Information transmission method and apparatus, terminal, network device, and storage medium
By dividing the compressed CSI bitstream into multiple bit groups and configuring appropriate transmission methods and priorities, the problem of the lack of physical meaning in the compressed CSI bitstream of artificial intelligence models is solved, the bit error rate is reduced, and the transmission overhead is reduced.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA MOBILE COMM LTD RES INST
- Filing Date
- 2023-08-28
- Publication Date
- 2026-04-24
AI Technical Summary
In existing technologies, CSI bitstream segmentation based on artificial intelligence model compression lacks clear physical meaning, resulting in a high bit error rate and making it impossible to select a suitable transmission method.
The network device sends configuration information to the terminal, indicating the grouping method of the compressed CSI bitstream and related information of the bit group. The terminal divides the CSI bitstream into multiple bit groups based on this information and configures an appropriate transmission method and priority for each bit group.
This reduces the bit error rate of CSI, minimizes performance loss during transmission, and reduces transmission overhead as much as possible.
Smart Images

Figure CN119544160B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of communication technology, and in particular to an information transmission method, apparatus, terminal, network device and storage medium. Background Technology
[0002] In related technologies, the scheme of segmenting Channel State Information (CSI) and configuring the transmission mode is based on a clear physical meaning. However, after the CSI bit stream is compressed using an Artificial Intelligence (AI) model, it does not have a clear physical meaning and cannot select a suitable transmission mode for the segmented CSI bit stream, resulting in a high bit error rate for CSI. Summary of the Invention
[0003] To address the related technical issues, embodiments of this application provide an information transmission method, apparatus, terminal, network device, and storage medium.
[0004] The technical solution of this application embodiment is implemented as follows:
[0005] This application provides an information transmission method applied to a terminal, the method comprising:
[0006] Receive configuration information sent by the network device, the configuration information being used to configure the grouping method and / or related information of the compressed CSI bit stream;
[0007] Based on the configuration information, the compressed CSI bitstream is divided into multiple bit groups, and first information is determined, which indicates the transmission mode and / or transmission priority of each bit group in the multiple bit groups.
[0008] The above scheme, the method further includes at least one of the following:
[0009] Based on the first information, the plurality of bit groups are sent to the network device;
[0010] Send the first information to the network device.
[0011] In the above scheme, the configuration information includes at least one of the following:
[0012] The second information indicates the transmission quality requirements;
[0013] The third information indicates the number of bit groups in the compressed CSI bitstream and the number of bits contained in each bit group;
[0014] The fourth information indicates the weight of each bit group;
[0015] The fifth piece of information indicates the transmission mode supported by the bit group.
[0016] In the above scheme, when the weight of the first bit group is greater than the weight of the second bit group, the reliability of the transmission method of the first bit group is higher than that of the transmission method of the second bit group, and / or, the transmission priority of the first bit group is higher than that of the second bit group.
[0017] In the above scheme, determining the first information includes at least one of the following:
[0018] Based at least on the second information and the fourth information, the transmission priority of each bit group is determined;
[0019] Based on the first relationship, the transmission method corresponding to the transmission priority of each bit group is determined; the first relationship includes the correspondence between transmission priority and transmission method.
[0020] In the above scheme, determining the transmission priority of each bit group based at least on the second information and the fourth information includes:
[0021] The first score is determined based on the second information;
[0022] Based on the fourth information, the second score and the third score are determined; wherein, the second score represents the score corresponding to the weight of the i-th bit group, and the third score represents the score corresponding to the weight of the (i+1)-th bit group, where i is a positive integer;
[0023] If the second score is less than or equal to the first score, and / or the third score is greater than the first score, determine the same transmission priority for the i bit groups corresponding to the second score.
[0024] In the above scheme, the second score is determined based on the sum of a set coefficient and the weights of the i-bit groups;
[0025] The third score is determined based on the sum of the set coefficients and the weights of the (i+1)th bit group.
[0026] In the above scheme, the transmission method indicates the correspondence between at least two of the coding method, the number of layers, and the modulation method.
[0027] This application also provides an information transmission method applied to a network device, the method comprising:
[0028] Send configuration information to the terminal; among which,
[0029] The configuration information is used to configure the grouping method and / or related information of the compressed CSI bit stream. The configuration information is used for the terminal to group the compressed CSI bit stream and determine the transmission method and / or transmission priority of each bit group.
[0030] The method in the above scheme further includes:
[0031] Obtain the configuration information.
[0032] In the above scheme, the configuration information includes at least one of the following:
[0033] The second information indicates the transmission quality requirements;
[0034] The third information indicates the number of bit groups in the compressed CSI bitstream and the number of bits contained in each bit group;
[0035] The fourth information indicates the weight of each bit group;
[0036] The fifth piece of information indicates the transmission mode supported by the bit group.
[0037] In the above scheme, the transmission method indicates the correspondence between at least two of the coding method, the number of layers, and the modulation method.
[0038] In the above scheme, obtaining the configuration information includes:
[0039] Obtain the fourth information determined by the first model; wherein,
[0040] The first model is used to determine the weight of each bit group in the input.
[0041] In the above scheme, the first model is trained using the following method:
[0042] The first bitstream is decompressed using the first model to obtain N first CSIs and N second CSIs; wherein, one third bit group corresponds to one first CSI, one bit combination corresponding to one third bit group corresponds to one second CSI, and one bit combination contains at least one third bit group; N is a positive integer greater than or equal to 2.
[0043] Based on N second CSIs and third CSIs, and based on the first weights of N third bit groups, the second weights of the N third bit groups are determined; wherein, the third CSI represents the calibration CSI corresponding to the first bit stream; the first weight represents the configured initial weights or the second weights in the previous iteration training.
[0044] The total loss value is determined based on N first CSIs and the third CSI, and based on the second weights of N third bit groups;
[0045] The first model is trained based on the second weights of the N third bit groups and / or the total loss value until the set convergence condition is met; wherein the second weights of the N third bit groups are used to determine the fourth information or to update the first weights.
[0046] In the above scheme, determining the second weights of the N third bit groups based on the N second CSIs and the third CSIs, and based on the first weights of the N third bit groups, includes:
[0047] Based on the third CSI and the second CSI corresponding to the third bit group, determine the first loss value of the third bit group;
[0048] Based on the first loss value and the corresponding first weight of the third bit group, the second weight of the third bit group is determined.
[0049] The method in the above scheme further includes:
[0050] Based on the second weights of the N third bit groups, the first weights of each third bit group are updated to the corresponding second weights.
[0051] In the above scheme, determining the total loss value based on N first CSIs and the third CSI, and based on the second weights of N third bit groups, includes:
[0052] Based on the N first CSIs and the third CSI, determine the second loss value of the N third bit groups;
[0053] The total loss value is determined based on the second weight and the corresponding second loss value of each of the N third bit groups.
[0054] The method in the above scheme further includes:
[0055] Receive multiple bit groups and / or first information sent by the terminal, wherein the first information indicates the transmission mode and / or transmission priority of each bit group in the multiple bit groups, and the transmission priority of the bit group is used to determine the transmission mode of the bit group;
[0056] Based on the transmission method corresponding to each of the multiple bit groups, the multiple bit groups are processed to obtain the processing result.
[0057] This application also provides an information transmission device, including:
[0058] The first receiving unit is used to receive configuration information sent by the network device, wherein the configuration information is used to configure the grouping method and / or related information of the compressed CSI bit stream;
[0059] The determining unit is configured to divide the compressed CSI bitstream into multiple bit groups based on the configuration information, and determine first information, wherein the first information indicates the transmission mode and / or transmission priority of each bit group in the multiple bit groups.
[0060] This application also provides an information transmission device, including:
[0061] The first sending unit is used to send configuration information to the terminal; wherein...
[0062] The configuration information is used to configure the grouping method and / or related information of the compressed CSI bit stream. The configuration information is used for the terminal to group the compressed CSI bit stream and determine the transmission method and / or transmission priority of each bit group.
[0063] This application embodiment also provides a terminal, including a first processor and a first communication interface, wherein,
[0064] The first communication interface is used to receive configuration information sent by the network device, wherein the configuration information is used to configure the grouping method and / or related information of the compressed CSI bit stream;
[0065] The first processor is configured to divide the compressed CSI bitstream into multiple bit groups based on the configuration information, and determine first information, wherein the first information indicates the transmission mode and / or transmission priority of each bit group in the multiple bit groups.
