Method and device for sending and receiving channel state information, and communication system

Abstract

The embodiment of the invention provides a channel state information sending method, a channel state information receiving method, a channel state information sending device, a channel state information receiving device and a communication system. The transmitting device is applied to the terminal equipment, and the device comprises a first generation unit which is configured to generate at least one part of information of channel state information (CSI) based on an artificial intelligence model; and a first discarding unit, which is configured to discard (omit) the first information of the CSI according to the priority order of the CSI and / or the first configuration information, and a second discarding unit, which is configured to discard (omit) the first information of the CSI according to the priority order of the CSI and / or the first configuration information.

Description

Method, device and communication system for sending and receiving channel state information 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 channel state 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 (for example, 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] 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.

[0007] Figure 1 is a schematic diagram of AI / ML-based CSI feedback. As shown in Figure 1, in operation 101, the terminal device uses the AI / ML-based CSI generation component to process and obtain compressed CSI; the network device receives this CSI over the air interface; in operation 102, the network device uses the AI / ML-based CSI reconstruction component to process the received CSI and obtain recovered CSI.

[0008] It should be noted that the above technical background is merely provided to provide a clear and complete description of the technical solutions of this application and to 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.

[0009] Summary of the Invention

[0010] When using a codebook for CSI feedback, a priority can be set for the CSI, and the terminal device can feedback the CSI in order from high priority level (e.g., small priority level value) to low priority level (e.g., large priority level value). In addition, if it is necessary to discard some CSI, the terminal device can discard (omit) the CSI according to the priority order, where the priority order is the order set according to the priority level, for example, the priority order is the order from large to small priority level value, that is, the larger the priority level value, the sooner it is discarded.

[0011] The inventors of this application discovered that the prior art does not yet address how to discard CSI generated based on AI / ML. Therefore, when a terminal device discards at least part of the information in the CSI generated based on AI / ML, ambiguity may arise when the network device reads the received CSI. In addition, the prior art does not address how to set the priority order of CSI generated based on AI / ML.

[0012] In response to at least one of the above-mentioned problems or other similar problems, embodiments of the present application provide a method, apparatus, and communication system for sending and receiving channel state information, which discards (omit) the first information of the CSI based on the priority order and / or first configuration information of the CSI generated based on AI / ML. Thus, the CSI generated based on AI / ML can be discarded, thereby avoiding possible ambiguity when the network device reads the CSI.

[0013] According to one aspect of an embodiment of the present application, a device for transmitting channel state information (CSI) is provided, which is applied to a terminal device, and the device includes:

[0014] a first generating unit configured to generate at least a portion of channel state information (CSI) based on an artificial intelligence model; and

[0015] A first discarding unit is configured to discard (omit) the first information of the CSI according to the priority order of the CSI and / or the first configuration information.

[0016] According to another aspect of an embodiment of the present application, a device for transmitting channel state information (CSI) is provided, which is applied to a terminal device, and the device includes:

[0017] A second generating unit is configured to generate at least a portion of channel state information (CSI) based on an artificial intelligence model, wherein the CSI has a priority order.

[0018] According to another aspect of an embodiment of the present application, a device for transmitting channel state information is provided, which is applied to a terminal device. The device includes a first transmitting unit, and the first transmitting unit is configured to:

[0019] sending at least a portion of first channel state information (CSI); and

[0020] Send indication information, where the indication information is used to indicate an extension method of the at least part of the first channel state information (CSI).

[0021] One of the beneficial effects of the embodiments of the present application is that the terminal device can discard the CSI generated based on AI / ML, thereby avoiding possible ambiguity when the network device reads the CSI.

[0022] 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.

[0023] 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.

[0024] 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

[0025] 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.

[0026] Figure 1 is a schematic diagram of CSI feedback based on AI / ML;

[0027] FIG2 is a schematic diagram of the communication system of the present application;

[0028] FIG3 is a schematic diagram of a method for transmitting channel state information (CSI) according to the first aspect of the present application;

[0029] FIG4 is a schematic diagram of a method for transmitting channel state information (CSI) according to the second aspect of the present application;

[0030] FIG5 is a schematic diagram of a method for transmitting channel state information (CSI) according to the third aspect of the present application;

[0031] FIG6 is a schematic diagram of a method for receiving channel state information according to an embodiment of the fourth aspect;

[0032] FIG7 is a schematic diagram of a method for receiving channel state information according to an embodiment of the fifth aspect;

[0033] FIG8 is a schematic diagram of a method for receiving channel state information according to an embodiment of the sixth aspect;

[0034] FIG9 is a schematic diagram of a device for transmitting channel state information according to an embodiment of the seventh aspect;

[0035] FIG10 is a schematic diagram of a device for transmitting channel state information according to an embodiment of the eighth aspect;

[0036] FIG11 is a schematic diagram of a device for transmitting channel state information according to an embodiment of the ninth aspect;

[0037] FIG12 is a schematic diagram of a device for receiving channel state information according to an embodiment of the tenth aspect;

[0038] FIG13 is a schematic diagram of a device for receiving channel state information according to an embodiment of the eleventh aspect;

[0039] FIG14 is a schematic diagram of a device for receiving channel state information according to an embodiment of the twelfth aspect;

[0040] FIG15 is a schematic diagram of a terminal device according to an embodiment of the thirteenth aspect;

[0041] Figure 16 is a schematic diagram of a network device of an embodiment of the thirteenth aspect. DETAILED DESCRIPTION

[0042] 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.

[0043] 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.

[0044] 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.

[0045] 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.

[0046] 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.

[0047] 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.

[0048] 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.

[0049] 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.

[0050] 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.

[0051] 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.

[0052] 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.

[0053] 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.

[0054] 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.

[0055] 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.

[0056] 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.

[0057] The following describes the scenarios of the embodiments of the present application through examples, but the present application is not limited thereto.

[0058] 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).

[0059] 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.

[0060] 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.

[0061] 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.

[0062] 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.

[0063] 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.

[0064] The AI / ML-based CSI generation part includes an AI / ML model, which can be used to generate one or more of 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 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 a module for generating CQI. The AI / ML-based CSI generation part may also include other modules, such as a module for truncating a bit sequence.

[0065] 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).

[0066] An AI / ML model can consist of three parts: a preprocessing module, an AI / ML encoder, and a quantizer. Therefore, AI / ML model information can include preprocessing module information, AI / ML encoder information, and quantizer information. For example, an AI / ML model information can be described as "preprocessing module #2, AI / ML encoder #4, Quantizer #A." Furthermore, the preprocessing module, AI / ML encoder, and quantizer can be considered as a whole to label the AI / ML model information. That is, the AI / ML model information can also be represented as, for example, AI / ML model information #4.

[0067] The AI / ML reconstruction model of the AI / ML-based CSI reconstruction component, paired with the AI / ML model in the AI / ML-based CSI generation component, can also include three components: a dequantizer, an AI / ML decoder, and a post-processing module. Thus, the AI / ML reconstruction model information can include dequantizer information, AI / ML decoder information, and post-processing module information. For example, an AI / ML reconstruction model information can be described as "dequantizer #B, AI / ML decoder #1, post-processing module #2." Furthermore, the AI / ML reconstruction model information can also be represented as, for example, AI / ML reconstruction model #1, or simply AI / ML model #1, to indicate its pairing relationship with the AI / ML model #1 in the AI / ML-based CSI generation component.

[0068] The AI / ML model may also consist of two parts (for example, without a pre-processing module, or the pre-processing module is included in the AI / ML encoder and is regarded as a whole with the AI / ML encoder), that is, the 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 AI / ML reconstruction model of the AI / ML-based CSI reconstruction part paired with the 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 pre-processing 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.

[0069] The AI / ML model can 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 not. 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 AI / ML reconstruction model can 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 not. 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.

[0070] In various embodiments of the present application, reporting may refer to an action in which a terminal device sends information to a network device. For example, reporting CSI by a terminal device may refer to sending CSI by the terminal device to a network device.

[0071] Embodiments of the first aspect

[0072] An embodiment of the first aspect provides a method for sending channel state information (CSI), which is applied to a terminal device, for example, the terminal device 202 in FIG. 2 .

[0073] FIG3 is a schematic diagram of a method for transmitting channel state information (CSI) according to the first aspect of the present application. As shown in FIG3 , the method includes:

[0074] Operation 301: Generate at least a portion of channel state information (CSI) based on an artificial intelligence model; and

[0075] Operation 302: Omit the first information of the CSI according to the priority order of the CSI and / or the first configuration information.

[0076] In at least one embodiment, the terminal device can perform operation 302 in response to situations such as the occurrence of a CSI conflict, limited uplink resources, or saving uplink resources. The uplink resources include, for example, a physical uplink shared channel (PUSCH) and / or a physical uplink control channel (PUCCH). For example, the discarding in operation 302 may occur in a CSI report carried by the physical uplink shared channel (PUSCH) and / or in a CSI report carried by the physical uplink control channel (PUCCH).

[0077] Through the embodiments of the first aspect, the terminal device can discard the CSI generated based on the AI / ML model, thereby avoiding possible ambiguity when the network device reads the CSI.

[0078] In at least one embodiment, in operation 301, at least a portion of the CSI generated by the terminal device includes two parts, namely, a first part (Part 1) and a second part (Part 2). The first part of the CSI includes a rank indication (RI) and / or at least a portion of a channel quality indication (CQI) and / or a channel state information reference signal resource indication (CRI); the second part of the CSI includes information about a precoding matrix and / or at least a portion of a channel quality indication (CQI) and / or a layer indication (LI), wherein at least the information about the precoding matrix is ​​generated based on an artificial intelligence model. In addition, the present application is not limited to this, and other information in the CSI may also be generated based on an artificial intelligence model. For example, at least a portion of the channel quality indication (CQI) and / or layer indication (LI) in the second part of the CSI may be generated based on an artificial intelligence model.

[0079] The first CSI information discarded in operation 302 may be at least a portion of the second part of the CSI. For example, in operation 302, a portion of the second part of the CSI (a portion of Part 2) is discarded; or, in operation 302, all of the second part of the CSI is discarded. When the terminal device discards all of the second part of the CSI, the network device may use the identity matrix as the precoding matrix used for downlink transmission.

[0080] In at least one embodiment of operation 302, the terminal device may discard the first CSI information based on the priority order of the CSI. For example, the first CSI information may be discarded in descending order of priority, with information with a lower priority (e.g., a smaller number corresponding to the priority order) being discarded first and information with a higher priority (e.g., a larger number corresponding to the priority order) being discarded later.

[0081] In at least one CSI report, the CSI priority can be set based on the layer information of the second part and / or the predetermined bit information in the layer. For example, the priority can be set based only on the layer information; or based on both the layer information and the predetermined bit information; or based only on the predetermined bit information. For example, if the CSI has only one layer, the priority can be set based only on the predetermined bit information.

[0082] In at least one embodiment, a certain mapping relationship can be formed between the priority and the information of the layer and / or the information of the predetermined bit in the layer. The mapping relationship can have one group or at least two groups. According to the mapping relationship, the priority of the CSI can be determined.

[0083] In the case where there are at least two groups of mapping relationships, the priority of the CSI can be set based on one group of mapping relationships in the at least two groups of mapping relationships. The group of mapping relationships can be pre-set, or selected by a terminal device (for example, terminal device 202), or configured by a network device (for example, network device 201). In the case where the terminal device selects the group of mapping relationships, the terminal device can receive information sent by the network device, which instructs the terminal device to send information about the group of mapping relationships to the network device. The terminal device can send information about the group of mapping relationships to the network device based on the information, thereby enabling the network device to know the setting method of the priority of the CSI. The information about the group of mapping relationships may include information such as the index of the group of mapping relationships.

[0084] In at least one embodiment, in the CSI report, the second part (Part 2) has one layer or at least two layers. In the case where the second part has at least two layers, each layer can be generated based on the same artificial intelligence model, or at least two layers can be generated based on different artificial intelligence models.

[0085] In at least one embodiment, the layer information includes the order of the layers. The order of the layers may be determined based on the order of the eigenvalues ​​or singular values ​​of the spatial channel matrix corresponding to the layer. For example, the larger the eigenvalues ​​or singular values ​​corresponding to the layer, the higher the order of the layer, and the higher the priority of the CSI corresponding to the layer, i.e., the CSI of the layer is discarded later.

[0086] In at least one embodiment, the information of the predetermined bit position may include: the proportion of the predetermined bit position in the bit sequence corresponding to the layer.

[0087] In the case where the second part of the CSI report has at least two layers: the ratio is equal for different layers; or the ratio is unequal for at least two layers.

[0088] Based on the ratio, the predetermined number of bits, i.e., the number of bits, can be determined. For example, the total number of bits in the bit sequence corresponding to the layer can be multiplied by the ratio, and the result can be rounded (e.g., rounded up, rounded down, or rounded to the nearest integer). The resulting number is the number of bits.

[0089] In at least another embodiment, the information about the predetermined bits may include the number of the predetermined bits. That is, the number of predetermined bits is used instead of the ratio. This allows for more direct confirmation of the number of predetermined bits.

[0090] In the case where the second part of the CSI report has at least two layers: the number of the predetermined bits is the same for different layers; or the number of the predetermined bits is different for at least two layers.

