Communication method, communication device, communication system, storage medium, and program product

Abstract

A communication method, a communication device, a communication system, a storage medium, and a program product. The method comprises: monitoring semantic communication performance on the basis of first information, wherein the first information is semantically related information in a semantic communication process. That is, on the basis of the semantically related first information in the semantic communication process, a receiving end can accurately evaluate the integrity and the degree of intent recovery of semantic information in the semantic communication process, and thus can effectively monitor the semantic communication performance, such that the receiving end can perform different processing on received semantic data on the basis of the monitoring result of the semantic communication performance, thereby improving the reliability of semantic communication.

Description

Communication methods, communication equipment, communication systems, storage media and software products Technical Field

[0001] This disclosure relates to the field of communication technology, and in particular to a communication method, communication device, communication system, storage medium, and program product. Background Technology

[0002] Semantic communication is a communication paradigm centered on information semantics. Its core principle is to extract features and understand the semantics of the original signal, and then use semantic information for communication. Semantic communication is task-oriented, prioritizing understanding before transmission, thus significantly improving transmission efficiency. However, how to monitor the performance of semantic communication is a crucial issue that needs to be addressed. Summary of the Invention

[0003] In order to monitor the performance of semantic communication and improve its efficiency and reliability, embodiments of this disclosure propose a communication method, communication device, communication system, storage medium, and program product.

[0004] According to a first aspect of the embodiments of this disclosure, a communication method is provided, executed by a receiving end, the method comprising:

[0005] The performance of semantic communication is monitored based on the first information; the first information is semantically related information during the semantic communication process.

[0006] According to a second aspect of the embodiments of this disclosure, a communication method is provided, executed by a sending end, the method comprising:

[0007] Send the first message to the receiving end;

[0008] The first information is used by the receiving end to monitor the semantic communication performance; the first information is semantic-related information during the semantic communication process.

[0009] According to a third aspect of the embodiments of this disclosure, a communication device is provided that can be used to perform the methods described in an optional implementation of the first or second aspect.

[0010] According to a fourth aspect of the present disclosure, a communication system is provided, including a transmitting end and a receiving end, wherein the receiving end is configured to implement the communication method described in the first aspect, and the transmitting end is configured to implement the communication method described in the second aspect.

[0011] According to a fifth aspect of the present disclosure, a storage medium is provided that stores instructions that, when executed on a communication device, cause the communication device to perform the communication method as described in the first or second aspect.

[0012] According to a sixth aspect of the present disclosure, a program product is provided, including at least one of a program and instructions, wherein the program and instructions, when executed by a communication device, implement the communication method described in the first or second aspect.

[0013] By adopting the above technical solution, at least the following beneficial technical effects can be achieved:

[0014] Based on the first semantically related information during semantic communication, the receiving end can accurately assess the completeness of semantic information and the degree of intent restoration during semantic communication, thereby effectively monitoring the performance of semantic communication. This allows the receiving end to perform different processing on the received semantic data based on the monitoring results of semantic communication performance, thus improving the reliability of semantic communication.

[0015] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings required for the description of the embodiments are introduced below. The following drawings are only some embodiments of this disclosure and do not impose specific limitations on the protection scope of this disclosure.

[0017] Figure 1A is a schematic diagram of the architecture of a communication system according to an embodiment of the present disclosure.

[0018] Figure 1B is a schematic diagram of the structure of a communication system model according to an embodiment of the present disclosure.

[0019] Figure 1C is a schematic diagram of the structure of a communication system model according to an embodiment of the present disclosure.

[0020] Figure 1D is a schematic diagram of the structure of a communication system model according to an embodiment of the present disclosure.

[0021] Figure 1E is a schematic diagram of an architecture for semantically aware communication according to an embodiment of the present disclosure.

[0022] Figure 1F is a schematic diagram of an architecture for semantically aware communication according to an embodiment of the present disclosure.

[0023] Figure 2A is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure.

[0024] Figure 2B is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure.

[0025] Figure 2C is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure.

[0026] Figure 2D is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure.

[0027] Figure 2E is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure.

[0028] Figure 3A is a flowchart illustrating a communication method according to an embodiment of the present disclosure.

[0029] Figure 3B is a flowchart illustrating a communication method according to an embodiment of the present disclosure.

[0030] Figure 4A is a schematic diagram of the structure of a receiving end according to an embodiment of this disclosure.

[0031] Figure 4B is a schematic diagram of the structure of a transmitting end according to an embodiment of this disclosure.

[0032] Figure 5A is a schematic diagram of the structure of the communication device proposed in an embodiment of this disclosure.

[0033] Figure 5B is a schematic diagram of the chip structure proposed in an embodiment of this disclosure. Detailed Implementation

[0034] This disclosure provides a communication method, communication device, communication system, storage medium, and program product.

[0035] In a first aspect, embodiments of this disclosure provide a communication method executed by a receiving end, the method comprising:

[0036] The performance of semantic communication is monitored based on the first information; the first information is semantically related information during the semantic communication process.

[0037] In the above embodiments, the receiving end can accurately evaluate the integrity and intent reproduction of semantic information during semantic communication based on the first information related to semantics during the semantic communication process. This enables the receiving end to effectively monitor the performance of semantic communication and perform different processing on the received semantic data based on the monitoring results of semantic communication performance, thereby improving the reliability of semantic communication.

[0038] In conjunction with some embodiments of the first aspect, in some embodiments, the first information includes at least one of the following:

[0039] First semantic data;

[0040] The source data for the first semantic data;

[0041] Channel decoding result; the channel decoding result is obtained by the receiving end after performing channel decoding on the first semantic data;

[0042] The semantic verification information corresponding to the first semantic data;

[0043] The semantic task information corresponding to the first semantic data;

[0044] The first semantic data is the semantic data received by the receiving end from the sending end.

[0045] In the above embodiments, the first information includes multi-source information such as first semantic data, source data, channel decoding results, semantic verification information, and semantic task information. Based on the above multi-source information, the receiving end monitors the semantic communication performance through different means, which can improve the accuracy of semantic communication performance monitoring.

[0046] In conjunction with some embodiments of the first aspect, in some embodiments, the monitoring of semantic communication performance based on the first information includes at least one of the following:

[0047] Based on the first information, determine the semantic similarity between the first semantic data and the source data; monitor the semantic communication performance based on the semantic similarity.

[0048] Based on the first information, determine the task completion degree of the semantic task corresponding to the first semantic data; and monitor the semantic communication performance based on the task completion degree.

[0049] In the above embodiments, on the one hand, the receiving end determines the semantic similarity between the first semantic data and the source data based on the first information. Through the semantic similarity, the receiving end can determine whether the first semantic data is the semantics of the source data, thereby enabling the receiving end to determine whether it can receive the correct semantics from the sending end during the semantic communication process, thus realizing accurate monitoring of the semantic communication performance.

[0050] On the other hand, the receiving end determines the task completion degree of the semantic task corresponding to the first semantic data based on the first information. Through the task completion degree, the receiving end can determine the task completion status of the second semantic data, thereby enabling the receiving end to determine whether the task indicated by the sending end can be correctly executed during the semantic communication process, thus realizing accurate monitoring of the semantic communication performance.

[0051] In conjunction with some embodiments of the first aspect, in some embodiments, determining the semantic similarity between the first semantic data and the source data based on the first information includes at least one of the following:

[0052] The semantic similarity is determined based on the first semantic data in the first information and the source data in the first information;

[0053] If the channel decoding result determines that the channel decoding was successful, the semantic similarity is determined based on the first semantic data in the first information and the source data in the first information.

[0054] Based on the first semantic data in the first information and the semantic verification information in the first information, the semantic similarity is determined;

[0055] If the channel decoding result indicates that the channel decoding was successful, the semantic similarity is determined based on the first semantic data in the first information and the semantic verification information in the first information.

[0056] In the above embodiments, on the one hand, the receiving end directly compares the semantic similarity between the first semantic data and the source data, which can improve the accuracy of semantic similarity calculation.

[0057] On the other hand, the receiving end can verify the first semantic data using the semantic verification information corresponding to the first semantic data, thereby indirectly determining the semantic similarity between the first semantic data and the source data. In the above method, the receiving end does not need to obtain the source data of the sending end, which reduces the communication resources and bandwidth occupation in the semantic communication process, improves the monitoring efficiency of semantic communication performance, and reduces the energy consumption of the receiving end.

[0058] On the other hand, the receiver determines the semantic similarity when the first semantic data channel is successfully decoded. Through the above method, the receiver can directly determine the monitoring result of semantic communication performance when the first semantic data channel fails to be decoded, thereby further reducing the energy consumption of the receiver and improving the monitoring efficiency of semantic communication performance.

[0059] In conjunction with some embodiments of the first aspect, in some embodiments, the task completion degree is determined based on the first semantic data in the first information and the semantic task information in the first information;

[0060] If the channel decoding result indicates that the channel decoding was successful, the task completion degree is determined based on the first semantic data and the semantic task information in the first information.

[0061] In the above embodiments, on the one hand, the receiving end decodes the first semantic data, then executes the task corresponding to the first semantic data, obtains the task completion status, compares the task completion status with the semantic task information, and determines the task completion degree; through the above method, the receiving end can determine whether it can correctly execute the task indicated by the sending end based on the first semantic data during the semantic communication process, thereby realizing accurate monitoring of semantic communication performance.

[0062] On the other hand, the receiving end determines the task completion rate when the first semantic data channel is successfully decoded. Through the above method, the receiving end can directly determine the monitoring result of semantic communication performance when the first semantic data channel is not decoded, thereby further reducing the energy consumption of the receiving end and improving the monitoring efficiency of semantic communication performance.

[0063] In conjunction with some embodiments of the first aspect, in some embodiments, the monitoring of semantic communication performance based on the first information includes at least one of the following:

[0064] If the semantic similarity between the first semantic data and the source data is lower than a first threshold, it is determined that the monitored semantic communication performance is substandard; the semantic similarity is determined by the receiving end based on the first information.

[0065] If the task completion rate of the semantic task corresponding to the first semantic data is lower than the second threshold, it is determined that the monitored semantic communication performance is substandard; the task completion rate is determined by the receiving end based on the first information.

[0066] If the channel decoding result in the first information is a channel decoding failure, it is determined that the monitored semantic communication performance is substandard.

[0067] In the above embodiments, on the one hand, the receiving end determines whether the monitoring result of semantic communication performance meets the standard based on the relationship between semantic similarity and a first threshold, and / or based on the relationship between task completion and a second threshold. The above method is simple and efficient, improves the monitoring efficiency of semantic communication performance and saves the computing resources of the receiving end.

[0068] On the other hand, when the receiver fails to decode the first semantic data channel, it can directly determine the monitoring result of semantic communication performance, thereby reducing the receiver's energy consumption and improving the monitoring efficiency of semantic communication performance.

[0069] In conjunction with some embodiments of the first aspect, in some embodiments, the first threshold is determined by at least one of the following parameters:

[0070] The semantic features of the first semantic data;

[0071] The network environment during semantic communication;

[0072] Application requirements;

[0073] Semantic device capability, wherein the semantic device includes at least one of a transmitter, the receiver, and a network device;

[0074] And / or, the second threshold is determined by at least one of the following parameters:

[0075] The semantic features of the first semantic data;

[0076] The network environment during semantic communication;

[0077] Application requirements;

[0078] Semantic device capability, wherein the semantic device includes at least one of the sending end, the receiving end, and the network device.

[0079] In the above embodiments, the values ​​of the first threshold and / or the second threshold are determined by various types of parameters, enabling the receiving end to dynamically adjust the values ​​of the first threshold and / or the second threshold according to the real-time environment during the semantic communication process, thereby further improving the accuracy of the monitoring results of semantic communication performance.

[0080] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0081] If the monitored semantic communication performance fails to meet the standard, the first semantic data is discarded.

[0082] In the above embodiments, the semantic communication performance fails to meet the standards, for example, due to at least one of the following reasons: semantic similarity is lower than a first threshold, task completion is lower than a second threshold, and channel decoding result is channel decoding failure. In the above method, the failure to meet the semantic communication performance standards indicates that the first semantic data received by the receiver is incorrect and is not the semantic data initially sent by the sender; for example, the semantic data initially sent by the sender may have had noise added during transmission. Therefore, the receiver can directly discard the erroneous first semantic data, reducing the processing of invalid data and saving resource overhead.

[0083] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0084] Receive the first information sent by the sending end.

[0085] In the above embodiments, the receiving end receives the first information sent by the sending end, enabling the receiving end to accurately assess the integrity and intent reproduction of semantic information during semantic communication based on the first information. This allows the receiving end to effectively monitor the performance of semantic communication and perform different processing on the received data based on the monitoring results of semantic communication performance, thereby improving the reliability of semantic communication.

[0086] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0087] If the monitored semantic communication performance is substandard, a first operation is performed; the first operation is used to improve the semantic communication performance.

[0088] In the above embodiments, when the semantic communication performance is substandard, the receiving end performs a first operation to improve the semantic communication performance, thereby improving the accuracy of the semantic information received by the receiving end and the reliability of the semantic communication.

[0089] In conjunction with some embodiments of the first aspect, in some embodiments, performing the first operation includes at least one of the following:

[0090] Update semantic decoding related parameters; the semantic decoding related parameters include at least one of the following: semantic decoding model, semantic reasoning model, and semantic knowledge base;

[0091] Send a first indication message to the sending end; the first indication message is used to instruct the sending end to send second semantic data, the second semantic data being the same as or related to the first semantic data;

[0092] Send first semantic related parameter information to the sending end, the first semantic related parameter information including semantic related parameters used by the receiving end to decode the first semantic data;

[0093] Send a second indication message to the sending end; the second indication message is used to instruct the sending end to send a second semantic related parameter message, the second semantic related parameter message including semantic related parameters used by the sending end to encode the source data.

[0094] In the above embodiments, on the one hand, by updating the semantic decoding-related parameters, the receiving end can improve its decoding capability and semantic reasoning capability, thereby improving the accuracy of decoding the first semantic data and thus improving the semantic communication performance.

[0095] On the other hand, by sending a first indication message to the sender, the receiver instructs the sender to send second semantic data related to the first semantic data. By processing the second semantic data, the receiver can improve the accuracy of decoding the first semantic data, thereby improving the semantic communication performance.

[0096] On the other hand, the receiving end sends the first semantic related parameter information to the sending end, enabling the sending end to determine the semantic related parameters used by the receiving end when decoding the first semantic data. Through the above method, the sending end can adjust relevant configuration parameters, such as transmission configuration parameters and semantic encoding configuration parameters, according to the first semantic related parameter information, thereby reducing the bit error rate of semantic data in the semantic communication process and improving the accuracy of the receiving end's decoding process, thus improving the performance of semantic communication.

[0097] On the other hand, by sending a second indication information to the sender, the receiver enables the sender to send a second semantic related parameter information. The receiver can then determine the semantic related parameters used by the sender to encode the source data, thereby allowing the receiver to adjust the related parameters based on the second semantic related parameter information, such as adjusting the decoding related parameters. This improves the accuracy of the receiver's decoding process and thus enhances the semantic communication performance.