[0066] This application also provides a network device, including a second processor and a second communication interface, wherein...
[0067] The second communication interface is used to send configuration information to the terminal; wherein,
[0068] The configuration information is used to configure the grouping method and / or related information of the compressed CSI bit stream. The configuration information is used for the terminal to group the compressed CSI bit stream and determine the transmission method and / or transmission priority of each bit group.
[0069] This application also provides a terminal, including a first processor and a first memory for storing computer programs that can run on the first processor.
[0070] Wherein, the first processor is used to execute the steps of any method on the terminal side when running the computer program.
[0071] This application also provides a network device, including a second processor and a second memory for storing computer programs that can run on the second processor.
[0072] The second processor is used to execute the steps of any method on the network device side when running the computer program.
[0073] This application also provides a storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of any method on the terminal side or the steps of any method on the network device side.
[0074] In an embodiment of this application, an information transmission method, apparatus, terminal, network device, and storage medium are provided. The network device sends configuration information to the terminal. This configuration information is used to configure the grouping method and / or related information of the compressed CSI bitstream. The terminal receives the configuration information from the network device and, based on the configuration information, divides the compressed CSI bitstream into multiple bit groups and determines first information. The first information indicates the transmission method and / or transmission priority of each bit group. In this scheme, the terminal can group the compressed CSI bitstream based on the configuration information and configure a suitable transmission method and / or transmission priority for each bit group. Therefore, the terminal can configure different transmission methods and / or transmission priorities for different bit groups, which can reduce the bit error rate of CSI and minimize transmission overhead while reducing performance loss caused by bit errors during transmission. Attached Figure Description
[0075] Figure 1 This is a schematic diagram illustrating the implementation process of an information transmission method according to an embodiment of this application;
[0076] Figure 2 This is an example diagram of the grouping of the compressed CSI bitstream according to an embodiment of this application;
[0077] Figure 3 This is an example of configuring transmission priorities for multiple bit groups according to embodiments of this application;
[0078] Figure 4 This is a schematic diagram illustrating the implementation process of an information transmission method according to an embodiment of this application;
[0079] Figure 5 Example of calculating a first loss value for an embodiment of this application;
[0080] Figure 6 This is an example of simulation verification results for dividing the first bit stream into two bit groups according to an embodiment of this application.
[0081] Figure 7This is an example of the simulation verification results of dividing the first bit stream of this application embodiment into 3 bit groups;
[0082] Figure 8 This is a schematic diagram of the interaction process of the information transmission method in an embodiment of this application;
[0083] Figure 9 This is a schematic diagram of the information transmission device structure according to an embodiment of this application;
[0084] Figure 10 This is a schematic diagram of the information transmission device structure according to an embodiment of this application;
[0085] Figure 11 This is a schematic diagram of the terminal structure according to an embodiment of this application;
[0086] Figure 12 This is a schematic diagram of the network device structure according to an embodiment of this application. Detailed Implementation
[0087] In related technologies, the CSI reported by the terminal to the network side consists of two parts. The first part includes: Rank Indication (RI), Channel Quality Indicator (CQI), and the number of non-zero broadband amplitude coefficients in the broadband amplitude W2. The second part is used to report: indication information of broadband feedback W1, the subband amplitude corresponding to the non-zero broadband amplitude of W2, and the subband phase corresponding to the non-zero broadband amplitude. The two parts of the CSI are independently coded. In the CSI reported by the terminal, the number of bits in the first part is fixed, while the number of bits in the second part is variable. The number of bits in the second part can be determined by the RI in the first part and the number of non-zero broadband amplitude coefficients in W2. The network side can demodulate the information bits in the second part based on the information in the first part.
[0088] While related technologies define schemes for segmenting CSI and configuring transmission methods, these schemes are based on explicit physical meanings. However, CSI compression methods based on AI models differ significantly from current compression methods based on CSI feature vectors. After segmentation, the CSI bitstream compressed using AI models does not have explicit physical meanings like existing CSI feedback systems. For example, when the system directly uses AI models to feed back full-channel information, the RI and CQI (CSI part 1) mentioned above cannot be distinguished, making it impossible to determine the importance of each part of the CSI. Consequently, it is impossible to select an appropriate transmission method for the segmented CSI bitstream, resulting in a high bit error rate for CSI.
[0089] Based on this, in various embodiments of this application, the network device sends configuration information to the terminal. This configuration information is used to configure the grouping method and / or related information of the compressed CSI bitstream. The terminal receives the configuration information from the network device and, based on the configuration information, divides the compressed CSI bitstream into multiple bit groups, and determines first information, which indicates the transmission method and / or transmission priority of each bit group. In this scheme, the terminal can group the compressed CSI bitstream based on the configuration information and configure a suitable transmission method and / or transmission priority for each bit group. Therefore, the terminal can configure different transmission methods and / or transmission priorities for different bit groups, which can reduce the bit error rate of CSI and minimize transmission overhead while reducing performance loss caused by bit errors during transmission.
[0090] The present application will now be described in further detail with reference to the accompanying drawings and embodiments.
[0091] This application provides an information transmission method, such as... Figure 1 As shown, the method includes:
[0092] Step 101: Receive configuration information from the network device.
[0093] The configuration information is used to configure the grouping method and / or related information of the compressed CSI bit stream.
[0094] Here, configuration information can be carried in Radio Resource Control (RRC) signaling, or in Media Access Control (MAC) control elements (CE), or in other signaling. The information related to the bit group can be information used to transmit the bit group.
[0095] To facilitate the terminal in grouping compressed CSI bitstreams and determining the transmission method for each bit group, in one embodiment, the configuration information includes at least one of the following:
[0096] The second information indicates the transmission quality requirements;
[0097] The third information indicates the number of bit groups in the compressed CSI bitstream and the number of bits contained in each bit group;
[0098] The fourth information indicates the weight of each bit group;
[0099] The fifth piece of information indicates the transmission mode supported by the bit group.
[0100] Here, the second and / or fourth information can be used by the terminal to determine the transmission method of the bit group in order to reduce the bit error rate. The transmission methods of the bit group all belong to the set of transmission methods supported by the bit group configured by the network device; each transmission method corresponds to a transmission reliability, and different transmission methods may have the same or different transmission reliability. The transmission quality requirements indicated by the second information are for all bit groups, and the second information may include the bit error rate and / or transmission rate. The fourth information may include the weight of each bit group. The fifth information may include the transmission methods supported by the bit group; all bit groups may support the same transmission method or at least two different transmission methods.
[0101] The third information may include the number of bit groups and the number of bits in each bit group. This third information is used by the terminal to group the compressed CSI bitstream. Since the third information indicates the number of bit groups and the number of bits in each bit group of the compressed CSI bitstream, grouping the compressed CSI bitstream based on the third information can improve grouping efficiency.
[0102] To diversify transmission methods and facilitate flexible configuration of bit groups by the terminal, in one embodiment, the transmission method indicates the correspondence between at least two of the encoding method, number of layers, and modulation method.
[0103] Here, the number of layers is related to the rank of the channel matrix; the rank of the channel matrix is used to indicate how many independent channels exist between the terminal and the network device. In actual transmission, not all independent channels are used. The number of independent channels used is the number of layers, also known as Layer.
[0104] The encoding methods include polar code encoding and / or low-density parity-check code (LDPC). The modulation methods include quadrature amplitude modulation (QAM), which can include 16QAM and / or 64QAM.
[0105] Table 1 provides examples of transmission methods, and there is a corresponding relationship between transmission methods and transmission priorities.
[0106] Table 1
[0107] Encoding method number of floors Modulation method Priority Transmission Method 1 Polar codes <![CDATA[L1]]> <![CDATA[Q1]]> Transmission priority 1 Transmission Method 2 LDPC <![CDATA[L2]]> <![CDATA[Q2]]> Transmission priority 2 Transmission Method 3 LDPC <![CDATA[L3]]> <![CDATA[Q3]]> Transmission priority 3 ··· ··· ··· ··· ···
[0108] Each transmission method corresponds to a transmission priority, and the transmission reliability varies depending on the transmission method. In Table 1, transmission priority 1 has the highest priority, transmission priority 2 has a lower priority than transmission priority 1, and transmission priority 3 has a lower priority than transmission priority 2. The transmission reliability of transmission method 1 is greater than that of transmission method 2, and the transmission reliability of transmission method 2 is greater than that of transmission method 3.
