

[0022] It should be emphasized that the term "include / comprising" when used herein refers to the presence of features, integers, steps or components, but does not exclude the presence or addition of one or more other features, integers, steps or components. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The elements and features described in one figure or one embodiment of the present application can be combined with the elements and features shown in one or more other figures or embodiments. In addition, in the accompanying drawings, similar reference numerals represent corresponding parts in several figures and can be used to indicate corresponding parts used in more than one embodiment.

[0024] Figure 1 is a schematic diagram of CSI feedback based on AI / ML;

[0025] FIG2 is a schematic diagram of the communication system of the present application;

[0026] FIG3 is a schematic diagram of a channel state information generation method according to an embodiment of the first aspect of the present application;

[0027] FIG4 is a schematic diagram of a channel state information configuration method according to an embodiment of the second aspect of the present application;

[0028] FIG5 is a schematic diagram of a channel state information generating device according to an embodiment of the third aspect of the present application;

[0029] FIG6 is a schematic diagram of a channel state information configuration device according to an embodiment of the fourth aspect of the present application;

[0030] FIG7 is a schematic diagram of a terminal device according to an embodiment of the fifth aspect;

[0031] FIG8 is a schematic diagram of a network device according to an embodiment of the fifth aspect. DETAILED DESCRIPTION

[0032] The above and other features of the present application will become apparent through the following description with reference to the accompanying drawings. In the description and the accompanying drawings, specific embodiments of the present application are disclosed in detail, which illustrate some embodiments in which the principles of the present application can be adopted. It should be understood that the present application is not limited to the described embodiments. On the contrary, the present application includes all modifications, variations and equivalents that fall within the scope of the appended claims.

[0033] In the embodiments of the present application, the terms "first", "second", etc. are used to distinguish different elements from the name, but do not indicate the spatial arrangement or temporal order of these elements, and these elements should not be limited by these terms. The term "and / or" includes any one and all combinations of one or more of the associated listed terms. The terms "comprising", "including", "having", etc. refer to the presence of the stated features, elements, components or components, but do not exclude the presence or addition of one or more other features, elements, components or components.

[0034] In the embodiments of this application, the singular forms "a," "the," etc. include plural forms and should be broadly understood to mean "a" or "a type" rather than being limited to "one." Furthermore, the term "said" should be understood to include both singular and plural forms, unless the context clearly indicates otherwise. Furthermore, the term "according to" should be understood to mean "at least in part based on...", and the term "based on" should be understood to mean "at least in part based on...", unless the context clearly indicates otherwise.

[0035] In the embodiments of the present application, the term "communication network" or "wireless communication network" may refer to a network that complies with any of the following communication standards, such as New Radio (NR), Long Term Evolution (LTE), Enhanced Long Term Evolution (LTE-A, LTE-Advanced), Wideband Code Division Multiple Access (WCDMA), High-Speed ​​Packet Access (HSPA), etc.

[0036] Furthermore, communication between devices in the communication system may be carried out according to communication protocols of any stage, for example, including but not limited to the following communication protocols: 1G (generation), 2G, 2.5G, 2.75G, 3G, 4G, 4.5G and 5G, New Radio (NR), etc., and / or other communication protocols currently known or to be developed in the future.

[0037] In the embodiments of the present application, the term "network device" refers to, for example, a device in a communication system that connects a terminal device to a communication network and provides services for the terminal device. Network devices may include, but are not limited to, the following devices: an integrated access and backhaul node (IAB-node), a base station (BS), an access point (AP), a transmission reception point (TRP), a broadcast transmitter, a mobile management entity (MME), a gateway, a server, a radio network controller (RNC), a base station controller (BSC), and the like.

[0038] Base stations may include, but are not limited to, NodeB (NB), evolved NodeB (eNodeB or eNB), and 5G base stations (gNB), among others. They may also include remote radio heads (RRHs), remote radio units (RRUs), relays, or low-power nodes (e.g., femeto, pico, etc.). The term "base station" may include some or all of their functions, and each base station may provide communication coverage for a specific geographic area. The term "cell" may refer to a base station and / or its coverage area, depending on the context in which the term is used.

[0039] In the embodiments of the present application, the term "user equipment" (UE) or "terminal equipment" (TE) refers to, for example, a device that accesses a communication network through a network device and receives network services. A terminal device can be fixed or mobile and may also be referred to as a mobile station (MS), a terminal, a subscriber station (SS), an access terminal (AT), a station, and so on.

[0040] Among them, terminal devices may include but are not limited to the following devices: cellular phones, personal digital assistants (PDAs), wireless modems, wireless communication devices, handheld devices, machine-type communication devices, laptop computers, cordless phones, smart phones, smart watches, digital cameras, etc.

[0041] For another example, in scenarios such as the Internet of Things (IoT), the terminal device can also be a machine or device for monitoring or measurement, including but not limited to: machine type communication (MTC) terminal, vehicle-mounted communication terminal, device-to-device (D2D) terminal, machine-to-machine (M2M) terminal, and so on.

[0042] In addition, the term "network side" or "network device side" refers to one side of the network, which can be a base station or one or more network devices as mentioned above. The term "user side" or "terminal side" or "terminal device side" refers to the user or terminal side, which can be a UE or one or more terminal devices as mentioned above.

[0043] In the following description, the terms "uplink control signal" and "uplink control information (UCI)" or "physical uplink control channel (PUCCH)" are interchangeable, and the terms "uplink data signal" and "uplink data information" or "physical uplink shared channel (PUSCH)" are interchangeable to avoid confusion.

[0044] The terms "downlink control signal" and "downlink control information (DCI)" or "physical downlink control channel (PDCCH)" are interchangeable, and the terms "downlink data signal" and "downlink data information" or "physical downlink shared channel (PDSCH)" are interchangeable.

[0045] In addition, sending or receiving PUSCH can be understood as sending or receiving uplink data carried by PUSCH, sending or receiving PUCCH can be understood as sending or receiving uplink information carried by PUCCH, and sending or receiving PRACH can be understood as sending or receiving preamble carried by PRACH; uplink signals can include uplink data signals and / or uplink control signals, etc., and can also be referred to as uplink transmission (UL transmission) or uplink information or uplink channels. Sending uplink transmission on uplink resources can be understood as sending the uplink transmission using the uplink resources. Similarly, downlink data / signals / channels / information can be understood accordingly.

[0046] In the embodiments of the present application, the high-layer signaling may be, for example, radio resource control (RRC) signaling; for example, an RRC message, including, for example, an MIB, system information, or a dedicated RRC message; or an RRC information element (RRC IE). The high-layer signaling may also be, for example, MAC (Medium Access Control) signaling; or a MAC control element (MAC CE). However, the present application is not limited thereto.

[0047] The following describes the scenarios of the embodiments of the present application through examples, but the present application is not limited thereto.

[0048] Figure 2 is a schematic diagram of the communication system of the present application, which schematically illustrates a situation taking a terminal device and a network device as an example. As shown in Figure 2, the communication system 100 may include a network device 201 and a terminal device 202 (for simplicity, Figure 2 only illustrates one terminal device as an example).

[0049] In the embodiment of the present application, existing services or future services can be carried out between the network device 201 and the terminal device 202. For example, these services include but are not limited to: enhanced mobile broadband (eMBB), massive machine type communication (mMTC), and ultra-reliable and low-latency communication (URLLC), etc.

[0050] Among them, the terminal device 202 can send data to the network device 201, for example, using an authorized or unauthorized transmission mode. The network device 201 can receive data sent by one or more terminal devices 202 and feedback information to the terminal device 202, such as confirmation ACK / non-confirmation NACK information. The terminal device 202 can confirm the end of the transmission process, or can continue new data transmission, or can retransmit the data based on the feedback information.

[0051] In the following description of this application, artificial intelligence (AI) models may also be referred to as artificial intelligence / machine learning (AI / ML) models, and these two terms are interchangeable.

[0052] In the following embodiments of the present application, the signaling sent by the network device to the terminal device can be sent through downlink control information (DCI), and / or media access control element (MAC CE), and / or radio resource control (RRC) signaling.

[0053] In the following embodiments of the present application, the AI / ML-based CSI generation part and the AI / ML-based CSI reconstruction part are paired. The former can be applied to the terminal device side, and the latter can be applied to the network device side. If the terminal device uses a certain AI / ML-based CSI generation part, the network device must use the AI / ML-based CSI reconstruction part paired with the AI / ML-based CSI generation part to successfully reconstruct the channel information. If the network device uses a certain AI / ML-based CSI reconstruction part, the terminal device must use the AI / ML-based CSI generation part paired with the AI / ML-based CSI reconstruction part to successfully reconstruct the channel information on the network device side.

[0054] The AI / ML-based CSI generation part includes a first AI / ML model, that is, an AI / ML-based CSI generation model, which can be used to generate precoding matrix information, rank indication (RI), layer indication (LI), channel resource indication (CRI) and channel quality indication (CQI). In addition, RI, LI, CRI, and CQI may not be generated by the first AI / ML model. For example, the AI / ML-based CSI generation part may also include a module for generating RI, a module for generating LI, a module for generating CRI, and one or more modules for generating CQI. The AI / ML-based CSI generation part may also include other modules, such as a module for truncating a bit sequence.

[0055] The information of the AI / ML-based CSI generation part may consist of AI / ML model information and / or information of the module for generating RI and / or information of the module for generating LI and / or information of the module for generating CRI and / or information of the module for generating CQI and / or information of the bit sequence truncation module and / or information of implementing other functional modules (if any).

[0056] The first AI / ML model may include three parts: a preprocessing module, an AI / ML encoder, and a quantizer. Therefore, the first AI / ML model information may include preprocessing module information, AI / ML encoder information, and quantizer information. For example, an AI / ML model information may be described as "preprocessing module #2, AI / ML encoder #4, Quantizer #A." Furthermore, the preprocessing module, AI / ML encoder, and quantizer may be considered as a whole to label the AI / ML model information. Thus, the AI / ML model information may be represented as, for example, AI / ML model information #4.