[0098] In conjunction with some embodiments of the first aspect, in some embodiments, the first indication information carries at least one of the following:

[0099] The third indication information indicates the reason why the sending end sends the second semantic data;

[0100] The fourth indication information indicates the manner in which the sending end transmits the second semantic data.

[0101] In the above embodiments, the receiving end sends first indication information to the sending end, enabling the sending end to determine the reason and method for sending the second semantic data; through the above method, the sending end can adjust relevant configuration parameters according to the first indication information to send the second semantic data to the receiving end in the manner expected, thereby improving the semantic communication performance.

[0102] In conjunction with some embodiments of the first aspect, in some embodiments, the third indication information includes at least one of the following:

[0103] The second piece of information is used to indicate channel quality information;

[0104] The third piece of information is used to indicate semantic similarity information;

[0105] The fourth piece of information is used to indicate the progress of the task.

[0106] The fifth piece of information is used to indicate the monitoring results of the semantic communication performance.

[0107] In the above embodiments, the sending end can determine the reason why the receiving end sends the second semantic data through the third indication information, such as poor channel quality, low semantic similarity, low task completion rate, or substandard semantic communication performance. This enables the sending end to adjust the transmission parameters of the semantic data based on the above reasons and send the second semantic data to the receiving end, thereby reducing the bit error rate of the second semantic data in the semantic communication process and improving the accuracy of the receiving end's decoding of the first semantic data, thus improving the semantic communication performance.

[0108] In conjunction with some embodiments of the first aspect, in some embodiments, the fourth indication information includes at least one of the following:

[0109] The sixth piece of information is used to instruct the sending end to send the second semantic data based on the channel retransmission mechanism;

[0110] The seventh piece of information is used to instruct the sending end to send the second semantic data through non-semantic communication.

[0111] The eighth piece of information is used to instruct the sending end to send the second semantic data based on the adjusted transmission parameters; the adjusted transmission parameters are obtained by the sending end after adjusting them based on at least one of the channel conditions and network environment during the semantic communication process.

[0112] The ninth piece of information is used to instruct the sending end to send the second semantic data and semantic redundancy data associated with the second semantic data.

[0113] In the above embodiments, the sending end can determine the method by which the receiving end expects the sending end to send the second semantic data through the fourth indication information, thereby improving the success rate of the receiving end in receiving the second semantic data and improving the accuracy of the receiving end in decoding the first semantic data, thus improving the semantic communication performance.

[0114] In conjunction with some embodiments of the first aspect, in some embodiments, the second semantic data includes at least one of the following:

[0115] First semantic data;

[0116] The source data for the first semantic data;

[0117] Semantic redundancy data;

[0118] The third semantic data; the third semantic data is related to the transmission parameters of the first semantic data.

[0119] In the above embodiments, on the one hand, the receiving end can decode the first semantic data received again by receiving the first semantic data from the sending end, thereby improving the accuracy of the sending end's decoding of the first semantic data and thus improving the semantic communication performance.

[0120] On the other hand, by receiving the source data of the first semantic data, the receiving end can recalculate the semantic similarity using the re-received source data, thus ensuring the reliability of semantic communication performance monitoring.

[0121] On the other hand, the receiving end can restore the second semantic data based on the semantic redundancy data. Even if the second semantic data received by the receiving end is not the original semantic data sent by the sending end, the second semantic data can still be restored through the semantic redundancy data, which improves the accuracy of receiving the second semantic data and thus improves the performance of semantic communication.

[0122] On the other hand, by receiving third semantic data related to the transmission parameters of the first semantic data, the receiving end can determine the transmission parameters when the sending end sends the first semantic data. For example, the transmission parameters (such as transmission power, modulation method and coding rate) dynamically adjusted by the sending end according to channel conditions and network environment. Through the aforementioned third semantic data, the transmission quality of semantic data can be optimized, thereby improving the performance of semantic communication.

[0123] In conjunction with some embodiments of the first aspect, in some embodiments, the semantically redundant data includes at least one of the following:

[0124] Semantic knowledge base information;

[0125] Contextual information;

[0126] Multimodal information;

[0127] The fourth semantic data, wherein the semantic similarity between the fourth semantic data and the first semantic data reaches a third threshold;

[0128] Historical information is used to indicate the historical interaction records between the sending end and the receiving end.

[0129] In the above embodiments, by adding redundant information when sending the second semantic data, the sending end can improve the fault tolerance and anti-interference capability of the second semantic data. Even if the signal is partially lost or distorted during the transmission of the second semantic data, the receiving end can still accurately restore the content of the second semantic data after receiving it through the redundant information, thereby improving the receiving end's semantic understanding capability of the second semantic data and thus improving the semantic communication performance.

[0130] In conjunction with some embodiments of the first aspect, in some embodiments, the first semantically related parameter information includes at least one of the following:

[0131] Semantic knowledge base information;

[0132] Semantic context information;

[0133] Semantic modal information;

[0134] Semantic importance information;

[0135] And / or, the second semantically related parameter information includes at least one of the following:

[0136] Semantic knowledge base information;

[0137] Semantic context information;

[0138] Semantic modal information;

[0139] Semantic importance information.

[0140] In the above embodiments, on the one hand, by using the first semantic related parameter information, the sending end can determine at least one of the semantic knowledge base information, semantic context information, semantic modality information, and semantic importance information of the receiving end during the decoding process of the first semantic data. This enables the sending end to adjust the transmission parameters based on the first semantic related parameter information and send the second semantic data to the receiving end, thereby improving the accuracy of the receiving end in decoding the second semantic data and thus improving the semantic communication performance.

[0141] On the other hand, by using the second semantic related parameter information, the receiving end can determine at least one of the semantic knowledge base information, semantic context information, semantic modality information, and semantic importance information of the sending end during the encoding process of the source data. This enables the receiving end to adjust the transmission parameters based on the second semantic related parameter information, such as adjusting the decoding related parameters, thereby improving the accuracy of the receiving end's decoding of semantic data, such as the first semantic data, and improving the semantic communication performance.

[0142] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0143] Receive the second semantic related parameter information sent by the sending end.

[0144] In the above embodiments, by receiving the second semantic related parameter information, the receiving end can determine at least one of the semantic knowledge base information, semantic context information, semantic modality information, and semantic importance information of the sending end during the encoding process of the source data. This enables the receiving end to adjust the transmission parameters based on the second semantic related parameter information, such as adjusting the decoding related parameters, thereby improving the accuracy of the receiving end's decoding of semantic data, such as the first semantic data, and improving the semantic communication performance.

[0145] Secondly, embodiments of this disclosure provide a communication method executed by a sending end, the method comprising:

[0146] Send the first message to the receiving end;

[0147] The first information is used by the receiving end to monitor the semantic communication performance; the first information is semantic-related information during the semantic communication process.

[0148] In conjunction with some embodiments of the second aspect, in some embodiments, the first information includes at least one of the following:

[0149] First semantic data;

[0150] The source data for the first semantic data;

[0151] Channel decoding result; the channel decoding result is obtained by the receiving end after performing channel decoding on the first semantic data;

[0152] The semantic verification information corresponding to the first semantic data;

[0153] The semantic task information corresponding to the first semantic data;

[0154] The first semantic data is the semantic data received by the receiving end from the sending end.

[0155] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes at least one of the following:

[0156] Send second semantic data to the receiving end; the second semantic data is sent by the sending end after receiving the first indication information sent by the receiving end;

[0157] The receiver receives first semantic related parameter information sent by the receiving end, the first semantic related parameter information including semantic related parameters used by the receiving end to decode the first semantic data;

[0158] The sending end sends second semantic related parameter information to the receiving end; the second semantic related parameter information is sent by the sending end after receiving the second indication information sent by the receiving end; the second semantic related parameter information includes semantic related parameters used by the sending end to encode the source data.

[0159] In conjunction with some embodiments of the second aspect, in some embodiments, the first indication information carries at least one of the following:

[0160] The third indication information indicates the reason why the sending end sends the second semantic data;

[0161] The fourth indication information indicates the manner in which the sending end transmits the second semantic data.

[0162] In conjunction with some embodiments of the second aspect, in some embodiments, the third indication information includes at least one of the following:

[0163] The second piece of information is used to indicate channel quality information;

[0164] The third piece of information is used to indicate semantic similarity information;

[0165] The fourth piece of information is used to indicate the progress of the task.

[0166] The fifth piece of information is used to indicate the monitoring results of the semantic communication performance.

[0167] In conjunction with some embodiments of the second aspect, in some embodiments, the fourth indication information includes at least one of the following:

[0168] The sixth piece of information is used to instruct the sending end to send the second semantic data based on the channel retransmission mechanism;

[0169] The seventh piece of information is used to instruct the sending end to send the second semantic data through non-semantic communication.

[0170] The eighth piece of information is used to instruct the sending end to send the second semantic data based on the adjusted transmission parameters; the adjusted transmission parameters are obtained by the sending end after adjusting them based on at least one of the channel conditions and network environment during the semantic communication process.

[0171] The ninth piece of information is used to instruct the sending end to send the second semantic data and semantic redundancy data associated with the second semantic data.

[0172] In conjunction with some embodiments of the second aspect, in some embodiments, the second semantic data includes at least one of the following:

[0173] First semantic data;

[0174] The source data for the first semantic data;

[0175] Semantic redundancy data;

[0176] The third semantic data; the third semantic data is related to the transmission parameters of the first semantic data.

[0177] In conjunction with some embodiments of the second aspect, in some embodiments, the semantically redundant data includes at least one of the following:

[0178] Semantic knowledge base information;

[0179] Contextual information;

[0180] Multimodal information;

[0181] The fourth semantic data, wherein the semantic similarity between the fourth semantic data and the first semantic data reaches a third threshold;

[0182] Historical information is used to indicate the historical interaction records between the sending end and the receiving end.

[0183] In conjunction with some embodiments of the second aspect, in some embodiments, the first semantically related parameter information includes at least one of the following:

[0184] Semantic knowledge base information;

[0185] Semantic context information;

[0186] Semantic modal information;

[0187] Semantic importance information;

[0188] And / or, the second semantically related parameter information includes at least one of the following:

[0189] Semantic knowledge base information;

[0190] Semantic context information;

[0191] Semantic modal information;

[0192] Semantic importance information.

[0193] Thirdly, embodiments of this disclosure provide a communication device, which is a receiving end. The receiving end may include at least one of a transceiver module and a processing module; wherein the receiving end may be used to execute an optional implementation of the first aspect.

[0194] Fourthly, embodiments of this disclosure provide a communication device, which is a transmitting end. The transmitting end may include at least one of a transceiver module and a processing module; wherein the transmitting end may be used to execute an optional implementation of the second aspect.

[0195] Fifthly, embodiments of this disclosure provide a communication device, which is a receiving end, and the receiving end may include one or more processors; wherein the receiving end may be used to execute an optional implementation of the first aspect.

[0196] In a sixth aspect, embodiments of this disclosure provide a communication device, which is a transmitter and may include one or more processors; wherein the transmitter may be used to execute an optional implementation of the second aspect.

[0197] In a seventh aspect, embodiments of this disclosure provide a communication system comprising: a receiving end and a transmitting end; wherein the receiving end is configured to perform the method described in the optional implementation of the first aspect, and the transmitting end is configured to perform the method described in the optional implementation of the second aspect.

[0198] Eighthly, embodiments of this disclosure provide a storage medium storing instructions that, when executed on a communication device, cause the communication device to perform the method as described in the optional implementation of the first or second aspect.

[0199] Ninthly, embodiments of this disclosure provide a program product that, when executed by a communication device, causes the communication device to perform the method as described in the optional implementation of the first or second aspect.

[0200] In a tenth aspect, embodiments of this disclosure provide a computer program that, when run on a computer, causes the computer to perform the method as described in an optional implementation of the first or second aspect.

[0201] Eleventhly, embodiments of this disclosure provide a chip or chip system. The chip or chip system includes processing circuitry configured to perform the methods described according to optional implementations of the first or second aspect above.

[0202] It is understood that the aforementioned communication equipment, receiving end, transmitting end, communication system, storage medium, program product, etc., are all used to execute the methods proposed in the embodiments of this disclosure. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0203] This disclosure provides a communication method, a communication device, a communication system, a storage medium, and a program product. In some embodiments, the terms "communication method" and "information processing method," "method for requesting data collection configuration," etc., may be used interchangeably.

[0204] This disclosure is not exhaustive, but merely illustrative of some embodiments, and is not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment can be arbitrarily interchanged. Furthermore, the optional implementation methods in a particular embodiment can be arbitrarily combined; moreover, the embodiments can be arbitrarily combined, for example, some or all steps of different embodiments can be arbitrarily combined, and a particular embodiment can be arbitrarily combined with the optional implementation methods of other embodiments. In all embodiments of this disclosure, unless otherwise specified or logically conflicting, the terminology and / or descriptions between the embodiments are consistent and can be mutually referenced. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0205] The terminology used in the embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the scope of this disclosure.

[0206] In this embodiment of the disclosure, unless otherwise stated, elements expressed in the singular form, such as "a," "an," "the," "the," "the," "the," "the," "the," "this," etc., can mean "one and only one," or "one or more," "at least one," etc. For example, when using articles such as "a," "an," "the," etc. in translation, the noun following the article can be understood as either a singular expression or a plural expression.

[0207] In the embodiments of this disclosure, "multiple" can refer to two or more.

[0208] In some embodiments, the terms “at least one of A or B, at least one of A and B”, “one or more”, “a plurality of”, “multiple”, etc., may be used interchangeably.

[0209] In some embodiments, the notation "at least one of A and B", "A and / or B", "A in one case, B in another", "in response to one case A, in response to another case B", etc., may include the following technical solutions depending on the situation: in some embodiments, A (execute A regardless of B); in some embodiments, B (execute B regardless of A); in some embodiments, execution is selected from A and B (A and B are selectively executed); in some embodiments, A and B (both A and B are executed). The same applies when there are more branches such as A, B, C, etc.

[0210] In some embodiments, the notation "A or B" may include the following technical solutions, depending on the situation: in some embodiments, A (execution of A regardless of B); in some embodiments, B (execution of B regardless of A); in some embodiments, execution is selected from A and B (A and B are selectively executed). The same applies when there are more branches such as A, B, C, etc.

[0211] The prefixes "first," "second," etc., used in the embodiments of this disclosure are merely for distinguishing different descriptive objects and do not impose restrictions on the position, order, priority, quantity, or content of the descriptive objects. The description of the descriptive objects is found in the claims or the context of the embodiments, and the use of prefixes should not constitute unnecessary restrictions. For example, if the descriptive object is a "field," the ordinal numbers preceding "field" in "first field" and "second field" do not restrict the position or order of the "fields." "First" and "second" do not restrict whether the "fields" they modify are in the same message, nor do they restrict the order of "first field" and "second field." Similarly, if the descriptive object is a "level," the ordinal numbers preceding "level" in "first level" and "second level" do not restrict the priority between "levels." Furthermore, the number of descriptive objects is not limited by ordinal numbers and can be one or more. For example, in "first device," the number of "devices" can be one or more. Furthermore, the objects modified by different prefixes can be the same or different. For example, if the object being described is "device", then "first device" and "second device" can be the same device or different devices, and their types can be the same or different. Similarly, if the object being described is "information", then "first information" and "second information" can be the same information or different information, and their content can be the same or different.