[0109] For example, transmission mode 1 can indicate that the encoding method is polar code, the number of layers is 1, and the modulation method is 16QAM. Transmission mode 1 corresponds to transmission priority 1 (highest transmission priority); transmission mode 2 can indicate that the encoding method is LDPC, the number of layers is 1, and the modulation method is 16QAM. Transmission mode 2 corresponds to transmission priority 2 (second priority); transmission mode 3 can indicate that the encoding method is LDPC, the number of layers is 2, and the modulation method is 64QAM. Transmission mode 3 corresponds to transmission priority 3 (third priority).
[0110] It should be noted that transmission method 1 can guarantee higher channel quality and lower inter-symbol interference during transmission, but it requires more transmission resources; transmission method 2 or transmission method 3 can ensure basic transmission quality while avoiding excessive use of transmission resources.
[0111] Step 102: Based on the configuration information, divide the compressed CSI bitstream into multiple bit groups and determine the first information.
[0112] The first information indicates the transmission method and / or transmission priority of each bit group in the plurality of bit groups.
[0113] Here, the terminal obtains the compressed CSI bitstream, divides it into multiple bit groups based on the grouping method of the compressed CSI bitstream indicated by the configuration information, and determines the transmission method and / or transmission priority of each bit group based on the relevant information of the bit groups indicated by the configuration information. For example... Figure 2 As shown, the terminal divides the compressed CSI bitstream into n bit groups based on configuration information and assigns a corresponding transmission mode to each of the n bit groups. The process by which the terminal obtains the compressed CSI bitstream can be as follows: the terminal receives a Channel State Information-Reference Signal (CSI-RS) from the network device; performs CSI measurement using the received CSI-RS to obtain the measured CSI; and compresses the measured CSI to obtain the compressed CSI bitstream.
[0114] Specifically, when the configuration information includes third information, the compressed CSI bitstream is divided into multiple bit groups based on the number of bit groups indicated by the third information and the number of bits contained in each bit group; the number of bits contained in different bit groups can be the same or different.
[0115] When the configuration information includes the second information, the transmission mode for each bit group is determined based on the transmission quality requirements indicated by the second information. In practical applications, when the second information includes the bit error rate, since bit groups with less information can tolerate a higher bit error rate, while bit groups with more information can tolerate a lower bit error rate, the terminal can configure a more reliable transmission mode for bit groups with more information and a less reliable transmission mode for bit groups with less information. This ensures transmission quality, such as preventing the loss of most CSI information, while avoiding excessive consumption of transmission resources. When the second information includes the transmission rate, the terminal can configure a lower transmission priority mode for bit groups with higher transmission rates and a higher transmission priority mode for bit groups with lower transmission rates.
[0116] When the configuration information includes the fourth information, the transmission mode for each bit group is determined based on the weight of each bit group indicated by the fourth information. Specifically, for bit groups with higher weights, a more reliable transmission mode can be configured to ensure that the bit groups with higher weights have higher channel quality and lower inter-symbol interference during transmission, thereby preserving most of the CSI information. For bit groups with lower weights, a less reliable transmission mode can be configured to ensure transmission quality while avoiding excessive consumption of transmission resources.
[0117] If the configuration information includes the fifth piece of information, the transmission mode supported by the bit group is determined based on the fifth piece of information. The transmission mode configured by the terminal for each bit group belongs to the transmission mode supported by the bit group indicated by the fifth piece of information.
[0118] Since the higher the weight of a bit group, the more important it is or the more information it contains, in order to minimize the bit error rate of the bit group with a larger weight and improve the transmission reliability of the bit group with a larger weight, in one embodiment, when the weight of the first bit group is greater than the weight of the second bit group, the reliability of the transmission mode of the first bit group is higher than the reliability of the transmission mode of the second bit group, and / or, the transmission priority of the first bit group is higher than the transmission priority of the second bit group.
[0119] Here, the terminal can determine the transmission priority of each bit group based on the fourth information, and determine the transmission mode of each bit group based on the transmission priority of each bit group and the correspondence between the transmission priority and the transmission mode.
[0120] For example, if the transmission reliability of transmission mode 1, transmission mode 2 and transmission mode 3 in Table 1 decreases sequentially, and the weights of bit group 1, bit group 2 and bit group 3 decrease sequentially, and the weight of bit group 3 is the same as that of bit group 4, then the terminal can configure transmission mode 1 for bit group 1, transmission mode 2 for bit group 2, and transmission mode 3 for both bit group 3 and bit group 4.
[0121] In order to configure a suitable transmission method for each bit group and save transmission resources as much as possible while ensuring transmission reliability, in one embodiment, determining the first information includes at least one of the following:
[0122] Based at least on the second information and the fourth information, the transmission priority of each bit group is determined;
[0123] Based on the first relationship, the transmission method corresponding to the transmission priority of each bit group is determined; the first relationship includes the correspondence between transmission priority and transmission method.
[0124] Here, the terminal compares the value of the indicator corresponding to the transmission quality requirement indicated by the second information with a set threshold to obtain a comparison result; based on the weight of each bit group indicated by the fourth information and the priority configuration rule matching the comparison result, it determines the transmission priority of each bit group. The number of set thresholds is at least one. The allocation of transmission priorities can be very flexible; each bit group can correspond to a different transmission priority, or multiple bit groups can correspond to the same transmission priority.
[0125] For example, if the second information includes transmission rate and / or bit error rate, then if the transmission rate is higher and / or the bit error rate is higher, the terminal will configure a lower transmission priority for bit groups with larger weights, and most bit groups will have a lower transmission priority; if the transmission rate is lower and / or the bit error rate is lower, then the terminal will configure a higher transmission priority for bit groups with larger weights, and most bit groups will have a higher transmission priority.
[0126] In order to configure a suitable transmission method for each bit group for different transmission quality requirements, in one embodiment, determining the transmission priority of each bit group based at least on the second information and the fourth information includes:
[0127] The first score is determined based on the second information;
[0128] Based on the fourth information, the second score and the third score are determined; wherein, the second score represents the score corresponding to the weight of the i-th bit group, and the third score represents the score corresponding to the weight of the (i+1)-th bit group, where i is a positive integer;
[0129] If the second score is less than or equal to the first score, and / or the third score is greater than the first score, determine the same transmission priority for the i bit groups corresponding to the second score.
[0130] Here, if the second information includes the transmission rate and / or bit error rate, the first score is determined based on the following formula:
[0131]
[0132] Where copoint represents the first score, β and γ are both configured coefficients, R represents the transmission rate, and BER represents the bit error rate.
[0133] The terminal determines the weight of each bit group in the multiple bit groups based on the fourth information; based on the set coefficients and the weights of the i bit groups in the multiple bit groups, it determines the score corresponding to the weights of the i bit groups, and obtains the second score; based on the set coefficients and the weights of the (i+1) bit groups in the multiple bit groups, it determines the score corresponding to the (i+1) bit groups, and obtains the third score.
[0134] In order to accurately determine the second score and the third score, in one embodiment, the second score is determined based on a set coefficient and the sum of the weights of the i-bit groups;
[0135] The third score is determined based on the sum of the set coefficients and the weights of the (i+1)th bit group.
[0136] Here, the second score represents the product of the sum of the weights of the i-th bit groups and the first predetermined coefficient, and the third score represents the product of the sum of the weights of the (i+1)-th bit groups and the first predetermined coefficient. In practical applications, the terminal can be based on... Determine the second and third scores; where Score n The score represents the weight of the n bit groups. When determining the second score, n = i, and when determining the third score, n = i + 1. i is a positive integer and less than the total number of bit groups. α represents the set coefficient. λn represents the weight of the nth bit group.
[0137] Given a first score, a second score, and a third score, the terminal determines whether the second score is less than or equal to the first score, and whether the third score is greater than the first score. If at least one of the following conditions is met, the terminal determines that the i bit groups corresponding to the second score belong to the same transmission priority:
[0138] The second score is less than or equal to the first score;
[0139] The second score is less than or equal to the first score, and the third score is greater than the first score.
[0140] If the second score is less than or equal to the first score and the third score is less than or equal to the first score, i is incremented by 1; then, the second and third scores are re-determined based on the fourth information, and subsequent steps are performed until either of the above conditions is met.