[0091] In at least one further embodiment, the predetermined bit information further includes: the position of the predetermined bit in the bit sequence corresponding to the layer, for example, a certain number or a certain proportion of the predetermined bits are located at the front, back, odd, or even positions of the bit sequence.

[0092] In at least one embodiment of the present application, the predetermined bit information may be pre-set information; or, the predetermined bit information is configured by the network device; or, the predetermined bit information is determined by the terminal device, and the terminal device also reports the predetermined bit information to the network device.

[0093] It should be noted that in the tables and text of this application, "priority N (N is a non-negative integer, for example, N is 1, 2, 3, etc.)" can be referred to as priority level N, or as "priority level N", or as "priority reporting level N", or as "priority value N", etc.

[0094] Several specific examples are used below to illustrate a specific manner of discarding (omitting) the first information of the CSI according to the priority order of the CSI in operation 302.

[0095] In the following example, it is assumed that there are M (M is a natural number) CSI reports. The priority of these M CSI reports is different from the CSI priority order. The priority of CSI reports can be determined based on relevant technologies. In the following example, it is assumed that each CSI report has 4 layers and M = 3. In each CSI report, the priority order of the second part of the CSI can be based on the layer information and regulations, such as those shown in Tables 1 to 4 below.

[0096] Tables 1 through 4 are two examples of CSI priority. In Tables 1 and 2, the layers are ordered by the eigenvalues ​​or singular values ​​of the spatial channel matrix, from largest to smallest. The rank of the spatial channel matrix is ​​equal to the number of eigenvalues ​​or singular values ​​in the matrix. The total number of layers is the same as the RI, which is less than or equal to the rank.

[0097] Table 1

[0098] In Table 1, the terminal device may discard the first CSI information in descending order of priority values.

[0099] In Table 1, #1 to #4 represent different mapping relationships. In the mapping relationship shown in #1, the CSI priority is set based on layer information. In the mapping relationships shown in #2, #3, and #4, the CSI priority is set based on layer information and information about predetermined bits in the layer, where the predetermined bit information includes the predetermined bit ratio.

[0100] In Table 1, for the mapping relationship shown in #2, the "certain proportion of bits" may be the same for all priority orders, or the proportions of at least two priority orders may be different.

[0101] In Table 1, for the mapping relationship shown in #3, the "certain proportion of bits" may be the same for all priority orders, or the proportions of at least two priority orders may be different.

[0102] In Table 1, for the mapping relationship shown in #4, the "certain proportion of bits" may be the same for all priority orders, or the proportions of at least two priority orders may be different.

[0103] In Table 1, the method for calculating the number of bits based on "a certain proportion of bits" can be predetermined or configured by the network device. For example, the number of bits in the bit sequence corresponding to the layer can be multiplied by the proportion, and the result can be rounded according to a certain method, such as rounding up, rounding down, or rounding off.

[0104] In Table 1, "a certain proportion of bits" and / or the position of the certain proportion of bits in the bit sequence can be predetermined or configured by the network device, or determined by the terminal device. For example, the certain proportion of bits and their positions can correspond to: the first K bits in the bit sequence; or, the last K bits in the bit sequence; or, K bits, wherein the priority of odd bits is lower than the priority of even bits; or, K bits, wherein the priority of even bits is lower than the priority of odd bits, but not limited thereto. In the case of network device configuration, the network device can send index (index) 1 to the terminal device, and the index 1 is used to indicate the certain proportion of bits and / or the position of the certain proportion of bits in the bit sequence. In the case of terminal device determination, the terminal device can report index (index) 2 to the network device, and the index 2 is used to indicate information such as the certain proportion of bits and / or the position of the certain proportion of bits in the bit sequence determined by the terminal device. Among them, the positions of index 1 and index 2 in the feedback bit sequence can be specified by the standard or agreed in advance by the network device and the terminal device.

[0105] In some implementations, there may be only one regulation for the priority of the CSI, such as the mapping relationship corresponding to a column in Table 1. The terminal device may discard the first information in the CSI according to the priority of the CSI.

[0106] In some implementations, there may be at least two provisions for the priority of CSI, such as the mapping relationships corresponding to at least two columns in Table 1. The terminal device may determine which set of mapping relationships to use to set the priority of CSI and discard CSI based on the configuration of the network device; alternatively, the terminal device may independently determine which set of mapping relationships to use to set the priority of CSI and discard CSI, and then feed back the index of the set of mapping relationships to the network device. The position of the mapping relationship index in the feedback bit sequence may be specified by the standard or agreed upon in advance by the network device and the terminal device.

[0107] In the examples shown in Table 2 and Table 3, it is assumed that M=3, that is, there are 3 CSI reports. As shown in Table 2 and Table 3, the number of bits of the second part of the CSI with priority k is n k , then there is a k ≤n k , b k ≤n k , c k ≤n k , k=1,2,…12. n k , k=1,2,3,4, can be equal or there can be more than two n k Not equal. k , k=5,6,7,8, can be equal, or there can be more than two n k Not equal. k , k=9,10,11,12, can be equal or there can be more than two n k Not equal. These 12 a k Can be equal, or there can be more than two a k Not equal. These 12 b k Can be equal, or there can be more than two b k Not equal. These 12 c k Can be equal, or there can be more than two c k Not equal.

[0108] Table 2:

[0109] Table 3

[0110] In Table 2 or Table 3, the terminal device may discard the first CSI information in descending order of priority values.

[0111] In Table 2 or Table 3, #1 to #3 represent different mapping relationships. In the mapping relationships shown in #1, #2, and #3, the priority of CSI is set based on the layer information and the information of the predetermined bits in the layer, wherein the information of the predetermined bits includes: the number of the predetermined bits, that is, the number of bits, for example, the number of bits a in Table 2 or Table 3. k 、b k 、c k etc. Among them, for the same priority order, ak 、b k 、c k Can be the same, or at least two different.

[0112] In Table 2 or Table 3, the number of predetermined bits and / or the position of the predetermined bit in the bit sequence can be predetermined or configured by the network device, or determined by the terminal device. For example, the number of predetermined bits and their positions can correspond to: the first K bits in the bit sequence; or the last K bits in the bit sequence; or K bits, where the priority of odd bits is lower than the priority of even bits; or K bits, where the priority of even bits is lower than the priority of odd bits, without limitation. In the case of network device configuration, the network device can send index (index) 3 to the terminal device, where index 3 is used to indicate the number of predetermined bits and / or the position of the predetermined bit in the bit sequence. In the case of terminal device determination, the terminal device can report index (index) 4 to the network device, where index 4 is used to indicate information such as the number of predetermined bits and / or the position of the predetermined bit in the bit sequence determined by the terminal device. The positions of index 3 and index 4 in the feedback bit sequence can be specified by the standard or agreed upon in advance by the network device and the terminal device.

[0113] In some implementations, there may be only one specification for the priority of the CSI, such as a mapping relationship corresponding to a column in Table 2 or Table 3. The terminal device may discard the first information in the CSI according to the priority of the CSI.

[0114] In some implementations, there may be at least two provisions for the priority of CSI, such as the mapping relationships corresponding to at least two columns in Table 2 or Table 3. The terminal device may determine which set of mapping relationships to use to set the priority of CSI and discard CSI based on the configuration of the network device; alternatively, the terminal device may independently determine which set of mapping relationships to use to set the priority of CSI and discard CSI, and then feed back the index of the set of mapping relationships to the network device. The position of the mapping relationship index in the feedback bit sequence may be specified by the standard or agreed upon in advance by the network device and the terminal device.

[0115] In the example corresponding to Table 4, assume that M=3, that is, there are 3 CSI reports. In the example corresponding to Table 4, the CSI report has only one downlink transmission layer, that is, only one layer. As shown in Table 4, the number of bits of the second part of the CSI with priority k is m. k , then x k ≤m k ,y k ≤m k, z k ≤m k , k=1,2,3,4. n k , k=1,2,3,4, can be equal or there can be more than two n k Not equal. These 4 x k Can be equal, or there can be more than two x k These four y k Can be equal, or there can be more than two y k These four z k Can be equal, or there can be more than two z k Not equal.

[0116] Table 4:

[0117] In Table 4, #1 to #3 represent different mapping relationships. Since there is only one layer in the example of Table 4, in the mapping relationships shown in #1, #2, and #3, the priority of CSI is set based on the information of the predetermined bits in the layer, wherein the information of the predetermined bits includes: the number of the predetermined bits, that is, the number of bits, for example, the number of bits x in Table 4 k ,y k , z k etc. Among them, for the same priority order, x k ,y k , z k Can be the same, or at least two different.

[0118] In Table 4, the number of predetermined bits and / or the position of the predetermined bit in the bit sequence can be predetermined or configured by the network device, or determined by the terminal device. For example, the number of predetermined bits and their positions can correspond to: the first K bits in the bit sequence; or the last K bits in the bit sequence; or K bits, wherein the priority of odd bits is lower than the priority of even bits; or K bits, wherein the priority of even bits is lower than the priority of odd bits, without limitation. In the case of network device configuration, the network device can send an index (index) 5 to the terminal device, where the index 5 is used to indicate the number of predetermined bits and / or the position of the predetermined bit in the bit sequence. In the case of terminal device determination, the terminal device can report an index (index) 6 to the network device, where the index 6 is used to indicate information such as the number of predetermined bits and / or the position of the predetermined bit in the bit sequence determined by the terminal device. The positions of index 5 and index 6 in the feedback bit sequence can be specified by the standard or agreed upon in advance by the network device and the terminal device.

[0119] In some implementations, there may be only one regulation for the priority of the CSI, such as the mapping relationship corresponding to a column in Table 4. The terminal device may discard the first information in the CSI according to the priority of the CSI.

[0120] In some implementations, there may be at least two provisions for the priority of CSI, such as the mapping relationships corresponding to at least two columns in Table 4. The terminal device may determine which set of mapping relationships to use to set the priority of CSI and discard CSI based on the configuration of the network device; alternatively, the terminal device may independently determine which set of mapping relationships to use to set the priority of CSI and discard CSI, and then feed back the index of the set of mapping relationships to the network device. The position of the mapping relationship index in the feedback bit sequence may be specified by the standard or agreed upon in advance by the network device and the terminal device.

[0121] In some embodiments of operation 302, when the terminal device discards (omit) the first information of the CSI according to the priority order of the CSI, the discarded first information may be all or part of the CSI corresponding to at least one priority reporting level in the priority order. Here, "priority reporting level N" may correspond to "priority order N (N is a non-negative integer, for example, N is 1, 2, 3, etc.)" in Tables 1 to 4 or other tables, and may be referred to as priority level N, or as "priority order level N", or as "priority order value N", etc.

[0122] In some examples, for a certain CSI report, starting from a certain CSI priority reporting level in the used CSI priority order, there are insufficient uplink resources, and the terminal device discards or ignores (omit) the CSI reporting information corresponding to the priority reporting level and the priority reporting level with a larger numerical value.

[0123] For example, in the scenario shown in Table 1, there are four transmission layers. The bit widths of the second information (e.g., the second information refers to the information output by the AI / ML model used by these transmission layers) for transmission layers 1, 2, 3, and 4 are 120 bits, 100 bits, 80 bits, and 80 bits, respectively. This means that the sum of the bit widths of the second information for all layers is 380 bits. The CSI priority order given in column "#2" of Table 1 is used for CSI reporting. For CSI reporting 3, the number of "certain percentage of bits" in CSI priority reporting levels 16, 17, and 19 is the result of multiplying the bit width of the second part of the CSI for the transmission layer in the priority order by 80%, 70%, and 60%, respectively, rounded down. The uplink resources available for the second information for all layers of CSI reporting 3 are less than 380 bits; assuming 340 bits, this is 40 bits less than the sum of the bit widths of the second information for all layers. In this embodiment, there are 32 bits in CSI priority reporting level 21 and 24 bits in CSI priority reporting level 20. Even though 16 bits of the uplink resources (340 bits) are available to transmit bits in CSI priority level 20, according to the method of this example, all bits in CSI priority reporting level 20 and CSI priority reporting level 21 are discarded.

[0124] In this example, after receiving the CSI report from the terminal device, the network device, in accordance with the standard, padded 24 zeros after the last bit of the received Layer 3 CSI and padded 32 zeros after the last bit of the received Layer 4 CSI. The network device then restored the channel information.

[0125] In other examples, for a certain CSI report, there are not enough uplink resources starting from a certain CSI priority reporting level in the CSI priority order used. The terminal device sends the information of the number of bits in the CSI report corresponding to the priority reporting level that the uplink resources are sufficient to send, where the bit can traverse various possibilities (for example, the first K bits, the last K bits, the even bits first and then the odd bits, a total of K bits, the odd bits first and then the even bits, a total of K bits, etc.). The terminal device discards / omitted the information of other bits of the CSI report corresponding to the priority reporting level, and the information of all CSI reports corresponding to values ​​greater than the priority reporting level.