[0057] The AI / ML-based CSI reconstruction part includes a second AI / ML model (also referred to as an AI / ML reconstruction model, or an AI / ML-based CSI reconstruction model). The second AI / ML model may include three parts, namely, a dequantizer, an AI / ML decoder, and a post-processing module. Thus, the AI / ML reconstruction model information may include dequantizer information, AI / ML decoder information, and post-processing module information. For example, an AI / ML reconstruction model information may be described as "dequantizer #B, AI / ML decoder #1, post-processing module #2". In addition, the AI / ML reconstruction model information may also be expressed as, for example, AI / ML reconstruction model #1, or simply as AI / ML model #1, to indicate a pairing relationship with the AI / ML model #1 in the AI / ML-based CSI generation part.

[0058] The first AI / ML model and the second AI / ML model are in a paired relationship.

[0059] In some embodiments, the first AI / ML model may also consist of two parts (for example, without a preprocessing module, or the preprocessing module is included in the AI / ML encoder and is regarded as a whole with the AI / ML encoder), that is, the first AI / ML model includes an AI / ML encoder and a quantizer. At this time, the AI / ML model information may consist of AI / ML encoder information and quantizer information. The second AI / ML model paired with the first AI / ML model may also consist of two parts, namely a dequantizer and an AI / ML decoder. At this time, the AI / ML reconstruction model information consists of dequantizer information and AI / ML decoder information. The preprocessing module may be included in the AI / ML encoder or not. The post-processing module may be included in the AI / ML decoder or not.

[0060] In some other embodiments, the first AI / ML model may also be composed of a part, that is, the AI / ML encoder and quantizer are regarded as a whole (for example, the AI / ML encoder and quantizer are inseparable and cannot be freely combined), and the AI / ML encoder may include a pre-processing module or may not include a pre-processing module. In this case, the AI / ML model information is composed of only a part, for example, the AI / ML model information is AI / ML model #5. The second AI / ML model may also be composed of a part, that is, the dequantizer and AI / ML decoder are regarded as a whole (for example, the AI / ML decoder and dequantizer are inseparable and cannot be freely combined), and the AI / ML decoder may include a post-processing module or may not include a post-processing module. In this case, the AI / ML reconstruction model information is composed of only a part, for example, the AI / ML reconstruction model information is AI / ML reconstruction model #5, or simply referred to as AI / ML model #5, to indicate the pairing relationship with the AI / ML model #5 in the AI / ML-based CSI generation part.

[0061] In the various embodiments of the present application, the first AI / ML model and the second AI / ML model may be collectively referred to as an AI / ML model, that is, the AI / ML model may include the first AI / ML model, or the second AI / ML model, or the first AI / ML model and the second AI / ML model that are paired with each other.

[0062] The embodiments of this application are based on the following scenarios and meet the following conditions:

[0063] 1. The terminal device and the network device have completed pairing of the AI / ML model. That is, the first AI / ML model supported by the terminal device and the second AI / ML model supported by the network device have been paired.

[0064] 2. After the AI / ML models are paired, the bit width of the output of each AI / ML-based generation model (for example, the bit width related to the precoding matrix information) corresponds to only one first AI / ML model (i.e., the AI / ML-based generation model).

[0065] In various embodiments of the present application, reporting may refer to an action of a terminal device sending information to a network device. For example, a terminal device reporting a CSI report may refer to the terminal device sending a CSI report to a network device.

[0066] Embodiments of the first aspect

[0067] An embodiment of the first aspect provides a channel state information generation method, which is applied to a terminal device, for example, the terminal device 202 shown in FIG. 2 .

[0068] FIG3 is a schematic diagram of a method for generating channel state information according to an embodiment of the first aspect. As shown in FIG3 , the method includes:

[0069] Operation 301: A terminal device receives a first configuration from a network device, where the first configuration is used to configure the terminal device to send channel state information (CSI) to the network device, where the first configuration includes model information and / or bit width information related to precoding matrix information; and

[0070] Operation 302: The terminal device generates the CSI based on a model, where the model is determined based on at least the first configuration, and the CSI includes at least the precoding matrix information.

[0071] According to an embodiment of the first aspect, the terminal device receives a first configuration corresponding to a model sent from a network device, thereby enabling the terminal device to be configured with respect to CSI reporting. Furthermore, the terminal device can generate CSI based on the model corresponding to the first configuration.

[0072] As shown in FIG3 , the method may further include:

[0073] Operation 303: The terminal device sends the CSI to the network device.

[0074] In some embodiments, the first configuration in operation 301 includes at least one of the following configurations: CSI reporting configuration, physical uplink control channel (PUCCH) configuration, physical uplink shared channel (PUSCH) configuration, and configuration regarding uplink control information.

[0075] In some embodiments, the precoding matrix information is related to information of the spatial layer.

[0076] The bit width information related to the precoding matrix information includes:

[0077] The bit width of the precoding matrix information, and / or the index of the bit width of the precoding matrix information, and / or the maximum value of the bit width of the precoding matrix information, and / or the index of the maximum value of the bit width of the precoding matrix information.

[0078] In some embodiments, the network device may directly configure the bit width information related to the precoding matrix information through a first configuration.

[0079] In other embodiments, the network device may implicitly configure the bit width information related to the precoding matrix information through the first configuration.

[0080] For example: the network device may configure (e.g., through a first configuration) the bit width of the CSI and / or the maximum bit width of the CSI; the network device may also configure (e.g., through a first configuration) a CSI report quantity (reportQuantity), the CSI report quantity including the precoding matrix information; the bit width of other information in the CSI report quantity other than the precoding matrix information is given by the standard and / or may be derived according to the standard; thus, the bit width of the precoding matrix information and / or the maximum bit width of the precoding matrix information is equal to the bit width of the CSI configured by the network device and / or the maximum bit width of the CSI minus the sum of the bit widths of other information in the CSI report quantity other than the precoding matrix information. Thus, the bit width of the precoding matrix information and / or the maximum bit width of the precoding matrix information may be implicitly configured.

[0081] In operation 302 , the model may be an artificial intelligence model, such as the aforementioned AI / ML model.

[0082] In some embodiments of operation 302 , the model is determined based on at least the first configuration, for example, the model is set by the first configuration, and / or the model is determined by the terminal device based on the first configuration.

[0083] In operation 302, the terminal device may generate CSI based on the model, where the CSI at least includes the precoding matrix information. For example, the precoding matrix information in the CSI may be generated by the model.

[0084] The present application is further described below in conjunction with multiple embodiments. In the following multiple embodiments, precoding matrix information may also be referred to as first information, and CSI generated by the terminal device based on the model may also be referred to as second information, wherein the first information is part of the second information.

[0085] Example 1

[0086] In the first embodiment, in addition to including model information and / or bit width information related to precoding matrix information, the first configuration also instructs the terminal device to report a rank indication, wherein the CSI also includes the rank indication.

[0087] In some implementations, the terminal device further receives third information sent by the network device.

[0088] For example, a terminal device receives a second configuration sent by a network device, where the second configuration includes third information and / or antenna port information, where the third information is used to limit a rank indication (RI) in the CSI and / or a value corresponding to the rank indication. The second configuration is used to provide a configuration for generating the first information and / or the second information. At least a portion of the first configuration is the second configuration, or the first configuration does not include the second configuration.

[0089] For another example, the third information is included in a third configuration, and the third configuration includes a configuration for generating the precoding matrix information and / or the CSI, wherein the third configuration is included in the second configuration, or the third configuration is not included in the second configuration.

[0090] In example, the third information may be included in the first configuration.

[0091] The following is an example of Example 1.

[0092] The network device sends a first configuration to the terminal device. In addition to including model information and / or bit width information related to precoding matrix information, the first configuration also indicates that the second information reported by the terminal device includes a rank indication.

[0093] In some embodiments, the first configuration further includes third information. The third information is used to restrict the rank indication in the second information. For example, the third information may be a rank indication restriction (RI restriction) parameter. The first configuration may be at least one of the following configurations: CSI report configuration, physical uplink control channel configuration, physical uplink shared channel configuration, and uplink control information (UCI) configuration. The third information may be provided by a bitmap or an index.

[0094] Among them, when the first configuration includes the CSI report configuration, one configuration includes configurations for the CSI report amount, time domain characteristics, frequency domain characteristics, etc. (such as configurations applicable to various methods of generating CSI (traditional codebooks, AI) and related technical configurations), as well as configurations for the AI / ML model for generating precoding matrix information based on the AI / ML method for generating CSI, and / or the bit width and / or maximum value of the bit width of the precoding matrix information, and configurations for the method of using the AI / ML model (all spatial layers use the same AI / ML model, at least two spatial layers use different AI / ML models, etc.). This implementation method has the advantages of saving control signaling and simple operation.

[0095] When the first configuration includes at least one of the physical uplink control channel configuration, the physical uplink shared channel configuration, and the configuration of uplink control information, it has the following beneficial effects: the "configuration of the AI / ML model for generating precoding matrix information, and / or the configuration of the bit width and / or the maximum value of the bit width of the precoding matrix information, the configuration of the AI / ML model usage method (all spatial layers use the same AI / ML model, at least two spatial layers use different AI / ML models, etc.)" is configured independently of the CSI report configuration. When changing the configuration of these contents, there is no need to change the content in the CSI report configuration, which is beneficial to the flexible configuration of the AI / ML method to generate CSI. At the same time, there is no need to resend the unchanged content of the CSI report configuration, thereby saving signaling overhead.