[0141] It should be noted that the i-th bit group or i+1-th bit group is determined sequentially according to the arrangement order of the multiple bit groups. After determining the transmission priority of the i-th bit group, the terminal determines the transmission priority of the remaining bit groups in sequence.
[0142] Figure 3 An example of configuring transmission priorities for multiple bit groups is shown, such as Figure 3 As shown, the terminal divides the data into n bit groups, with bit groups 1 and 2 having higher weights and bit groups 3 through 5 having lower weights. Based on the weights of bit groups 1 and 2, the terminal determines a second score; based on the weights of bit groups 1 through 3, it determines a third score. If the second score is less than or equal to the first score, and the third score is less than or equal to the first score, the terminal assigns a transmission priority of 1 to both bit groups 1 and 2. Then, the terminal determines a second score based on the weights of bit groups 3 through 5, and a third score based on the weights of bit groups 3 through 6. If the second score is less than or equal to the first score, and the third score is less than or equal to the first score, the terminal assigns a transmission priority of 2 to both bit groups 3 through 5. This process is repeated to determine the transmission priorities of all remaining bit groups.
[0143] In this embodiment of the application, Score can be n Infinitely close to copoint, and Score n The priority should be less than or equal to copoint, thus allowing for the allocation of lower transmission priority to as many bit groups as possible in scenarios with higher transmission rates and / or higher bit error rates; conversely, in scenarios with lower transmission rates and / or lower bit error rates, allowing for the allocation of higher transmission priority to as many bit groups as possible. For example, while ensuring Score... n Without exceeding the copoint limit, prioritize as many bit groups as possible into transmission priority 1; while ensuring the score... n Without exceeding the copoint limit, then include as many bit groups as possible in transmission priority 2, and so on.
[0144] After the terminal divides the data into multiple bit groups, it needs to send the bit groups to the network device so that the network device can obtain the CSI. Based on this, in one embodiment, the method further includes at least one of the following:
[0145] Based on the first information, the plurality of bit groups are sent to the network device;
[0146] Send the first information to the network device.
[0147] Here, since the first information can indicate the transmission method and / or transmission priority of each bit group in multiple bit groups, the terminal can determine the transmission order of all bit groups based on the transmission priority of each bit group; and based on the transmission order of all bit groups, send the corresponding bit groups to the network device according to the transmission method of each bit group.
[0148] Where the transmission mode indicates a correspondence between at least two of the coding method, the number of layers, and the modulation method, the terminal can encode the bit group using the coding method indicated by the transmission mode, modulate the bit group using the modulation method indicated by the transmission mode, and determine the number of channels used by the terminal based on the number of layers indicated by the transmission mode.
[0149] The terminal sends first information to the network device so that the network device can decode and / or demodulate the received bit group based on the first information to obtain the correct CSI.
[0150] Correspondingly, embodiments of this application also provide an information transmission method applied to a network device, the network device including a base station, such as... Figure 4 As shown, the method includes:
[0151] Step 401: Send configuration information to the terminal.
[0152] The configuration information is used to configure the grouping method and / or related information of the compressed CSI bit stream. The configuration information is used by the terminal to group the compressed CSI bit stream and determine the transmission method and / or transmission priority of each bit group.
[0153] Here, the configuration information sent by the network device to different terminals can be the same or different.
[0154] In one embodiment, the method further includes:
[0155] Obtain the configuration information.
[0156] Here, the configuration information can be pre-configured, determined in real time, or obtained from other devices.
[0157] To facilitate the terminal in grouping compressed CSI bitstreams and determining the transmission method for each bit group, in one embodiment, the configuration information includes at least one of the following:
[0158] The second information indicates the transmission quality requirements;
[0159] The third information indicates the number of bit groups in the compressed CSI bitstream and the number of bits contained in each bit group;
[0160] The fourth information indicates the weight of each bit group;
[0161] The fifth piece of information indicates the transmission mode supported by the bit group.
[0162] To ensure that the weights of different bit groups are significantly different or not completely identical, and to improve the accuracy of the bit group weights, in one embodiment, obtaining the configuration information includes:
[0163] Obtain the fourth information determined by the first model; wherein,
[0164] The first model is used to determine the weight of each bit group in the input.
[0165] Here, the first model can be trained by a network device or other terminal based on a compressed CSI bitstream. The compressed CSI bitstream used to train the first model is different from the compressed bitstream in step 102.
[0166] In one embodiment, the first model is trained using the following method:
[0167] The first bitstream is decompressed using the first model to obtain N first CSIs and N second CSIs; wherein, one third bit group corresponds to one first CSI, one bit combination corresponding to one third bit group corresponds to one second CSI, and one bit combination contains at least one third bit group; N is a positive integer greater than or equal to 2.
[0168] Based on N second CSIs and third CSIs, and based on the first weights of N third bit groups, the second weights of the N third bit groups are determined; wherein, the third CSI represents the calibration CSI corresponding to the first bit stream; the first weight represents the configured initial weights or the second weights in the previous iteration training.
[0169] The total loss value is determined based on N first CSIs and the third CSI, and based on the second weights of N third bit groups;
[0170] The first model is trained based on the second weights of the N third bit groups and / or the total loss value until the set convergence condition is met; wherein the second weights of the N third bit groups are used to determine the fourth information or to update the first weights.
[0171] Here, the first bitstream can be divided into N third bit groups based on the third information. The first bitstream is a compressed CSI bitstream, which is different from the compressed bitstream in step 102. The N third bit groups are input into the first model for decompression, resulting in N first CSIs and N second CSIs. The N first CSIs are obtained by decompressing the N third bit groups respectively, with one third bit group corresponding to one first CSI. The N second CSIs are obtained by decompressing N combinations of bits (combinations of bit groups) of different lengths, with each bit combination containing at least one third bit group. Any bit combination corresponding to a third bit group must include at least that third bit group, and may also include at least one third bit group preceding it. During iterative training of the first model, the number of third bit groups contained in the bit combination corresponding to a third bit group can be changed. Figure 5 As shown, in practical applications, the bit combination corresponding to any third bit group includes that third bit group and all third bit groups located before that bit group, which allows the bit groups at the beginning of the first CSI bit stream to receive higher weights.
[0172] Given N second CSIs, a first loss value is determined for each of the N second CSIs based on the difference between each second CSI and the third CSI; and a second weight is determined for each of the N third bit groups based on the first loss value of the N second CSIs and the first weight of the N third bit groups.
[0173] Given N first CSIs, a second loss value is determined for each of the N first CSIs based on the difference between each first CSI and the third CSI. The total loss value is determined based on the second loss values of the N first CSIs and the second weights of the N third bit groups. The first model is trained based on the second weights of the N third bit groups and / or the total loss value until the set convergence condition is met, at which point training stops, and the first model is obtained after training is completed.
[0174] For example, the convergence conditions may include a total loss value less than or equal to a set threshold, and / or, the number of training iterations reaching a set number. If the total loss value is less than or equal to the set threshold, and / or the number of training iterations reaches the set number, backpropagation is performed on the first model based on the total loss value. During backpropagation, the model parameters of the first model are updated, and the first model with updated model parameters is used as the first model after training ends. Fourth information is generated from the weights of N third bit groups. If the total loss value is greater than the set threshold, and / or the number of training iterations is less than the set number, after updating the model parameters of the first model, the first weights of the N third bit groups are updated based on the second weights of the N third bit groups, and the next iteration of training is performed until the set convergence conditions are met.
[0175] In this embodiment of the application, the weights of the third bit group can be continuously updated during the training of the first model, which can make the amount of CSI information contained in different bit groups significantly different, so that the third bit group with a larger amount of information can obtain higher weights, thereby improving the accuracy of the weights of each bit group indicated by the fourth information.
[0176] During the training of the first model, the weights of the third bit group can be continuously updated to make the final weights of the bit groups more accurate. Based on this, in one embodiment, after determining the second weights of the N third bit groups, the method further includes:
[0177] Based on the second weights of the N third bit groups, the first weights of each third bit group are updated to the corresponding second weights.
[0178] Here, the first weight of any third bit group is replaced or updated with the second weight of that third bit group, so that in the next round of training iteration, the second weight of the third bit group and the total loss value can be redetermined using the updated weight of the third bit group.
[0179] To accurately determine the second weight of each third bit group, in one embodiment, determining the second weight of the N third bit groups based on N second CSIs and third CSIs, and based on the first weights of the N third bit groups, includes:
[0180] Based on the third CSI and the second CSI corresponding to the third bit group, determine the first loss value of the third bit group;
[0181] Based on the first loss value and the corresponding first weight of the third bit group, the second weight of the third bit group is determined.