[0126] For example, the standard specifies the three possible CSI priority orders as given in Table 2. The terminal device has four transmission layers. The bit widths of the second information of the first, second, third, and fourth transmission layers are 120 bits, 100 bits, 80 bits, and 80 bits, respectively. That is, the sum of the bit widths of the second information of all layers is 380 bits. For CSI reporting 3, a_9 = 120, a_ 10 =80, a_ 11 =60, a_ 12 =40. The uplink resources of the second information of all layers that can be used for the CSI reporting 3 are less than 380 bits, assuming it is 330 bits, which is 50 bits less than the sum of the bit widths of the second information of all layers. The terminal device selects the CSI priority given in the "#1" column of Table 32 for CSI reporting, and reports the information of the CSI priority to the base station, which requires 2 bits. Therefore, the uplink resources of the second information of all layers that can be used for the CSI reporting 3 are 330–2=328 bits. Among them, the terminal device sends the first K bits of the CSI reporting information corresponding to the priority reporting level that the uplink resources are sufficient to send. According to the method in this example, CSI priority reporting level 24 (40 bits) cannot be reported, and the last 12 bits in CSI priority reporting level 23 cannot be reported. In other words, the first 8 bits in the CSI priority reporting level 23 are reported, and the remaining bits in the CSI priority reporting level 23 and all bits in the CSI priority reporting level 24 are discarded.

[0127] In this example, after receiving the report from the terminal device, the network device determines, based on the report content, the CSI priority order given in column "#1" of Table 2 for CSI reporting. According to the standard, the network device appends 12 "1s" after the last bit of the received Layer 3 CSI and 40 "1s" after the last bit of the received Layer 4 CSI. The network device then recovers the channel information.

[0128] In this example, compared with the scheme of discarding all the CSI of the third layer, in the scheme of discarding part of the CSI of the third layer, the part of the information that is sufficient for reporting in the uplink resources at the priority reporting level of the CSI is reported, thereby making full use of all available uplink resources.

[0129] In at least another embodiment of operation 302, the terminal device discards the first information of the CSI based on a discarding criterion corresponding to the first configuration information sent by the network device.

[0130] The discarding criterion may include at least one parameter, which may include: the number of bits corresponding to the discarded first information and / or the position of the bits corresponding to the discarded first information; and / or the number of bits corresponding to the information retained in the CSI and / or the position of the bits corresponding to the information retained in the CSI. The retained information refers to information that needs to be retained and not discarded when the terminal device discards the first information of the CSI.

[0131] The parameters in the discarding criterion are predetermined parameters, or the parameters in the discarding criterion are obtained by configuring the network device through parameter configuration information.

[0132] In at least one embodiment, the discard criteria may include at least one of the following:

[0133] discarding the first first number of bits in the bit sequence corresponding to the layer;

[0134] discarding a second-lowest number of bits in the bit sequence;

[0135] first discarding odd bits in the bit sequence, and then discarding even bits in the bit sequence, until the total number of discarded bits reaches a third number;

[0136] discarding even bits in the bit sequence first, and then discarding odd bits in the bit sequence, until the total number of discarded bits reaches a fourth number;

[0137] The (P*Q+R)th bit of the bit sequence is retained, and the remaining bits are discarded, where Q is a positive integer, P is an integer greater than or equal to 0, and R is a positive integer greater than or equal to 1 and less than Q.

[0138] Table 5 shows an example of the discarding criteria.

[0139] Form 5

[0140] In the example corresponding to Table 5, the network device may send first configuration information to instruct the terminal device to discard the first information of the CSI based on a discarding criterion corresponding to any one of configurations 0 to 5.

[0141] In Table 5, the position of the discarded bits and / or the position of the retained bits may be agreed upon or configured by the network device. For example, it may be the first K bits in the bit sequence; or the last K bits; or the odd bits may be discarded first, then the even bits, until the K bits; or the even bits may be discarded first, then the odd bits, until the K bits, but not limited thereto. The position of the discarded bits and / or the position of the retained bits may be one or at least two agreed upon by the terminal device and the network device, or may be pre-agreed upon. For the case of network device configuration, it may be indicated by index 7 configured by the network device. The position of index 7 in the feedback bit sequence may be specified by the standard or agreed upon in advance by the network device and the terminal device.

[0142] According to an embodiment of the first aspect of the present application, the terminal device can discard (omit) the first information of the CSI based on the priority order and / or first configuration information of the CSI generated based on the artificial intelligence model. Thus, the CSI generated based on the artificial intelligence model can be discarded, thereby avoiding possible ambiguity when the network device reads the CSI.

[0143] Embodiments of the second aspect

[0144] The embodiment of the second aspect provides a method for transmitting channel state information (CSI), which is applied to a terminal device, for example, the terminal device 202 in FIG2 . For the parts of the embodiment of the second aspect that are the same as those in the embodiment of the first aspect, reference can be made to the description of the embodiment of the first aspect, and no repetition is given here.

[0145] FIG4 is a schematic diagram of a method for transmitting channel state information (CSI) according to the second aspect of the present application. As shown in FIG4 , the method includes:

[0146] Operation 401: Generate at least a portion of channel state information (CSI) based on an artificial intelligence model, wherein the CSI has a priority order.

[0147] In addition, as shown in FIG4 , the method further includes:

[0148] Operation 402: Send at least part of the CSI information.

[0149] In some embodiments of operation 401, at least a portion of the CSI includes two parts: a first part and a second part. The first part includes a rank indication (RI) and / or at least a portion of a channel quality indication (CQI) and / or a channel state information reference signal resource indication (CRI); and the second part includes information about a precoding matrix and / or at least a portion of a channel quality indication (CQI) and / or a layer indication (LI). At least the precoding matrix information is generated based on an artificial intelligence model.

[0150] In at least one CSI report, the priority of the CSI may be set according to information of a layer in the second part and / or information of a predetermined bit in the layer.

[0151] There is one or at least two groups of mapping relationships between the priority and the information of the layer and / or the information of the predetermined bit in the layer. When there are at least two groups of mapping relationships, the priority is set based on one group of mapping relationships in the at least two groups of mapping relationships.

[0152] The set of mapping relationships is pre-set, or selected by the terminal device, or configured by the network device. Wherein, in the case where the set of mapping relationships is selected by the terminal device, the terminal device may also send information about the selected set of mapping relationships to the network device.

[0153] In at least one embodiment, the layer information includes the order of the layers, and the order of the layers is set according to the order of the eigenvalues ​​or singular values ​​of the spatial channel matrix corresponding to the layers. For example, the larger the eigenvalue or singular value, the higher the priority corresponding to the layer.

[0154] In the CSI report, the second part has one layer or at least two layers. When the second part has at least two layers, each layer is generated based on the same artificial intelligence model, or at least two layers are generated based on different artificial intelligence models.

[0155] In at least one embodiment, the predetermined bit information includes: a ratio of the predetermined bit in the bit sequence of the layer, and / or a position of the predetermined bit in the bit sequence. Wherein, when the second part of the CSI report includes at least two layers, the ratio is the same for different layers, or the ratio is different for at least two layers.

[0156] The predetermined number of bits can be obtained by multiplying the total number of bits in the bit sequence of the layer by the above ratio and rounding the result.

[0157] In at least another embodiment, the predetermined bit information includes: the number of the predetermined bits and / or the position of the predetermined bits in the bit sequence. Specifically, when the second part of the CSI report has at least two layers: the number of the predetermined bits is the same for different layers; or the number of the predetermined bits is different for at least two layers.

[0158] In at least one embodiment, the predetermined bit information is pre-set; or, the predetermined bit information is configured by the network device; or, the predetermined bit information is determined by the terminal device. Where the predetermined bit information is determined by the terminal device, the terminal device further reports the predetermined bit information to the network device.

[0159] According to an embodiment of the second aspect, a priority order of CSI generated based on an artificial intelligence model can be set, whereby terminal devices and network devices can perform corresponding processing and operations based on the priority order.

[0160] Embodiments of the third aspect

[0161] The properties of the spatial channel between a terminal device and a network device may vary due to different locations or other reasons. The important bits of the channel state information (CSI) bit sequence obtained by the terminal device based on AI / ML models or other methods may also vary.

[0162] When uplink channel resources are insufficient, the terminal device can discard unimportant bits in the CSI. However, since there may be more than one set of important CSI bits, it is sometimes difficult for the network device to determine the bits discarded by the terminal device.

[0163] The embodiment of the third aspect provides a method for transmitting channel state information (CSI), which is applied to a terminal device, such as the terminal device 202 in FIG2 . For the parts of the embodiment of the third 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, and no repetition is given here.

[0164] FIG5 is a schematic diagram of a method for transmitting channel state information (CSI) according to the third aspect of the present application. As shown in FIG5 , the method includes:

[0165] Operation 501: A terminal device sends at least a portion of first channel state information (CSI);

[0166] Operation 502: The terminal device sends indication information, where the indication information is used to indicate an extension method of the at least part of the first channel state information (CSI).

[0167] In operation 501, at least a portion of the first CSI information may be, for example, a CSI payload. That is, the CSI payload may be all information of the first CSI or a portion of information of the first CSI.

[0168] In an embodiment of the third aspect, the terminal device sends indication information to the network device, whereby the network device can expand the received CSI according to the received indication information, thereby facilitating subsequent processing by the terminal device.

[0169] As shown in FIG5 , the method further includes:

[0170] Operation 503: The terminal device discards the second channel state information according to the extended mode to form the at least a portion of the first channel state information.

[0171] In operation 503, the discarding process is, for example, discarding some bits in the second channel state information (CSI). The second CSI is, for example, output by an AI / ML model on the terminal device side, or generated based on a traditional codebook. This application does not limit the generation method of the second CSI.

[0172] In an embodiment of the third aspect, the terminal device discards the second CSI, sends at least a portion of the first CSI obtained after the discarding process to the network device, and sends indication information of the extension method corresponding to the discarding process to the network device. Thus, the network device can perform extension processing on at least a portion of the received first CSI (for example, filling the bits discarded by the terminal device with 0 or 1 or a predetermined bit sequence, such as 10011, etc.), thereby obtaining the extended CSI.

[0173] In at least one embodiment, the extension mode indicated by the indication information includes:

[0174] The number of extended bits, and / or the content of the extended bits, and / or the position of the extended bits in the channel state information, etc.

[0175] There may be at least one of the number and / or position of the extended bits.

[0176] For example, the extended bit position may be located at the front of at least a portion of the information of the first CSI, or at the back, or may be extended between two bits (for example, at the pth bit position). i and p i+1 bits between the expansion i ≥0, i is a positive integer. iThey can all be the same, or at least two can be unequal).

[0177] The extended content of the extended bit may be at least one.

[0178] For example, the extended bits can be padded with all 0s, or all 1s, or a predetermined set of bit sequences can be padded into the extended bits, such as y=10011…, without limitation. The length of the padded bit sequence depends on all the above a i For an i, take the a of sequence y from left to right. i The bits are padded at corresponding positions of at least a portion of the first CSI information.

[0179] Correspondingly, the contents of the discard processing corresponding to the extended mode may include:

[0180] The number of discarded bits, and / or the content of the discarded bits, and / or the position of the discarded bits in the channel state information, etc.

[0181] In at least one embodiment, the extension mode may be at least one of at least two candidate extension modes, and the indication information may include an index of the candidate extension mode, thereby indicating the extension mode, wherein the at least two candidate extension modes are predefined or configured by the network device.

[0182] In at least one embodiment, in at least one channel state information report, the at least one portion of the first channel state information has one layer or at least two layers. When the at least one portion of the first CSI has at least two layers, the extension mode of each layer may be the same, or the extension mode of at least two layers may be different. For example, when there are at least two layers, each layer may have the indication information indicating the extension mode of the layer, that is, the number of indication information and the number of layers may be the same; for another example, when there are at least two layers, layers with the same extension mode may share the indication information for indicating the extension mode.

[0183] In at least one embodiment of operation 502, the number of bits and / or position of the resources used to send the indication information is predefined or configured by the network device. For example, 3 bits can be used to send the indication information, and the bits used to send the indication information can be located before, after, or at other predetermined positions of at least a portion of the first CSI information.

[0184] The method for sending channel state information of the third embodiment is described below with reference to specific embodiments. In the following embodiments, the number and / or position of bits of the resource used to send the indication information is predefined or configured by the network device.

[0185] Example 1:

[0186] Assume that the network device configures an 80-bit CSI uplink channel PUSCH resource, of which 77 bits are used for the CSI payload (i.e., at least a portion of the first CSI signal) and 3 bits are used to send indication information, which indicates the extension method of the CSI payload. The 3 bits used to indicate the extension method are located in the last three bits of the 80-bit value.

[0187] The CSI encoder based on the AI / ML model on the terminal device side and the CSI decoder based on the AI / ML model on the network device side have been jointly trained. The encoder output and decoder input are both 100 bits.

[0188] n is the value obtained by subtracting the number of bits in the CSI payload from the number of bits in the encoder output. There are eight candidate extension methods for extending the CSI payload, corresponding to 3 bits of indication information:

[0189] 1. Add n zeros at the front position;

[0190] 2. Add n 1s at the last position;

[0191] 3. Padded 0 between every two bits from bit 1 to bit n+1 of the CSI payload;

[0192] 4. Padded 0 between every two bits from the penultimate to the penultimate (n+1) bits of the CSI payload;

[0193] 5. Add one zero after each of the 1st, 3rd, 5th, 7th, ..., 2n-1th bits of the CSI payload;

[0194] 6. Patch a zero in front of the first, third, fifth, seventh, ..., and 2n-1th bits of the CSI payload;

[0195] 7. Add two zeros after the first bit of the CSI payload, and add one zero after each of the third, fifth, ..., 37th, and 2n-3th bits;

[0196] 8. Predefine a sequence x of length m, for example, 10011001111…001101110. Complement bits 1, 3, 5, 7, …, 2n-1 of the CSI payload with bits 1, 2, 3, 4, …, n of sequence x, respectively.