[0096] In some embodiments, the first configuration includes a second configuration, where the second configuration is used to provide a configuration for generating the first information and / or the second information. In this example, the second configuration is named CodebookConfig-ai, but it can also be named by other names. The third information can be included in the second configuration. In this example, the third information can be named AI-RI-Restriction in the information element (IE), but it can also be named by other names. In this embodiment, the second configuration and the third information are the configuration of the precoding matrix information and the rank indication restriction information required for CSI generation based on AI / ML methods. The configuration is provided in a manner similar to the logical relationship between the configuration of the precoding matrix information and the rank indication restriction information in CSI generation using codebooks. This embodiment has the advantage that similar variables are used to implement similar functions in the CSI generation scenario based on AI / ML methods and in the CSI generation scenario based on codebooks, minimizing changes to the standard, thereby reducing the complexity of standard understanding and implementation. Another advantage is that in product production, the implementation logic is similar to the corresponding part of CSI generation using codebooks, facilitating product design, implementation, and manufacturing.

[0097] Table 1 and Table 2 below provide a specific example. This example provides a method for defining an information element (IE) for configuring the third information.

[0098] Table 1

[0099] Table 2

[0100] In some embodiments, the first configuration does not include the second configuration. In this embodiment, the configuration for generating the first information and / or the second information is configured separately from the first configuration. For example, the second configuration is not included in the CSI report configuration. This embodiment has the beneficial effect of enabling on-demand configuration, enhancing the flexibility of CSI generation based on AI / ML methods, thereby facilitating the support and implementation of rich and varied functions. Another beneficial effect of this embodiment is that the configuration required for CSI generation based on AI / ML can be provided separately, that is, independent of the configuration applicable to all CSI generation (such as CSI generation using a codebook method). This helps to clearly describe the characteristics of CSI generation using AI / ML, making it easy to find the standard changes introduced by the AI / ML characteristics in the standard, making the standard clear and easy to understand; it also makes changes to AI / ML configurations clearer, and minimizes the misoperation of parameters of non-AI / ML characteristics due to changes in AI / ML parameters and variables.

[0101] In some implementations, the third information is not included in the second configuration. This implementation has the advantage of supporting more flexible configuration of the third information. For example, if the third information is included in the third configuration, which is not included in the second configuration, when the configuration of the rank indication restriction needs to be changed, there is no need to resend the entire configuration for generating CSI; only the configuration of the third information needs to be changed, thus saving signaling overhead.

[0102] Furthermore, when the third information is included in the third configuration, the third configuration can also be included in the second configuration. This embodiment has the beneficial effect of using similar variables to implement similar functions in scenarios where CSI is generated based on AI / ML methods and scenarios where CSI is generated based on codebook methods, minimizing changes to the standard and thus reducing the complexity of understanding and implementing the standard. Another beneficial effect is that in product production, the implementation logic is similar to the corresponding part of CSI generation using codebooks, facilitating product design, implementation, and manufacturing.

[0103] The above description of the first embodiment is applicable to any of the following embodiments. That is, the first embodiment can be implemented alone or in combination with any of the following embodiments.

[0104] Example 2

[0105] In the second embodiment, the first configuration includes one or more bit width information and / or model information.

[0106] The following description will be made by taking the case where the first configuration includes the bit width information as an example.

[0107] In some embodiments, the network device configures a bit width for the first information. This configuration is included in the CSI report configuration. Based on the scenario of the present application, a model is available for the terminal device. The terminal device uses the model to generate CSI for all spatial transmission layers for each possible value corresponding to the rank indicator, for example, to generate the first information and / or the second information.

[0108] Table 3 below provides a specific example, which provides a method for configuring a bit width.

[0109] Table 3

[0110] Table 3 above adds a configuration for the bit width of the first information, which can be an index named "payloadSize-ai" or another name. In Table 2 above, it is assumed that there are a total of eight AI / ML model pairs after the terminal device and network device are paired. This means that there are eight possible bit widths of the supported first information, which can be described using 3 bits. See Table 4 below for details.

[0111] Table 4

[0112] For example, the bit index of the bit width of the first information given by the network device in the CSI report configuration is represented as "100", which means that the network device configures the terminal device to report the bit width index of the first information as 5, corresponding to 90 bits.

[0113] In the second embodiment, the format of the CSI report sent by the terminal device through the uplink channel can refer to the relevant technology.

[0114] Example 3

[0115] In the third embodiment, the first configuration includes two or more types of bit width information and / or model information, wherein the precoding matrix information of at least one spatial layer is configured with one or more types of bit width information and / or model information.

[0116] The following description will be made by taking the case where the first configuration includes bit width information (eg, bit width and / or maximum value of bit width) as an example.

[0117] In some embodiments, the network device configures two or more bit widths of the first information. The configuration is included in the CSI report configuration (i.e., the first configuration). The network device configures one or more bit widths and / or maximum bit widths of the first information for each spatial layer. The number of spatial layers is equal to the value corresponding to the third information.

[0118] In some embodiments, the network device configures a bit width and / or a maximum bit width of the first information for each spatial layer. These bit widths and / or maximum bit widths may be the same, or at least two of them may be unequal. At this time, the terminal device generates CSI using the corresponding AI / ML model according to the configuration. For example, if the network device is configured with the information shown in Table 5 below, the value corresponding to the third information is 4, and the value corresponding to the RI obtained by the terminal device is 2, the terminal device uses the AI / ML model corresponding to 120 bits to generate the first information of the spatial layer with an index of 1, and the terminal device uses the AI / ML model corresponding to 100 bits to generate the first information of the spatial layer with an index of 2.

[0119] Table 5

[0120] For another example, the network device is configured with the information shown in Table 6 below, the value corresponding to the third information is 6, and the value corresponding to the RI obtained by the terminal device is 6, then the terminal device uses the AI / ML model corresponding to 120 bits to generate the first information of the spatial layer with an index of 1, the terminal device uses the AI / ML model corresponding to 100 bits to generate the first information of the spatial layer with an index of 2, the terminal device uses the AI / ML model corresponding to 80 bits to generate the first information of the spatial layer with an index of 3, the terminal device uses the AI / ML model corresponding to 70 bits to generate the first information of the spatial layer with an index of 4, the terminal device uses the AI / ML model corresponding to 70 bits to generate the first information of the spatial layer with an index of 5, and the terminal device uses the AI / ML model corresponding to 60 bits to generate the first information of the spatial layer with an index of 6.

[0121] Table 6

[0122] For another example, if the network device is configured with the information shown in Table 7 below, the value corresponding to the third information is 5, and the value corresponding to the RI obtained by the terminal device is 3, then the terminal device uses the AI / ML model corresponding to 100 bits to generate the first information of the spatial layer with an index of 1, the terminal device uses the AI / ML model corresponding to 100 bits to generate the first information of the spatial layer with an index of 2, and the terminal device uses the AI / ML model corresponding to 100 bits to generate the first information of the spatial layer with an index of 3. In this example, the three AI / ML models are the same.

[0123] Table 7

[0124] In the third embodiment, the format of the CSI report sent by the terminal device through the uplink channel can refer to the relevant technology.

[0125] Example 4

[0126] In embodiment four, for a spatial domain layer configured with two or more bit width information and / or model information, the terminal device sends a first indication message to the network device, where the first indication message is used to instruct the terminal device to determine the bit width information and / or model information on which the model is based.

[0127] The following description will be made by taking the case where the first configuration includes bit width information (eg, bit width and / or maximum value of bit width) as an example.

[0128] In some embodiments, the network device configures two or more bit widths of the first information. The configuration is included in the CSI report configuration. The network device configures one or more bit widths and / or maximum bit widths of the first information for each spatial layer. The number of the spatial layers is equal to the value corresponding to the third information.

[0129] In some implementations, the network device configures one or more bit widths and / or maximum bit widths of the first information for each spatial layer, wherein at least two spatial layers are configured with two or more bit widths and / or maximum bit widths of the first information. There may be more than two spatial layers with a common bit width and / or maximum bit width of the first information, or there may be no such a configuration.

[0130] For example, the network device is configured with the information shown in Table 8 below, the value corresponding to the third information is 3, and the value corresponding to the RI obtained by the terminal device is 2. The terminal device uses the AI / ML model corresponding to 120 bits to generate the first information of the spatial layer with an index of 1, and the terminal device uses the AI / ML model corresponding to 80 bits to generate the first information of the spatial layer with an index of 2. The terminal device may also use the AI / ML model corresponding to 100 bits to generate the first information of the spatial layer with an index of 1, and the terminal device uses the AI / ML model corresponding to 120 bits to generate the first information of the spatial layer with an index of 2. The terminal device may also use the AI / ML model corresponding to 80 bits to generate the first information of the spatial layer with an index of 1, and the terminal device uses the AI / ML model corresponding to 80 bits to generate the first information of the spatial layer with an index of 2.

[0131] Table 8

[0132] Because the bit width and / or maximum bit width of the first information for each spatial domain layer is configured by the network device, the network device knows which spatial domain layers have two or more optional bit widths and / or maximum bit widths of the first information, and also knows the number of optional bit widths for each layer. For the bit widths and / or maximum bit widths of the first information that have two or more optional values, these values ​​can be mapped to indexes, for example, as shown in Table 9 below.

[0133] Table 9

[0134] N / A indicates not applicable. The bit width index can be determined based on a specific rule, such as a standard or an agreement between network devices and terminal devices. In this example, the index is sorted in ascending order of bit width.

[0135] The CSI report sent by the terminal device through the uplink channel may include the index of the bit width used by the terminal device for reporting the spatial layer configured with two or more bit widths of the first information and / or the maximum value of the bit width. This information can be included in the first part of the CSI (Part 1 CSI). For example, the value corresponding to the RI obtained by the terminal device is 2, the terminal device uses the AI / ML model corresponding to 120 bits to generate the first information of the spatial layer with an index of 1, and the terminal device uses the AI / ML model corresponding to 80 bits to generate the first information of the spatial layer with an index of 2. Then in the first part of the CSI report, the bit description of the index of the bit width of the spatial layer with an index of 1 is also reported, that is, 10; the bit description of the index of the bit width of the spatial layer with an index of 2 is also reported, that is, 1.

[0136] In addition, for the description of the first part of CSI (Part 1 CSI), please refer to the relevant technology.

[0137] Example 5

[0138] In the fifth embodiment, for a value of the rank indicator, the precoding matrix information is configured with one or more bit width information and / or model information.