[0182] Here, the second weight of any third bit group can be determined as follows: based on the difference between the third CSI and the second CSI corresponding to the third bit group, the first loss value of the third bit group is determined; based on the first loss value of the third bit group and the corresponding first weight, the second weight of the third bit group is determined.
[0183] In practical applications, the second weight of the third bit group is determined according to the following formula:
[0184]
[0185] in, The second weight representing the i-th third bit group; λ i The first weight representing the i-th third bit group; Loss i The first loss value representing the i-th third bit group; Norm(λ) i +Loss i Characterize the pair (λ) i +Loss i Normalization is performed, and the formula for normalization is as follows:
[0186] In this embodiment, the longer the bit combination, the more accurate the output of the first model and the smaller the total loss value. Therefore, the above-mentioned method of updating weights can enable the first bit group in the first bit stream to obtain higher weights, so that the first bit group can learn more CSI information.
[0187] To improve the accuracy of the first model, and thus improve the accuracy of the fourth information indicating the weight of each bit group determined by the first model, in one embodiment, determining the total loss value based on N first CSIs and the third CSI, and based on the second weights of N third bit groups, includes:
[0188] Based on the N first CSIs and the third CSI, determine the second loss value of the N third bit groups;
[0189] The total loss value is determined based on the second weight and the corresponding second loss value of each of the N third bit groups.
[0190] Here, based on the difference between each of the N first CSIs and the third CSI, the second loss value of the third bit group corresponding to the first CSI is determined; based on the second weight of each of the N third bit groups and the corresponding second loss value, the total loss value is determined.
[0191] In practical applications, the total loss value is determined using the following formula:
[0192]
[0193] Where Lossσ represents the total loss value; loss i The second loss value represents the i-th third bit group.
[0194] Figure 6 An example of simulation verification results is given by dividing the first bitstream into two bit groups. Figure 7 An example of simulation verification results is given, showing the first bitstream divided into three bit groups. In the simulation graph, the vertical axis represents cosine similarity; a higher cosine similarity indicates higher recovery accuracy and more information contained within that bit group. Figure 6 (a) and Figure 7 (a) is the simulation verification result of the cosine similarity of each bit group when training the first model without considering the weights of the bit groups. Figure 6 (b) and Figure 7 (b) is the simulation verification result of the cosine similarity of each bit group when training the first model considering the weight of the bit group, that is, the simulation verification result of the loss value when training the first model according to the above method. Figure 7 Among them, the CSI recovered by the third bit group 1 has the highest cosine similarity, followed by the CSI recovered by the third bit group 2, and the CSI recovered by the third bit group 3 has the lowest cosine similarity, with the third bit group 3 having the smallest loss value. (Comparison) Figure 6 and Figure 7 It is understood that the first model trained in the embodiments of this application can allocate the information in CSI to the third bit group 1, the third bit group 2 and the third bit group 3 in order of more or less.
[0195] After the terminal sends multiple bit groups to the network device, the network device receives the multiple bit groups sent by the terminal and obtains the CSI based on the received multiple bit groups. Therefore, in one embodiment, the method further includes:
[0196] Receive multiple bit groups and / or first information sent by the terminal, wherein the first information indicates the transmission mode and / or transmission priority of each bit group in the multiple bit groups, and the transmission priority of the bit group is used to determine the transmission mode of the bit group;
[0197] Based on the transmission method corresponding to each of the multiple bit groups, the multiple bit groups are processed to obtain the processing result.
[0198] Here, since there is a correspondence or mapping relationship between transmission priority and transmission mode, network devices can determine the transmission mode corresponding to the transmission priority of a bit group based on the correspondence between transmission priority and transmission mode.
[0199] When the network device receives all the bit groups sent by the terminal, it processes each bit group based on the transmission method corresponding to the bit group, such as decoding and / or demodulating the bit group to obtain the processing result; it sorts and concatenates the processing results of each bit group to obtain the complete CSI bit stream; and it decompresses the complete CSI bit stream to obtain the CSI.
[0200] The embodiments of this application will be further described below with reference to the interactive flow diagram. Figure 8 As shown, the information transmission methods include:
[0201] Step 1: The network device sends configuration information to the terminal, and the terminal receives the configuration information sent by the network device.
[0202] The configuration information is used to configure the grouping method and / or related information of the compressed CSI bit stream.
[0203] In one embodiment, the configuration information includes at least one of the following:
[0204] The second information indicates the transmission quality requirements;
[0205] The third information indicates the number of bit groups in the compressed CSI bitstream and the number of bits contained in each bit group;
[0206] The fourth information indicates the weight of each bit group;
[0207] The fifth piece of information indicates the transmission mode supported by the bit group.
[0208] In one embodiment, the transmission mode indicates the correspondence between at least two of the coding mode, the number of layers, and the modulation mode.
[0209] Optionally, the network device acquires fourth information determined by the first model; wherein the first model is used to determine the weight of each bit group of the input.
[0210] Optionally, the first model can be trained by the network device using the following method:
[0211] The first bitstream is decompressed using the first model to obtain N first CSIs and N second CSIs; wherein, one third bit group corresponds to one first CSI, one bit combination corresponding to one third bit group corresponds to one second CSI, and one bit combination contains at least one third bit group; N is a positive integer greater than or equal to 2.
[0212] Based on N second CSIs and third CSIs, and based on the first weights of N third bit groups, the second weights of N third bit groups are determined; wherein, the third CSI represents the calibration CSI corresponding to the first bit stream; the first weight represents the configured initial weights or the second weights in the previous iteration training.
[0213] The total loss value is determined based on N first CSIs and the third CSI, and based on the second weights of N third bit groups;
[0214] The first model is trained based on the second weights of the N third bit groups and / or the total loss value until the set convergence condition is met; wherein the second weights of the N third bit groups are used to determine the fourth information or to update the first weights.
[0215] Optionally, determining the second weights of the N third bit groups based on the N second CSIs and the third CSIs, and based on the first weights of the N third bit groups, includes:
[0216] Based on the third CSI and the second CSI corresponding to the third bit group, determine the first loss value of the third bit group;
[0217] Based on the first loss value and the corresponding first weight of the third bit group, the second weight of the third bit group is determined.
[0218] Alternatively, the first weight of each third bit group can be updated to the second weight based on the second weight of the N third bit groups.
[0219] Optionally, determining the total loss value based on N first CSIs and the third CSI, and a second weight based on N third bit groups, includes:
[0220] Based on the N first CSIs and the third CSI, determine the second loss value of the N third bit groups;
[0221] The total loss value is determined based on the second weight and the corresponding second loss value of each of the N third bit groups.
[0222] Step 2: The network device sends CSI-RS to the terminal.
[0223] Step 3: The terminal performs CSI measurement based on CSI-RS to obtain CSI, and then compresses the CSI to obtain a compressed CSI bit stream.
[0224] Step 4: The terminal divides the compressed CSI bitstream into multiple bit groups based on the configuration information and determines the first information.
[0225] The first information indicates the transmission method and / or transmission priority of each bit group in the plurality of bit groups.
[0226] In one embodiment, determining the first information includes at least one of the following:
[0227] Based at least on the second information and the fourth information, the transmission priority of each bit group is determined;
[0228] Based on the first relationship, the transmission method corresponding to the transmission priority of each bit group is determined; the first relationship includes the correspondence between transmission priority and transmission method.
[0229] Optionally, determining the transmission priority of each bit group based at least on the second information and the fourth information includes:
[0230] The first score is determined based on the second information;
[0231] Based on the fourth information, the second score and the third score are determined; wherein, the second score represents the score corresponding to the weight of the i-th bit group, and the third score represents the score corresponding to the weight of the (i+1)-th bit group, where i is a positive integer;
[0232] If the second score is less than or equal to the first score, and / or the third score is greater than the first score, determine the same transmission priority for the i bit groups corresponding to the second score.
[0233] The second score is determined based on the sum of the set coefficients and the weights of the i-th bit groups; the third score is determined based on the set coefficients and the sum of the weights of the i+1 bit groups.
[0234] Step 5: The terminal sends the multiple bit groups to the network device based on the first information, and / or sends the first information to the network device.
[0235] Step 6: The network device receives multiple bit groups and / or first information sent by the terminal, processes the multiple bit groups based on the transmission mode corresponding to each bit group, and obtains the processing result.