[0212] In some embodiments, “including A,” “containing A,” “for indicating A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.

[0213] In some embodiments, terms such as "time / frequency" and "time-frequency domain" refer to the time domain and / or frequency domain.

[0214] In some embodiments, terms such as “in response to…”, “in response to determining…”, “in the case of…”, “when…”, “when…”, “if…”, etc. can be used interchangeably. These descriptions all refer to the device making a corresponding action under certain objective circumstances. They do not necessarily limit the time, nor do they require the device to make a judgment action when implementing it, nor do they mean that there must be other limitations.

[0215] In some embodiments, the terms “greater than,” “greater than or equal to,” “not less than,” “more than,” “more than or equal to,” “not less than,” “higher than,” “higher than or equal to,” “not lower than,” and “above” can be used interchangeably, as can the terms “less than,” “less than or equal to,” “not greater than,” “less than,” “less than or equal to,” “not more than,” “lower than,” “lower than or equal to,” “not higher than,” and “below”.

[0216] In some embodiments, devices, etc., may be interpreted as physical or virtual, and their names are not limited to those described in the embodiments. Terms such as “device,” “equipment,” “circuit,” “network element,” “node,” “function,” “unit,” “section,” “system,” “network,” “chip,” “chip system,” “entity,” and “subject” are interchangeable.

[0217] In some embodiments, "network" can be interpreted as devices included in a network (e.g., access network devices, core network devices, etc.).

[0218] In some embodiments, the terms "Access Network Device (AN Device)," "Radio Access Network Device (RAN Device)," "Base Station (BS)," "Radio Base Station," "Fixed Station," "Node," "Access Point," "Transmission Point (TP)," "Reception Point (RP)," "Transmission / Reception Point (TRP)," "Panel," "Antenna Panel," "Antenna Array," "Cell," "Macro Cell," "Small Cell," "Femto Cell," "Pico Cell," "Sector," "Cell Group," "Serving Cell," "Carrier," "Component Carrier," and "Bandwidth Part (BWP)" can be used interchangeably.

[0219] In some embodiments, the terms "terminal", "terminal device", "user equipment (UE)", "user terminal", "mobile station (MS)", "mobile terminal (MT)", "subscriber station", "mobile unit", "subscriber unit", "wireless unit", "remote unit", "mobile device", "wireless device", "wireless communication device", "remote device", "mobile subscriber station", "access terminal", "mobile terminal", "wireless terminal", "remote terminal", "handset", "user agent", "mobile client", and "client" can be used interchangeably.

[0220] In some embodiments, access network devices, core network devices, or network devices can be replaced with terminals. For example, embodiments of this disclosure can also be applied to structures where communication between access network devices, core network devices, or network devices and terminals is replaced with communication between multiple terminals (e.g., device-to-device (D2D), vehicle-to-everything (V2X), etc.). In this case, the structure can also be configured such that the terminal has all or part of the functions of the access network device. Furthermore, terms such as "uplink" and "downlink" can be replaced with terms corresponding to communication between terminals (e.g., "sidelink"). For example, uplink channel, downlink channel, etc., can be replaced with sidelink channel or direct channel, and uplink link, downlink, etc., can be replaced with sidelink link or direct link.

[0221] In some embodiments, the terminal may be replaced by an access network device, a core network device, or a network device. In this case, the access network device, core network device, or network device may also be configured to have all or some of the functions of the terminal.

[0222] In some embodiments, the acquisition of data, information, etc., may comply with the laws and regulations of the country where the location is situated.

[0223] In some embodiments, data, information, etc., may be obtained with the user's consent.

[0224] Furthermore, each element, each row, or each column in the table of this disclosure can be implemented as an independent embodiment, and any combination of any element, any row, or any column can also be implemented as an independent embodiment.

[0225] Figure 1A is a schematic diagram of the architecture of a communication system according to an embodiment of the present disclosure. As shown in Figure 1, the communication system 100 may include a receiver 101 and a transmitter 102. The receiver 101 is also referred to as a semantic receiver, and the transmitter 102 is also referred to as a semantic transmitter. It should be noted that "receiver 101" and "transmitter 102" are defined here from the perspective of one or more data transmission processes. It can be understood that in other data transmission processes, the receiver 101 can also send data, that is, act as a transmitter. Similarly, the transmitter 102 can also receive data, that is, act as a receiver. In some embodiments, the receiver 101 can communicate directly with the transmitter 102. In other embodiments, the receiver 101 can also communicate with the transmitter 102 through other devices.

[0226] In some embodiments, the receiving end 101 can be a terminal or a network device. The sending end 102 can be a terminal or a network device.

[0227] In some embodiments, the terminal may include at least one of, but is not limited to, a mobile phone, a wearable device, an Internet of Things device, a car with communication capabilities, a smart car, a tablet computer, a computer with wireless transceiver capabilities, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical surgery, a wireless terminal device in a smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city, and a wireless terminal device in a smart home.

[0228] In some embodiments, a network device may include at least one of an access network device and a core network device.

[0229] In some embodiments, the access network device may be a node or device that connects a terminal device to a wireless network. The access network device may include, but is not limited to, at least one of the following in a 5G communication system: evolved Node B (eNB), next-generation eNB (ng-eNB), next-generation Node B (gNB), node B (NB), home node B (HNB), home evolved node B (HeNB), radio backhaul device, radio network controller (RNC), base station controller (BSC), base transceiver station (BTS), base band unit (BBU), mobile switching center, base station in a 6G communication system, open RAN, cloud RAN, base station in other communication systems, and access node in a Wi-Fi system.

[0230] In some embodiments, the technical solutions of this disclosure can be applied to the Open RAN architecture. In this case, the interfaces between or within access network devices involved in the embodiments of this disclosure can be transformed into internal interfaces of Open RAN. The processes and information interactions between these internal interfaces can be implemented by software or programs.

[0231] In some embodiments, the access network device may be composed of a central unit (CU) and a distributed unit (DU). The CU may also be called a control unit. The CU-DU structure can separate the protocol layer of the access network device. Some protocol layer functions are centrally controlled by the CU, while the remaining part or all protocol layer functions are distributed in the DU and centrally controlled by the CU. However, this is not the only possibility.

[0232] In some embodiments, the core network equipment may be a single device, including a first network element, a second network element, etc., or it may be multiple devices or a group of devices, each including all or part of the first network element, the second network element, etc. Network elements may be virtual or physical. The core network may include, for example, at least one of the Evolved Packet Core (EPC), 5G Core Network (5GCN), and Next Generation Core (NGC).

[0233] It is understood that the communication system described in this disclosure is for the purpose of more clearly illustrating the technical solutions of this disclosure, and does not constitute a limitation on the technical solutions proposed in this disclosure. As those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions proposed in this disclosure are also applicable to similar technical problems.

[0234] The following embodiments of this disclosure can be applied to the communication system 100 shown in FIG1, or to some of the main bodies, but are not limited thereto. The main bodies shown in FIG1 are examples. The communication system may include all or some of the main bodies in FIG1, or may include other main bodies outside of FIG1. ​​The number and form of each main body are arbitrary. Each main body may be physical or virtual. The connection relationship between the main bodies is an example. The main bodies may not be connected or may be connected. The connection can be in any way, it can be a direct connection or an indirect connection, it can be a wired connection or a wireless connection.

[0235] The embodiments disclosed herein can be applied to Long Term Evolution (LTE), LTE-Advanced (LTE-A), LTE-Beyond (LTE-B), SUPER 3G, IMT-Advanced, 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 5G New Radio (NR), Future Radio Access (FRA), New-Radio Access Technology (RAT), New Radio (NR), New Radio Access (NX), Future generation radio access (FX), Global System for Mobile communications (GSM), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), and IEEE 802.20, Ultra-Wideband (UWB), Bluetooth (a registered trademark), Public Land Mobile Network (PLMN) networks, Device-to-Device (D2D) systems, Machine-to-Machine (M2M) systems, Internet of Things (IoT) systems, Vehicle-to-Everything (V2X) systems, systems utilizing other communication methods, and next-generation systems built upon them, etc. Furthermore, multiple systems can be combined (e.g., a combination of LTE or LTE-A with 5G).

[0236] In some embodiments, 6G semantic communication is the core paradigm in sixth-generation mobile communication. Its core lies in achieving intelligent transmission of information "semantics" through artificial intelligence (AI), rather than focusing solely on bit stream transmission in traditional communication.

[0237] In some embodiments, as the demand for intelligent services continues to grow, 6G wireless networks will shift from a traditional architecture focused solely on high transmission rates to a new architecture based on the intelligent connectivity of everything. Unlike traditional data-oriented communication methods, semantic communication integrates user and application needs, as well as the meaning of information, into data processing and transmission, and will become the core paradigm of 6G.

[0238] In some embodiments, traditional communication, based on Shannon's classical information theory, focuses on optimizing data-oriented performance metrics such as data rate and bit error rate, while neglecting metrics related to service, objective, or semantics. Therefore, semantic communication differs from traditional data-oriented communication networks, which increase capacity at the expense of system complexity. Semantic communication, through artificial intelligence techniques, preprocesses data and delivers information most relevant to the receiver or communication task objective to all participants, thereby reducing network burden. Semantic communication achieves a higher level of intelligent communication at both the semantic and effectiveness levels, transforming communication nodes from simple symbol-exchanging senders and receivers into more intelligent agents that exchange the semantic aspects of data to efficiently achieve communication goals.

[0239] In some embodiments, the following requirements exist in 6G wireless communication networks:

[0240] 1. The emergence of new services, such as the Metaverse, requires 6G networks to support the wireless transmission of large amounts of data.

[0241] 2. 6G applications with a large number of nodes, such as collaborative robots and ultra-intelligent IoT, require rapid system response and reliable, efficient information exchange.

[0242] 3. More network resources need to be used for real-time information updates and user data analysis to ensure a better service experience.

[0243] In some embodiments, the development of semantic communication is complementary to the advancement of 6G. On the one hand, the availability and connectivity of distributed computing and ubiquitous AI networks in 6G will enable the large-scale deployment of semantic communication. On the other hand, semantic communication overcomes the limitations of traditional communication, leading to unprecedented improvements in network performance. Therefore, with the successful training and development of semantic communication, the vision of 6G, such as lower latency and enhanced reliability than 5G, can be fully realized.

[0244] In some embodiments, semantic communication has the following advantages:

[0245] 1. Reduce the wireless data transmission burden on 6G networks;

[0246] 2. Improve the efficiency of 6G network management and control;

[0247] 3. Utilize information semantics to design effective network resource allocation schemes.

[0248] Figure 1B is a schematic diagram of a communication system model according to an embodiment of the present disclosure. As shown in Figure 1B, it is a schematic diagram of a classic communication system model, oriented towards data transmission. This communication system model includes a source encoding module, a channel encoding module, a physical channel, a channel decoding module, and a source decoding module; wherein, the physical channel includes physical noise.

[0249] In some embodiments, source data is input to the source encoding module, and the source decoding module outputs the data replication corresponding to the source data.

[0250] In some embodiments, the communication system model shown in Figure 1B focuses on the accuracy of each bit and each symbol, with all bits and symbols being equally important.

[0251] Figure 1C is a schematic diagram of a communication system model according to an embodiment of the present disclosure. As shown in Figure 1C, it is a schematic diagram of a semantic communication system model, which is semantically oriented communication. This semantic communication system model uses semantic information reconstruction to reconstruct source data.

[0252] In some embodiments, the semantic communication system model includes a sender and a receiver.

[0253] In some embodiments, the sending end includes: a semantic encoding module, a semantic representation module, a channel encoding module, and a local knowledge base.

[0254] In some embodiments, the receiver includes: a channel decoding module, a semantic decoding module, a semantic inference module, and a local knowledge base.

[0255] In some embodiments, the sender and receiver share a database (shared knowledge).

[0256] In some embodiments, the transmitting end and the receiving end transmit semantic data through a physical channel, which includes physical noise, and semantic noise is included during the semantic data transmission process.

[0257] In some embodiments, source data is input to the semantic encoding module, and the semantic reasoning module outputs the desired semantics.

[0258] Figure 1D is a schematic diagram of a communication system model according to an embodiment of the present disclosure. As shown in Figure 1D, it is a schematic diagram of a semantic communication system model, which is a target-oriented communication model. This semantic communication system model utilizes semantic information to complete intelligent communication tasks, such as image retrieval, speech recognition, and scene classification.

[0259] In some embodiments, the semantic communication system model includes a sender and a receiver.

[0260] In some embodiments, the sending end includes: a semantic encoding module, a semantic representation module, a semantic filtering module, a channel encoding module, and a local knowledge base.

[0261] In some embodiments, the receiver includes: a channel decoding module, a semantic decoding module, a semantic inference module, and a local knowledge base.

[0262] In some embodiments, the sender and receiver share a database (shared knowledge).

[0263] In some embodiments, the transmitting end and the receiving end transmit semantic data through a physical channel, which includes physical noise, and semantic noise is included during the semantic data transmission process.

[0264] In some embodiments, the transmitting end first extracts the semantic features of the source data that serve the intelligent task, and then maps them directly to the channel input symbols after joint source-channel coding; the receiving end directly uses the decoded semantic features to perform the task.

[0265] Figure 1E is a schematic diagram of a semantic-aware communication architecture according to an embodiment of the present disclosure. This semantic-aware communication is a centralized task-oriented communication. As shown in Figure 1E, hollow circles represent communication agents, solid lines represent task-related data transmission, and dashed lines represent semantic information exchange for better cooperation.

[0266] Figure 1F is a schematic diagram of a semantic-aware communication architecture according to an embodiment of the present disclosure. This semantic-aware communication is distributed task-oriented communication, where hollow circles represent communication agents, solid lines represent the transmission of task-related data, and dashed lines represent the exchange of semantic information to promote better cooperation.

[0267] In some embodiments, semantic communication focuses not only on the reliable transmission of the data itself, but also on whether the receiving end can make correct decisions and execute the expected tasks after receiving the information. The core of semantic communication lies in extracting semantic information from the data and saving bandwidth resources, improving network capacity and communication efficiency through efficient transmission methods. Non-semantic communication, on the other hand, typically refers to traditional communication methods that primarily focus on the accurate transmission of data without particularly considering its semantic content.

[0268] In some embodiments, within a semantic communication system, a method is employed where semantic information is extracted and encoded before bit-level error-free transmission. The receiving end performs semantic decoding and semantic information recovery, determines the correctness of the received semantic information, and feeds back to the sending end. Since the semantic communication system architecture incorporates elements of a classical communication system, how to monitor the performance of the semantic communication system and improve its reliability are issues that need to be considered.

[0269] Figure 2A is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure, the method including:

[0270] Step S2101: The sending end 102 sends the first semantic data and the source data of the first semantic data to the receiving end 101.