[0139] The following description will be made by taking the case where the first configuration includes bit width information (eg, bit width and / or maximum value of bit width) as an example.

[0140] In some embodiments, the network device configures two or more bit widths of the first information. The configuration is included in the CSI report configuration. The network device configures one or more bit widths and / or maximum bit widths of the first information for each possible rank indication (RI) value in the CSI report. The value corresponding to the RI is a positive integer less than or equal to the value corresponding to the third information. These bit widths and / or maximum bit widths can be the same, or at least two of them can be unequal.

[0141] In some embodiments, the network device configures a bit width and / or maximum bit width of the first information for each possible RI value in the CSI report. For each possible RI value, the terminal device generates CSI using the corresponding AI / ML model based on the configuration. Specifically, the bit width and / or maximum bit width of the first information for each spatial layer are the same. In other words, the terminal device uses the same AI / ML model to generate CSI for each spatial layer.

[0142] For example, if the network device is configured with the information described in Table 10 below, the value corresponding to the third information is 4, and the value corresponding to the RI obtained by the terminal device is 2, the terminal device uses the AI / ML model corresponding to 110 bits to generate the first information of the spatial layer with an index of 1, and the terminal device uses the AI / ML model corresponding to 110 bits to generate the first information of the spatial layer with an index of 2.

[0143] Table 10

[0144] Since the bit width and / or maximum bit width of the first information corresponding to each RI value is configured by the network device, after knowing the RI, the network device can know the bit width and / or maximum bit width of the first information of each spatial layer. In this case, the format of the CSI report sent by the terminal device via the uplink channel may be specified in accordance with relevant technical regulations.

[0145] Example 6

[0146] In embodiment six, for the values ​​configured with more than two of the bit width information and / or model information, the terminal device sends a second indication information to the network device, and the second indication information is used to instruct the terminal device to determine the bit width information and / or model information based on which the model is determined.

[0147] The following description will be made by taking the case where the first configuration includes bit width information (eg, bit width and / or maximum value of bit width) as an example.

[0148] In some embodiments, the network device configures two or more bit widths of the first information. The configuration is included in the CSI report configuration. The network device configures one or more bit widths and / or maximum bit widths of the first information for each possible RI value in the CSI report. The RI value is a positive integer less than or equal to the value corresponding to the third information. These bit widths and / or maximum bit widths can be the same, or at least two of them can be unequal.

[0149] In some embodiments, the network device configures at least one possible RI value and configures the bit width and / or maximum bit width of two or more of the first information. For each possible RI value, the terminal device generates CSI using the corresponding AI / ML model based on the configuration. Specifically, the bit width and / or maximum bit width of the first information for each spatial layer are the same. In other words, the terminal device uses the same AI / ML model to generate CSI for each spatial layer.

[0150] For example, the network device is configured with the information shown in Table 11 below, where the value corresponding to the third information is 4. Since the bit width and / or the maximum bit width of the first information corresponding to each RI value is configured by the network device, the network device knows which RI values ​​have two or more optional bit widths and / or maximum bit widths of the first information, and also knows how many of these optional bit widths there are. Therefore, the network device knows the maximum number of optional bit widths and / or maximum bit widths of the first information for all RI values, and records this "maximum number" as the tenth information.

[0151] Table 11

[0152] Since the network device is not sure about the RI value obtained by the terminal device, the CSI report needs to include information about the bit width of the first information and / or the maximum value of the bit width (for example, recorded as the eleventh information), such as an index, which can be described by a bit string. In this example, the tenth information is 2, so the eleventh information can be represented as Table 12 below, which can be specified by the standard or agreed upon by the terminal device and the network device. The index of the bit width can be formulated according to a certain rule, such as specified by the standard or agreed upon by the network device and the terminal device. In this example, the order of the indexes is arranged in ascending order from large to small according to the bit width.

[0153] Table 12

[0154] The eleventh information may be included in the first part of the CSI (Part 1 CSI). For example, the value corresponding to the RI obtained by the terminal device is 2, the terminal device uses the AI / ML model corresponding to 110 bits to generate the first information of the spatial layer with an index of 1, and the terminal device uses the AI / ML model corresponding to 110 bits to generate the first information of the spatial layer with an index of 2 (the same AI / ML model). Then, in the first part of the CSI report, the bit representation of the eleventh information, that is, 10, is also reported. For another example, the value corresponding to the RI obtained by the terminal device is 3, the terminal device uses the AI / ML model corresponding to 90 bits to generate the first information of the spatial layer with an index of 1, the terminal device uses the AI / ML model corresponding to 90 bits to generate the first information of the spatial layer with an index of 2, and the terminal device uses the AI / ML model corresponding to 90 bits to generate the first information of the spatial layer with an index of 3 (the same AI / ML model). Then, in the first part of the CSI report, the bit representation of the eleventh information, that is, 00, is also reported.

[0155] Example 7

[0156] In the seventh embodiment, at least one spatial domain layer under at least one value of the rank indication is configured with more than one bit width information or model information.

[0157] The following description will be made by taking the case where the first configuration includes bit width information (eg, bit width and / or maximum value of bit width) as an example.

[0158] In some embodiments, the network device configures two or more bit widths of the first information. The configuration is included in the CSI report configuration. The network device configures one or more bit widths and / or maximum bit widths of the first information for each spatial layer corresponding to each possible RI value in the CSI report. The RI value is a positive integer less than or equal to the value corresponding to the third information. These bit widths and / or maximum bit widths can be the same, or at least two of them can be unequal.

[0159] The following example is based on Example 5. For RI values ​​greater than 1, the network device further configures a bit width and / or a maximum bit width of the first information for each spatial layer. For example, the network device configures the information shown in Table 13 below, where the value corresponding to the third information is 3.

[0160] Table 13

[0161] The format of the CSI report sent by the terminal device through the uplink channel may be specified by relevant technologies.

[0162] Example 8

[0163] In the eighth embodiment, the terminal device sends a third indication information to the network device, where the third indication information is used to indicate the bit width information and / or model information corresponding to the model determined by the terminal device for each spatial layer.

[0164] The following description will be made by taking the case where the first configuration includes bit width information (eg, bit width and / or maximum value of bit width) as an example.

[0165] In some implementations, the network device configures two or more bit widths for the first information. This configuration is independent of the spatial layer and RI. For example, the network device configures the information shown in Table 14 below, where the value corresponding to the third information is 4. The two or more bit widths and / or the maximum bit widths for the first information are shown in Table 14.

[0166] Table 14

[0167] Where index 0 indicates that the terminal device does not report the first information in this spatial layer. The terminal device selects the bit width and / or the maximum bit width of the first information for each spatial layer based on the RI it obtains, thereby selecting the corresponding AI / ML model.

[0168] For example, the value corresponding to the RI obtained by the terminal device is 2. The terminal device uses the AI / ML model corresponding to the bit width of the first information with an index of 2 for the spatial domain layer with an index of 1 to generate the first information; the terminal device uses the AI / ML model corresponding to the bit width of the first information with an index of 4 for the spatial domain layer with an index of 2 to generate the first information.

[0169] In the CSI report, since the network device (before receiving the CSI report) does not know the RI value obtained by the terminal device, the terminal device needs to report the bit width information of the first information of Y spatial domain layers, such as the index, where Y is equal to the value corresponding to the third information.

[0170] In this example, the value corresponding to the third information is 4, that is, Y=4. The terminal device can report RI and the index of the bit width of the Y first information in the first part of the CSI. The terminal device reports the first information in the second part of the CSI. For example, the value corresponding to the RI obtained by the terminal device is 2, and the terminal device reports RI and the information of the bit width of the 4 first information in the first part of the CSI, which is 010100000000, wherein the meaning of each bit from left to right in this information is: 010 represents the index of the bit width of the first information of the spatial layer with an index of 1; 100 represents the index of the bit width of the first information of the spatial layer with an index of 2; 000 represents the index of the bit width of the first information of the spatial layer with an index of 3; 000 represents the index of the bit width of the first information of the spatial layer with an index of 4.

[0171] Example 9

[0172] In each embodiment of the present application, since the terminal device and the network device complete the AI / ML model pairing, and after the AI / ML model pairing, the bit width and / or the maximum value of the bit width of a first information only corresponds to one AI / ML model pair (for example, an AI / ML model pair includes a first AI / ML model and a second AI / ML model that are paired with each other).

[0173] In Example 9, the configuration of "bit width and / or maximum bit width" in Examples 1 to 8 (for example, Tables 1 to 14) can be replaced by the configuration of AI / ML model information.

[0174] After the AI / ML models are paired, a first identifier, such as an ID or index, may be assigned to the paired AI / ML models. The arrangement of the first identifiers may be specified by the standard or agreed upon by the terminal device and the network device. In the case where an AI / ML model only supports one bit width of the first information, one first identifier may be assigned to the AI / ML model. In the case where an AI / ML model supports Z types (Z>1, Z is a natural number) of bit widths of the first information, Z first identifiers may be assigned to the model, and each first identifier corresponds to a bit width of the first information. Since the bit width and / or the maximum value of the bit width of one first information only corresponds to one AI / ML model pair, the first identifier and the bit width of the first information are in a one-to-one correspondence.

[0175] In some embodiments, assuming that after the AI / ML model is paired, the network device and the terminal device jointly support three models, and the three models have unique information describing them, such as information that can be uniquely identified in network devices and terminal devices produced by all manufacturers, such as a global identifier. The first bit width of the first information is 140 bits, and the global identifier is doengjf0t3; the second bit width of the first information is 70 bits, and the global identifier is swirnvv024jos; the third supports three bit widths of the first information, and the global identifier is 43dnfogba0cndi. The bit widths of the first information supported are 120 bits, 105 bits, and 60 bits, respectively. The first identifier is assigned in descending order according to the bit width of the supported first information, as shown in Table 15.

[0176] Table 15

[0177] The first identifier is used when the network device configures and / or the terminal device reports AI / ML model information.