[0236] The first information indicates the transmission mode and / or transmission priority of each bit group in the plurality of bit groups, and the transmission priority of the bit group is used to determine the transmission mode of the bit group.
[0237] The above scheme allows the terminal to configure different transmission methods and / or transmission priorities for different bit groups, which can reduce the bit error rate of CSI and minimize transmission overhead while reducing performance loss caused by bit errors during transmission.
[0238] To implement the information transmission method of this application embodiment, this application embodiment also provides an information transmission device, which is installed on a terminal, such as... Figure 9 As shown, the device includes:
[0239] The first receiving unit 901 is used to receive configuration information sent by the network device, wherein the configuration information is used to configure the grouping method and / or related information of the compressed CSI bit stream;
[0240] The determining unit 902 is used to divide the compressed CSI bitstream into multiple bit groups based on the configuration information, and to determine first information, wherein the first information indicates the transmission mode and / or transmission priority of each bit group in the multiple bit groups.
[0241] In one embodiment, the apparatus further includes a second transmitting unit for performing at least one of the following:
[0242] Based on the first information, the plurality of bit groups are sent to the network device;
[0243] Send the first information to the network device.
[0244] In one embodiment, the configuration information includes at least one of the following:
[0245] The second information indicates the transmission quality requirements;
[0246] The third information indicates the number of bit groups in the compressed CSI bitstream and the number of bits contained in each bit group;
[0247] The fourth information indicates the weight of each bit group;
[0248] The fifth piece of information indicates the transmission mode supported by the bit group.
[0249] In one embodiment, when the weight of the first bit group is greater than the weight of the second bit group, the reliability of the transmission method of the first bit group is higher than the reliability of the transmission method of the second bit group, and / or, the transmission priority of the first bit group is higher than the transmission priority of the second bit group.
[0250] In one embodiment, the determining unit 902 is specifically used for at least one of the following:
[0251] Based at least on the second information and the fourth information, the transmission priority of each bit group is determined;
[0252] Based on the first relationship, the transmission method corresponding to the transmission priority of each bit group is determined; the first relationship includes the correspondence between transmission priority and transmission method.
[0253] In one embodiment, the determining unit 902 is specifically used to determine a first score based on the second information; and to determine a second score and a third score based on the fourth information; wherein the second score represents the score corresponding to the weight of i bit groups, and the third score represents the score corresponding to the weight of i+1 bit groups, where i is a positive integer; and when the second score is less than or equal to the first score, and / or the third score is greater than the first score, the same transmission priority of the i bit groups corresponding to the second score is determined.
[0254] In one embodiment, the second score is determined based on a set coefficient and the sum of the weights of the i-bit groups;
[0255] The third score is determined based on the sum of the set coefficients and the weights of the (i+1)th bit group.
[0256] In one embodiment, the transmission mode indicates the correspondence between at least two of the coding mode, the number of layers, and the modulation mode.
[0257] In practical applications, the determining unit 902 can be implemented by a processor in the information transmission device, and the first receiving unit 901 and the second sending unit can be implemented by a communication interface in the information transmission device combined with a processor.
[0258] To implement the information transmission method of this application embodiment, this application embodiment also provides an information transmission device, which is installed on a network device, such as... Figure 10 As shown, the device includes:
[0259] The first sending unit 1001 is used to send configuration information to the terminal; wherein...
[0260] The configuration information is used to configure the grouping method and / or related information of the compressed CSI bit stream. The configuration information is used for the terminal to group the compressed CSI bit stream and determine the transmission method and / or transmission priority of each bit group.
[0261] In one embodiment, the device further includes:
[0262] The acquisition unit is used to obtain the configuration information.
[0263] In one embodiment, the configuration information includes at least one of the following:
[0264] The second information indicates the transmission quality requirements;
[0265] The third information indicates the number of bit groups in the compressed CSI bitstream and the number of bits contained in each bit group;
[0266] The fourth information indicates the weight of each bit group;
[0267] The fifth piece of information indicates the transmission mode supported by the bit group.
[0268] In one embodiment, the transmission mode indicates the correspondence between at least two of the coding mode, the number of layers, and the modulation mode.
[0269] In one embodiment, the acquisition unit is specifically used to acquire the fourth information determined by a first model; wherein the first model is used to determine the weight of each input bit group.
[0270] In one embodiment, the device further includes a training unit for training a first model by:
[0271] The first bitstream is decompressed using the first model to obtain N first CSIs and N second CSIs; wherein, one third bit group corresponds to one first CSI, one bit combination corresponding to one third bit group corresponds to one second CSI, and one bit combination contains at least one third bit group; N is a positive integer greater than or equal to 2.
[0272] Based on N second CSIs and third CSIs, and based on the first weights of N third bit groups, the second weights of N third bit groups are determined; wherein, the third CSI represents the calibration CSI corresponding to the first bit stream; the first weight represents the configured initial weights or the second weights in the previous iteration training.
[0273] The total loss value is determined based on N first CSIs and the third CSI, and based on the second weights of N third bit groups;
[0274] The first model is trained based on the second weights of the N third bit groups and / or the total loss value until the set convergence condition is met; wherein the second weights of the N third bit groups are used to determine the fourth information or to update the first weights.
[0275] In one embodiment, the training unit is specifically used to determine a first loss value for the third bit group based on the third CSI and the second CSI corresponding to the third bit group; and to determine a second weight for the third bit group based on the first loss value and the corresponding first weight.
[0276] In one embodiment, the training unit is further configured to update the first weight of each third bit group to the second weight based on the second weight of the N third bit groups.
[0277] In one embodiment, the training unit is specifically used to determine the second loss value of N third bit groups based on N first CSIs and the third CSI; and to determine the total loss value based on the second weight of each third bit group and the corresponding second loss value in the N third bit groups.
[0278] In one embodiment, the device further includes:
[0279] The second receiving unit is used to receive multiple bit groups and / or first information sent by the terminal, wherein the first information indicates the transmission mode and / or transmission priority of each bit group in the multiple bit groups, and the transmission priority of the bit group is used to determine the transmission mode of the bit group.
[0280] The processing unit is used to process the multiple bit groups based on the transmission mode corresponding to each bit group in the multiple bit groups to obtain the processing result.
[0281] In practical applications, the acquisition unit, the training unit, and the processing unit can be implemented by a processor in the information transmission device, and the first sending unit 1001 and the second receiving unit can be implemented by a communication interface in the information transmission device combined with a processor.
[0282] It should be noted that the information transmission device provided in the above embodiments is only illustrated by the division of the above program modules. In actual applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the device can be divided into different program modules to complete all or part of the processing described above. In addition, the information transmission device and the information transmission method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.
[0283] Based on the hardware implementation of the above program modules, and in order to implement the terminal-side method of the embodiments of this application, the embodiments of this application also provide a terminal, such as... Figure 11 As shown, terminal 1100 includes:
[0284] The first communication interface 1101 is capable of exchanging information with other network nodes;
[0285] The first processor 1102 is connected to the first communication interface 1101 to enable information interaction with other network nodes and to execute the methods provided by one or more of the aforementioned terminal-side technical solutions when running a computer program. The computer program is stored in the first memory 1103.
[0286] Specifically, the first communication interface 1101 is used to receive configuration information sent by the network device, the configuration information being used to configure the grouping method and / or related information of the compressed CSI bit stream;
[0287] The first processor 1102 is configured to divide the compressed CSI bitstream into multiple bit groups based on the configuration information, and determine first information, wherein the first information indicates the transmission mode and / or transmission priority of each bit group in the multiple bit groups.
[0288] In one embodiment, the first communication interface 1101 is further configured to perform at least one of the following:
[0289] Based on the first information, the plurality of bit groups are sent to the network device;
[0290] Send the first information to the network device.
[0291] In one embodiment, the configuration information includes at least one of the following:
[0292] The second information indicates the transmission quality requirements;
[0293] The third information indicates the number of bit groups in the compressed CSI bitstream and the number of bits contained in each bit group;
[0294] The fourth information indicates the weight of each bit group;
[0295] The fifth piece of information indicates the transmission mode supported by the bit group.
[0296] In one embodiment, when the weight of the first bit group is greater than the weight of the second bit group, the reliability of the transmission method of the first bit group is higher than the reliability of the transmission method of the second bit group, and / or, the transmission priority of the first bit group is higher than the transmission priority of the second bit group.