[0197] In Example 1, 0 <n<m。

[0198] The 3-bit indication information corresponding to the first to eighth candidate extension modes may be 000, 001, 010, 011, 100, 101, 110, and 111 respectively.

[0199] Since the uplink resource is 80 bits, in this example, n=23. Before sending the CSI payload to the network device through the uplink channel, the terminal device selects one of the above-mentioned 8 candidate extension modes as the extension mode, for example, selects the 8th one. Then, according to the selected extension mode, the terminal device discards the 2nd, 4th, 6th, 8th,... , 44th, and 46th bits of the 100-bit bit sequence output by the encoder (the 100-bit bit sequence corresponds to the second CSI). Thus, a bit sequence with a length of 77 bits is obtained. The terminal device uses "111" as indication information to indicate the extension mode, and appends this 3-bit bit sequence to the previously obtained 77-bit bit sequence to obtain a bit sequence with a length of 80. The terminal device uploads this 80-bit bit sequence through the uplink channel (for example, PUSCH).

[0200] The network device receives this 80-bit bit sequence and, based on its own specifications, determines that a 3-bit bit sequence exists to indicate the extended format. This bit sequence is located in the last 3 bits of the 80-bit sequence received by the network device. The network device reads these last 3 bits and obtains 111, thus determining to use candidate extension method 8 to extend the first 77 bits of the received sequence. This extension results in a 100-bit bit sequence. This 100-bit bit sequence is then fed into the decoder, and the decoder outputs a restored representation of the information fed into the encoder.

[0201] Example 2:

[0202] In Example 2, as shown in Table 6, the indication information for indicating the extended mode can be combined with the priority of the CSI. For example, the predetermined bit information described in the embodiment of the first aspect can be set based on the extended mode. That is, the priority can have a mapping relationship with the layer information and / or the bit information set according to the extended mode.

[0203] Assume that there are 3 CSI reports, and each CSI report corresponds to 2 layers. In addition, this embodiment is not limited thereto, for example, at least two CSI reports may correspond to different numbers of layers.

[0204] For the extension method of the CSI payload of each layer (i.e., at least a portion of the first CSI information), one of the eight candidate extension methods in Example 1 can be selected. The same extension method can be selected for each layer, or different extension methods can be selected for at least two layers. Table 6:

[0205] In Table 6, the bits retained according to the selected “CSI payload extension method” refer to the bits retained in the CSI payload after the terminal device discards the bits based on the selected extension method.

[0206] In Table 6, the bits discarded according to the selected "CSI payload extension method" refer to: the bits discarded from the second CSI when the terminal device performs a discard process based on the selected extension method.

[0207] In Table 6, the indication information for indicating “the manner in which the CSI payload is extended” of the three CSI reports is set to have the highest priority, ie, priority 0.

[0208] In some implementations, there may be only one specification for the priority of CSI, for example, there is only one column of mapping relationships in Table 6, for example, corresponding to #1 or #2.

[0209] In other embodiments, there may be at least two specifications for CSI priority, such as at least two columns of mapping relationships in Table 6, corresponding to #1 and #2, for example. The terminal device may determine which set of mapping relationships to use to set CSI priority and discard CSI based on the configuration of the network device. Alternatively, the terminal device may independently determine which set of mapping relationships to use to set CSI priority and discard CSI, and then feed back the index of the set of mapping relationships to the network device. The position of the mapping relationship index in the feedback bit sequence may be specified by the standard or agreed upon in advance by the network device and the terminal device.

[0210] Example 3:

[0211] Example 3 is similar to Example 2.

[0212] In embodiment 3, all layers in the same CSI report use the same “CSI payload extension method”.

[0213] In embodiment 2, each CSI report has two layers, and each layer has a separate indication information to indicate the "CSI payload extension method". The indication information is 3 bits, so each CSI report requires 6 bits to indicate the "CSI payload extension method".

[0214] In Example 3, each CSI report has two layers. These two layers can share a three-bit indication to indicate the "CSI payload extension method." Therefore, each CSI report requires three bits to indicate the "CSI payload extension method." The location of these three bits can be predefined or configured by the network device. For example, these three bits can be placed after the first layer's CSI payload or at another location.

[0215] Example 4:

[0216] Embodiment 4 is similar to embodiment 3, except that in embodiment 4, different CSI reports may have different numbers of layers.

[0217] In embodiment 4, as shown in Table 7, all layers in the same CSI report use the same “CSI payload extension method”.

[0218] In the fourth embodiment, the indication information for indicating the “CSI payload extension method” of the three CSI reports is not set to have the highest priority.

[0219] Table 7:

[0220] Adjusting at least part of the priority order shown in column #1 in Table 7 can serve as the mapping relationship of #2.

[0221] In some implementations, there may be only one specification for the priority of CSI, for example, there is only one column of mapping relationships in Table 7, for example, corresponding to #1 or #2.

[0222] In other embodiments, there may be at least two provisions for CSI priority, such as at least two columns of mapping relationships in Table 7, corresponding to #1 and #2, for example. The terminal device may determine which set of mapping relationships to use to set CSI priority and discard CSI based on the configuration of the network device. Alternatively, the terminal device may independently determine which set of mapping relationships to use to set CSI priority and discard CSI, and then feed back the index of the set of mapping relationships to the network device. The position of the mapping relationship index in the feedback bit sequence may be specified by the standard or agreed upon in advance by the network device and the terminal device.

[0223] Embodiment of the fourth aspect (corresponding to the first aspect, network side)

[0224] At least for the same problem as the embodiment of the first aspect, the embodiment of the fourth aspect of the present application provides a method for receiving channel state information (CSI), which is applied to a network device and corresponds to the embodiment of the first aspect.

[0225] FIG6 is a schematic diagram of a method for receiving channel state information according to an embodiment of the fourth aspect, the method including:

[0226] Operation 601: Receive first channel state information (CSI).

[0227] The first channel state information is obtained by discarding (omitting) the first information from at least a portion of the channel state information (CSI) generated based on the artificial intelligence model according to the priority order of the CSI and / or the first configuration information.

[0228] In at least one embodiment, at least a portion of the CSI includes two parts, wherein:

[0229] The first part includes a rank indication (RI) and / or at least a portion of a channel quality indication (CQI) and / or a channel state information reference signal resource indication (CRI), and the second part includes information of a precoding matrix and / or at least a portion of a channel quality indication (CQI) and / or a layer indication (LI), wherein at least the information of the precoding matrix is ​​generated based on the artificial intelligence model, and the first information is at least a portion of the information in the second part.

[0230] In at least one embodiment, discarding the first information of the CSI according to the priority order includes:

[0231] The first information of the CSI is discarded in order of the priority from low to high.

[0232] In at least one embodiment, in at least one CSI report, the priority order is set according to information of a layer of the second part and / or information of a predetermined bit in the layer.

[0233] In at least one embodiment, there is one or at least two sets of mapping relationships between the priority order and the information of the layer and / or the information of the predetermined bit in the layer. In the case where there are at least two sets of mapping relationships, the priority order is set based on one of the at least two sets of mapping relationships. The set of mapping relationships is pre-set, or selected by the terminal device, or configured by the network device.

[0234] In at least one embodiment, when the terminal device selects the set of mapping relationships, the network device receives information about the set of mapping relationships sent by the terminal device.

[0235] In at least one embodiment, the layer information includes an order of the layers, and the order of the layers is set according to an arrangement order of eigenvalues ​​or singular values ​​of a spatial channel matrix corresponding to the layers. The larger the eigenvalue or singular value, the higher the priority order corresponding to the layer.

[0236] In at least one embodiment, in the CSI report, the second part has one layer or at least two layers. When the second part has at least two layers, each layer is generated based on the same artificial intelligence model, or at least two layers are generated based on different artificial intelligence models.

[0237] In at least one embodiment, the predetermined bit information includes: a proportion of the predetermined bit in the bit sequence of the layer. Wherein, when the second part of the CSI report includes at least two layers: the proportions are equal for different layers; or the proportions are unequal for at least two layers.

[0238] In at least one embodiment, the predetermined number of bits is: the number of bits obtained by multiplying the total number of bits in the bit sequence of the layer by the ratio and rounding the result.

[0239] In at least one embodiment, the information of the predetermined bit position further includes: the position of the predetermined bit position in the bit sequence.

[0240] In at least another embodiment, the information about the predetermined bits includes: the number of the predetermined bits. Wherein, when the second part of the CSI report has at least two layers: the number of the predetermined bits is the same for different layers; or the number of the predetermined bits is different for at least two layers.

[0241] The information of the predetermined bit position also includes: the position of the predetermined bit position in the bit sequence.

[0242] In at least one embodiment, the predetermined bit information is pre-set information; or the predetermined bit information is configured by the network device; or the predetermined bit information is determined by the terminal device.

[0243] In a case where the information of the predetermined bit position is determined by the terminal device, the network device further receives the information of the predetermined bit position reported by the terminal device.

[0244] In at least one embodiment, the terminal device discards the first information of the CSI based on a discarding criterion corresponding to the first configuration information.

[0245] The parameters in the discard criteria include:

[0246] the number and / or position of bits corresponding to the discarded first information; and / or

[0247] The number and / or position of bits corresponding to the information retained in the CSI.

[0248] The parameters in the discarding criterion are predetermined parameters, or are configured by the network device through parameter configuration information.

[0249] The discard criteria include at least one of the following:

[0250] discarding a first first number of bits in a bit sequence corresponding to the layer;

[0251] discarding a last second number of bits in the bit sequence;

[0252] first discarding odd bits in the bit sequence, and then discarding even bits in the bit sequence, until the total number of discarded bits reaches a third number;

[0253] discarding even bits in the bit sequence first, and then discarding odd bits in the bit sequence, until the total number of discarded bits reaches a fourth number;

[0254] The (P*Q+R)th bit of the bit sequence is retained, and the remaining bits are discarded, where Q is a positive integer, P is an integer greater than or equal to 0, and R is a positive integer greater than or equal to 1 and less than M.

[0255] In at least one embodiment, the discarding occurs in a CSI report carried by a physical uplink shared channel (PUSCH) and / or in a CSI report carried by a physical uplink control channel (PUCCH).

[0256] As shown in FIG6 , the method further includes:

[0257] Operation 602: The network device fills the bits corresponding to the first information in the first channel state information with predetermined content to obtain second channel state information; and

[0258] Operation 603: The network device decodes the second channel state information.

[0259] Embodiments of the fifth aspect

[0260] At least for the same problem as the embodiment of the second aspect, the embodiment of the fifth aspect of the present application provides a method for receiving channel state information (CSI), which is applied to a network device and corresponds to the embodiment of the second aspect.

[0261] FIG7 is a schematic diagram of a method for receiving channel state information according to an embodiment of the fifth aspect, the method including:

[0262] Operation 701: Receive channel state information (CSI), wherein at least a portion of the channel state information is generated based on an artificial intelligence model, and the channel state information has a priority order.

[0263] In at least one embodiment, at least a portion of the CSI includes two parts, wherein:

[0264] The first part includes a rank indication (RI) and / or at least a portion of a channel quality indication (CQI) and / or a channel state information reference signal resource indication (CRI);

[0265] The second part includes information of the precoding matrix and / or at least part of the channel quality indication (CQI) and / or layer indication (LI), wherein at least the information of the precoding matrix is ​​generated based on an artificial intelligence model.

[0266] In at least one CSI report, the priority is set according to information of a layer of the second part and / or information of a predetermined bit in the layer.

[0267] There is one or at least two mapping relationships between the priority order and the information of the layer and / or the information of the predetermined bit in the layer. In the case where there are at least two mapping relationships, the priority order is set based on one mapping relationship of the at least two mapping relationships.

[0268] The set of mapping relationships is pre-set, or selected by the terminal device, or configured by the network device. In the case where the set of mapping relationships is selected by the terminal device, the network device receives information about the set of mapping relationships sent by the terminal device.

[0269] The layer information includes a layer order, where the layer order is set according to the order of eigenvalues ​​or singular values ​​of the spatial channel matrix corresponding to the layer, wherein the larger the eigenvalue or singular value, the higher the priority order corresponding to the layer.

[0270] In the CSI report, the second part has one layer or at least two layers. When the second part has at least two layers, each layer is generated based on the same artificial intelligence model, or at least two layers are generated based on different artificial intelligence models.

[0271] In at least one embodiment, the predetermined bit information includes: a ratio of the predetermined bit in the bit sequence of the layer and / or a position of the predetermined bit in the bit sequence. When the second part of the CSI report has at least two layers: the ratio is the same for different layers; or the ratio is different for at least two layers.

[0272] The predetermined number of bits is: the number of bits obtained by multiplying the total number of bits in the bit sequence of the layer by the ratio and rounding the result.

[0273] In at least another embodiment, the predetermined bit information includes: the number of the predetermined bits and / or the position of the predetermined bits in the bit sequence. Wherein, when the second part of the CSI report has at least two layers: the number of the predetermined bits is the same for different layers; or the number of the predetermined bits is different for at least two layers.