[0178] Example 10

[0179] In the tenth embodiment, the terminal device receives a fourth configuration from the network device, where the fourth configuration is used to configure:

[0180] The model used in each spatial layer is the same, or the model used in at least two spatial layers is different; and / or

[0181] For at least two values ​​of the rank indication, the models used to generate the precoding matrix information corresponding to each of the values ​​are the same, or the models used to generate the precoding matrix information corresponding to at least two of the values ​​are different.

[0182] In at least one embodiment, at least a portion of the first configuration is the fourth configuration, or the first configuration does not include the fourth configuration.

[0183] In at least one embodiment, if the models configured to be used in each spatial layer are the same, the terminal device sends fourth indication information to the network device, where the fourth indication information is used to indicate information of one of the determined models.

[0184] In at least one embodiment, if the models configured to be used in at least two spatial layers are different, the terminal device sends fifth indication information to the network device, where the fifth indication information is used to indicate information of the model determined in each of the spatial layers.

[0185] In at least one embodiment, the first value corresponding to the rank indication is less than the value corresponding to the third information, and the fifth indication information may include N fourth information, where N is the difference between the value corresponding to the third information and the first value. The fourth information indicates that the model does not exist. Furthermore, the fourth information is predefined.

[0186] For example, if the value corresponding to the third information is configured as 4, the first value corresponding to the rank indication reported by the terminal device cannot exceed 4. Assuming that the first value corresponding to the rank indication reported by the terminal device is 3, it means that the terminal device reports the information of the model corresponding to the 2-layer transmission, such as A, B, and A. However, since the network device does not know the first value before the terminal device reports, the terminal device needs to report 4 model information, such as A, B, A, and empty. The "empty" here refers to the fourth information.

[0187] The following is an example of the tenth embodiment.

[0188] In some embodiments, the terminal device provides one or more of the following information through the fourth configuration: whether the same or different AI / ML models are used for the spatial layer; and whether the same or different AI / ML models are used for all possible values ​​corresponding to more than one RI. This embodiment advantageously allows the network device to directly and clearly configure the use of the AI / ML model for the spatial layer and / or the range of values ​​corresponding to the RI, making it easy to understand. Furthermore, there are no restrictions on the specific model used, giving the terminal device the opportunity to select the most appropriate model, which can improve system performance, such as system throughput.

[0189] The fourth configuration also includes information about one or more AI / ML models configured on the network device. The fourth configuration may be a CSI reporting configuration. For example, the fourth configuration is included in the first configuration.

[0190] For example, the information in the fourth configuration described above may be mapped to indexes as shown in Table 16 and Table 17 below.

[0191] Table 16

[0192] Table 17

[0193] In the fourth configuration, the order of the first index and the second index can be specified by the standard or agreed upon by the terminal device and the network device. In this example, it is assumed that the first index comes before the second index. In the fourth configuration, information about the available AI / ML models (i.e., information about the paired AI / ML models) is also provided, such as Table 15 above.

[0194] In some implementations, if the first and second indices provided by the network device in the fourth configuration are 00, then all spatial layers use the same AI / ML model; and all possible RIs use the same AI / ML model. In this case, the terminal device only needs to report information about one AI / ML model. For example, the identifier and / or index of the AI / ML model, such as the first identifier, can be reported in the first part of the CSI report.

[0195] In some implementations, if the first and second indices provided by the network device in the fourth configuration are 01, all spatial layers use the same AI / ML model, and at least two possible RIs use different AI / ML models. In this case, the format of the CSI report by the terminal device can be the same as when the first and second indices are 00.

[0196] In some embodiments, the first index and the second index given by the network device in the fourth configuration are 10, then the AI / ML models used by at least two spatial layers are different; and the AI / ML model used is the same for all possible RIs. In this case, the number of pieces of information that the terminal device needs to report for one AI / ML model is the value corresponding to the third information. If the value corresponding to the RI is less than the value corresponding to the third information, after reporting the AI / ML model identifier whose number is the value corresponding to the RI, the 30th piece of information whose number is the difference between the value corresponding to the third information and the value corresponding to the RI is reported, and the 30th piece of information indicates that there is no AI / ML model. For example, the identifier and / or index of the AI / ML model can be reported in the first part of the CSI report, such as the second representation and / or the 30th piece of information. For example, if the value corresponding to the third information is 3 and the value corresponding to the RI is 2, the terminal device needs to report 2 second identifiers and 1 piece of the 30th piece of information.

[0197] In some implementations, if the first and second indices provided by the network device in the fourth configuration are 11, then at least two spatial layers use different AI / ML models; and at least two possible RIs use different AI / ML models. In this case, the format of the CSI report by the terminal device can be the same as when the first and second indices are 10.

[0198] The above is a description of the embodiments of the first aspect of the present application in combination with Embodiments 1 to 10. The above Embodiments 1 to 10 do not limit the implementation of the technical solution of the present application. For example, the above Embodiments 1 to 10 can be reasonably combined or modified.

[0199] Embodiments of the first aspect of the present application provide the configuration and CSI reporting format required to generate and transmit CSI based on AI / ML methods. The present application provides corresponding configurations and reporting formats for one or more possible scenarios. The present application provides a CSI reporting format applicable to at least some configurations, enabling network devices to unambiguously understand CSI. The present application provides a reporting format for some configurations that can reduce the content of the CSI report, thereby reducing the overhead of reporting CSI. This reporting format also enables network devices to unambiguously understand CSI.

[0200] Embodiments of the second aspect

[0201] The embodiment of the second aspect provides a channel state information configuration method, which is applied to a network device, such as the network device 201 in Figure 2. For the parts of the embodiment of the second aspect that are the same as those of the embodiment of the first aspect, reference can be made to the description of the embodiment of the first aspect, which will not be repeated here.

[0202] FIG4 is a schematic diagram of a channel state information configuration method according to an embodiment of the second aspect. The method includes:

[0203] Operation 401: The network device sends a first configuration to a terminal device, where the first configuration is used to configure the terminal device to send channel state information (CSI) to the network device, and the first configuration includes model information and / or bit width information related to precoding matrix information; and

[0204] Operation 402: The CSI is generated by the terminal device based on a model, the model is determined based on at least the first configuration, and the CSI includes at least the precoding matrix information.

[0205] In some embodiments, as shown in FIG4 , the method further includes:

[0206] Operation 403: The network device further receives CSI.

[0207] In some embodiments, the first configuration includes a CSI reporting configuration and / or a physical uplink control channel configuration and / or a physical uplink shared channel configuration.

[0208] In some embodiments, the model is an artificial intelligence model.

[0209] In some embodiments, the model is set by the first configuration, and / or the model is determined by the terminal device based on the first configuration.

[0210] In some embodiments, the precoding matrix information is related to information of a spatial layer.

[0211] In some embodiments, the bit width information related to the precoding matrix information includes:

[0212] The bit width of the precoding matrix information, and / or the index of the bit width of the precoding matrix information, and / or the maximum value of the bit width of the precoding matrix information, and / or the index of the maximum value of the bit width of the precoding matrix information.

[0213] In some embodiments, the first configuration further instructs the terminal device to report a rank indication, and the CSI further includes the rank indication.

[0214] In some embodiments, the network device further sends a second configuration to the terminal device.

[0215] The second configuration includes third information and / or antenna port information, where the third information is used to limit the rank indication in the CSI and / or a value corresponding to the rank indication.

[0216] In some embodiments, at least a portion of the first configuration is the second configuration, or the first configuration does not include the second configuration.

[0217] In some embodiments, the network device further sends a third configuration to the terminal device.

[0218] The third configuration includes third information,

[0219] The third configuration includes a configuration for generating the precoding matrix information and / or the CSI,

[0220] The third information is used to limit the rank indication in the CSI and / or a value corresponding to the rank indication.

[0221] In some embodiments, the third configuration is included in the second configuration, or the third configuration is not included in the second configuration.

[0222] In some embodiments, the first configuration includes more than one type of bit width information and / or model information.

[0223] In some embodiments, the first configuration includes more than two types of the bit width information and / or model information.

[0224] In some embodiments, the precoding matrix information of at least one spatial layer is configured with more than one type of bit width information and / or model information.

[0225] In some embodiments, for the spatial domain layer configured with more than two types of bit width information and / or model information, the network device receives first indication information sent by the terminal device, and the first indication information is used to instruct the terminal device to determine the bit width information or model information based on which the model is determined.

[0226] In some embodiments, for a value of the rank indication, the precoding matrix information is configured with more than one type of bit width information and / or model information.

[0227] In some embodiments, for the values ​​configured with more than two of the bit width information or model information, the network device receives second indication information sent by the terminal device, and the second indication information is used to instruct the terminal device to determine the bit width information and / or model information based on which the model is determined.

[0228] In some embodiments, at least one spatial layer under at least one value of the rank indication is configured with more than one type of the bit width information and / or model information.

[0229] In some embodiments, the network device receives third indication information sent by the terminal device, where the third indication information is used to indicate the bit width information and / or model information corresponding to the model determined by the terminal device for each spatial layer.

[0230] In some embodiments, the network device sends a fourth configuration to the terminal device, where the fourth configuration is used to configure:

[0231] The model used in each spatial layer is the same, or the model used in at least two spatial layers is different; and / or

[0232] For at least two values ​​of the rank indication, the models used to generate the precoding matrix information corresponding to each of the values ​​are the same, or the models used to generate the precoding matrix information corresponding to at least two of the values ​​are different.

[0233] In some embodiments, at least a portion of the first configuration is the fourth configuration, or the first configuration does not include the fourth configuration.

[0234] In some embodiments, the model configured to be used in each spatial layer is the same.

[0235] The network device receives fourth indication information sent by the terminal device, where the fourth indication information is used to indicate information of one of the determined models.

[0236] In some embodiments, the models used by at least two spatial layers are configured to be different.

[0237] The network device receives fifth indication information sent by the terminal device, where the fifth indication information is used to indicate information of the model determined in each of the spatial domain layers.