[0297] In one embodiment, the first processor 1102 is specifically used for at least one of the following:
[0298] Based at least on the second information and the fourth information, the transmission priority of each bit group is determined;
[0299] Based on the first relationship, the transmission method corresponding to the transmission priority of each bit group is determined; the first relationship includes the correspondence between transmission priority and transmission method.
[0300] In one embodiment, the first processor 1102 is specifically configured to determine a first score based on the second information; and to determine a second score and a third score based on the fourth information; wherein the second score represents the score corresponding to the weights of i bit groups, and the third score represents the score corresponding to the weights of i+1 bit groups, where i is a positive integer; and if the second score is less than or equal to the first score, and / or the third score is greater than the first score, the same transmission priority of the i bit groups corresponding to the second score is determined.
[0301] In one embodiment, the second score is determined based on a set coefficient and the sum of the weights of the i-bit groups;
[0302] The third score is determined based on the sum of the set coefficients and the weights of the (i+1)th bit group.
[0303] In one embodiment, the transmission mode indicates the correspondence between at least two of the coding mode, the number of layers, and the modulation mode.
[0304] It should be noted that the specific processing procedures of the first processor 1102 and the first communication interface 1101 can be understood by referring to the above method.
[0305] Of course, in practical applications, the various components in terminal 1100 are coupled together through bus system 1104. It can be understood that bus system 1104 is used to realize the connection and communication between these components. In addition to a data bus, bus system 1104 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, in... Figure 11 The general designated all buses as Bus System 1104.
[0306] The first memory 1103 in this embodiment is used to store various types of data to support the operation of the terminal 1100. Examples of such data include any computer program used to operate on the terminal 1100.
[0307] The methods disclosed in the above embodiments of this application can be applied to the first processor 1102, or implemented by the first processor 1102. The first processor 1102 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware or by instructions in the form of software in the first processor 1102. The first processor 1102 may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The first processor 1102 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the methods disclosed in the embodiments of this application can be directly reflected as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium, which is located in the first memory 1103. The first processor 1102 reads the information in the first memory 1103 and completes the steps of the aforementioned method in combination with its hardware.
[0308] In an exemplary embodiment, terminal 1100 may be implemented by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers (MCUs), microprocessors, or other electronic components to perform the aforementioned method.
[0309] Based on the hardware implementation of the above program modules, and in order to implement the method on the network device side of the embodiments of this application, the embodiments of this application also provide a network device, such as... Figure 12 As shown, the network device 1200 includes:
[0310] The second communication interface 1201 is capable of exchanging information with other network nodes;
[0311] The second processor 1202 is connected to the second communication interface 1201 to enable information interaction with other network nodes. When running a computer program, it executes the methods provided by one or more technical solutions on the network device side. The computer program is stored in the second memory 1203.
[0312] Specifically, the second communication interface 1201 is used to send configuration information to the terminal; wherein,
[0313] The configuration information is used to configure the grouping method and / or related information of the compressed CSI bit stream. The configuration information is used for the terminal to group the compressed CSI bit stream and determine the transmission method and / or transmission priority of each bit group.
[0314] In one embodiment, the second processor 1202 is used to obtain the configuration information.
[0315] In one embodiment, the configuration information includes at least one of the following:
[0316] The second information indicates the transmission quality requirements;
[0317] The third information indicates the number of bit groups in the compressed CSI bitstream and the number of bits contained in each bit group;
[0318] The fourth information indicates the weight of each bit group;
[0319] The fifth piece of information indicates the transmission mode supported by the bit group.
[0320] In one embodiment, the transmission mode indicates the correspondence between at least two of the coding mode, the number of layers, and the modulation mode.
[0321] In one embodiment, the second processor 1202 is specifically used to acquire the fourth information determined by a first model; wherein the first model is used to determine the weight of each input bit group.
[0322] In one embodiment, the second processor 1202 is further configured to train the first model by the following method:
[0323] The first bitstream is decompressed using the first model to obtain N first CSIs and N second CSIs; wherein, one third bit group corresponds to one first CSI, one bit combination corresponding to one third bit group corresponds to one second CSI, and one bit combination contains at least one third bit group; N is a positive integer greater than or equal to 2.
[0324] Based on N second CSIs and third CSIs, and based on the first weights of N third bit groups, the second weights of N third bit groups are determined; wherein, the third CSI represents the calibration CSI corresponding to the first bit stream; the first weight represents the configured initial weights or the second weights in the previous iteration training.
[0325] The total loss value is determined based on N first CSIs and the third CSI, and based on the second weights of N third bit groups;
[0326] The first model is trained based on the second weights of the N third bit groups and / or the total loss value until the set convergence condition is met; wherein the second weights of the N third bit groups are used to determine the fourth information or to update the first weights.
[0327] In one embodiment, the second processor 1202 is specifically used to determine a first loss value of the third bit group based on the third CSI and the second CSI corresponding to the third bit group; and to determine a second weight of the third bit group based on the first loss value of the third bit group and the corresponding first weight.
[0328] In one embodiment, the second processor 1202 is further configured to update the first weight of each third bit group to the second weight based on the second weight of the N third bit groups.
[0329] In one embodiment, the second processor 1202 is specifically configured to determine a second loss value for N third bit groups based on N first CSIs and the third CSI; and to determine the total loss value based on the second weight of each third bit group and the corresponding second loss value in the N third bit groups.
[0330] In one embodiment, the second communication interface 1201 is further configured to receive multiple bit groups and / or first information sent by the terminal, wherein the first information indicates the transmission mode and / or transmission priority of each bit group in the multiple bit groups, and the transmission priority of the bit group is used to determine the transmission mode of the bit group;
[0331] The second processor 1202 is further configured to process the plurality of bit groups based on the transmission method corresponding to each bit group in the plurality of bit groups, and obtain a processing result.
[0332] It should be noted that the specific processing procedures of the second processor 1202 and the second communication interface 1201 can be understood by referring to the above method.
[0333] Of course, in practical applications, the various components in network device 1200 are coupled together through bus system 1204. It can be understood that bus system 1204 is used to implement communication between these components. In addition to a data bus, bus system 1204 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 12 The general designated all buses as Bus System 1204.
[0334] The second memory 1203 in this embodiment is used to store various types of data to support the operation of the network device 1200. Examples of such data include any computer program used to operate on the network device 1200.
[0335] The methods disclosed in the embodiments of this application can be applied to the second processor 1202, or implemented by the second processor 1202. The second processor 1202 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware or by instructions in the form of software in the second processor 1202. The second processor 1202 may be a general-purpose processor, a DSP, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The second processor 1202 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the methods disclosed in the embodiments of this application can be directly manifested as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium, which is located in the second memory 1203. The second processor 1202 reads the information in the second memory 1203 and completes the steps of the aforementioned method in combination with its hardware.
[0336] In an exemplary embodiment, the network device 1200 may be implemented by one or more ASICs, DSPs, PLDs, CPLDs, FPGAs, general-purpose processors, controllers, MCUs, microprocessors, or other electronic components to perform the aforementioned method.
[0337] It is understood that the memories (first memory 1103, second memory 1203) in the embodiments of this application can be volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM); magnetic surface memory can be disk storage or magnetic tape storage. Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), SyncLink Dynamic Random Access Memory (SLDRAM), and Direct Rambus Random Access Memory (DRRAM).The memories described in the embodiments of this application are intended to include, but are not limited to, these and any other suitable types of memories.
[0338] In an exemplary embodiment, this application also provides a storage medium, namely a computer storage medium, specifically a computer-readable storage medium, such as a first memory 1103 storing a computer program, which can be executed by the first processor 1102 of the terminal 1100 to complete the steps described in the aforementioned terminal-side method. Another example is a second memory 1203 storing a computer program, which can be executed by the second processor 1202 of the network device 1200 to complete the steps described in the aforementioned network device-side method. The computer-readable storage medium can be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface memory, optical disc, or CD-ROM.
[0339] It should be noted that terms such as "first" and "second" are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.
[0340] In this document, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.
[0341] Furthermore, the technical solutions described in the embodiments of this application can be combined arbitrarily without conflict.
[0342] The above description is merely a preferred embodiment of this application and is not intended to limit the scope of protection of this application.