[0271] In some embodiments, the receiving end 101 receives source data and first semantic data sent by the sending end 102, but is not limited thereto. The receiving end 101 may also receive source data and first semantic data sent by other subjects, in which case step S2101 can be omitted.

[0272] In some embodiments, the receiving end 101 obtains the source data and the first semantic data specified by the protocol, in which case step S2101 can be omitted.

[0273] In some embodiments, the receiving end 101 obtains source data and first semantic data from the upper layer(s), in which case step S2101 can be omitted.

[0274] In some embodiments, the receiving end 101 can obtain source data and first semantic data from at least one of the following messages sent by the sending end 102: Non-Access Stratum (NAS) messages, Access Stratum (AS) messages, and Application Layer messages.

[0275] In some embodiments, the receiving end 101 processes the data to obtain the source data and the first semantic data, in which case step S2101 can be omitted.

[0276] In some embodiments, the receiving end 101 autonomously implements the functions indicated by the source data and the first semantic data, or the above functions are default or default, in which case step S2101 can be omitted.

[0277] In some embodiments, the receiving end 101 receives source data and first semantic data. For example, the receiving end 101 receives source data and first semantic data sent by the sending end 102.

[0278] In some embodiments, the first semantic data is semantic data received by the receiver from the sender 102.

[0279] In some embodiments, the first semantic data is the semantic data of the source data sent by the sender 101.

[0280] In some embodiments, the first semantic data is used to reflect the semantic information of the source data.

[0281] In some embodiments, the first semantic data is the semantic data that the sending end 101 encodes and processes the semantic information of the source data and sends through the semantic communication system, and the receiving end 102 receives the semantic data.

[0282] In some embodiments, the first semantic data may be the same as or different from the semantic information encoded by the transmitter 101 on the source data. If they are different, it may be because the semantic information encoded by the transmitter 101 on the source data introduces noise (e.g., semantic noise, channel noise, etc.) into the channel.

[0283] In some embodiments, the transmitter 102 extracts semantic information from the source data to generate raw semantic data. The transmitter 102 then transmits the raw semantic data through a semantic communication system. In practical applications, the raw semantic data may be subject to interference such as noise in the channel, including channel noise and semantic noise. Therefore, under noise interference, the first semantic data received by the receiver 101 may be different from or the same as the raw semantic data transmitted by the transmitter 102.

[0284] In some embodiments, the sending end 102 sends the original semantic data through a semantic communication system, and the receiving end 101 receives the first semantic data from the sending end 102. This process can be understood as the sending end 102 sending the first semantic data and the receiving end 101 receiving the first semantic data sent by the sending end 102.

[0285] In some embodiments, the sender 102 and receiver 101 can be terminals, network devices, or any communication node in a semantic communication system.

[0286] In some embodiments, source data refers to raw, unprocessed data, or data that has only undergone simple preprocessing. In some embodiments, raw data may be data collected by a device (e.g., a sensor), data received by a device (e.g., a sensor, or transmitter 102), or data that has undergone simple preprocessing by a device (e.g., a sensor, or transmitter 102).

[0287] For example, in the agricultural sector, when environmental sensors are used to monitor the growth environment of crops, the source data may include data such as environmental humidity, temperature, time, temperature difference, and crop images collected by the environmental sensors, and the first semantic data may include, for example, that the current growth environment of the crops is arid and the soil nutrient content is low.

[0288] For example, in a fire alarm sensor monitoring system, the source data might be data collected by the fire alarm sensor, such as location, ambient temperature, smoke concentration, and brightness. The first semantic data might be, for example, "A fire has occurred on the first floor."

[0289] In some embodiments, the source data and the first semantic data are used to monitor the performance of semantic communication.

[0290] In some embodiments, the source data and the first semantic data are used by the receiver 101 to monitor the semantic communication performance.

[0291] In some embodiments, semantic communication performance is used to reflect the accuracy of the semantic communication system in transmitting semantic information.

[0292] For example, semantic communication performance is used to reflect the accuracy of semantic information transmission between any two communication nodes in a semantic communication system.

[0293] For example, semantic communication performance is used to reflect the accuracy of semantic information transmission between the sender 102 and receiver 101 in a semantic communication system.

[0294] In some embodiments, semantic communication performance is used to reflect the accuracy of the semantic communication system in transmitting the semantic information that the sender 102 intends to send.

[0295] In some embodiments, semantic communication performance is used to reflect the accuracy of the semantic communication system in transmitting semantic information of the source data from the sender 102.

[0296] In some embodiments, if the semantic communication performance meets the standard, it means that the semantic communication system can accurately transmit semantic information.

[0297] In some embodiments, if the semantic communication performance is substandard, it means that the semantic communication system cannot accurately transmit semantic information.

[0298] In some embodiments, semantic communication performance meeting or failing to meet standards can be represented numerically or binaryly (e.g., 0, 1). For example, a monitoring value of 60 or higher indicates that semantic communication performance meets standards, while a monitoring value below 60 indicates that semantic communication performance fails to meet standards. As another example, a monitoring value of 1 indicates that semantic communication performance meets standards, while a monitoring value of 0 indicates that semantic communication performance fails to meet standards.

[0299] In some embodiments, the sending end 102 sends source data and first semantic data to the receiving end 101. The receiving end 101 monitors the semantic communication performance based on the source data and the first semantic data.

[0300] In some embodiments, monitoring semantic communication performance refers to the receiving end 101 monitoring the semantic communication performance between the sending end 102 and the receiving end 101.

[0301] In some embodiments, monitoring semantic communication performance means that the receiver 101 monitors the communication performance between any communication nodes in the semantic communication system.

[0302] In some embodiments, the sending end 102 is a first terminal and the receiving end 101 is a second terminal. The second terminal monitors the semantic communication performance between the first terminal and the second terminal based on the source data and the first semantic data sent by the first terminal.

[0303] In some embodiments, the sending end 102 is a network device and the receiving end 101 is a terminal; then, the terminal monitors the semantic communication performance between the network device and the terminal based on the source data sent by the network device and the first semantic data.

[0304] In some embodiments, the sending end 102 is a terminal and the receiving end 101 is any node in the semantic communication system. The node monitors the semantic communication performance between the terminal and the node based on the source data sent by the terminal and the first semantic data.

[0305] In some embodiments, the sending end 102 is any first node in the semantic communication system, and the receiving end 101 is any second node in the semantic communication system. Then, the second node monitors the semantic communication performance between the first node and the second node based on the source data and the first semantic data sent by the first node.

[0306] In some embodiments, the sending end 102 is a first terminal and the receiving end 101 is a second terminal; then, the second terminal monitors the semantic communication performance between any communication nodes between the first terminal and the second terminal based on the source data and the first semantic data sent by the first terminal.

[0307] In some embodiments, the sending end 102 periodically or non-periodically sends source data to the receiving end 101.

[0308] In some embodiments, the sender 102 sends source data to the receiver 101 based on a request from the receiver 101.

[0309] In some embodiments, the sending end 102 determines to send source data to the receiving end 101 based on implementation. For example, the sending end 102 sends source data to the receiving end 101 based on configuration parameters.

[0310] In some embodiments, the receiver 101 may directly receive the first semantic data sent by the sender 102 during semantic communication.

[0311] In some embodiments, the sending end 102 transmits the source data and the first semantic data to the receiving end 101, respectively, by carrying the source data and the first semantic data in two separate signaling messages.

[0312] In some embodiments, the sender 102 places the source data after the first semantic data and carries them together in a single signaling message to the receiver 101.

[0313] In some embodiments, the sender 102 transmits the first semantic data and the source data together in a single signaling to the receiver 101.

[0314] Step S2102: The receiving end 101 determines the semantic similarity between the first semantic data and the source data based on the source data and the first semantic data.

[0315] In some embodiments, after receiving the first semantic data, the receiving end 101 needs to perform decoding (e.g., channel decoding, semantic decoding) and semantic reasoning on the first semantic data.

[0316] In some embodiments, the result of channel decoding of the first semantic data by the receiver 101 does not affect the accuracy of semantic decoding. The receiver 101 determines the semantic similarity directly based on the source data and the first semantic data.

[0317] In some embodiments, the result of channel decoding of the first semantic data by the receiver 101 affects the accuracy of semantic decoding. Therefore, the receiver 101 determines the semantic similarity based on the source data and the first semantic data only after the channel decoding of the first semantic data is successful.

[0318] In some embodiments, the receiving end 101 determines the semantic similarity between the first semantic data and the source data based on the first semantic data and the source data, which can be achieved in the following ways:

[0319] Step 1: Receiver 101 performs semantic decoding on the first semantic data;

[0320] Step 2: Receiver 101 calculates the semantic similarity between the first semantic data after decoding and the source data.

[0321] In some embodiments, semantic decoding processing includes channel decoding, semantic decoding, and semantic reasoning.

[0322] For example, the receiver 101 decodes the first semantic data based on the source-channel joint semantic decoder to obtain the decoded first semantic data.

[0323] For example, the semantic similarity between the first semantic data and the source data can be calculated in several ways: for instance, by extracting the vectors of the first semantic data and the source data respectively, and comparing their cosine similarity to obtain the semantic similarity. Another example is by inputting the first semantic data and the source data into a semantic similarity recognition model to obtain the semantic similarity output by the model. The semantic similarity recognition model can be a WordNet model, a BERT model, etc.

[0324] Step S2103: The receiving end 101 performs performance monitoring of semantic communication based on semantic similarity.

[0325] In some embodiments, if the semantic similarity is lower than a first threshold, the receiver 101 determines that the monitoring result of semantic communication performance is substandard.

[0326] In some embodiments, if the semantic similarity is not higher than a first threshold, the receiver 101 determines that the monitoring result of semantic communication performance is that the semantic communication performance is substandard.

[0327] In some embodiments, if the semantic similarity is less than a first threshold, the receiver 101 determines that the monitoring result of semantic communication performance is that the semantic communication performance is substandard.

[0328] In some embodiments, if the semantic similarity is not greater than a first threshold, the receiver 101 determines that the monitoring result of the semantic communication performance is that the semantic communication performance is substandard.

[0329] In some embodiments, if the semantic similarity is greater than or equal to a first threshold, the receiver 101 determines that the monitoring result of the semantic communication performance is satisfactory.

[0330] In some embodiments, if the semantic similarity is greater than a first threshold, the receiver 101 determines that the monitoring result of the semantic communication performance is satisfactory.

[0331] In some embodiments, if the semantic similarity is higher than a first threshold, the receiver 101 determines that the monitoring result of the semantic communication performance is satisfactory.

[0332] In some embodiments, if the semantic similarity is not less than a first threshold, the receiver 101 determines that the monitoring result of the semantic communication performance is satisfactory.

[0333] In some embodiments, substandard semantic communication performance can be understood as poor semantic communication performance.

[0334] In some embodiments, channel decoding errors may not affect the accuracy of semantic decoding. The receiver 101 directly determines, based on the results of the source-channel joint semantic decoder, that semantic communication performance is poor only when the semantic similarity is below a first threshold, or the semantic similarity is not higher than the first threshold, or the semantic similarity is less than the first threshold, or the semantic similarity is not greater than the first threshold; and determines that semantic communication performance meets the standard only when the semantic similarity is greater than or equal to the first threshold, or the semantic similarity is greater than the first threshold, or the semantic similarity is higher than the first threshold, or the semantic similarity is not less than the first threshold.

[0335] In some embodiments, the receiver 101 performs semantic decoding only when the channel decoding is correct, and determines, based on the semantic decoding result, that semantic communication performance is poor only when the semantic similarity is lower than a first threshold, or the semantic similarity is not higher than the first threshold, or the semantic similarity is less than the first threshold, or the semantic similarity is not greater than the first threshold; and determines that semantic communication performance meets the standard only when the semantic similarity is greater than or equal to the first threshold, or the semantic similarity is greater than the first threshold, or the semantic similarity is higher than the first threshold, or the semantic similarity is not less than the first threshold.

[0336] In some embodiments, the first threshold is determined by at least one of the following parameters:

[0337] a) Semantic features of the first semantic data; for example, the type, importance, and completeness of the first semantic data.

[0338] b) The network environment during semantic communication; for example, channel quality, load, etc.

[0339] c) Application requirements; for example, latency, security, etc.

[0340] d) Semantic device capabilities; the semantic device includes at least one of the following: the transmitter 102, the receiver 101, and a network device. The network device can be understood as a semantic network device.

[0341] In some embodiments, the first threshold can be flexibly configured through protocol agreement or network signaling configuration.

[0342] In some embodiments, the first threshold may be predefined by the protocol, configured by the network, or determined autonomously by the receiver or the sender.

[0343] In some embodiments, if the task completion rate of the semantic task corresponding to the first semantic data is lower than a second threshold, the receiver 101 determines that the monitored semantic communication performance is substandard. The specific implementation method of the receiver 101 determining the task completion rate is shown in steps S2302 to S2303 in Figure 2C.

[0344] In some embodiments, if the task completion rate is not higher than the second threshold, the receiver 101 determines that the monitoring result of semantic communication performance is that the semantic communication performance is substandard.

[0345] In some embodiments, if the task completion rate is less than the second threshold, the receiver 101 determines that the monitoring result of semantic communication performance is that the semantic communication performance is substandard.

[0346] In some embodiments, if the task completion rate is not greater than the second threshold, the receiver 101 determines that the monitoring result of semantic communication performance is that the semantic communication performance is substandard.

[0347] In some embodiments, if the task completion rate is greater than or equal to the second threshold, the receiver 101 determines that the monitoring result of the semantic communication performance is satisfactory.

[0348] In some embodiments, if the task completion rate is greater than the second threshold, the receiver 101 determines that the monitoring result of semantic communication performance is that the semantic communication performance meets the standard.

[0349] In some embodiments, if the task completion rate is higher than the second threshold, the receiver 101 determines that the monitoring result of semantic communication performance is satisfactory.

[0350] In some embodiments, if the task completion rate is not less than the second threshold, the receiver 101 determines that the monitoring result of the semantic communication performance is that the semantic communication performance meets the standard.

[0351] In some embodiments, the second threshold can be flexibly configured through protocol agreement or network signaling configuration.

[0352] In some embodiments, the second threshold may be predefined by the protocol, configured by the network, or determined autonomously by the receiver or the sender.

[0353] In some embodiments, the second threshold is determined by at least one of the following parameters:

[0354] a) Semantic features of the first semantic data; for example, the type, importance, and completeness of the first semantic data.

[0355] b) The network environment during semantic communication; for example, channel quality, load, etc.

[0356] c) Application requirements; for example, latency, security, etc.

[0357] d) Semantic device capabilities; the semantic device includes at least one of the following: the transmitter 102, the receiver 101, and a network device. The network device can be understood as a semantic network device.

[0358] In some embodiments, the channel decoding result in the first information is a channel decoding failure, indicating that the monitored semantic communication performance is substandard.

[0359] Step S2104: If the monitored semantic communication performance is substandard, the receiver 101 discards the first semantic data.

[0360] In some embodiments, if the channel decoding result is a channel decoding failure, it can be understood that the receiver 101 has made a mistake in decoding the first semantic data channel, thus determining that the semantic communication performance is substandard.