[0238] In some embodiments, the first value corresponding to the rank indication is smaller than the value corresponding to the third information, and the fifth indication information includes N fourth information, where N is the difference obtained by subtracting the first value from the value corresponding to the third information.

[0239] In some embodiments, the fourth information is predefined information.

[0240] In some embodiments, the fourth information indicates that the model does not exist.

[0241] Embodiments of the third aspect

[0242] At least for the same problem as the embodiment of the first aspect, the embodiment of the third aspect of the present application provides a channel state information generation device, which is applied to a terminal device and corresponds to the embodiment of the first aspect.

[0243] FIG5 is a schematic diagram of a channel state information generation apparatus according to an embodiment of the third aspect. As shown in FIG5 , the channel state information generation apparatus 500 includes: a first processing unit 501 .

[0244] The first processing unit 501 causes the terminal device to perform the following operations:

[0245] The terminal device receives a first configuration from a network device, where the first configuration is used to configure the terminal device to send channel state information (CSI) to the network device, where the first configuration includes model information and / or bit width information related to precoding matrix information; and

[0246] The terminal device generates the CSI based on a model, where the model is determined based on at least the first configuration, and the CSI includes at least the precoding matrix information.

[0247] In some embodiments, the operations further include:

[0248] The terminal device sends the CSI to the network device.

[0249] In some embodiments, the first configuration includes a CSI reporting configuration and / or a physical uplink control channel configuration and / or a physical uplink shared channel configuration.

[0250] In some embodiments, the model is an artificial intelligence model.

[0251] In some embodiments, the model is set by the first configuration, and / or the model is determined by the terminal device based on the first configuration.

[0252] In some embodiments, the precoding matrix information is related to information of a spatial layer.

[0253] In some embodiments, the bit width information related to the precoding matrix information includes:

[0254] The bit width of the precoding matrix information, and / or the index of the bit width of the precoding matrix information, and / or the maximum value of the bit width of the precoding matrix information, and / or the index of the maximum value of the bit width of the precoding matrix information.

[0255] In some embodiments, the first configuration further instructs the terminal device to report a rank indication, and the CSI further includes the rank indication.

[0256] In some embodiments, the terminal device further receives a second configuration sent by the network device.

[0257] The second configuration includes third information and / or antenna port information, where the third information is used to limit the rank indication in the CSI and / or a value corresponding to the rank indication.

[0258] In some embodiments, at least a portion of the first configuration is the second configuration, or the first configuration does not include the second configuration.

[0259] In some embodiments, the terminal device also receives a third configuration sent by the network device, the third configuration including third information, the third configuration including a configuration for generating the precoding matrix information and / or the CSI, and the third information is used to limit the rank indication in the CSI and / or the value corresponding to the rank indication.

[0260] In some embodiments, the third configuration is included in the second configuration, or the third configuration is not included in the second configuration.

[0261] In some embodiments, the first configuration includes more than one type of bit width information and / or model information.

[0262] In some embodiments, the first configuration includes more than two types of the bit width information and / or model information.

[0263] In some embodiments, the precoding matrix information of at least one spatial layer is configured with more than one type of bit width information and / or model information.

[0264] In some embodiments, for the spatial domain layer configured with more than two types of bit width information and / or model information, the terminal device sends a first indication information to the network device, and the first indication information is used to instruct the terminal device to determine the bit width information and / or model information based on which the model is determined.

[0265] In some embodiments, for a value of the rank indication, the precoding matrix information is configured with more than one type of bit width information and / or model information.

[0266] In some embodiments, for the values ​​configured with more than two of the bit width information and / or model information, the terminal device sends a second indication information to the network device, and the second indication information is used to instruct the terminal device to determine the bit width information and / or model information based on which the model is determined.

[0267] In some embodiments, at least one spatial layer under at least one value of the rank indication is configured with more than one bit width information or model information.

[0268] In some embodiments, the terminal device sends third indication information to the network device, where the third indication information is used to indicate the bit width information and / or model information corresponding to the model determined by the terminal device for each spatial layer.

[0269] In some embodiments, the terminal device receives a fourth configuration from the network device, where the fourth configuration is used to configure:

[0270] The model used in each spatial layer is the same, or the model used in at least two spatial layers is different; and / or

[0271] For at least two values ​​of the rank indication, the models used to generate the precoding matrix information corresponding to each of the values ​​are the same, or the models used to generate the precoding matrix information corresponding to at least two of the values ​​are different.

[0272] In some embodiments, at least a portion of the first configuration is the fourth configuration, or the first configuration does not include the fourth configuration.

[0273] In some embodiments, the model configured to be used in each spatial layer is the same, and the terminal device sends fourth indication information to the network device, where the fourth indication information is used to indicate information of one of the determined models.

[0274] In some embodiments, the models used in at least two spatial layers are configured to be different, and the terminal device sends fifth indication information to the network device, where the fifth indication information is used to indicate information of the model determined in each of the spatial layers.

[0275] In some embodiments, the first value corresponding to the rank indication is smaller than the value corresponding to the third information, and the fifth indication information includes N fourth information, where N is the difference obtained by subtracting the first value from the value corresponding to the third information.

[0276] In some embodiments, the fourth information is predefined information.

[0277] In some embodiments, the fourth information indicates that the model does not exist.

[0278] Embodiments of the fourth aspect

[0279] An embodiment of the fourth aspect of the present application provides a channel state information configuration device, which is applied to a network device and corresponds to the method of the embodiment of the second aspect.

[0280] FIG6 is a schematic diagram of a channel state information configuration device according to an embodiment of the fourth aspect. As shown in FIG6 , the device 600 includes: a second processing unit 601 .

[0281] In at least one embodiment, the second processing unit 601 controls the network device to perform the following operations:

[0282] The network device sends a first configuration to the terminal device, where the first configuration is used to configure the terminal device to send channel state information (CSI) to the network device, and the first configuration includes model information and / or bit width information related to precoding matrix information; and

[0283] The CSI is generated by the terminal device based on a model, the model is determined based on at least the first configuration, and the CSI includes at least the precoding matrix information.

[0284] In some embodiments, the network device also receives the CSI.

[0285] In some embodiments, the first configuration includes a CSI reporting configuration and / or a physical uplink control channel configuration and / or a physical uplink shared channel configuration.

[0286] In some embodiments, the model is an artificial intelligence model.

[0287] In some embodiments, the model is set by the first configuration, and / or the model is determined by the terminal device based on the first configuration.

[0288] In some embodiments, the precoding matrix information is related to information of a spatial layer.

[0289] In some embodiments, the bit width information related to the precoding matrix information includes:

[0290] The bit width of the precoding matrix information, and / or the index of the bit width of the precoding matrix information, and / or the maximum value of the bit width of the precoding matrix information, and / or the index of the maximum value of the bit width of the precoding matrix information.

[0291] In some embodiments, the first configuration further instructs the terminal device to report a rank indication, and the CSI further includes the rank indication.

[0292] In some embodiments, the network device also sends a second configuration to the terminal device, where the second configuration includes third information and / or antenna port information, and the third information is used to limit the rank indication in the CSI and / or the value corresponding to the rank indication.

[0293] In some embodiments, at least a portion of the first configuration is the second configuration, or the first configuration does not include the second configuration.

[0294] In some embodiments, the network device also sends a third configuration to the terminal device, wherein the third configuration includes third information, and the third configuration includes a configuration for generating the precoding matrix information and / or the CSI, and the third information is used to limit the rank indication in the CSI and / or the value corresponding to the rank indication.

[0295] In some embodiments, the third configuration is included in the second configuration, or the third configuration is not included in the second configuration.

[0296] In some embodiments, the first configuration includes more than one type of bit width information and / or model information.

[0297] In some embodiments, the first configuration includes more than two types of the bit width information and / or model information.

[0298] In some embodiments, the precoding matrix information of at least one spatial layer is configured with more than one type of bit width information and / or model information.

[0299] In some embodiments, for the spatial domain layer configured with more than two types of bit width information and / or model information, the network device receives first indication information sent by the terminal device, and the first indication information is used to instruct the terminal device to determine the bit width information or model information based on which the model is determined.

[0300] In some embodiments, for a value of the rank indication, the precoding matrix information is configured with more than one type of bit width information and / or model information.

[0301] In some embodiments, for the values ​​configured with more than two of the bit width information or model information, the network device receives second indication information sent by the terminal device, and the second indication information is used to instruct the terminal device to determine the bit width information and / or model information based on which the model is determined.

[0302] In some embodiments, at least one spatial layer under at least one value of the rank indication is configured with more than one type of the bit width information and / or model information.

[0303] In some embodiments, the network device receives third indication information sent by the terminal device, where the third indication information is used to indicate the bit width information and / or model information corresponding to the model determined by the terminal device for each spatial layer.

[0304] In some embodiments, the network device sends a fourth configuration to the terminal device, where the fourth configuration is used to configure:

[0305] The model used in each spatial layer is the same, or the model used in at least two spatial layers is different; and / or

[0306] For at least two values ​​of the rank indication, the models used to generate the precoding matrix information corresponding to each of the values ​​are the same, or the models used to generate the precoding matrix information corresponding to at least two of the values ​​are different.

[0307] In some embodiments, at least a portion of the first configuration is the fourth configuration, or the first configuration does not include the fourth configuration.

[0308] In some embodiments, the model configured to be used in each spatial layer is the same.

[0309] The network device receives fourth indication information sent by the terminal device, where the fourth indication information is used to indicate information of one of the determined models.

[0310] In some embodiments, the models used by at least two spatial layers are configured to be different.

[0311] The network device receives fifth indication information sent by the terminal device, where the fifth indication information is used to indicate information of the model determined in each of the spatial domain layers.

[0312] In some embodiments, the first value corresponding to the rank indication is smaller than the value corresponding to the third information, and the fifth indication information includes N fourth information, where N is the difference obtained by subtracting the first value from the value corresponding to the third information.