[0274] In at least one embodiment, the predetermined bit information is pre-set information; or, the predetermined bit information is configured by the network device; or, the predetermined bit information is determined by the terminal device. Where the predetermined bit information is determined by the terminal device, the network device further receives the predetermined bit information reported by the terminal device.

[0275] Embodiments of the sixth aspect

[0276] At least for the same problem as the embodiment of the third aspect, the embodiment of the sixth aspect of the present application provides a method for receiving channel state information (CSI), which is applied to a network device and corresponds to the embodiment of the third aspect.

[0277] FIG8 is a schematic diagram of a method for receiving channel state information according to an embodiment of the sixth aspect, the method including:

[0278] Operation 801: A network device receives at least a portion of first channel state information (CSI);

[0279] Operation 802: The network device receives indication information, where the indication information is used to indicate an extension method of the at least a portion of the first channel state information.

[0280] In at least one embodiment, the number and / or position of bits of the resource used to receive the indication information is predefined or configured by the network device.

[0281] In at least one embodiment, the expansion method includes:

[0282] The number of extended bits, and / or the content of the extended bits, and / or the position of the extended bits in the channel state information.

[0283] In at least one embodiment, the extension mode is at least one of at least two candidate extension modes, wherein the at least two candidate extension modes are predetermined or configured by the network device.

[0284] In at least one embodiment, as shown in FIG8 , the method further includes:

[0285] Operation 803: The network device expands the at least a portion of the first channel state information based on the expansion method.

[0286] In at least one embodiment, in at least one channel state information report, the at least one portion of the first channel state information comprises one layer or at least two layers. In the case of at least two layers, the extension mode of each layer is the same, or the extension modes of at least two layers are different. In the case of at least two layers, layers with the same extension mode share the same indication information.

[0287] Embodiments of the seventh aspect

[0288] An embodiment of the seventh aspect of the present application provides a device for sending channel state information (CSI), which is applied to a terminal device and corresponds to the method of the embodiment of the first aspect.

[0289] FIG9 is a schematic diagram of a device for transmitting channel state information according to an embodiment of the seventh aspect. As shown in FIG9 , the device 900 includes:

[0290] A first generating unit 91 is configured to generate at least a portion of channel state information (CSI) based on an artificial intelligence model; and

[0291] The first discarding unit 92 is configured to discard (omit) the first information of the CSI according to the priority order of the CSI and / or the first configuration information.

[0292] At least a portion of the CSI includes two parts, wherein:

[0293] The first part includes a rank indication (RI) and / or at least a portion of a channel quality indication (CQI) and / or a channel state information reference signal resource indication (CRI), and the second part includes information of a precoding matrix and / or at least a portion of a channel quality indication (CQI) and / or a layer indication (LI), wherein at least the information of the precoding matrix is ​​generated based on the artificial intelligence model, and the first information is at least a portion of the information in the second part.

[0294] The first discarding unit 92 discards the first CSI information according to the priority order from low to high. For example, the discarded first information is all or part of the channel state information corresponding to at least one priority reporting level in the priority order.

[0295] In at least one CSI report, the priority is set according to information of a layer of the second part and / or information of a predetermined bit in the layer.

[0296] There is one or at least two sets of mapping relationships between the priority order and the information of the layer and / or the information of the predetermined bit in the layer. When there are at least two sets of mapping relationships, the priority order is set based on one of the at least two sets of mapping relationships. The set of mapping relationships is pre-set, or selected by the terminal device, or configured by the network device. When the terminal device selects the set of mapping relationships, the apparatus 900 is configured to send information about the set of mapping relationships to the network device.

[0297] In at least one embodiment, the layer information includes an order of the layers, where the order of the layers is determined based on the order of eigenvalues ​​or singular values ​​of the spatial channel matrix corresponding to the layers. For example, a larger eigenvalue or singular value indicates a higher priority for the layer.

[0298] In the CSI report, the second part has one layer or at least two layers. When the second part has at least two layers, each layer is generated based on the same artificial intelligence model, or at least two layers are generated based on different artificial intelligence models.

[0299] In at least one embodiment, the information of the predetermined bit includes: the proportion of the predetermined bit in the bit sequence of the layer and / or the position of the predetermined bit in the bit sequence.

[0300] Wherein, when the second part of the CSI report has at least two layers: the ratios are equal for different layers; or the ratios are unequal for at least two layers. The predetermined number of bits is the number of bits obtained by multiplying the total number of bits in the bit sequence of the layer by the ratio and rounding the result.

[0301] In at least another embodiment, the information of the predetermined bit positions includes: the number of the predetermined bit positions and / or the position of the predetermined bit positions in the bit sequence.

[0302] Wherein, in a case where the second part of the CSI report has at least two layers:

[0303] For different layers, the number of the predetermined bits is the same; or, for at least two layers, the number of the predetermined bits is different.

[0304] In at least one embodiment, the predetermined bit information is pre-set information; or, the predetermined bit information is configured by the network device; or, the predetermined bit information is determined by the terminal device.

[0305] In the case where the information of the predetermined bit position is determined by the terminal device, the apparatus 900 further reports the information of the predetermined bit position to the network device.

[0306] In at least one embodiment, the first discarding unit 92 is configured to discard the first information of the CSI based on a discarding criterion corresponding to the first configuration information.

[0307] The parameters in the discard criteria include:

[0308] the number and / or position of bits corresponding to the discarded first information; and / or

[0309] The number and / or position of bits corresponding to the information retained in the CSI.

[0310] The parameters in the discarding criterion are predetermined parameters, or are obtained by configuring the network device through parameter configuration information.

[0311] In at least one embodiment, the discard criteria include at least one of the following:

[0312] discarding a first first number of bits in a bit sequence corresponding to the layer;

[0313] discarding a last second number of bits in the bit sequence;

[0314] first discarding odd bits in the bit sequence, and then discarding even bits in the bit sequence, until the total number of discarded bits reaches a third number;

[0315] discarding even bits in the bit sequence first, and then discarding odd bits in the bit sequence, until the total number of discarded bits reaches a fourth number;

[0316] The (P*Q+R)th bit of the bit sequence is retained, and the remaining bits are discarded, where Q is a positive integer, P is an integer greater than or equal to 0, and R is a positive integer greater than or equal to 1 and less than Q.

[0317] In at least one embodiment, the discarding by the first discarding unit 92 occurs in a CSI report carried by a physical uplink shared channel (PUSCH) and / or in a CSI report carried by a physical uplink control channel (PUCCH).

[0318] Embodiments of the eighth aspect

[0319] An embodiment of the eighth aspect of the present application provides a device for sending channel state information (CSI), which is applied to a terminal device and corresponds to the method of the embodiment of the second aspect.

[0320] FIG10 is a schematic diagram of a device for transmitting channel state information according to an embodiment of the eighth aspect. As shown in FIG10 , the device 1000 includes:

[0321] The second generating unit 1001 is configured to generate at least a portion of channel state information (CSI) based on an artificial intelligence model, wherein the CSI has a priority order.

[0322] At least a portion of the CSI includes two parts, wherein:

[0323] The first part includes a rank indication (RI) and / or at least a portion of a channel quality indication (CQI) and / or a channel state information reference signal resource indication (CRI), and the second part includes information of a precoding matrix and / or at least a portion of a channel quality indication (CQI) and / or a layer indication (LI), wherein at least the information of the precoding matrix is ​​generated based on the artificial intelligence model.

[0324] In at least one CSI report, the priority is set according to information of a layer of the second part and / or information of a predetermined bit in the layer.

[0325] There is one or at least two sets of mapping relationships between the priority order and the information of the layer and / or the information of the predetermined bit in the layer. When there are at least two sets of mapping relationships, the priority order is set based on one of the at least two sets of mapping relationships. The set of mapping relationships is pre-set, or selected by the terminal device, or configured by the network device. When the terminal device selects the set of mapping relationships, the apparatus 1000 is configured to send information about the set of mapping relationships to the network device.

[0326] In at least one embodiment, the layer information includes an order of the layers, where the order of the layers is determined based on the order of eigenvalues ​​or singular values ​​of the spatial channel matrix corresponding to the layers. For example, a larger eigenvalue or singular value indicates a higher priority for the layer.

[0327] In the CSI report, the second part has one layer or at least two layers. When the second part has at least two layers, each layer is generated based on the same artificial intelligence model, or at least two layers are generated based on different artificial intelligence models.

[0328] In at least one embodiment, the information of the predetermined bit includes: the proportion of the predetermined bit in the bit sequence of the layer and / or the position of the predetermined bit in the bit sequence.

[0329] Wherein, when the second part of the CSI report has at least two layers: the ratios are equal for different layers; or the ratios are unequal for at least two layers. The predetermined number of bits is the number of bits obtained by multiplying the total number of bits in the bit sequence of the layer by the ratio and rounding the result.

[0330] In at least another embodiment, the information of the predetermined bit positions includes: the number of the predetermined bit positions and / or the position of the predetermined bit positions in the bit sequence.

[0331] Wherein, in a case where the second part of the CSI report has at least two layers:

[0332] For different layers, the number of the predetermined bits is the same; or, for at least two layers, the number of the predetermined bits is different.

[0333] In at least one embodiment, the predetermined bit information is pre-set information; or, the predetermined bit information is configured by the network device; or, the predetermined bit information is determined by the terminal device.

[0334] In the case where the information of the predetermined bit position is determined by the terminal device, the apparatus 1000 further reports the information of the predetermined bit position to the network device.

[0335] Embodiments of the ninth aspect

[0336] An embodiment of the ninth aspect of the present application provides a device for sending channel state information (CSI), which is applied to a terminal device and corresponds to the method of the embodiment of the third aspect.

[0337] FIG11 is a schematic diagram of a device for transmitting channel state information according to an embodiment of the ninth aspect. As shown in FIG11 , the device 1100 includes a first transmitting unit 1101, which is configured to:

[0338] sending at least a portion of first channel state information (CSI); and

[0339] Send indication information, where the indication information is used to indicate an extension method of the at least part of the first channel state information (CSI).

[0340] The number of bits and / or position of the resource used to send the indication information is predefined or configured by the network device.

[0341] In at least one embodiment, the extension includes:

[0342] The number of extended bits, and / or the content of the extended bits, and / or the position of the extended bits in the channel state information.

[0343] The extension mode is at least one of at least two candidate extension modes. The at least two candidate extension modes are predefined or configured by the network device.

[0344] As shown in FIG11 , the apparatus 1100 further includes:

[0345] The second discarding unit 1102 is configured to perform a discarding process corresponding to the extension mode on the second channel state information to form the at least a part of the first channel state information.

[0346] In at least one embodiment, in at least one channel state information report, the at least one portion of the first channel state information comprises one layer or at least two layers. When there are at least two layers, the extension mode of each layer is the same, or the extension modes of at least two layers are different. When there are at least two layers, the layers having the same extension mode share the same indication information.

[0347] Embodiments of the tenth aspect

[0348] The embodiment of the tenth aspect of the present application provides a device for receiving channel state information (CSI), which is applied to a network device and corresponds to the method of the embodiment of the fourth aspect.

[0349] FIG12 is a schematic diagram of a device for receiving channel state information according to an embodiment of the tenth aspect. As shown in FIG12 , the device 1200 includes:

[0350] The first receiving unit 1201 is configured to receive first channel state information (CSI), wherein the first channel state information is obtained by discarding (omitting) the first information from at least a portion of the channel state information (CSI) generated based on the artificial intelligence model according to the priority order (priority order) of the CSI and / or the first configuration information.

[0351] In at least one embodiment, at least a portion of the CSI includes two parts, wherein:

[0352] The first part includes a rank indication (RI) and / or at least a portion of a channel quality indication (CQI) and / or a channel state information reference signal resource indication (CRI), and the second part includes information of a precoding matrix and / or at least a portion of a channel quality indication (CQI) and / or a layer indication (LI), wherein at least the information of the precoding matrix is ​​generated based on the artificial intelligence model, and the first information is at least a portion of the information in the second part.

[0353] In at least one embodiment, discarding the first information of the CSI according to the priority order includes:

[0354] The first information of the CSI is discarded in order of the priority from low to high.

[0355] In at least one CSI report, the priority order is set based on layer information of the second part and / or information of predetermined bits in the layer. There are one or at least two mapping relationships between the priority order and the layer information and / or information of predetermined bits in the layer. If there are at least two mapping relationships, the priority order is set based on one of the at least two mapping relationships.

[0356] The set of mapping relationships is pre-set, or selected by the terminal device, or configured by the network device. Wherein, in the case where the set of mapping relationships is selected by the terminal device, the network device receives information about the set of mapping relationships sent by the terminal device.

[0357] In at least one embodiment, the layer information includes an order of the layers, and the order of the layers is set according to the order of eigenvalues ​​or singular values ​​of the spatial channel matrix corresponding to the layers. The larger the eigenvalue or singular value, the higher the priority order corresponding to the layer.

[0358] In the CSI report, the second part has one layer or at least two layers. When the second part has at least two layers, each layer is generated based on the same artificial intelligence model, or at least two layers are generated based on different artificial intelligence models.

[0359] In at least one embodiment, the information of the predetermined bit position includes: the proportion of the predetermined bit position in the bit sequence of the layer and / or the position of the predetermined bit position in the bit sequence.