[0361] In some embodiments, if the receiver 101 decodes the first semantic data channel incorrectly, the first semantic data is discarded directly.

[0362] In some embodiments, if the semantic similarity is lower than a first threshold, or the semantic similarity is not higher than the first threshold, or the semantic similarity is less than the first threshold, or the semantic similarity is not greater than the first threshold, then the semantic communication performance is determined to be substandard.

[0363] In some embodiments, if the semantic similarity is lower than a first threshold, or the semantic similarity is not higher than a first threshold, or the semantic similarity is less than a first threshold, or the semantic similarity is not greater than a first threshold, then the first semantic data is directly discarded.

[0364] In some embodiments, if the task completion rate is lower than the second threshold, or the task completion rate is not higher than the second threshold, or the task completion rate is less than the second threshold, or the task completion rate is not greater than the second threshold, then the semantic communication performance is determined to be substandard.

[0365] In some embodiments, if the task completion rate is lower than the second threshold, or the task completion rate is not higher than the second threshold, or the task completion rate is less than the second threshold, or the task completion rate is not greater than the second threshold, then the first semantic data is directly discarded.

[0366] Step S2105: Receiver 101 sends second indication information to sender 102.

[0367] In some embodiments, if the semantic communication performance monitoring result is that the semantic communication performance is substandard, the receiver 101 sends a second indication message to the sender 102.

[0368] In some embodiments, the second indication information is used to instruct the sending end 102 to send second semantic related parameter information, which includes semantic related parameters used by the sending end 102 to encode the source data.

[0369] In some embodiments, encoding the source data includes at least one of semantic representation, semantic filtering, semantic coding, and channel coding.

[0370] In some embodiments, the second semantically related parameter information includes at least one of the following:

[0371] a) Semantic knowledge base information; for example, the semantic knowledge base applied to the sender 102, the semantic knowledge base version, etc.

[0372] b) Semantic context information; for example, contextual information and historical semantic information when the sending end 102 encodes the source data.

[0373] For example, the contextual information is the background information (such as sending time, location, sender identity, etc.) when the sending end 102 encodes the source data.

[0374] For example, historical semantic information is a record of historical semantic interactions between the sender 102 and the receiver 101. The receiver 101 can infer the semantics of the current information based on the historical semantic information.

[0375] c) Semantic modality information; for example, the modality of the first semantic data sent by the sender 102 is an image, text, etc.

[0376] d) Semantic importance information.

[0377] Step S2106: The sending end 102 sends the second semantic related parameter information to the receiving end 101.

[0378] In some embodiments, the sending end 102 sends second semantic related parameter information, which can be understood as the sending end 102 sending semantically encoded semantic related information parameters.

[0379] In some embodiments, the second semantic related parameter information can be understood as semantically related information parameters used by the sending end 102 in the process of semantically encoding the source data.

[0380] In some embodiments, the receiving end 101 sends a second indication information to the sending end 102. The second indication information is used to request the sending end 102 to send semantically related information parameters of semantic encoding to the receiving end 101. The receiving end 101 determines the cause and / or operation of poor semantic performance based on the semantically related information parameters of semantic encoding and semantic decoding, and then takes corresponding semantic data recovery and error correction mechanisms.

[0381] In some embodiments, the semantic data recovery and error correction mechanism may include, for example, the receiver 101 updating the decoding-related parameters or the receiver 101 sending a first indication message to the sender 102. The specific implementation process will be described in detail in subsequent embodiments.

[0382] Step S2107: Receiver 101 updates semantic decoding related parameters.

[0383] In some embodiments, the semantic decoding related parameters include at least one of a semantic decoding model, a semantic reasoning model, and a semantic knowledge base.

[0384] In some embodiments, updating decoding-related parameters can be understood as decoder reconstruction.

[0385] In some embodiments, decoder refactoring includes reselecting or updating at least one of the semantic decoding model, semantic reasoning model, and semantic knowledge base.

[0386] For example, if the semantic similarity is low, it may be because the current semantic decoding model or semantic knowledge base is not suitable for the current communication scenario. The receiver 101 can try to reselect or update the semantic decoding model or update the semantic knowledge base to add more semantic information.

[0387] Step S2108: Receiver 101 sends the first semantic related parameter information to sender 102.

[0388] In some embodiments, the first semantic related parameter information includes semantic related parameters used by the receiver 101 to decode the first semantic data.

[0389] In some embodiments, the first semantically related parameter information includes at least one of the following:

[0390] a) Semantic knowledge base information; for example, the semantic knowledge base applied to the receiver 101, the semantic knowledge base version, etc.

[0391] b) Semantic context information; for example, contextual information and historical semantic information when the receiver 101 decodes the first semantic data.

[0392] For example, the contextual information is the background information (such as the time of reception, location, and identity of the receiver) when the receiver 101 decodes the first semantic data.

[0393] For example, historical semantic information is a record of historical semantic interactions between receiver 101 and sender 102. Receiver 101 can infer the semantics of the current information based on the historical semantic information.

[0394] c) Semantic modality information; for example, the modality of the first semantic data sent by the sender 102 is an image, text, etc.

[0395] d) Semantic importance information.

[0396] In some embodiments, the receiving end 101 sends first semantic related parameter information to the sending end 102, enabling the sending end 102 to determine the semantic knowledge base information, semantic context information (including contextual information, historical semantic information, etc.), semantic modality information, semantic importance information, etc. used by the receiving end 101, thereby assisting the sending end 102 in determining the cause of poor semantic performance based on the above information, and thus taking corresponding semantic data recovery and error correction mechanisms.

[0397] Step S2109: Receiver 101 sends first indication information to sender 102.

[0398] In some embodiments, the first indication information is used to instruct the sending end 102 to send second semantic data.

[0399] In some embodiments, the second semantic data is the same as or related to the first semantic data.

[0400] In some embodiments, the first indication information carries at least one of the following:

[0401] The third indication information indicates the reason why the sending end 102 sends the second semantic data; including the reason why the sending end 102 needs to resend the second semantic data; such as poor channel quality, low semantic similarity, etc.

[0402] The fourth indication information indicates the method by which the sending end 102 sends the second semantic data; including the method by which the sending end 102 sends the second semantic data; such as falling back to the traditional communication method, dynamically adjusting the transmission parameters, adding redundant information, processing based on the channel retransmission mechanism, etc.; wherein, the channel retransmission mechanism is, for example, Automatic Repeat reQuest (ARQ).

[0403] In some embodiments, the name of the third indication information is not limited, and may be, for example, retransmission reason information, semantic data transmission reason information, etc.

[0404] In some embodiments, the name of the fourth indication information is not limited, and may be, for example, retransmission mode information, semantic data transmission mode information, etc.

[0405] In some embodiments, the third instruction information includes at least one of the following:

[0406] a) Second information, used to indicate channel quality information; for example, poor channel quality.

[0407] b) Third information, used to indicate semantic similarity information; for example, low semantic similarity.

[0408] c) The fourth piece of information is used to indicate the degree of task completion; for example, the degree of task completion is low.

[0409] d) The fifth piece of information is used to indicate the monitoring results of semantic communication performance; for example, the monitoring result of semantic communication performance is that the semantic communication performance does not meet the standard.

[0410] In some embodiments, the fourth instruction information includes at least one of the following:

[0411] a) The sixth information is used to instruct the transmitter 102 to send the second semantic data based on the channel retransmission mechanism;

[0412] For example, if the receiver 101 determines that the channel decoding is incorrect, it will directly discard the data without performing semantic decoding and instruct the sender 102 to send second semantic data based on a channel retransmission mechanism (such as ARQ).

[0413] b) The seventh message, used to instruct the sender 102 to send the second semantic data through non-semantic communication;

[0414] In some embodiments, sending second semantic data through non-semantic communication can be understood as reverting to traditional communication methods for data transmission.

[0415] c) The eighth information is used to instruct the sender to send the second semantic data based on the adjusted transmission parameters; the adjusted transmission parameters are obtained by the sender 102 after adjusting the channel conditions and network environment during the semantic communication process.

[0416] For example, the transmitter 102 dynamically adjusts transmission parameters, such as transmission power, modulation scheme, and coding rate, based on at least one of the channel conditions and network environment to optimize the transmission quality of information. Then, it transmits second semantic data based on the dynamically adjusted transmission parameters.

[0417] d) Ninth information, used to instruct the sender 102 to send the second semantic data and the semantic redundancy data associated with the second semantic data.

[0418] In some embodiments, semantically redundant data is used to improve decoding reliability.

[0419] In some embodiments, the second semantic data includes at least one of the following:

[0420] a) First semantic data;

[0421] b) The source data for the first semantic data;

[0422] c) Semantic redundancy data;

[0423] d) Third semantic data; the third semantic data is related to the transmission parameters of the first semantic data.

[0424] In some embodiments, the third semantic data includes transmission parameters when the sender 102 sends the first semantic data.

[0425] In some embodiments, when transmitting first semantic data to the receiving end, the transmitting end 102 dynamically adjusts transmission parameters, such as transmission power, modulation method and coding rate, according to channel conditions and network environment to optimize the transmission quality of the first semantic data.

[0426] In some embodiments, semantically redundant data includes at least one of the following:

[0427] a) Semantic knowledge base information.

[0428] In some embodiments, semantic redundancy data includes semantic knowledge base information, which means: instructing the sending end 102 to add semantic knowledge base information as redundant information, such as a knowledge base version.

[0429] b) Contextual information.

[0430] In some embodiments, semantic redundancy data includes contextual information, meaning that the sender 102 is instructed to add contextual information as redundant information. For example, during the encoding stage, background information of the first semantic data (such as sending time, location, and sender identity) is encoded together. In this way, the receiver 101 can use this background information during decoding to help infer more accurate semantic information.

[0431] c) Multimodal information.

[0432] In some embodiments, semantic redundancy data includes multimodal information, meaning that the transmitter 102 is instructed to add multimodal information as semantic redundancy data. For example, image features can be embedded in text information, or text features can be embedded in image information, to help the receiver 101 perform error correction during decoding.

[0433] d) Fourth semantic data, the semantic similarity between the fourth semantic data and the first semantic data reaches the third threshold.

[0434] In some embodiments, semantic redundancy data includes fourth semantic data, which means: instructing the sending end 102 to add multiple pieces of information with semantic similarity within a certain threshold (i.e., fourth semantic data whose semantic similarity with the first semantic data reaches a third threshold) as semantic redundancy data.

[0435] For example, if a word has multiple synonyms, these synonyms can be selected as semantic redundancy data during encoding to help the receiver correct errors during decoding.

[0436] For example, if the first semantic data is "a fire has occurred", then the fourth semantic data can be "a fire has broken out".

[0437] In some embodiments, the semantic similarity between the fourth semantic data and the first semantic data is higher than a third threshold.

[0438] In some embodiments, the semantic similarity between the fourth semantic data and the first semantic data is greater than or equal to a third threshold.

[0439] In some embodiments, the semantic similarity between the fourth semantic data and the first semantic data is greater than a third threshold.

[0440] In some embodiments, the semantic similarity between the fourth semantic data and the first semantic data is not less than a third threshold.

[0441] In some embodiments, the third threshold is determined by at least one of the following parameters:

[0442] The semantic features of the first semantic data;

[0443] The network environment during semantic communication;

[0444] Application requirements;

[0445] Semantic device capability, where a semantic device includes at least one of the following: the transmitter 102, the receiver 101, and a network device. A network device can be understood as a semantic network device.

[0446] In some embodiments, the third threshold can be flexibly configured through protocol agreement or network signaling configuration.

[0447] In some embodiments, the third threshold may be predefined by the protocol, configured by the network, or determined autonomously by the semantic receiver or the semantic sender.

[0448] e) Historical information, used to indicate the historical interaction records between the sender 102 and the receiver 101.

[0449] In some embodiments, semantic redundancy data includes historical information, which means that the sending end 102 is instructed to add historical information as semantic redundancy data.

[0450] In some embodiments, receiver 101 instructs sender 102 to predict the possible content of the current information using historical interaction records. For example, in a dialogue system, the semantics of the current information can be inferred from previous dialogue content.

[0451] In some embodiments, the transmitter 102 adds semantic redundancy data based on the first indication information during retransmission encoding.

[0452] In some embodiments, the sending end 102 autonomously adds semantic redundancy data during the initial transmission.

[0453] In some embodiments, the sender 102 adds semantically redundant data based on a request from the receiver 101 or other network devices.

[0454] In some embodiments, the order of steps S2105, S2107 and S2108 can be interchanged, they can be executed simultaneously, or only one of the steps can be executed.

[0455] Step S2110: The sending end 102 sends the second semantic data to the receiving end 101.

[0456] In some embodiments, after receiving the first indication information sent by the receiver 101, the sender 102 sends the second semantic data to the receiver 101.

[0457] In some embodiments, after receiving the first indication information sent by the receiver 101, the sender 102 sends the second semantic data to the receiver 101 based on the first semantic related parameter information.

[0458] In some embodiments, the names of information, etc., are not limited to the names described in the embodiments. Terms such as "information", "message", "signal", "signaling", "report", "configuration", "indication", "instruction", "command", "channel", "parameter", "domain", "field", "symbol", "symbol", "codebook", "codeword", "codepoint", "bit", "data", "program", and "chip" can be used interchangeably.

[0459] In some embodiments, the terms "uplink", "uplink", and "physical uplink" can be used interchangeably, as can the terms "downlink", "downlink", and "physical downlink", as well as the terms "sidelink", "sidelink", "sidelink communication", "sidelink communication", "direct connection", "direct link", "direct communication", and "direct link communication".

[0460] In some embodiments, terms such as "physical downlink shared channel (PDSCH)" and "DL data" can be used interchangeably, as can terms such as "physical uplink shared channel (PUSCH)" and "UL data".

[0461] In some embodiments, the terms “radio”, “wireless”, “radio access network (RAN)”, “access network (AN)”, and “RAN-based” can be used interchangeably.

[0462] In some embodiments, terms such as wireless access scheme and waveform can be used interchangeably.

[0463] In some embodiments, the terms "precoding", "precoder", "weight", "precoding weight", "quasi-co-location (QCL)", "transmission configuration indication (TCI) status", "spatial relation", "spatial domain filter", "transmission power", "phase rotation", "antenna port", "antenna port group", "layer", "the number of layers", "rank", "resource", "resource set", "resource group", "beam", "beam width", "beam angle", "antenna", "antenna element", and "panel" can be used interchangeably.

[0464] In some embodiments, "acquire," "get," "obtain," "receive," "transmit," "bidirectional transmission," and "send and / or receive" can be used interchangeably and can be interpreted as receiving from other entities, acquiring from protocols, acquiring from higher layers, obtaining through self-processing, or autonomous implementation. Protocols include, for example, at least one of the 3GPP protocol, Wi-Fi protocol, and audio and / or video protocols.

[0465] In some embodiments, terms such as “send,” “transmit,” “report,” “distribute,” “transfer,” “bidirectional transmission,” “send and / or receive” can be used interchangeably.