[0313] In some embodiments, the fourth information is predefined information.

[0314] In some embodiments, the fourth information indicates that the model does not exist.

[0315] Embodiments of the fifth aspect

[0316] An embodiment of the fifth aspect of the present application provides a communication system, which may include a network device and a terminal device.

[0317] FIG7 is a schematic diagram of a terminal device according to an embodiment of the fifth aspect. As shown in FIG7 , the terminal device 700 (e.g., corresponding to the terminal device 202 in FIG2 ) may include a processor 710 and a memory 720; the memory 720 stores data and programs and is coupled to the processor 710. It should be noted that this diagram is exemplary; other types of structures may be used to supplement or replace this structure to implement telecommunication functions or other functions.

[0318] For example, the processor 710 can be configured to execute a program to implement the method in the embodiment of the first aspect.

[0319] As shown in Figure 7 , the terminal device 700 may further include: a communication module 730, an input unit 740, a display 750, and a power supply 760. The functions of these components are similar to those in the prior art and are not described in detail here. It is worth noting that the terminal device 700 does not necessarily include all of the components shown in Figure 7 , and these components are not essential. Furthermore, the terminal device 700 may also include components not shown in Figure 7 , for which reference may be made to the prior art.

[0320] FIG8 is a schematic diagram of a network device according to an embodiment of the fifth aspect. As shown in FIG8 , network device 800 (e.g., corresponding to network device 201 in FIG2 ) may include a processor 810 (e.g., a central processing unit (CPU)) and a memory 820; the memory 820 is coupled to the processor 810. The memory 820 may store various data and may also store an information processing program 830, which is executed under the control of the processor 88.

[0321] For example, the processor 88 may be configured to execute a program to implement the method described in the embodiment of the second aspect.

[0322] In addition, as shown in FIG8 , network device 800 may further include: a transceiver 840 and an antenna 850, etc.; wherein, the functions of the above components are similar to those in the prior art and are not described in detail here. It is worth noting that network device 800 does not necessarily include all the components shown in FIG8 ; in addition, network device 800 may also include components not shown in FIG8 , and reference may be made to the prior art for details.

[0323] An embodiment of the present application also provides a computer program, wherein when the program is executed in a terminal device, the program causes the terminal device to execute the method described in the embodiment of the first aspect.

[0324] An embodiment of the present application also provides a storage medium storing a computer program, wherein the computer program enables a terminal device to execute the method described in the embodiment of the first aspect.

[0325] An embodiment of the present application also provides a computer program, wherein when the program is executed in a network device, the program causes the network device to execute the method described in the embodiment of the second aspect.

[0326] An embodiment of the present application also provides a storage medium storing a computer program, wherein the computer program enables a network device to execute the method described in the embodiment of the second aspect.

[0327] The above devices and methods of the present application can be implemented by hardware or by a combination of hardware and software. The present application relates to such a computer-readable program that, when executed by a logic component, enables the logic component to implement the devices or components described above, or enables the logic component to implement the various methods or steps described above. The present application also relates to a storage medium for storing the above program, such as a hard disk, a magnetic disk, an optical disk, a DVD, a flash memory, etc.

[0328] The method / device described in conjunction with the embodiments of the present application can be directly embodied as hardware, a software module executed by a processor, or a combination of the two. For example, one or more of the functional block diagrams shown in the figure and / or one or more combinations of functional block diagrams can correspond to various software modules of the computer program flow or to various hardware modules. These software modules can respectively correspond to the various steps shown in the figure. These hardware modules can be implemented by solidifying these software modules, for example, using a field programmable gate array (FPGA).

[0329] The software module may be located in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. A storage medium may be coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium; or the storage medium may be an integral part of the processor. The processor and the storage medium may be located in an ASIC. The software module may be stored in the memory of the mobile terminal or in a memory card that can be inserted into the mobile terminal. For example, if the device (such as a mobile terminal) uses a large-capacity MEGA-SIM card or a large-capacity flash memory device, the software module may be stored in the MEGA-SIM card or the large-capacity flash memory device.

[0330] One or more of the functional blocks and / or one or more combinations of functional blocks described in the accompanying drawings may be implemented as a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, or any appropriate combination thereof for performing the functions described in this application. One or more of the functional blocks and / or one or more combinations of functional blocks described in the accompanying drawings may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in communication with a DSP, or any other such configuration.

[0331] The present application has been described above in conjunction with specific embodiments. However, those skilled in the art should understand that these descriptions are merely illustrative and are not intended to limit the scope of protection of the present application. Those skilled in the art may make various modifications and variations to the present application based on the spirit and principles of the present application, and such modifications and variations are also within the scope of the present application.

[0332] Regarding the implementation methods including the above embodiments, the following additional notes are also disclosed:

[0333] Terminal-side method:

[0334] 1. A method for generating channel state information, applied to a terminal device, the method comprising:

[0335] The terminal device receives a first configuration from a network device, where the first configuration is used to configure the terminal device to send channel state information (CSI) to the network device, where the first configuration includes model information and / or bit width information related to precoding matrix information; and

[0336] The terminal device generates the CSI based on a model, where the model is determined based on at least the first configuration, and the CSI includes at least the precoding matrix information.

[0337] 2. The method as described in Note 1, wherein the method further comprises:

[0338] The terminal device sends the CSI to the network device.

[0339] 3. The method as described in Note 1, wherein:

[0340] The first configuration includes CSI reporting configuration and / or physical uplink control channel configuration and / or physical uplink shared channel configuration.

[0341] 4. The method as described in Note 1, wherein:

[0342] The model is an artificial intelligence model.

[0343] 5. The method as described in Note 1, wherein:

[0344] The model is set by the first configuration, and / or the model is determined by the terminal device based on the first configuration.

[0345] 6. The method as described in Note 1, wherein:

[0346] The precoding matrix information is related to the information of the spatial domain layer.

[0347] 7. The method as described in Supplement 1, wherein:

[0348] The bit width information related to the precoding matrix information includes:

[0349] The bit width of the precoding matrix information, and / or the index of the bit width of the precoding matrix information, and / or the maximum value of the bit width of the precoding matrix information, and / or the index of the maximum value of the bit width of the precoding matrix information.

[0350] 8. The method as described in Note 1, wherein:

[0351] The first configuration further instructs the terminal device to report a rank indication, and the CSI further includes the rank indication.

[0352] 9. The method as described in Supplementary Note 8, wherein:

[0353] The terminal device also receives a second configuration sent by the network device,

[0354] The second configuration includes third information and / or antenna port information, where the third information is used to limit the rank indication in the CSI and / or a value corresponding to the rank indication.

[0355] 10. The method as described in Supplementary Note 9, wherein:

[0356] at least a portion of the first configuration is the second configuration, or

[0357] The first configuration does not include the second configuration.

[0358] 11. The method as described in Supplementary Note 8, wherein:

[0359] The terminal device also receives a third configuration sent by the network device,

[0360] The third configuration includes third information,

[0361] The third configuration includes a configuration for generating the precoding matrix information and / or the CSI,

[0362] The third information is used to limit the rank indication in the CSI and / or a value corresponding to the rank indication.

[0363] 12. The method as described in Note 11, wherein:

[0364] The third configuration is included in the second configuration, or

[0365] The third configuration is not included in the second configuration.

[0366] 13. The method as described in Note 1, wherein:

[0367] The first configuration includes more than one type of bit width information and / or model information.

[0368] 14. The method as described in Note 1, wherein:

[0369] The first configuration includes two or more types of bit width information and / or model information.

[0370] 15. The method as described in Note 14, wherein:

[0371] The precoding matrix information of at least one spatial layer is configured with more than one type of bit width information and / or model information.

[0372] 16. The method as described in Note 15, wherein:

[0373] For the spatial domain layer configured with two or more bit width information and / or model information,

[0374] The terminal device sends first indication information to the network device, where the first indication information is used to instruct the terminal device to determine the bit width information and / or model information based on which the model is determined.

[0375] 17. The method as described in Note 14, wherein:

[0376] For a value of the rank indicator, the precoding matrix information is configured with more than one bit width information and / or model information.

[0377] 18. The method as described in Note 17, wherein:

[0378] For the values ​​configured with two or more of the bit width information and / or model information,

[0379] The terminal device sends second indication information to the network device, where the second indication information is used to instruct the terminal device to determine the bit width information and / or model information based on which the model is determined.

[0380] 19. The method as described in Note 14, wherein:

[0381] At least one spatial domain layer under at least one value of the rank indication is configured with more than one bit width information or model information.

[0382] 20. The method as described in Note 14, wherein:

[0383] The terminal device sends third indication information to the network device, where the third indication information is used to indicate the bit width information and / or model information corresponding to the model determined by the terminal device for each spatial layer.

[0384] 21. The method as described in Note 13, wherein:

[0385] The terminal device receives a fourth configuration from the network device, where the fourth configuration is used to configure:

[0386] The model used in each spatial layer is the same, or the model used in at least two spatial layers is different; and / or

[0387] For at least two values ​​of the rank indication, the models used to generate the precoding matrix information corresponding to each of the values ​​are the same, or the models used to generate the precoding matrix information corresponding to at least two of the values ​​are different.

[0388] 22. The method as described in Note 21, wherein:

[0389] at least a portion of the first configuration is the fourth configuration, or

[0390] The first configuration does not include the fourth configuration.

[0391] 23 The method as described in Note 21, wherein

[0392] The same model is configured to be used in each airspace layer.

[0393] The terminal device sends fourth indication information to the network device, where the fourth indication information is used to indicate information of one of the determined models.

[0394] 24. The method as described in Note 21, wherein:

[0395] The models used in at least two spatial layers are configured to be different,

[0396] The terminal device sends fifth indication information to the network device, where the fifth indication information is used to indicate information of the model determined in each of the spatial layers.

[0397] 25. The method as described in Note 24, wherein:

[0398] The first value corresponding to the rank indication is smaller than the value corresponding to the third information, and the fifth indication information includes N fourth information, where N is a difference obtained by subtracting the first value from the value corresponding to the third information.