[0360] In the case where the second part of the CSI report has at least two layers: the ratios are equal for different layers; or the ratios are unequal for at least two layers.

[0361] The predetermined number of bits is the number of bits obtained by multiplying the total number of bits in the bit sequence of the layer by the ratio and rounding the result.

[0362] In at least another embodiment, the information of the predetermined bit positions includes: the number of the predetermined bit positions and / or the position of the predetermined bit positions in the bit sequence.

[0363] In the case where the second part of the CSI report has at least two layers: for different layers, the number of the predetermined bits is the same; or, for at least two layers, the number of the predetermined bits is different.

[0364] In at least one embodiment, the predetermined bit information is pre-set information; or, the predetermined bit information is configured by the network device; or, the predetermined bit information is determined by the terminal device. In the case where the predetermined bit information is determined by the terminal device, the first receiving unit 1201 is further configured to receive the predetermined bit information reported by the terminal device.

[0365] In at least one embodiment, the terminal device discards the first information of the CSI based on a discarding criterion corresponding to the first configuration information.

[0366] The parameters in the discard criteria include:

[0367] the number and / or position of bits corresponding to the discarded first information; and / or

[0368] The number and / or position of bits corresponding to the information retained in the CSI.

[0369] In at least one embodiment, the parameters in the discarding criterion are predetermined parameters, or are configured by the network device through parameter configuration information.

[0370] The discard criteria include at least one of the following:

[0371] discarding a first first number of bits in a bit sequence corresponding to the layer;

[0372] discarding a last second number of bits in the bit sequence;

[0373] first discarding odd bits in the bit sequence, and then discarding even bits in the bit sequence, until the total number of discarded bits reaches a third number;

[0374] discarding even bits in the bit sequence first, and then discarding odd bits in the bit sequence, until the total number of discarded bits reaches a fourth number;

[0375] The (P*Q+R)th bit of the bit sequence is retained, and the remaining bits are discarded, where Q is a positive integer, P is an integer greater than or equal to 0, and R is a positive integer greater than or equal to 1 and less than M.

[0376] In at least one embodiment, the discarding occurs in a CSI report carried by a physical uplink shared channel (PUSCH) and / or in a CSI report carried by a physical uplink control channel (PUCCH).

[0377] As shown in FIG12 , the apparatus 1200 further includes a first recovery unit 1202 configured to:

[0378] Filling the bits corresponding to the first information in the first channel state information with predetermined content to obtain second channel state information; and

[0379] The second channel state information is decoded.

[0380] Embodiment of the eleventh aspect

[0381] An embodiment of the eleventh aspect of the present application provides a device for receiving channel state information (CSI), which is applied to a network device and corresponds to the method of the embodiment of the fifth aspect.

[0382] FIG13 is a schematic diagram of a device for receiving channel state information according to an embodiment of the eleventh aspect. As shown in FIG13 , the device 1300 includes:

[0383] The second receiving unit 1301 is configured to receive channel state information (CSI), wherein at least a portion of the channel state information is generated based on an artificial intelligence model, and the channel state information has a priority order.

[0384] At least a portion of the CSI includes two parts, wherein:

[0385] The first part includes a rank indication (RI) and / or at least a portion of a channel quality indication (CQI) and / or a channel state information reference signal resource indication (CRI), and the second part includes information of a precoding matrix and / or at least a portion of a channel quality indication (CQI) and / or a layer indication (LI), wherein at least the information of the precoding matrix is ​​generated based on the artificial intelligence model.

[0386] In at least one CSI report, the priority is set according to information of a layer of the second part and / or information of a predetermined bit in the layer.

[0387] There is one or at least two groups of mapping relationships between the priority order and the information of the layer and / or the information of the predetermined bit in the layer. In the case where there are at least two groups of mapping relationships, the priority order is set based on one group of mapping relationships in the at least two groups of mapping relationships. The group of mapping relationships is pre-set, or selected by the terminal device, or configured by a network device. In the case where the terminal device selects the group of mapping relationships, the second receiving unit 1301 is further configured to receive information of the group of mapping relationships sent by the terminal device.

[0388] In at least one embodiment, the layer information includes an order of the layers, and the order of the layers is set according to the order of eigenvalues ​​or singular values ​​of the spatial channel matrix corresponding to the layers. The larger the eigenvalue or singular value, the higher the priority order corresponding to the layer.

[0389] In the CSI report, the second part has one layer or at least two layers. When the second part has at least two layers, each layer is generated based on the same artificial intelligence model, or at least two layers are generated based on different artificial intelligence models.

[0390] In at least one embodiment, the information of the predetermined bit position includes: the proportion of the predetermined bit position in the bit sequence of the layer and / or the position of the predetermined bit position in the bit sequence.

[0391] Wherein, in a case where the second part of the CSI report has at least two layers:

[0392] The ratio is the same for different layers; or

[0393] For at least two layers, the ratios are different.

[0394] The number of predetermined bits is:

[0395] The number of bits is obtained by multiplying the total number of bits in the bit sequence of the layer by the ratio and rounding the result.

[0396] In at least one embodiment, the information of the predetermined bit positions includes: the number of the predetermined bit positions and / or the position of the predetermined bit positions in the bit sequence.

[0397] Wherein, in a case where the second part of the CSI report has at least two layers:

[0398] For different layers, the number of predetermined bits is the same; or

[0399] For at least two layers, the predetermined number of bits is different.

[0400] In at least one embodiment, the predetermined bit information is pre-set information; or, the predetermined bit information is configured by the network device; or, the predetermined bit information is determined by the terminal device. Wherein, in the case where the predetermined bit information is determined by the terminal device, the second receiving unit is further configured to receive the predetermined bit information reported by the terminal device.

[0401] Embodiments of the twelfth aspect

[0402] The embodiment of the twelfth aspect of the present application provides a device for receiving channel state information (CSI), which is applied to a network device and corresponds to the method of the embodiment of the sixth aspect.

[0403] FIG14 is a schematic diagram of a device for receiving channel state information according to an embodiment of the twelfth aspect. As shown in FIG14 , the device 1400 includes a third receiving unit 1401, and the third receiving unit 1401 is configured to:

[0404] receiving at least a portion of first channel state information (CSI); and

[0405] Indication information is received, where the indication information is used to indicate an extension method of the at least part of the information of the first channel state information.

[0406] In at least one embodiment, the number and / or position of bits of the resource used to receive the indication information is predefined or configured by the network device.

[0407] The extension manner includes: the number of extended bits, and / or the content of the extended bits, and / or the position of the extended bits in the channel state information.

[0408] The extension mode is at least one of at least two candidate extension modes, and the at least two candidate extension modes are predetermined or configured by the network device.

[0409] As shown in FIG14 , the apparatus 1400 further includes:

[0410] The second recovery unit 1402 is configured to expand the at least part of the first channel state information based on the expansion method.

[0411] In at least one channel state information report, the at least part of the first channel state information comprises one layer or at least two layers. When there are at least two layers, the extension mode of each layer is the same, or the extension modes of at least two layers are different. When there are at least two layers, the layers with the same extension mode share the same indication information.

[0412] Embodiments of the thirteenth aspect

[0413] An embodiment of the thirteenth aspect of the present application provides a communication system, which may include a network device and a terminal device.

[0414] FIG15 is a schematic diagram of a terminal device according to an embodiment of the thirteenth aspect. As shown in FIG15 , the terminal device 1500 (e.g., corresponding to the terminal device 202 in FIG2 ) may include a processor 1510 and a memory 1520; the memory 1520 stores data and programs and is coupled to the processor 1510. 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.

[0415] For example, the processor 1510 may be configured to execute a program to implement the method in the embodiment as described in any one of the embodiments of the first aspect to the third aspect.

[0416] As shown in Figure 15 , the terminal device 1500 may further include: a communication module 1530, an input unit 1540, a display 1550, and a power supply 1560. 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 1500 does not necessarily include all of the components shown in Figure 15 , and these components are not essential. Furthermore, the terminal device 1500 may also include components not shown in Figure 15 , for which reference may be made to the prior art.

[0417] FIG16 is a schematic diagram of a network device according to an embodiment of the fifth aspect. As shown in FIG16 , network device 1600 (e.g., corresponding to network device 201 in FIG2 ) may include a processor 1610 (e.g., a central processing unit (CPU)) and a memory 1620; the memory 1620 is coupled to the processor 1610. The memory 1620 may store various data and may also store an information processing program 1630, which is executed under the control of the processor 1610.

[0418] For example, the processor 1610 may be configured to execute a program to implement the method described in any one of the embodiments of the fourth to sixth aspects.

[0419] In addition, as shown in FIG16 , network device 1600 may further include: a transceiver 1640 and an antenna 1650, 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 1600 does not necessarily include all the components shown in FIG16 ; in addition, network device 1600 may also include components not shown in FIG16 , and reference may be made to the prior art for details.

[0420] An embodiment of the present application further 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 any one of the embodiments of the first to third aspects.

[0421] An embodiment of the present application further provides a storage medium storing a computer program, wherein the computer program enables a terminal device to execute the method described in any one of the first to third aspects.

[0422] 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 any one of the embodiments of the fourth to sixth aspects.

[0423] An embodiment of the present application further provides a storage medium storing a computer program, wherein the computer program enables a network device to execute the method described in any one of the embodiments of the fourth to sixth aspects.

[0424] 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.

[0425] 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).

[0426] 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.

[0427] 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.

[0428] 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.

[0429] Regarding the implementation methods including the above embodiments, the following additional notes are also disclosed:

[0430] Discarding method on the terminal side:

[0431] 1. A method for transmitting channel state information (CSI), applied to a terminal device, the method comprising:

[0432] generating at least a portion of channel state information (CSI) based on the artificial intelligence model; and

[0433] The first information of the CSI is discarded (omitted) according to the priority order of the CSI and / or the first configuration information.

[0434] 2. The method as described in Note 1, wherein:

[0435] At least a portion of said CSI comprises two parts,

[0436] In both sections:

[0437] The first part includes a rank indication (RI) and / or at least a portion of a channel quality indication (CQI) and / or a channel state information reference signal resource indication (CRI),

[0438] The second part includes information of a precoding matrix and / or at least part of a channel quality indicator (CQI) and / or a layer indicator (LI), wherein at least the information of the precoding matrix is ​​generated based on the artificial intelligence model,

[0439] The first information is at least a portion of information in the second portion.

[0440] 3. The method as described in Note 2, wherein:

[0441] The step of discarding the first information of the CSI according to the priority order includes:

[0442] The first information of the CSI is discarded in order of the priority from low to high.

[0443] 4. The method as described in Note 2, wherein:

[0444] In at least one CSI report, the priority is set according to information of a layer of the second part and / or information of a predetermined bit in the layer.

[0445] 5. The method as described in Note 4, wherein:

[0446] There is one or at least two mapping relationships between the priority order and the information of the layer and / or the information of the predetermined bit in the layer,

[0447] In the case that there are at least two groups of mapping relationships, the priority order is set based on one of the at least two groups of mapping relationships.

[0448] 5a. The method as described in Note 5, wherein:

[0449] The set of mapping relationships is pre-set, or selected by the terminal device, or configured by the network device.

[0450] 5b. The method as described in Note 5, wherein:

[0451] In the case where the terminal device selects the set of mapping relationships,

[0452] The terminal device receives information sent by the network device, where the information instructs the terminal device to send information about the set of mapping relationships to the network device.

[0453] 6. The method as described in Note 4, wherein:

[0454] The layer information includes the order of the layers,

[0455] The order of the layers is set according to the arrangement order of the eigenvalues ​​or singular values ​​of the spatial channel matrix corresponding to the layers.

[0456] 7. The method as described in Supplementary Note 6, wherein:

[0457] The larger the eigenvalue or singular value is, the higher the priority order corresponding to the layer is.

[0458] 8. The method as described in Note 4, wherein:

[0459] In the CSI report, the second part has one layer or at least two layers,

[0460] In case the second portion has at least two of said layers,

[0461] Each of the layers is generated based on the same artificial intelligence model, or at least two of the layers are generated based on different artificial intelligence models.

[0462] 9. The method as described in Note 4, wherein:

[0463] The information of the predetermined bit position includes: the proportion of the predetermined bit position in the bit sequence of the layer.

[0464] 10. The method as described in Supplementary Note 9, wherein:

[0465] In a case where the second part of the CSI report has at least two layers:

[0466] The ratios are equal for different layers; or

[0467] For at least two layers, the ratios are not equal.

[0468] 11. The method as described in Supplementary Note 9, wherein:

[0469] The predetermined number of bits is:

[0470] The number of bits is obtained by multiplying the total number of bits in the bit sequence of the layer by the ratio and rounding the result.

[0471] 12. The method as described in Supplementary Note 9, wherein:

[0472] The predetermined bit information also includes:

[0473] The predetermined bit position is the position in the bit sequence.

[0474] 13. The method as described in Note 4, wherein:

[0475] The information about the predetermined bits includes: the number of the predetermined bits.

[0476] 14. The method as described in Note 13, wherein:

[0477] In a case where the second part of the CSI report has at least two layers:

[0478] For different layers, the number of predetermined bits is the same; or

[0479] For at least two layers, the predetermined number of bits is different.