[0466] In some embodiments, terms such as "certain," "preset," "default," "set," "indicated," "a certain," "any," and "first" can be used interchangeably. "Certain A," "preset A," "default A," "set A," "indicated A," "a certain A," "any A," and "first A" can be interpreted as A pre-defined in a protocol or the like, or as A obtained through setting, configuration, or instruction, or as specific A, a certain A, any A, or first A, but are not limited thereto.

[0467] In some embodiments, the determination or judgment can be made by a value represented by 1 bit (0 or 1), or by a true or false value (boolean), or by a comparison of numerical values ​​(e.g., a comparison with a predetermined value), but is not limited thereto.

[0468] In some embodiments, if an arrow in the interaction diagram representing the sending of information, signaling, etc. from one subject to another passes through other subjects, it can be interpreted as the information being forwarded from one subject to another via other subjects, or it can be interpreted as the information being sent from one subject to another without passing through other subjects.

[0469] The communication method involved in the embodiments of this disclosure may include at least one of steps S2101 to S2110. For example, step S2103 may be implemented as an independent embodiment, steps S2105 and S2106 may be implemented as independent embodiments, step S2107 may be implemented as an independent embodiment, steps S2108, S2109 and S2110 may be implemented as independent embodiments, and steps S2101, S2102, S2103, S2107, S2108, S2109 and S2110 may be implemented as independent embodiments, but are not limited thereto.

[0470] In some embodiments, steps S2105-S2106, S2107, S2108, S2109, and S2110 may be performed in different orders or simultaneously.

[0471] In some embodiments, steps S2101, S2104, S2105, S2106, S2107, S2108, S2109, and S2110 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0472] In some embodiments, steps S2101, S2102, S2103, S2104, S2105, and S2106 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0473] In some embodiments, steps S2101, S2102, S2103, S2104, S2105, S2106, and S2107 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0474] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0475] Figure 2B is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure, the method including:

[0476] Step S2201: The sending end 102 sends the first semantic data and the semantic verification information corresponding to the first semantic data to the receiving end 101.

[0477] In some embodiments, the receiving end 101 receives the first semantic data and semantic verification information sent by the sending end 102, but is not limited thereto. The receiving end 101 may also receive the first semantic data and semantic verification information sent by other subjects, in which case step S2201 can be omitted.

[0478] In some embodiments, the receiving end 101 obtains the first semantic data and semantic verification information specified by the protocol, in which case step S2201 can be omitted.

[0479] In some embodiments, the receiving end 101 obtains the first semantic data and semantic verification information from the upper layer(s), in which case step S2201 can be omitted.

[0480] In some embodiments, the receiving end 101 processes the data to obtain the first semantic data and semantic verification information, in which case step S2201 can be omitted.

[0481] In some embodiments, the receiving end 101 autonomously implements the functions indicated by the first semantic data and semantic verification information, or the above functions are default or default, in which case step S2201 can be omitted.

[0482] In some embodiments, the receiving end 101 can obtain the first semantic data and semantic verification information from at least one of the NAS message, AS message, and application layer message sent by the sending end 102.

[0483] In some embodiments, the first semantic data and semantic verification information are used to monitor the performance of semantic communication.

[0484] In some embodiments, the first semantic data and semantic verification information are used by the receiver 101 to monitor the semantic communication performance.

[0485] In some embodiments, the sending end 102 sends first semantic data and semantic verification information to the receiving end 101. The receiving end 101 monitors the semantic communication performance based on the first semantic data and semantic verification information.

[0486] In some embodiments, the sending end 102 periodically or non-periodically sends semantic verification information to the receiving end 101.

[0487] In some embodiments, the sender 102 sends semantic verification information to the receiver 101 based on a request from the receiver 101.

[0488] In some embodiments, the sending end 102 determines to send semantic verification information to the receiving end 101 based on implementation. For example, the sending end 102 sends semantic verification information to the receiving end 101 based on configuration parameters.

[0489] In some embodiments, the receiver 101 may directly receive the first semantic data sent by the sender 102 during semantic communication.

[0490] In some embodiments, the sending end 102 transmits the first semantic data and semantic verification information to the receiving end 101 in two separate signaling messages.

[0491] In some embodiments, the sending end 102 places the semantic verification information after the first semantic data and carries it together in a single signaling message to the receiving end 101.

[0492] In some embodiments, the sending end 102 carries semantic verification information and first semantic data together in a single signaling and sends it to the receiving end 101.

[0493] The optional implementation of step S2201 can be found in the optional implementation of step S2101 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0494] Step S2202: The receiving end 101 determines the semantic similarity between the first semantic data and the source data based on the first semantic data and semantic verification information.

[0495] In some embodiments, after receiving the first semantic data, the receiving end 101 needs to perform decoding (e.g., channel decoding, semantic decoding) and semantic reasoning on the first semantic data.

[0496] In some embodiments, the result of channel decoding of the first semantic data by the receiver 101 does not affect the accuracy of semantic decoding. The receiver 101 directly determines the semantic similarity based on the first semantic data and semantic verification information.

[0497] In some embodiments, the result of channel decoding of the first semantic data by the receiver 101 can affect the accuracy of semantic decoding. Therefore, the receiver 101 determines the semantic similarity based on the first semantic data and semantic verification information only after the channel decoding of the first semantic data is successful.

[0498] In some embodiments, the receiving end 101 determines the semantic similarity based on the first semantic data and semantic verification information, which can be achieved in the following ways:

[0499] Step 1: Receiver 101 performs semantic decoding on the first semantic data;

[0500] Step 2: The receiver 101 uses semantic verification information to perform semantic verification on the first semantic data after decoding, and determines the semantic similarity based on the verification result.

[0501] In some embodiments, semantic verification information may be, for example, a shared knowledge graph or a semantic encoding vector corresponding to the source data.

[0502] For example, the receiver 101 verifies the logical correctness of the first semantic data after semantic decoding and the source data based on the shared knowledge graph, thereby determining the semantic similarity between the first semantic data after semantic decoding and the source data.

[0503] For example, the receiving end performs a cosine similarity comparison between the encoded vector of the first semantic data after semantic decoding and the semantic encoded vector of the source data to obtain the semantic similarity between the first semantic data after semantic decoding and the source data.

[0504] The optional implementation of step S2202 can be found in the optional implementation of step S2102 in Figure 2A and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0505] Step S2203: The receiving end 101 monitors the semantic communication performance based on semantic similarity.

[0506] The optional implementation of step S2203 can be found in the optional implementation of step S2103 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0507] Step S2204: Semantic communication performance is substandard, and receiver 101 discards the first semantic data.

[0508] The optional implementation of step S2204 can be found in the optional implementation of step S2104 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0509] Step S2205: Receiver 101 sends second indication information to sender 102.

[0510] The optional implementation of step S2205 can be found in the optional implementation of step S2105 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0511] Step S2206: The sending end 102 sends the second semantic related parameter information to the receiving end 101.

[0512] The optional implementation of step S2206 can be found in the optional implementation of step S2105 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0513] Step S2207: Receiver 101 updates semantic decoding related parameters.

[0514] The optional implementation of step S2207 can be found in the optional implementation of step S2107 in Figure 2A and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0515] Step S2208: Receiver 101 sends the first semantic related parameter information to sender 102.

[0516] The optional implementation of step S2208 can be found in the optional implementation of step S2108 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0517] Step S2209: Receiver 101 sends first indication information to sender 102.

[0518] The optional implementation of step S2209 can be found in the optional implementation of step S2109 in Figure 2A and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0519] Step S2210: The sending end 102 sends the second semantic data to the receiving end 101.

[0520] The optional implementation of step S2210 can be found in the optional implementation of step S2110 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0521] The communication method involved in the embodiments of this disclosure may include at least one of steps S2201 to S2210. For example, step S2203 may be implemented as an independent embodiment, steps S2205 and S2206 may be implemented as independent embodiments, step S2207 may be implemented as an independent embodiment, steps S2208, S2209 and S2210 may be implemented as independent embodiments, and steps S2201, S2202, S2203, S2207, S2208, S2209 and S2210 may be implemented as independent embodiments, but are not limited thereto.

[0522] In some embodiments, steps S2205-S2206, S2207, S2208, S2209, and S2210 may be performed in different orders or simultaneously.

[0523] In some embodiments, steps S2201, S2204, S2205, S2206, S2207, S2208, S2209, and S2210 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0524] In some embodiments, steps S2201, S2202, S2203, S2204, S2205, and S2206 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0525] In some embodiments, steps S2201, S2202, S2203, S2204, S2205, S2206, and S2207 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0526] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0527] Figure 2C is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure, which may include:

[0528] Step S2301: The sending end 102 sends the first semantic data and the semantic task information corresponding to the first semantic data to the receiving end 101.

[0529] In some embodiments, the receiving end 101 receives the first semantic data and semantic task information sent by the sending end 102, but is not limited thereto. The receiving end 101 may also receive the first semantic data and semantic task information sent by other subjects, in which case step S2301 can be omitted.

[0530] In some embodiments, the receiving end 101 obtains the first semantic data and semantic task information specified by the protocol, in which case step S2301 can be omitted.

[0531] In some embodiments, the receiving end 101 obtains the first semantic data and semantic task information from the upper layer(s), in which case step S2301 can be omitted.

[0532] In some embodiments, the receiving end 101 processes the data to obtain the first semantic data and semantic task information, in which case step S2301 can be omitted.

[0533] In some embodiments, the receiving end 101 autonomously implements the functions indicated by the first semantic data and semantic task information, or the above functions are default or default, in which case step S2301 can be omitted.

[0534] In some embodiments, the receiving end 101 can obtain the first semantic data and semantic task information from at least one of the NAS message, AS message, and application layer message sent by the sending end 102.

[0535] In some embodiments, the first semantic data and semantic task information are used to monitor the performance of semantic communication.

[0536] In some embodiments, the first semantic data and semantic task information are used by the receiver 101 to monitor the semantic communication performance.

[0537] In some embodiments, the sending end 102 sends first semantic data and semantic task information to the receiving end 101. The receiving end 101 monitors the semantic communication performance based on the first semantic data and semantic task information.

[0538] In some embodiments, the sending end 102 periodically or non-periodically sends semantic task information to the receiving end 101.

[0539] In some embodiments, the sender 102 sends semantic task information to the receiver 101 based on a request from the receiver 101.

[0540] In some embodiments, the sending end 102 determines to send semantic task information to the receiving end 101 based on implementation. For example, the sending end 102 sends semantic task information to the receiving end 101 based on configuration parameters.

[0541] In some embodiments, the sending end 102 transmits the first semantic data and semantic task information to the receiving end 101 in two separate signaling messages.

[0542] In some embodiments, the sending end 102 places the semantic task information after the first semantic data and carries it together in a single signaling message to the receiving end 101.

[0543] In some embodiments, the sending end 102 transmits semantic task information and first semantic data together in a single signaling to the receiving end 101.

[0544] The optional implementation of step S2201 can be found in the optional implementation of step S2101 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0545] Step S2302: The receiving end 101 determines the task completion degree of the task corresponding to the first semantic data based on the first semantic data and semantic task information.

[0546] In some embodiments, after receiving the first semantic data, the receiving end 101 needs to perform decoding (e.g., channel decoding, semantic decoding) and semantic reasoning on the first semantic data.

[0547] In some embodiments, the result of channel decoding of the first semantic data by the receiver 101 does not affect the accuracy of semantic decoding. The receiver 101 directly determines the task completion rate based on the first semantic data and semantic task information.

[0548] In some embodiments, the result of channel decoding of the first semantic data by the receiver 101 can affect the accuracy of semantic decoding. Therefore, the receiver 101 only monitors the semantic communication performance based on the first semantic data and semantic task information after successful channel decoding of the first semantic data.

[0549] In some embodiments, the receiving end 101 determines the task completion degree based on the first semantic data and semantic task information, which can be achieved in the following ways:

[0550] Step 1: Receiver 101 performs semantic decoding on the first semantic data;

[0551] Step 2: The receiving end 101 executes the semantic task information corresponding to the first semantic data after semantic decoding processing to obtain the task completion status.

[0552] Step 3: Compare the task completion status with the semantic task information to determine the task completion rate.

[0553] Step S2303: The receiving end 101 monitors the semantic communication performance based on the task completion degree.

[0554] In some embodiments, if the task completion rate is lower than the second threshold, the receiver 101 determines that the monitoring result of semantic communication performance is that the semantic communication performance is substandard.

[0555] In some embodiments, if the task completion rate is not higher than the second threshold, the receiver 101 determines that the monitoring result of semantic communication performance is that the semantic communication performance is substandard.

[0556] In some embodiments, if the task completion rate is less than the second threshold, the receiver 101 determines that the monitoring result of semantic communication performance is that the semantic communication performance is substandard.

[0557] In some embodiments, if the task completion rate is not greater than the second threshold, the receiver 101 determines that the monitoring result of semantic communication performance is that the semantic communication performance is substandard.

[0558] In some embodiments, if the task completion rate is greater than or equal to the second threshold, the receiver 101 determines that the monitoring result of the semantic communication performance is satisfactory.

[0559] In some embodiments, if the task completion rate is greater than the second threshold, the receiver 101 determines that the monitoring result of semantic communication performance is that the semantic communication performance meets the standard.

[0560] In some embodiments, if the task completion rate is higher than the second threshold, the receiver 101 determines that the monitoring result of semantic communication performance is satisfactory.

[0561] In some embodiments, if the task completion rate is not less than the second threshold, the receiver 101 determines that the monitoring result of the semantic communication performance is that the semantic communication performance meets the standard.

[0562] In some embodiments, channel decoding errors may not affect the accuracy of semantic decoding. The receiver 101 directly determines, based on the results of the source-channel joint semantic decoder, that semantic communication performance is poor only when the task completion degree is lower than the second threshold, or the task completion degree is not higher than the second threshold, or the task completion degree is less than the second threshold, or the task completion degree is not greater than the second threshold; and determines that semantic communication performance meets the standard only when the task completion degree is greater than or equal to the second threshold, or the task completion degree is greater than the second threshold, or the task completion degree is higher than the second threshold, or the task completion degree is not less than the second threshold.

[0563] In some embodiments, the receiver 101 performs semantic decoding only when the channel decoding is correct, and determines that the semantic communication performance is poor only when the task completion rate is lower than a second threshold based on the semantic decoding result.

[0564] In some embodiments, the second threshold is determined by at least one of the following parameters:

[0565] a) Semantic features of the first semantic data; for example, the type, importance, and completeness of the first semantic data.

[0566] b) The network environment during semantic communication; for example, channel quality, load, etc.

[0567] c) Application requirements; for example, latency, security, etc.

[0568] d) Semantic device capabilities, whereby a semantic device includes at least one of the following: the transmitter 102, the receiver 101, and a network device. A network device can be understood as a semantic network device.

[0569] In some embodiments, the second threshold can be flexibly configured through protocol agreement or network signaling configuration.

[0570] In some embodiments, the second threshold may be predefined by the protocol, configured by the network, or determined autonomously by the receiver or the sender.

[0571] Step S2304: Semantic communication performance is substandard, and receiver 101 discards the first semantic data.