[0399] 26. The method as described in Note 25, wherein:

[0400] The fourth information is predefined information.

[0401] 27. The method as described in Note 25, wherein:

[0402] The fourth information indicates that the model does not exist.

[0403] Network side method (corresponding to the terminal side):

[0404] 1. A channel state information configuration method, applied to a network device, comprising:

[0405] The network device sends a first configuration to the terminal device, where the first configuration is used to configure the terminal device to send channel state information (CSI) to the network device, and the first configuration includes model information and / or bit width information related to precoding matrix information; and

[0406] The CSI is generated by the terminal device based on a model, the model is determined based on at least the first configuration, and the CSI includes at least the precoding matrix information.

[0407] 1a. The method as described in Note 1, wherein:

[0408] The network device also receives the CSI.

[0409] 2. The method as described in Note 1, wherein:

[0410] The first configuration includes CSI reporting configuration and / or physical uplink control channel configuration and / or physical uplink shared channel configuration.

[0411] 3. The method as described in Note 1, wherein:

[0412] The model is an artificial intelligence model.

[0413] 4. The method as described in Note 1, wherein:

[0414] The model is set by the first configuration, and / or the model is determined by the terminal device based on the first configuration.

[0415] 5. The method as described in Note 1, wherein:

[0416] The precoding matrix information is related to the information of the spatial domain layer.

[0417] 6. The method as described in Note 1, wherein:

[0418] The bit width information related to the precoding matrix information includes:

[0419] The bit width of the precoding matrix information, and / or the index of the bit width of the precoding matrix information, and / or the maximum value of the bit width of the precoding matrix information, and / or the index of the maximum value of the bit width of the precoding matrix information.

[0420] 7. The method as described in Note 1, wherein:

[0421] The first configuration further instructs the terminal device to report a rank indication, and the CSI further includes the rank indication.

[0422] 8. The method as described in Supplementary Note 7, wherein:

[0423] The network device further sends a second configuration to the terminal device,

[0424] The second configuration includes third information and / or antenna port information, where the third information is used to limit the rank indication in the CSI and / or a value corresponding to the rank indication.

[0425] 9. The method as described in Supplementary Note 8, wherein:

[0426] at least a portion of the first configuration is the second configuration, or

[0427] The first configuration does not include the second configuration.

[0428] 10. The method as described in Supplementary Note 7, wherein:

[0429] The network device further sends a third configuration to the terminal device,

[0430] The third configuration includes third information,

[0431] The third configuration includes a configuration for generating the precoding matrix information and / or the CSI,

[0432] The third information is used to limit the rank indication in the CSI and / or a value corresponding to the rank indication.

[0433] 11. The method as described in Supplementary Note 10, wherein:

[0434] The third configuration is included in the second configuration, or

[0435] The third configuration is not included in the second configuration.

[0436] 12. The method as described in Note 1, wherein:

[0437] The first configuration includes more than one type of bit width information and / or model information.

[0438] 13. The method as described in Note 1, wherein:

[0439] The first configuration includes two or more types of bit width information and / or model information.

[0440] 14. The method as described in Note 13, wherein:

[0441] The precoding matrix information of at least one spatial layer is configured with more than one type of bit width information and / or model information.

[0442] 15. The method as described in Note 14, wherein:

[0443] For the spatial domain layer configured with two or more bit width information and / or model information,

[0444] The network device receives first indication information sent by the terminal device, where the first indication information is used to instruct the terminal device to determine the bit width information or model information based on which the model is determined.

[0445] 16. The method as described in Note 13, wherein:

[0446] For a value of the rank indicator, the precoding matrix information is configured with more than one bit width information and / or model information.

[0447] 17. The method as described in Note 16, wherein:

[0448] For the value configured with two or more of the bit width information or model information,

[0449] The network device receives second indication information sent by the terminal device, where the second indication information is used to instruct the terminal device to determine the bit width information and / or model information based on which the model is determined.

[0450] 18. The method as described in Note 13, wherein:

[0451] At least one spatial layer under at least one value of the rank indication is configured with more than one type of bit width information and / or model information.

[0452] 19. The method as described in Note 13, wherein:

[0453] The network device receives third indication information sent by the terminal device, where the third indication information is used to indicate the bit width information and / or model information corresponding to the model determined by the terminal device for each spatial layer.

[0454] 20. The method as described in Note 12, wherein:

[0455] The network device sends a fourth configuration to the terminal device, where the fourth configuration is used to configure:

[0456] The model used in each spatial layer is the same, or the model used in at least two spatial layers is different; and / or

[0457] For at least two values ​​of the rank indication, the models used to generate the precoding matrix information corresponding to each of the values ​​are the same, or the models used to generate the precoding matrix information corresponding to at least two of the values ​​are different.

[0458] 21. The method as described in Note 20, wherein:

[0459] at least a portion of the first configuration is the fourth configuration, or

[0460] The first configuration does not include the fourth configuration.

[0461] 22 The method as described in Note 20, wherein

[0462] The same model is configured to be used in each airspace layer.

[0463] The network device receives fourth indication information sent by the terminal device, where the fourth indication information is used to indicate information of one of the determined models.

[0464] 23. The method as described in Note 20, wherein:

[0465] The models used in at least two spatial layers are configured to be different,

[0466] The network device receives fifth indication information sent by the terminal device, where the fifth indication information is used to indicate information of the model determined in each of the spatial domain layers.

[0467] 24. The method as described in Note 23, wherein:

[0468] The first value corresponding to the rank indication is smaller than the value corresponding to the third information, and the fifth indication information includes N fourth information, where N is a difference obtained by subtracting the first value from the value corresponding to the third information.

[0469] 25. The method as described in Note 24, wherein:

[0470] The fourth information is predefined information.

[0471] 26. The method as described in Note 24, wherein:

[0472] The fourth information indicates that the model does not exist.

Claims

1. A channel state information generating device, applied to a terminal device, the device comprising a first processing unit, the first processing unit controlling the terminal device to enable the terminal device to perform the following operations: The terminal device receives a first configuration from a network device, the first configuration being used to configure the terminal device to send channel state information (CSI) to the network device, the first configuration including model information and / or bit width information related to precoding matrix information; and, The terminal device generates the CSI based on a model, the model is determined based on at least the first configuration, and the CSI includes at least the precoding matrix information.

2. The device according to claim 1, wherein: The first configuration includes CSI report configuration and / or physical uplink control channel configuration and / or physical uplink shared channel configuration.

3. The device according to claim 1, wherein: The model is set by the first configuration, and / or the model is determined by the terminal device based on the first configuration.

4. The device according to claim 1, wherein: The precoding matrix information is related to the information of the spatial domain layer.

5. The device according to claim 1, wherein: The first configuration further instructs the terminal device to report a rank indication, and the CSI further includes the rank indication.

6. The device according to claim 5, wherein: The terminal device also receives a second configuration sent by the network device, The second configuration includes third information and / or antenna port information, where the third information is used to limit the rank indication in the CSI and / or a value corresponding to the rank indication.

7. The device according to claim 5, wherein: The terminal device also receives a third configuration sent by the network device, The third configuration includes third information, The third configuration includes a configuration for generating the precoding matrix information and / or the CSI, The third information is used to limit the rank indication in the CSI and / or the value corresponding to the rank indication system.

8. The device of claim 1, wherein: The first configuration includes more than one type of bit width information and / or model information.

9. The device of claim 1, wherein: The first configuration includes two or more types of the bit width information and / or model information.

10. The device of claim 9, wherein: The precoding matrix information of at least one spatial domain layer is configured with more than one type of bit width information and / or model information.

11. The device of claim 10, wherein: For the spatial domain layer configured with two or more of the bit width information and / or model information, The terminal device sends first indication information to the network device, where the first indication information is used to instruct the terminal device to determine the bit width information and / or model information based on which the model is determined.

12. The device of claim 9, wherein: The terminal device sends third indication information to the network device, where the third indication information is used to indicate the bit width information and / or model information corresponding to the model determined by the terminal device for each spatial layer.

13. The device of claim 8, wherein: The terminal device receives a fourth configuration from the network device, where the fourth configuration is used to configure: The models used in each spatial layer are the same, or the models used in at least two spatial layers are different; and / or For at least two values ​​of the rank indication, the models used to generate the precoding matrix information corresponding to each of the values ​​are the same, or the models used to generate the precoding matrix information corresponding to at least two of the values ​​are different.

14. A channel state information configuration device, applied to a network device, the device comprising a second processing unit, the second processing unit controlling the network device to enable the network device to perform the following operations: The network device sends a first configuration to the terminal device, the first configuration being used to configure the terminal device to send channel state information (CSI) to the network device, the first configuration including model information and / or bit width information related to precoding matrix information; and, The CSI is generated by the terminal device based on a model, the model is determined based on at least the first configuration, and the CSI includes at least the precoding matrix information.

15. The device of claim 14, wherein: The first configuration further instructs the terminal device to report a rank indication, and the CSI further includes the rank indication.

16. The device of claim 15, wherein: The network device further sends a second configuration to the terminal device, The second configuration includes third information and / or antenna port information, where the third information is used to limit the rank indication in the CSI and / or a value corresponding to the rank indication.

17. The device of claim 15, wherein: The network device further sends a third configuration to the terminal device, The third configuration includes third information, The third configuration includes a configuration for generating the precoding matrix information and / or the CSI, The third information is used to limit the rank indication in the CSI and / or a value corresponding to the rank indication.

18. The device of claim 14, wherein: The first configuration includes two or more types of the bit width information and / or model information.

19. The device of claim 18, wherein: The precoding matrix information of at least one spatial domain layer is configured with more than one type of bit width information and / or model information.

20. The device of claim 19, wherein: For the spatial domain layer configured with two or more of the bit width information and / or model information, The network device receives first indication information sent by the terminal device, where the first indication information is used to indicate the bit width information or model information on which the terminal device determines the model.

Images