[0480] 15. The method as described in Note 13, wherein:

[0481] The predetermined bit information also includes:

[0482] The predetermined bit position is the position in the bit sequence.

[0483] 16. The method as described in Note 4, wherein:

[0484] The predetermined bit information is pre-set information; or

[0485] The predetermined bit information is configured by the network device; or

[0486] The predetermined bit information is determined by the terminal device.

[0487] 17. The method as described in Note 16, wherein:

[0488] In the case where the predetermined bit information is determined by the terminal device,

[0489] The terminal device also reports the predetermined bit information to the network device.

[0490] 18. The method as described in Note 2, wherein:

[0491] The terminal device discards the first information of the CSI based on the discarding criteria corresponding to the first configuration information.

[0492] 19. The method as described in Note 18, wherein:

[0493] The parameters in the discard criteria include:

[0494] the number and / or position of bits corresponding to the discarded first information; and / or

[0495] The number and / or position of bits corresponding to the information retained in the CSI.

[0496] 20. The method as described in Note 19, wherein:

[0497] The parameters in the discarding criterion are predetermined parameters, or are obtained by configuring the network device through parameter configuration information.

[0498] 21. The method as described in Note 19, wherein:

[0499] The discard criteria include at least one of the following:

[0500] discarding a first first number of bits in a bit sequence corresponding to the layer of the second part;

[0501] discarding a last second number of bits in the bit sequence;

[0502] first discarding odd bits in the bit sequence, and then discarding even bits in the bit sequence, until the total number of discarded bits reaches a third number;

[0503] discarding even bits in the bit sequence first, and then discarding odd bits in the bit sequence, until the total number of discarded bits reaches a fourth number;

[0504] The (P*Q+R)th bit of the bit sequence is retained, and the remaining bits are discarded, where Q is a positive integer, P is an integer greater than or equal to 0, and R is a positive integer greater than or equal to 1 and less than Q.

[0505] 22. The method according to any one of Supplements 1 to 21, wherein

[0506] The discarding occurs in a CSI report carried by a physical uplink shared channel (PUSCH) and / or in a CSI report carried by a physical uplink control channel (PUCCH).

[0507] 23. The method according to any one of Supplementary Notes 1 to 22, wherein

[0508] The discarded first information is all or part of the channel state information corresponding to at least one priority reporting level in the priority order.

[0509] The priority order on the terminal side is determined as follows:

[0510] 1. A method for transmitting channel state information (CSI), applied to a terminal device, the method comprising:

[0511] Generate at least a portion of channel state information (CSI) based on an artificial intelligence model,

[0512] The CSI has a priority order.

[0513] 2. The method as described in Note 1, wherein:

[0514] At least a portion of said CSI comprises two parts,

[0515] In both sections:

[0516] The first part includes a rank indication (RI) and / or at least a portion of a channel quality indication (CQI) and / or a channel state information reference signal resource indication (CRI),

[0517] The second part includes information of a precoding matrix and / or at least part of a channel quality indication (CQI) and / or a layer indication (LI), wherein at least the information of the precoding matrix is ​​generated based on the artificial intelligence model.

[0518] 3. The method as described in Note 2, wherein:

[0519] In at least one CSI report, the priority is set according to information of a layer of the second part and / or information of a predetermined bit in the layer.

[0520] 4. The method as described in Note 3, wherein:

[0521] There is one or at least two mapping relationships between the priority order and the information of the layer and / or the information of the predetermined bit in the layer,

[0522] In the case that there are at least two groups of mapping relationships, the priority order is set based on one of the at least two groups of mapping relationships.

[0523] 4a. The method as described in Note 4, wherein:

[0524] The set of mapping relationships is pre-set, or selected by the terminal device, or configured by the network device.

[0525] 4b. The method as described in Note 4, wherein:

[0526] In the case where the terminal device selects the set of mapping relationships,

[0527] The terminal device sends information about the set of mapping relationships to the network device.

[0528] 5. The method as described in Note 3, wherein:

[0529] The layer information includes the order of the layers,

[0530] The order of the layers is set according to the arrangement order of the eigenvalues ​​or singular values ​​of the spatial channel matrix corresponding to the layers.

[0531] 6. The method as described in Note 5, wherein:

[0532] The larger the eigenvalue or singular value is, the higher the priority order corresponding to the layer is.

[0533] 7. The method as described in Note 3, wherein:

[0534] In the CSI report, the second part has one layer or at least two layers,

[0535] In case the second portion has at least two of said layers,

[0536] Each of the layers is generated based on the same artificial intelligence model, or at least two of the layers are generated based on different artificial intelligence models.

[0537] 8. The method as described in Note 3, wherein:

[0538] The information of the predetermined bit position includes: the proportion of the predetermined bit position in the bit sequence of the layer.

[0539] 9. The method as described in Supplementary Note 8, wherein:

[0540] In a case where the second part of the CSI report has at least two layers:

[0541] The ratio is the same for different layers; or

[0542] For at least two layers, the ratios are different.

[0543] 10. The method as described in Supplementary Note 8, wherein:

[0544] The predetermined number of bits is:

[0545] The number of bits is obtained by multiplying the total number of bits in the bit sequence of the layer by the ratio and rounding the result.

[0546] 11. The method as described in Supplementary Note 8, wherein:

[0547] The reserved bits also include:

[0548] The predetermined bit position is the position in the bit sequence.

[0549] 12. The method as described in Note 3, wherein:

[0550] The information about the predetermined bits includes: the number of the predetermined bits.

[0551] 13. The method as described in Note 12, wherein:

[0552] In a case where the second part of the CSI report has at least two layers:

[0553] For different layers, the number of predetermined bits is the same; or

[0554] For at least two layers, the predetermined number of bits is different.

[0555] 14. The method as described in Note 12, wherein:

[0556] The predetermined bit information also includes:

[0557] The predetermined bit position is the position in the bit sequence.

[0558] 15. The method as described in Note 3, wherein:

[0559] The predetermined bit information is pre-set information; or

[0560] The predetermined bit information is configured by the network device; or

[0561] The predetermined bit information is determined by the terminal device.

[0562] 16. The method as described in Note 15, wherein:

[0563] In the case where the predetermined bit information is determined by the terminal device,

[0564] The terminal device also reports the predetermined bit information to the network device.

[0565] Method for sending instruction information on the terminal side:

[0566] 1. A method for transmitting channel state information, applied to a terminal device, the method comprising:

[0567] The terminal device sends at least a portion of first channel state information (CSI);

[0568] The terminal device sends indication information, where the indication information is used to indicate an extension method of at least a portion of the first channel state information (CSI).

[0569] 2. The method as described in Note 1, wherein:

[0570] The number of bits and / or position of the resource used to send the indication information is predefined or configured by the network device.

[0571] 3. The method as described in Note 1, wherein:

[0572] The extension methods include:

[0573] The number of extended bits, and / or the content of the extended bits, and / or the position of the extended bits in the channel state information.

[0574] 4. The method as described in Note 1, wherein:

[0575] The extension mode is at least one of at least two candidate extension modes.

[0576] 5. The method as described in Note 4, wherein:

[0577] The at least two candidate extension modes are predefined or configured by the network device.

[0578] 6. The method as described in Supplementary Note 1, further comprising:

[0579] The terminal device performs a discarding process corresponding to the extension mode on the second channel state information to form the at least a portion of the first channel state information.

[0580] 7. The method as described in Note 1, wherein:

[0581] In at least one channel state information report,

[0582] The at least one portion of the first channel state information has one layer or at least two layers,

[0583] In the case of having at least two layers,

[0584] The expansion mode of each layer is the same, or the expansion modes of at least two layers are different.

[0585] 8. The method as described in Supplementary Note 7, wherein:

[0586] In the case of having at least two layers,

[0587] The layers with the same extension mode share the same indication information.

[0588] Discarding method on the network side:

[0589] 1. A method for receiving channel state information (CSI), applied to a network device, the method comprising:

[0590] receiving first channel state information (CSI),

[0591] The first channel state information is obtained by discarding (omitting) the first information from at least a part of the channel state information (CSI) generated based on the artificial intelligence model according to the priority order of the CSI and / or the first configuration information.

[0592] 2. The method as described in Note 1, wherein:

[0593] At least a portion of said CSI comprises two parts,

[0594] In both sections:

[0595] The first part includes a rank indication (RI) and / or at least a portion of a channel quality indication (CQI) and / or a channel state information reference signal resource indication (CRI),

[0596] The second part includes information of a precoding matrix and / or at least part of a channel quality indicator (CQI) and / or a layer indicator (LI), wherein at least the information of the precoding matrix is ​​generated based on the artificial intelligence model,

[0597] The first information is at least a portion of information in the second portion.

[0598] 3. The method as described in Note 2, wherein:

[0599] The step of discarding the first information of the CSI according to the priority order includes:

[0600] The first information of the CSI is discarded in order of the priority from low to high.

[0601] 4. The method as described in Note 2, wherein:

[0602] In at least one CSI report, the priority is set according to information of a layer of the second part and / or information of a predetermined bit in the layer.

[0603] 5. The method as described in Note 4, wherein:

[0604] There is one or at least two mapping relationships between the priority order and the information of the layer and / or the information of the predetermined bit in the layer,

[0605] In the case that there are at least two groups of mapping relationships, the priority order is set based on one of the at least two groups of mapping relationships.

[0606] 5a. The method as described in Note 5, wherein:

[0607] The set of mapping relationships is pre-set, or selected by the terminal device, or configured by the network device.

[0608] 5b. The method as described in Note 5, wherein:

[0609] In the case where the terminal device selects the set of mapping relationships,

[0610] The network device receives information about the set of mapping relationships sent by the terminal device.

[0611] 6. The method as described in Note 4, wherein:

[0612] The layer information includes the order of the layers,

[0613] The order of the layers is set according to the arrangement order of the eigenvalues ​​or singular values ​​of the spatial channel matrix corresponding to the layers.

[0614] 7. The method as described in Supplementary Note 6, wherein:

[0615] The larger the eigenvalue or singular value is, the higher the priority order corresponding to the layer is.

[0616] 8. The method as described in Note 4, wherein:

[0617] In the CSI report, the second part has one layer or at least two layers,

[0618] In case the second portion has at least two of said layers,

[0619] Each of the layers is generated based on the same artificial intelligence model, or at least two of the layers are generated based on different artificial intelligence models.

[0620] 9. The method as described in Note 4, wherein:

[0621] The information of the predetermined bit position includes: the proportion of the predetermined bit position in the bit sequence of the layer.

[0622] 10. The method as described in Supplementary Note 9, wherein:

[0623] In a case where the second part of the CSI report has at least two layers:

[0624] The ratios are equal for different layers; or

[0625] For at least two layers, the ratios are not equal.

[0626] 11. The method as described in Supplementary Note 9, wherein:

[0627] The predetermined number of bits is:

[0628] The number of bits is obtained by multiplying the total number of bits in the bit sequence of the layer by the ratio and rounding the result.

[0629] 12. The method as described in Supplementary Note 9, wherein:

[0630] The predetermined bit information also includes:

[0631] The predetermined bit position is the position in the bit sequence.

[0632] 13. The method as described in Note 4, wherein:

[0633] The information about the predetermined bits includes: the number of the predetermined bits.

[0634] 14. The method as described in Note 13, wherein:

[0635] In a case where the second part of the CSI report has at least two layers:

[0636] For different layers, the number of predetermined bits is the same; or

[0637] For at least two layers, the predetermined number of bits is different.

[0638] 15. The method as described in Note 13, wherein:

[0639] The predetermined bit information also includes:

[0640] The predetermined bit position is the position in the bit sequence.

[0641] 16. The method as described in Note 4, wherein:

[0642] The predetermined bit information is pre-set information; or

[0643] The predetermined bit information is configured by the network device; or

[0644] The predetermined bit information is determined by the terminal device.

[0645] 17. The method as described in Note 16, wherein:

[0646] In the case where the predetermined bit information is determined by the terminal device,

[0647] The network device also receives the predetermined bit information reported by the terminal device.

[0648] 18. The method as described in Note 2, wherein:

[0649] The terminal device discards the first information of the CSI based on the discarding criteria corresponding to the first configuration information.

[0650] 19. The method as described in Note 18, wherein:

[0651] The parameters in the discard criteria include:

[0652] the number and / or position of bits corresponding to the discarded first information; and / or

[0653] The number and / or position of bits corresponding to the information retained in the CSI.

[0654] 20. The method as described in Note 19, wherein:

[0655] The parameters in the discarding criterion are predetermined parameters, or are configured by the network device through parameter configuration information.

[0656] 21. The method as described in Note 19, wherein:

[0657] The discard criteria include at least one of the following:

[0658] discarding a first first number of bits in a bit sequence corresponding to the layer of the second part;

[0659] discarding a last second number of bits in the bit sequence;

[0660] first discarding odd bits in the bit sequence, and then discarding even bits in the bit sequence, until the total number of discarded bits reaches a third number;

[0661] discarding even bits in the bit sequence first, and then discarding odd bits in the bit sequence, until the total number of discarded bits reaches a fourth number;

[0662] The (P*Q+R)th bit of the bit sequence is retained, and the remaining bits are discarded, where Q is a positive integer, P is an integer greater than or equal to 0, and R is a positive integer greater than or equal to 1 and less than M.