Claims
1. An information transmission method, characterized in that, Applied to a terminal, the method includes: Receive configuration information sent by the network device, the configuration information being used to configure the grouping method and / or related information of the compressed Channel State Information (CSI) bit stream; Based on the configuration information, the compressed CSI bitstream is divided into multiple bit groups, and first information is determined, wherein the first information indicates the transmission method and / or transmission priority of each bit group in the multiple bit groups; the configuration information includes at least one of the following: The second information indicates the transmission quality requirements; The third information indicates the number of bit groups in the compressed CSI bitstream and the number of bits contained in each bit group; The fourth information indicates the weight of each bit group; The fifth piece of information indicates the transmission mode supported by the bit group.
2. The method according to claim 1, characterized in that, The method further includes at least one of the following: Based on the first information, the plurality of bit groups are sent to the network device; Send the first information to the network device.
3. The method according to claim 1, characterized in that, When the weight of the first bit group is greater than the weight of the second bit group, the reliability of the transmission method of the first bit group is higher than that of the transmission method of the second bit group, and / or, the transmission priority of the first bit group is higher than that of the second bit group.
4. The method according to claim 1, characterized in that, The determination of the first information includes at least one of the following: Based at least on the second information and the fourth information, the transmission priority of each bit group is determined; Based on the first relationship, the transmission method corresponding to the transmission priority of each bit group is determined; the first relationship includes the correspondence between transmission priority and transmission method.
5. The method according to claim 4, characterized in that, The determination of the transmission priority of each bit group based at least on the second information and the fourth information includes: The first score is determined based on the second information; Based on the fourth information, the second score and the third score are determined; wherein, the second score represents i The score corresponding to the weight of each bit group, the third score characterization i The score corresponding to the weight of +1 bit group i It is a positive integer; If the second score is less than or equal to the first score, and / or the third score is greater than the first score, determine the score corresponding to the second score. i The same transmission priority for each bit group.
6. The method according to claim 5, characterized in that, The second score is based on a set coefficient and i The sum of the weights of each bit group is determined; The third score is based on the set coefficients and i The sum of the weights of the +1 bit group is determined.
7. The method according to any one of claims 1 to 6, characterized in that, The transmission mode indicates the correspondence between at least two of the coding mode, number of layers, and modulation mode.
8. An information transmission method, characterized in that, Applied to network devices, the method includes: Send configuration information to the terminal; among which, The configuration information is used to configure the grouping method and / or related information of the compressed CSI bitstream. The configuration information is used by the terminal to group the compressed CSI bitstream and determine the transmission method and / or transmission priority of each bit group. The configuration information includes at least one of the following: The second information indicates the transmission quality requirements; The third information indicates the number of bit groups in the compressed CSI bitstream and the number of bits contained in each bit group; The fourth information indicates the weight of each bit group; The fifth piece of information indicates the transmission mode supported by the bit group.
9. The method according to claim 8, characterized in that, The method further includes: Obtain the configuration information.
10. The method according to claim 8, characterized in that, The transmission mode indicates the correspondence between at least two of the coding mode, number of layers, and modulation mode.
11. The method according to claim 9, characterized in that, Obtaining the configuration information includes: Obtain the fourth information determined by the first model; wherein, The first model is used to determine the weight of each bit group in the input.
12. The method according to claim 11, characterized in that, The first model was trained using the following method: The first bitstream is decompressed using the first model to obtain N first CSIs and N second CSIs; wherein, one third bit group corresponds to one first CSI, one bit combination corresponding to one third bit group corresponds to one second CSI, and one bit combination contains at least one third bit group; N is a positive integer greater than or equal to 2. Based on N second CSIs and third CSIs, and based on the first weights of N third bit groups, the second weights of the N third bit groups are determined; wherein, the third CSI represents the calibration CSI corresponding to the first bit stream; the first weight represents the configured initial weights or the second weights in the previous iteration training. The total loss value is determined based on N first CSIs and the third CSI, and based on the second weights of N third bit groups; The first model is trained based on the second weights of the N third bit groups and / or the total loss value until the set convergence condition is met; wherein the second weights of the N third bit groups are used to determine the fourth information or to update the first weights.
13. The method according to claim 12, characterized in that, The determination of the second weights of the N third bit groups based on the N second CSIs and the third CSIs, and the first weights based on the N third bit groups, includes: Based on the third CSI and the second CSI corresponding to the third bit group, determine the first loss value of the third bit group; Based on the first loss value and the corresponding first weight of the third bit group, the second weight of the third bit group is determined.
14. The method according to claim 12, characterized in that, The method further includes: Based on the second weights of the N third bit groups, the first weights of each third bit group are updated to the corresponding second weights.
15. The method according to claim 12, characterized in that, The determination of the total loss value based on N first CSIs and the third CSIs, and a second weight based on N third bit groups, includes: Based on the N first CSIs and the third CSIs, determine the second loss value of the N third bit groups; The total loss value is determined based on the second weight and the corresponding second loss value of each of the N third bit groups.
16. The method according to any one of claims 8 to 14, characterized in that, The method further includes: Receive multiple bit groups and / or first information sent by the terminal, wherein the first information indicates the transmission mode and / or transmission priority of each bit group in the multiple bit groups, and the transmission priority of the bit group is used to determine the transmission mode of the bit group; Based on the transmission method corresponding to each of the multiple bit groups, the multiple bit groups are processed to obtain the processing result.
17. An information transmission device, characterized in that, include: The first receiving unit is used to receive configuration information sent by the network device, wherein the configuration information is used to configure the grouping method and / or related information of the compressed CSI bit stream; The configuration information includes at least one of the following: The second information indicates the transmission quality requirements; The third information indicates the number of bit groups in the compressed CSI bitstream and the number of bits contained in each bit group; The fourth information indicates the weight of each bit group; The fifth piece of information indicates the transmission mode supported by the bit group; The determining unit is configured to divide the compressed CSI bitstream into multiple bit groups based on the configuration information, and determine first information, wherein the first information indicates the transmission mode and / or transmission priority of each bit group in the multiple bit groups.
18. An information transmission device, characterized in that, include: The first sending unit is used to send configuration information to the terminal; wherein... The configuration information is used to configure the grouping method and / or related information of the compressed CSI bitstream. The configuration information is used by the terminal to group the compressed CSI bitstream and determine the transmission method and / or transmission priority of each bit group. The configuration information includes at least one of the following: The second information indicates the transmission quality requirements; The third information indicates the number of bit groups in the compressed CSI bitstream and the number of bits contained in each bit group; The fourth information indicates the weight of each bit group; The fifth piece of information indicates the transmission mode supported by the bit group.
19. A terminal, characterized in that, Includes a first processor and a first communication interface, wherein, The first communication interface is used to receive configuration information sent by the network device. The configuration information is used to configure the grouping method and / or related information of the compressed CSI bitstream; the configuration information includes at least one of the following: The second information indicates the transmission quality requirements; The third information indicates the number of bit groups in the compressed CSI bitstream and the number of bits contained in each bit group; The fourth information indicates the weight of each bit group; The fifth piece of information indicates the transmission mode supported by the bit group; The first processor is configured to divide the compressed CSI bitstream into multiple bit groups based on the configuration information, and determine first information, wherein the first information indicates the transmission mode and / or transmission priority of each bit group in the multiple bit groups.
20. A network device, characterized in that, Includes a second processor and a second communication interface, wherein, The second communication interface is used to send configuration information to the terminal; wherein, The configuration information is used to configure the grouping method and / or related information of the compressed CSI bitstream. The configuration information is used by the terminal to group the compressed CSI bitstream and determine the transmission method and / or transmission priority of each bit group. The configuration information includes at least one of the following: The second information indicates the transmission quality requirements; The third information indicates the number of bit groups in the compressed CSI bitstream and the number of bits contained in each bit group; The fourth information indicates the weight of each bit group; The fifth piece of information indicates the transmission mode supported by the bit group.
21. A terminal, characterized in that, It includes a first processor and a first memory for storing computer programs that can run on the first processor. Wherein, when the first processor is used to run the computer program, it performs the steps of the method according to any one of claims 1 to 7.
22. A network device, characterized in that, It includes a second processor and a second memory for storing computer programs that can run on the second processor. Wherein, when the second processor is used to run the computer program, it performs the steps of the method according to any one of claims 8 to 16.
23. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7, or the steps of the method according to any one of claims 8 to 16.
Citation Information
Patent Citations
Channel state information CSI report transmission method, terminal and network side equipment
CN111836309A