[0572] The optional implementation of step S2304 can be found in the optional implementation of step S2104 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0573] Step S2305: Receiver 101 sends second indication information to sender 102.

[0574] The optional implementation of step S2305 can be found in the optional implementation of step S2105 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0575] Step S2306: The sending end 102 sends the second semantic related parameter information to the receiving end 101.

[0576] The optional implementation of step S2306 can be found in the optional implementation of step S2106 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0577] Step S2307: Receiver 101 updates semantic decoding related parameters.

[0578] For example, if the task completion rate is low, it may be due to an imperfect semantic reasoning model. Receiver 101 can try to reselect or update the semantic reasoning model.

[0579] The optional implementation of step S2307 can be found in the optional implementation of step S2107 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0580] Step S2308: Receiver 101 sends the first semantic related parameter information to sender 102.

[0581] The optional implementation of step S2308 can be found in the optional implementation of step S2108 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0582] Step S2309: Receiver 101 sends first indication information to sender 102.

[0583] The optional implementation of step S2309 can be found in the optional implementation of step S2109 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0584] Step S2310: The sending end 102 sends the second semantic data to the receiving end 101.

[0585] The optional implementation of step S2310 can be found in the optional implementation of step S2110 in Figure 2A, and other related parts in the embodiments involved in Figure 2A, which will not be repeated here.

[0586] The communication method involved in the embodiments of this disclosure may include at least one of steps S2301 to S2310. For example, step S2303 may be implemented as an independent embodiment, steps S2305 and S2306 may be implemented as independent embodiments, step S2307 may be implemented as an independent embodiment, steps S2308, S2309 and S2310 may be implemented as independent embodiments, and steps S2301, S2302, S2303, S2307, S2308, S2309 and S2310 may be implemented as independent embodiments, but are not limited thereto.

[0587] In some embodiments, steps S2305-S2306, S2307, S2308, S2309, and S2310 may be performed in different orders or simultaneously.

[0588] In some embodiments, steps S2301, S2304, S2305, S2306, S2307, S2308, S2309, and S2310 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0589] In some embodiments, steps S2301, S2302, S2303, S2304, S2305, and S2306 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0590] In some embodiments, steps S2301, S2302, S2303, S2304, S2305, S2306, and S2307 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0591] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0592] Figure 2D is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure, which may include:

[0593] Step S2401: The sending end 102 sends the first information to the receiving end 101.

[0594] In some embodiments, the receiving end 101 receives the first information sent by the sending end 102, but is not limited thereto. The receiving end 101 may also receive the first information sent by other entities, in which case step S2401 can be omitted.

[0595] In some embodiments, the receiving end 101 obtains the first information specified by the protocol, in which case step S2401 can be omitted.

[0596] In some embodiments, the receiving end 101 obtains the first information from the upper layer(s), in which case step S2401 can be omitted.

[0597] In some embodiments, the receiving end 101 processes the information to obtain the first information, in which case step S2401 can be omitted.

[0598] In some embodiments, the receiving end 101 autonomously implements the function indicated by the first information, or the above function is a default or default value, in which case step S2401 can be omitted.

[0599] In some embodiments, the receiving end 101 can obtain the first information from at least one of the NAS message, AS message, and application layer message sent by the sending end 102.

[0600] In some embodiments, the first information is semantically related information during semantic communication.

[0601] In some embodiments, the first information is used for semantic communication capability monitoring.

[0602] In some embodiments, the first information includes at least one of the following:

[0603] a) First semantic data;

[0604] b) The source data for the first semantic data;

[0605] c) Channel decoding result; The channel decoding result is obtained after the receiver 101 performs channel decoding on the first semantic data;

[0606] d) Semantic verification information corresponding to the first semantic data;

[0607] e) Semantic task information corresponding to the first semantic data;

[0608] The first semantic data is the semantic data received by the receiver 101 from the sender 102.

[0609] In some embodiments, the channel decoding result is obtained by the receiver performing channel decoding on the first semantic data.

[0610] In some embodiments, the first information may include all of the information in a) to e) above, or at least one of the information in a) to e). For example, the first information may include first semantic data and source data; for another example, the first information may include first semantic data and semantic verification information; for yet another example, the first information may include first semantic data and semantic task information; for yet another example, the first information may include channel decoding results; for yet another example, the first information may include first semantic data, source data, channel decoding results, semantic verification information, and semantic task information.

[0611] In some embodiments, the first information includes at least one of the following:

[0612] f) Semantic similarity between the first semantic data and the source data;

[0613] g) The task completion rate of the semantic task corresponding to the first semantic data;

[0614] h) The channel decoding result of the first semantic data.

[0615] In some embodiments, the first information may include all of the information in f) to h) above, or at least one of the information in f) to h). For example, the first information may include semantic similarity; for another example, the first information may include task completion degree; for yet another example, the first information may include channel decoding result; for yet another example, the first information may include semantic similarity, task completion degree, and channel decoding result.

[0616] In some embodiments, the first information may include all the information in a)-h) of the above embodiments, or it may include at least one of the information in a)-h).

[0617] In some embodiments, all the information a) to h) included in the first information can be carried in the same signaling message and sent to the receiving end 101, or they can be carried in different signaling messages and sent to the receiving end 101 respectively. For example, the receiving end 101 can obtain the first information a)-h) through the NAS message sent by the sending end 102; or, for example, the receiving end 101 can obtain the first information a)-e) through the first NAS message sent by the sending end 102, and obtain the first information f) to h) through the second NAS message sent by the sending end 102.

[0618] In some embodiments, when the first information includes at least one of the information in a) to e) above, the receiving end 101 needs to determine the semantic similarity and / or task completion degree based on the first information, and monitor the semantic communication performance based on the semantic similarity and / or task completion degree.

[0619] In some embodiments, when the first information includes at least one of the information f) to h) above, the receiving end 101 can directly monitor the semantic communication performance based on the first information.

[0620] Step S2402: The receiving end 101 monitors the semantic communication performance based on the first information.

[0621] In some embodiments, the receiver 101 monitors semantic communication performance based on the first information, including at least one of the following:

[0622] Method 1: The receiver 101 determines the semantic similarity between the first semantic data and the source data based on the first information; and monitors the semantic communication performance based on the semantic similarity.

[0623] Method 2: The receiving end 101 determines the task completion degree of the task corresponding to the first semantic data based on the first information; and monitors the semantic communication performance based on the task completion degree.

[0624] In some embodiments, Method 1 and Method 2 can be executed simultaneously or separately; when executed separately, the execution order is not limited. Simultaneous execution of Method 1 and Method 2 means that the receiving end 101 simultaneously determines the semantic similarity and task completion degree, and monitors the semantic communication performance based on these two factors. Separate execution of Method 1 and Method 2 means that the receiving end 101 can monitor the semantic communication performance based solely on either semantic similarity or task completion degree.

[0625] In some embodiments, the receiver 101 can monitor semantic communication performance in different ways based on different information carried by the first information. See methods a-i below for details:

[0626] Method a: If the first information includes at least first semantic data and source data, the receiving end 101 determines the semantic similarity between the first semantic data and the source data based on the first semantic data and the source data; and monitors the semantic communication performance based on the semantic similarity. For specific implementation methods, please refer to steps S2102 to S2103 in Figure 2A.

[0627] Method b: If the first information includes at least the first semantic data, the source data, and the channel decoding result, the receiver 101, upon determining that the channel decoding was successful based on the channel decoding result, determines the semantic similarity between the first semantic data and the source data; and monitors the semantic communication performance based on the semantic similarity. For specific implementation details, please refer to steps S2102 to S2103 in Figure 2A.

[0628] Method c: If the first information includes at least first semantic data and semantic verification information, the receiving end 101 determines the semantic similarity between the first semantic data and the source data based on the first semantic data and semantic verification information; and monitors the semantic communication performance based on the semantic similarity. For specific implementation details, please refer to steps S2202 to S2203 in Figure 2B.

[0629] Method d: If the first information includes at least first semantic data, semantic verification information, and channel decoding result, the receiver 101, upon determining that the channel decoding was successful based on the channel decoding result, determines the semantic similarity between the first semantic data and the source data based on the first semantic data and the semantic verification information; and monitors the semantic communication performance based on the semantic similarity. For specific implementation details, please refer to steps S2202 to S2203 in Figure 2B.

[0630] Method e: If the first information includes at least first semantic data and channel decoding results, the receiver 101, upon confirming successful channel decoding based on the channel decoding results, determines semantic similarity based on the first semantic data; and monitors semantic communication performance based on the semantic similarity. For specific implementation details, please refer to steps S2102 to S2103 in Figure 2A. The terminal 101 can rely on an AI algorithm to determine semantic similarity based on the first semantic data and channel decoding results, and monitor semantic communication performance based on the semantic similarity.

[0631] Method f: If the first information includes at least first semantic data, the receiving end 101 determines the semantic similarity based on the first semantic data; and monitors the semantic communication performance based on the semantic similarity. For specific implementation details, please refer to steps S2202 to S2203 in Figure 2B. The terminal 101 may rely on an AI algorithm to determine the semantic similarity based on the first semantic data and monitor the semantic communication performance based on the semantic similarity.

[0632] In some embodiments, the above methods a to d can be understood as different implementations of method 1, namely: the receiving end determines the semantic similarity between the first semantic data and the source data based on the first information; and monitors the semantic communication performance based on the semantic similarity.

[0633] Method g: If the first information includes at least first semantic data and semantic task information, the receiving end 101 determines the task completion degree corresponding to the first semantic data based on the first semantic data and semantic task information; and monitors the semantic communication performance based on the task completion degree. For specific implementation details, please refer to steps S2302 to S2303 in Figure 2C.

[0634] In method h, if the first information includes at least first semantic data, semantic task information, and channel decoding result, the receiver 101, upon determining that the channel decoding was successful based on the channel decoding result, determines the task completion degree corresponding to the first semantic data based on the first semantic data and the semantic task information; and monitors the semantic communication performance based on the task completion degree. For specific implementation details, please refer to steps S2302 to S2303 in Figure 2C.

[0635] Method i: If the first information includes at least first semantic data and channel decoding results, the receiver 101, upon confirming successful channel decoding based on the channel decoding results, determines the task completion degree based on the first semantic data; and monitors semantic communication performance based on the task completion degree. For specific implementation details, please refer to steps S2302 to S2303 in Figure 2C. The terminal 101 can rely on an AI algorithm to determine the task completion degree based on the first semantic data and channel decoding results, and monitor semantic communication performance based on the task completion degree.

[0636] Method j: If the first information includes at least first semantic data, the receiving end 101 determines the task completion degree based on the first semantic data; and monitors the semantic communication performance based on the task completion degree. For specific implementation details, please refer to steps S2302 to S2303 in Figure 2C. The terminal 101 can rely on an AI algorithm to determine the task completion degree based on the first semantic data and monitor the semantic communication performance based on the task completion degree.

[0637] In some embodiments, the above methods g to j can be understood as different implementations of method 2, namely: the receiving end 101 determines the task completion degree of the task corresponding to the first semantic data based on the first information; and monitors the semantic communication performance based on the task completion degree.

[0638] Method k: If the first information includes at least the semantic similarity between the first semantic data and the source data, the receiver 101 directly monitors the semantic communication performance based on the semantic similarity.

[0639] Method 1: If the first information includes at least the task completion degree of the semantic task corresponding to the first semantic data, the receiving end 101 directly monitors the semantic communication performance based on the task completion degree.

[0640] In mode m, if the first information includes at least the channel decoding result of the first semantic data, the receiver 101 directly monitors the semantic communication performance based on the channel decoding result.

[0641] In some embodiments, the above methods k to m can be understood as: the receiver 101 monitors the semantic communication performance based on at least one of the semantic similarity, task completion degree and channel decoding result in the first information.

[0642] In some embodiments, in methods a-m above, the receiving end 101 monitors the semantic communication performance based on the first information, which can be achieved by at least one of the following:

[0643] In some embodiments, if the semantic similarity is lower than a first threshold, the receiver 101 determines that the monitoring result of semantic communication performance is substandard.

[0644] In some embodiments, if the semantic similarity is not higher than a first threshold, the receiver 101 determines that the monitoring result of semantic communication performance is that the semantic communication performance is substandard.

[0645] In some embodiments, if the semantic similarity is less than a first threshold, the receiver 101 determines that the monitoring result of semantic communication performance is that the semantic communication performance is substandard.

[0646] In some embodiments, if the semantic similarity is not greater than a first threshold, the receiver 101 determines that the monitoring result of the semantic communication performance is that the semantic communication performance is substandard.

[0647] In some embodiments, if the semantic similarity is greater than or equal to a first threshold, the receiver 101 determines that the monitoring result of the semantic communication performance is satisfactory.

[0648] In some embodiments, if the semantic similarity is greater than a first threshold, the receiver 101 determines that the monitoring result of the semantic communication performance is satisfactory.

[0649] In some embodiments, if the semantic similarity is higher than a first threshold, the receiver 101 determines that the monitoring result of the semantic communication performance is satisfactory.

[0650] In some embodiments, if the semantic similarity is not less than a first threshold, the receiver 101 determines that the monitoring result of the semantic communication performance is satisfactory.

[0651] In some embodiments, if the task completion rate of the semantic task corresponding to the first semantic data is lower than the second threshold, the receiver 101 determines that the monitored semantic communication performance is substandard.

[0652] In some embodiments, if the task completion rate is not higher than the second threshold, the receiver 101 determines that the monitoring result of semantic communication performance is that the semantic communication performance is substandard.

[0653] In some embodiments, if the task completion rate is less than the second threshold, the receiver 101 determines that the monitoring result of semantic communication performance is that the semantic communication performance is substandard.

[0654] In some embodiments, if the task completion rate is not greater than the second threshold, the receiver 101 determines that the monitoring result of semantic communication performance is that the semantic communication performance is substandard.

[0655] In some embodiments, if the task completion rate is greater than or equal to the second threshold, the receiver 101 determines that the monitoring result of the semantic communication performance is satisfactory.

[0656] In some embodiments, if the task completion rate is greater than the second threshold, the receiver 101 determines that the monitoring result of semantic communication performance is that the semantic communication performance meets the standard.

[0657] In some embodiments, if the task completion rate is higher than the second threshold, the receiver 101 determines that the monitoring result of semantic communication performance is satisfactory.

[0658] In some embodiments, if the task completion rate is not less than the second threshold, the receiver 101 determines that the monitoring result of the semantic communication performance is that the semantic communication performance meets the standard.

[0659] In some embodiments, if the semantic similarity is lower than a first threshold, or the semantic similarity is not higher than a first threshold, or the semantic similarity is less than a first threshold, or the semantic similarity is not greater than a first threshold, then the first semantic data is directly discarded.

[0660] In some embodiments, if the task completion rate is lower than the second threshold, or the task completion rate is not higher than the second threshold, or the task completion rate is less than the second threshold, or the task completion rate is not greater than the second threshold, then the first semantic data is directly discarded.

[0661] In some embodiments, the first threshold and / or the second threshold are determined by at least one of the following parameters:

[0662] a) Semantic features of the first semantic data; for example, the type, importance, and completeness of the first semantic data.