[0663] 22. The method according to any one of Supplements 1 to 21, wherein

[0664] The discarding occurs in a CSI report carried by a physical uplink shared channel (PUSCH) and / or in a CSI report carried by a physical uplink control channel (PUCCH).

[0665] 23. The method according to any one of Notes 1 to 22, further comprising:

[0666] The network device fills the bits corresponding to the first information in the first channel state information with predetermined content to obtain second channel state information; and

[0667] The network device decodes the second channel state information.

[0668] 24. The method according to any one of Supplements 1 to 23, wherein

[0669] The discarded first information is all or part of the channel state information corresponding to at least one priority reporting level in the priority order.

[0670] The priority method on the network side:

[0671] 1. A method for receiving channel state information (CSI), applied to a network device, the method comprising:

[0672] Receive channel state information (CSI),

[0673] Wherein, at least a portion of the channel state information is generated based on an artificial intelligence model,

[0674] The channel state information has a priority order.

[0675] 2. The method as described in Note 1, wherein:

[0676] At least a portion of said CSI comprises two parts,

[0677] In both sections:

[0678] The first part includes a rank indication (RI) and / or at least a portion of a channel quality indication (CQI) and / or a channel state information reference signal resource indication (CRI),

[0679] The second part includes information of a precoding matrix and / or at least part of a channel quality indication (CQI) and / or a layer indication (LI), wherein at least the information of the precoding matrix is ​​generated based on the artificial intelligence model.

[0680] 3. The method as described in Note 2, wherein:

[0681] In at least one CSI report, the priority is set according to information of a layer of the second part and / or information of a predetermined bit in the layer.

[0682] 4. The method as described in Note 3, wherein:

[0683] There is one or at least two mapping relationships between the priority order and the information of the layer and / or the information of the predetermined bit in the layer,

[0684] In the case that there are at least two groups of mapping relationships, the priority order is set based on one of the at least two groups of mapping relationships.

[0685] 4a. The method as described in Note 4, wherein:

[0686] The set of mapping relationships is pre-set, or selected by the terminal device, or configured by the network device.

[0687] 4b. The method as described in Note 4, wherein:

[0688] In the case where the terminal device selects the set of mapping relationships,

[0689] The network device receives information about the set of mapping relationships sent by the terminal device.

[0690] 5. The method as described in Note 3, wherein:

[0691] The layer information includes the order of the layers,

[0692] The order of the layers is set according to the arrangement order of the eigenvalues ​​or singular values ​​of the spatial channel matrix corresponding to the layers.

[0693] 6. The method as described in Note 5, wherein:

[0694] The larger the eigenvalue or singular value is, the higher the priority order corresponding to the layer is.

[0695] 7. The method as described in Note 3, wherein:

[0696] In the CSI report, the second part has one layer or at least two layers,

[0697] In case the second portion has at least two of said layers,

[0698] Each of the layers is generated based on the same artificial intelligence model, or at least two of the layers are generated based on different artificial intelligence models.

[0699] 8. The method as described in Note 3, wherein:

[0700] The information of the predetermined bit position includes: the proportion of the predetermined bit position in the bit sequence of the layer.

[0701] 9. The method as described in Supplementary Note 8, wherein:

[0702] In a case where the second part of the CSI report has at least two layers:

[0703] The ratio is the same for different layers; or

[0704] For at least two layers, the ratios are different.

[0705] 10. The method as described in Supplementary Note 8, wherein:

[0706] The predetermined number of bits is:

[0707] The number of bits is obtained by multiplying the total number of bits in the bit sequence of the layer by the ratio and rounding the result.

[0708] 11. The method as described in Supplementary Note 8, wherein:

[0709] The reserved bits also include:

[0710] The predetermined bit position is the position in the bit sequence.

[0711] 12. The method as described in Note 3, wherein:

[0712] The information about the predetermined bits includes: the number of the predetermined bits.

[0713] 13. The method as described in Note 12, wherein:

[0714] In a case where the second part of the CSI report has at least two layers:

[0715] For different layers, the number of predetermined bits is the same; or

[0716] For at least two layers, the predetermined number of bits is different.

[0717] 14. The method as described in Note 12, wherein:

[0718] The predetermined bit information also includes:

[0719] The predetermined bit position is the position in the bit sequence.

[0720] 15. The method as described in Note 3, wherein:

[0721] The predetermined bit information is pre-set information; or

[0722] The predetermined bit information is configured by the network device; or

[0723] The predetermined bit information is determined by the terminal device.

[0724] 16. The method as described in Note 15, wherein:

[0725] In the case where the predetermined bit information is determined by the terminal device,

[0726] The network device also receives the predetermined bit information reported by the terminal device.

[0727] Method for receiving indication information on the network side:

[0728] 1. A method for receiving channel state information, applied to a network device, the method comprising:

[0729] The network device receives at least a portion of first channel state information (CSI);

[0730] The network device receives indication information, where the indication information is used to indicate an extension method of the at least a portion of the first channel state information.

[0731] 2. The method as described in Note 1, wherein:

[0732] The number of bits and / or position of the resources used to receive the indication information are predefined or configured by the network device.

[0733] 3. The method as described in Note 1, wherein:

[0734] The extension methods include:

[0735] The number of extended bits, and / or the content of the extended bits, and / or the position of the extended bits in the channel state information.

[0736] 4. The method as described in Note 1, wherein:

[0737] The extension mode is at least one of at least two candidate extension modes.

[0738] 5. The method as described in Note 4, wherein:

[0739] The at least two candidate extension modes are predetermined or configured by the network device.

[0740] 6. The method as described in Supplementary Note 1, further comprising:

[0741] The network device expands the at least a portion of the first channel state information based on the expansion method.

[0742] 7. The method as described in Note 1, wherein:

[0743] In at least one channel state information report,

[0744] The at least one portion of the first channel state information has one layer or at least two layers,

[0745] In the case of having at least two layers,

[0746] The expansion mode of each layer is the same, or the expansion modes of at least two layers are different.

[0747] 8. The method as described in Supplementary Note 7, wherein:

[0748] In the case of having at least two layers,

[0749] The layers with the same extension mode share the same indication information.

Claims

1. A device for transmitting channel state information (CSI), applied to a terminal device, the device comprising: a first generating unit configured to generate at least a portion of channel state information (CSI) based on an artificial intelligence model; as well as A first discarding unit is configured to discard (omit) first information of the channel state information according to a priority order of the channel state information and / or first configuration information.

2. The device according to claim 1, wherein At least a portion of said channel state information comprises two parts, In both sections: The first part includes a rank indication (RI) and / or at least a portion of a channel quality indication (CQI) and / or a channel state information reference signal resource indication (CRI), The second part includes information of a precoding matrix and / or at least part of a channel quality indicator (CQI) and / or a layer indicator (LI), wherein at least the information of the precoding matrix is ​​generated based on the artificial intelligence model, The first information is at least a portion of information in the second portion.

3. The device according to claim 2, wherein The first discarding unit discards the first information of the channel state information in order of the priority from low to high; and / or In at least one channel state information report, the priority order is set according to information of a layer of the second part and / or information of a predetermined bit in the layer.

4. The device according to claim 3, wherein There is one or at least two mapping relationships between the priority order and the information of the layer and / or the information of the predetermined bit in the layer, In the case where there are at least two groups of mapping relationships, the priority order is set based on one mapping relationship in the at least two groups of mapping relationships; and / or The layer information includes an order of the layers, where the order of the layers is set according to an arrangement order of eigenvalues ​​or singular values ​​of a spatial channel matrix corresponding to the layers; and / or In the channel state information report, the second part has one layer or at least two layers. In case the second portion has at least two of said layers, Each of the layers is generated based on the same artificial intelligence model, or at least two of the layers are generated based on different artificial intelligence models; and / or The information of the predetermined bit position includes at least one of the following: a proportion of the predetermined bit position in the bit sequence of the layer, the number of the predetermined bit positions, and a position of the predetermined bit position in the bit sequence; and / or The predetermined bit information is pre-set information, or the predetermined bit information is configured by a network device, or the predetermined bit information is determined by the terminal device.

5. The device according to claim 4, wherein The set of mapping relationships is pre-set, or selected by the terminal device, or configured by the network device; and / or In the case where the terminal device selects the set of mapping relationships, The apparatus is configured to receive information sent by the network device, where the information instructs the apparatus to send information of the set of mapping relationships to the network device.

6. The device according to claim 4, wherein In a case where the second part of the channel state information report has at least two layers: The ratios are equal for the different layers or unequal for at least two layers; and / or The predetermined number of bits is: the number of bits obtained by multiplying the total number of bits in the bit sequence of the layer by the ratio and rounding the result; and / or In a case where the second part of the channel state information report has at least two layers: For different layers, the number of the predetermined bits is the same; or, for at least two layers, the number of the predetermined bits is different.

7. The device according to claim 2, wherein The first discarding unit is configured to discard the first information of the channel state information based on a discarding criterion corresponding to the first configuration information.

8. The device according to claim 7, wherein The parameters in the discard criteria include: the number and / or position of bits corresponding to the discarded first information; and / or The number and / or position of bits corresponding to the information retained in the channel state information.

9. The device according to claim 8, wherein The parameters in the discarding criterion are predetermined parameters, or are obtained by configuring the network device through parameter configuration information; and / or The discard criteria include at least one of the following: discarding a first first number of bits in a bit sequence corresponding to the layer of the second part; discarding a last second number of bits in the bit sequence; first discarding odd bits in the bit sequence, and then discarding even bits in the bit sequence, until the total number of discarded bits reaches a third number; discarding even bits in the bit sequence first, and then discarding odd bits in the bit sequence, until the total number of discarded bits reaches a fourth number; The P*Q+Rth bit of the bit sequence is retained, and the remaining bits are discarded, where Q is a positive integer, P is an integer greater than or equal to 0, and R is a positive integer greater than or equal to 1 and less than Q.

10. The device of claim 1, wherein: The discarded first information is all or part of the channel state information corresponding to at least one priority reporting level in the priority order.

11. A device for transmitting channel state information (CSI), applied to a terminal device, the device comprising: A second generating unit is configured to generate at least a portion of channel state information (CSI) based on an artificial intelligence model, The channel state information has a priority order.

12. The device according to claim 11, wherein At least a portion of said channel state information comprises two parts, In both sections: The first part includes a rank indication (RI) and / or at least a portion of a channel quality indication (CQI) and / or a channel state information reference signal resource indication (CRI), The second part includes information of the precoding matrix and / or at least part of the channel quality indicator (CQI) and / or layer Indication (LI), wherein at least the information of the precoding matrix is ​​generated based on the artificial intelligence model.

13. The device of claim 12, wherein: In at least one channel state information report, the priority order is set according to information of a layer of the second part and / or information of a predetermined bit in the layer.

14. A channel state information (CSI) receiving device, applied to a network device, the device comprising: a first receiving unit configured to receive first channel state information (CSI), The first channel state information is obtained by discarding (omitting) the first information from at least a part of the channel state information (CSI) generated based on the artificial intelligence model according to the priority order of the channel state information and / or the first configuration information.

15. The apparatus of claim 14, wherein: At least a portion of said channel state information comprises two parts, In both sections: The first part includes a rank indication (RI) and / or at least a portion of a channel quality indication (CQI) and / or a channel state information reference signal resource indication (CRI), The second part includes information of a precoding matrix and / or at least part of a channel quality indicator (CQI) and / or a layer indicator (LI), wherein at least the information of the precoding matrix is ​​generated based on the artificial intelligence model, The first information is at least a portion of information in the second portion.

16. The apparatus of claim 15, wherein: Discarding the first information of the channel state information according to the priority order includes: discarding the first information of the channel state information in order of the priority order from low to high; and / or In at least one channel state information report, the priority order is set according to information of a layer of the second part and / or information of a predetermined bit in the layer.

17. The apparatus of claim 16, wherein: There is one or at least two mapping relationships between the priority order and the information of the layer and / or the information of the predetermined bit in the layer, In the case where there are at least two groups of mapping relationships, the priority order is set based on one mapping relationship in the at least two groups of mapping relationships; and / or The layer information includes the order of the layers, The order of the layers is set according to the order of arrangement of eigenvalues ​​or singular values ​​of the spatial channel matrix corresponding to the layers; and / or In the channel state information report, the second part has one layer or at least two layers. In case the second portion has at least two of said layers, Each of the layers is generated based on the same artificial intelligence model, or at least two of the layers are generated based on different artificial intelligence models; and / or The information of the predetermined bit position includes at least one of the following: the proportion of the predetermined bit position in the bit sequence of the layer, the position of the predetermined bit position in the bit sequence, the number of the predetermined bit positions; and / or The predetermined bit information is pre-set information, or the predetermined bit information is configured by the network device, or the predetermined bit information is determined by the terminal device.

18. The apparatus of claim 17, wherein: The set of mapping relationships is pre-set, or selected by the terminal device, or configured by the network device.

19. The apparatus of claim 15, wherein: The terminal device discards the first information of the channel state information based on the discarding criterion corresponding to the first configuration information.

20. The apparatus of claim 19, wherein The parameters in the discard criteria include: the number and / or position of bits corresponding to the discarded first information; and / or The number and / or position of bits corresponding to the information retained in the channel state information.

Images