[0663] b) The network environment during semantic communication; for example, channel quality, load, etc.

[0664] c) Application requirements; for example, latency, security, etc.

[0665] d) Semantic device capabilities, whereby a semantic device includes at least one of the following: the transmitter 102, the receiver 101, and a network device. A network device can be understood as a semantic network device.

[0666] In some embodiments, the first threshold and / or the second threshold can be flexibly configured through protocol agreements or network signaling configuration.

[0667] In some embodiments, the first threshold and / or the second threshold may be predefined by the protocol, configured by the network, or determined autonomously by the receiver or the sender.

[0668] Optional implementations of step S2402 can be found in the optional implementations of steps S2102 and S2103 in Figure 2A; the optional implementations of steps S2202 and S2203 in Figure 2B; the optional implementations of steps S2302 and S2303 in Figure 2C; and other related parts in the embodiments involved in Figures 2A, 2B, and 2C, which will not be repeated here.

[0669] Step S2403: Semantic communication performance is not up to standard, receiver 101 performs the first operation.

[0670] In some embodiments, the first operation is used to improve semantic communication performance.

[0671] In some embodiments, performing the first operation includes at least one of the following:

[0672] Operation 1: Update semantic decoding related parameters; semantic decoding related parameters include at least one of the following: semantic decoding model, semantic reasoning model, and semantic knowledge base. For the specific implementation method, please refer to step S2107 in Figure 2A, which will not be repeated here.

[0673] Operation 2: Send first indication information to the sending end; the first indication information is used to instruct the sending end to send second semantic data, which is the same as or related to the first semantic data. For the specific implementation method, please refer to step S2109 in Figure 2A, which will not be described in detail here.

[0674] Operation 3: Send the first semantic related parameter information to the sending end. The first semantic related parameter information includes semantic related parameters used by the receiving end to decode the first semantic data. For the specific implementation method, please refer to step S2108 in Figure 2A, which will not be described in detail here.

[0675] Operation 4: Send second indication information to the sending end; the second indication information is used to instruct the sending end to send second semantic related parameter information, which includes semantic related parameters used by the sending end to encode the source data. For specific implementation, please refer to steps S2105 to S2106 in Figure 2A, which will not be described in detail here.

[0676] In some embodiments, operations 1-4 can be executed simultaneously or separately; when executed separately, the execution order is not limited.

[0677] For example, operations 1 and 2 can be executed simultaneously, operations 1, 2 and 3 can be executed simultaneously, and operations 1, 2, 3 and 4 can be executed simultaneously.

[0678] The optional implementations of step S2403 can be found in the optional implementations of steps S2105 to S2110 in Figure 2A; the optional implementations of steps S2205 to S2210 in Figure 2B; the optional implementations of steps S2305 to S2310 in Figure 2C; and other related parts in the embodiments involved in Figures 2A, 2B, and 2C, which will not be repeated here.

[0679] The communication method involved in the embodiments of this disclosure may include at least one of steps S2401 to S2403. For example, step S2402 may be implemented as a separate embodiment, step S2403 may be implemented as a separate embodiment, and steps S2401, S2402, and S2403 may be implemented as separate embodiments, but are not limited thereto.

[0680] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0681] Figure 2E is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure, which may include:

[0682] Step S2501: The sending end 102 sends the first information to the receiving end 101.

[0683] In some embodiments, the receiving end 101 receives the first information sent by the sending end 102, but is not limited thereto. The receiving end 101 may also receive the first information sent by other entities, in which case step S2501 can be omitted.

[0684] In some embodiments, the receiving end 101 obtains the first information specified by the protocol, in which case step S2501 can be omitted.

[0685] In some embodiments, the receiving end 101 obtains the first information from the upper layer(s), in which case step S2501 can be omitted.

[0686] In some embodiments, the receiving end 101 processes the information to obtain the first information, in which case step S2501 can be omitted.

[0687] In some embodiments, the receiving end 101 autonomously implements the function indicated by the first information, or the above function is a default or default value, in which case step S2501 can be omitted.

[0688] In some embodiments, the receiving end 101 can obtain the first information from at least one of the NAS message, AS message, and application layer message sent by the sending end 102.

[0689] The optional implementation of step S2501 can be found in step S2401 of Figure 2D, and other related parts in the embodiment involved in Figure 2D, which will not be repeated here.

[0690] Step S2502: The receiver 101 fails to decode the first semantic data channel, and determines that the semantic communication performance is substandard.

[0691] In some embodiments, the first semantic data is semantic data sent by the sender 102 to the receiver 101.

[0692] Step S2503: Receiver 101 discards the first semantic data.

[0693] In some embodiments, the receiver 101 performs semantic decoding on the first semantic data only when the channel decoding is correct, and determines that the semantic communication performance is poor only when the semantic similarity is lower than a first threshold, or the semantic similarity is not higher than the first threshold, or the semantic similarity is less than the first threshold, or the semantic similarity is not greater than the first threshold.

[0694] In some embodiments, the receiver performs semantic decoding on the first semantic data only when the channel decoding is correct, and determines, based on the semantic decoding result, that the semantic communication performance is poor only when the task completion degree is lower than the second threshold, or the task completion degree is not higher than the second threshold, or the task completion degree is less than the second threshold, or the task completion degree is not greater than the second threshold.

[0695] In some embodiments, if a channel decoding error occurs, the data is discarded without semantic decoding.

[0696] Step S2504: Receiver 101 performs the first operation.

[0697] The communication method involved in the embodiments of this disclosure may include at least one of steps S2501 to S2504. For example, step S2502 may be implemented as an independent embodiment, step S2503 may be implemented as an independent embodiment, step S2504 may be implemented as an independent embodiment, and steps S2501, S2502, S2503, and S2504 may be implemented as independent embodiments, but are not limited thereto.

[0698] In some embodiments, steps S2503 and S2504 can be performed in different orders or simultaneously.

[0699] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0700] Figure 3A is a flowchart illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 3A, the present disclosure relates to a communication method that can be executed by a receiving end. The method may include:

[0701] Step S3101: Monitor semantic communication performance based on the first information; the first information is semantic-related information during the semantic communication process.

[0702] In some embodiments, the first information includes at least one of the following:

[0703] First semantic data;

[0704] The source data for the first semantic data;

[0705] Channel decoding result; the channel decoding result is obtained by the receiving end after performing channel decoding on the first semantic data;

[0706] The semantic verification information corresponding to the first semantic data;

[0707] The semantic task information corresponding to the first semantic data;

[0708] The first semantic data is the semantic data received by the receiving end from the sending end.

[0709] In some embodiments, the monitoring of semantic communication performance based on the first information includes at least one of the following:

[0710] Based on the first information, determine the semantic similarity between the first semantic data and the source data; monitor the semantic communication performance based on the semantic similarity.

[0711] Based on the first information, determine the task completion degree of the semantic task corresponding to the first semantic data; and monitor the semantic communication performance based on the task completion degree.

[0712] In some embodiments, determining the semantic similarity between the first semantic data and the source data based on the first information includes at least one of the following:

[0713] The semantic similarity is determined based on the first semantic data in the first information and the source data in the first information;

[0714] If the channel decoding result determines that the channel decoding was successful, the semantic similarity is determined based on the first semantic data in the first information and the source data in the first information.

[0715] Based on the first semantic data in the first information and the semantic verification information in the first information, the semantic similarity is determined;

[0716] If the channel decoding result indicates that the channel decoding was successful, the semantic similarity is determined based on the first semantic data in the first information and the semantic verification information in the first information.

[0717] In some embodiments, determining the task completion degree of the semantic task corresponding to the first semantic data based on the first information includes at least one of the following:

[0718] Based on the first semantic data in the first information and the semantic task information in the first information, the task completion degree is determined;

[0719] If the channel decoding result indicates that the channel decoding was successful, the task completion degree is determined based on the first semantic data and the semantic task information in the first information.

[0720] In some embodiments, the monitoring of semantic communication performance based on the first information includes at least one of the following:

[0721] If the semantic similarity between the first semantic data and the source data is lower than a first threshold, it is determined that the monitored semantic communication performance is substandard; the semantic similarity is determined by the receiving end based on the first information.

[0722] If the task completion rate of the semantic task corresponding to the first semantic data is lower than the second threshold, it is determined that the monitored semantic communication performance is substandard; the task completion rate is determined by the receiving end based on the first information.

[0723] If the channel decoding result in the first information is a channel decoding failure, it is determined that the monitored semantic communication performance is substandard.

[0724] In some embodiments, the first threshold is determined by at least one of the following parameters:

[0725] The semantic features of the first semantic data;

[0726] The network environment during semantic communication;

[0727] Application requirements;

[0728] Semantic device capability, wherein the semantic device includes at least one of a transmitter, the receiver, and a network device;

[0729] And / or, the second threshold is determined by at least one of the following parameters:

[0730] The semantic features of the first semantic data;

[0731] The network environment during semantic communication;

[0732] Application requirements;

[0733] Semantic device capability, wherein the semantic device includes at least one of the sending end, the receiving end, and the network device.

[0734] In some embodiments, the receiving end may also perform the following steps:

[0735] If the monitored semantic communication performance fails to meet the standard, the first semantic data is discarded.

[0736] In some embodiments, before monitoring the semantic communication performance based on the first information, the receiving end may further perform the following steps:

[0737] Receive the first information sent by the sending end.

[0738] In some embodiments, the receiving end may also perform the following steps:

[0739] If the monitored semantic communication performance is substandard, a first operation is performed; the first operation is used to improve the semantic communication performance.

[0740] In some embodiments, performing the first operation includes at least one of the following:

[0741] Update semantic decoding related parameters; the semantic decoding related parameters include at least one of the following: semantic decoding model, semantic reasoning model, and semantic knowledge base;

[0742] Send a first indication message to the sending end; the first indication message is used to instruct the sending end to send second semantic data, the second semantic data being the same as or related to the first semantic data;

[0743] Send first semantic related parameter information to the sending end, the first semantic related parameter information including semantic related parameters used by the receiving end to decode the first semantic data;

[0744] Send a second indication message to the sending end; the second indication message is used to instruct the sending end to send a second semantic related parameter message, the second semantic related parameter message including semantic related parameters used by the sending end to encode the source data.

[0745] In some embodiments, the first indication information carries at least one of the following:

[0746] The third indication information indicates the reason why the sending end sends the second semantic data;

[0747] The fourth indication information indicates the manner in which the sending end transmits the second semantic data.

[0748] In some embodiments, the third indication information includes at least one of the following:

[0749] The second piece of information is used to indicate channel quality information;

[0750] The third piece of information is used to indicate semantic similarity information;

[0751] The fourth piece of information is used to indicate the progress of the task.

[0752] The fifth piece of information is used to indicate the monitoring results of the semantic communication performance.

[0753] In some embodiments, the fourth indication information includes at least one of the following:

[0754] The sixth piece of information is used to instruct the sending end to send the second semantic data based on the channel retransmission mechanism;

[0755] The seventh piece of information is used to instruct the sending end to send the second semantic data through non-semantic communication.

[0756] The eighth piece of information is used to instruct the sending end to send the second semantic data based on the adjusted transmission parameters; the adjusted transmission parameters are obtained by the sending end after adjusting them based on at least one of the channel conditions and network environment during the semantic communication process.

[0757] The ninth piece of information is used to instruct the sending end to send the second semantic data and semantic redundancy data associated with the second semantic data.

[0758] In some embodiments, the second semantic data includes at least one of the following:

[0759] First semantic data;

[0760] The source data for the first semantic data;

[0761] Semantic redundancy data;

[0762] The third semantic data; the third semantic data is related to the transmission parameters of the first semantic data.

[0763] In some embodiments, the semantically redundant data includes at least one of the following:

[0764] Semantic knowledge base information;

[0765] Contextual information;

[0766] Multimodal information;

[0767] The fourth semantic data, wherein the semantic similarity between the fourth semantic data and the first semantic data reaches a third threshold;

[0768] Historical information is used to indicate the historical interaction records between the sending end and the receiving end.

[0769] In some embodiments, the first semantically related parameter information includes at least one of the following:

[0770] Semantic knowledge base information;

[0771] Semantic context information;

[0772] Semantic modal information;

[0773] Semantic importance information;

[0774] And / or, the second semantically related parameter information includes at least one of the following:

[0775] Semantic knowledge base information;

[0776] Semantic context information;

[0777] Semantic modal information;

[0778] Semantic importance information.

[0779] In some embodiments, the receiving end may also perform the following steps:

[0780] Receive the second semantic related parameter information sent by the sending end.

[0781] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0782] Figure 3B is a flowchart illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 3B, the present disclosure relates to a communication method that can be executed by a sending end. The method may include:

[0783] Step S3201: Send first information to the receiving end; wherein, the first information is used by the receiving end to monitor the semantic communication performance; the first information is semantically related information during the semantic communication process.

[0784] In some embodiments, the first information includes at least one of the following:

[0785] First semantic data;

[0786] The source data for the first semantic data;

[0787] Channel decoding result; the channel decoding result is obtained by the receiving end after performing channel decoding on the first semantic data;

[0788] The semantic verification information corresponding to the first semantic data;

[0789] The semantic task information corresponding to the first semantic data;

[0790] The first semantic data is the semantic data received by the receiving end from the sending end.

[0791] In some embodiments, the method further includes at least one of the following:

[0792] Send second semantic data to the receiving end; the second semantic data is sent by the sending end after receiving the first indication information sent by the receiving end;

[0793] The receiver receives first semantic related parameter information sent by the receiving end, the first semantic related parameter information including semantic related parameters used by the receiving end to decode the first semantic data;

[0794] The sending end sends second semantic related parameter information to the receiving end; the second semantic related parameter information is sent by the sending end after receiving the second indication information sent by the receiving end; the second semantic related parameter information includes semantic related parameters used by the sending end to encode the source data.

[0795] In some embodiments, the first indication information carries at least one of the following:

[0796] The third indication information indicates the reason why the sending end sends the second semantic data;

[0797] The fourth indication information indicates the manner in which the sending end transmits the second semantic data.

[0798] In some embodiments, the third indication information includes at least one of the following:

[0799] The second piece of information is used to indicate channel quality information;

[0800] The third piece of information is used to indicate semantic similarity information;

[0801] The fourth piece of information is used to indicate the progress of the task.

[0802] The fifth piece of information is used to indicate the monitoring results of the semantic communication performance.

[0803] In some embodiments, the fourth indication information includes at least one of the following:

[0804] The sixth piece of information is used to instruct the sending end to send the second semantic data based on the channel retransmission mechanism;

[0805] The seventh piece of information is used to instruct the sending end to send the second semantic data through non-semantic communication.

[0806] The eighth piece of information is used to instruct the sending end to send the second semantic data based on the adjusted transmission parameters; the adjusted transmission parameters are obtained by the sending end after adjusting them based on at least one of the channel conditions and network environment during the semantic communication process.

[0807] The ninth piece of information is used to instruct the sending end to send the second semantic data and semantic redundancy data associated with the second semantic data.

[0808] In some embodiments, the second semantic data includes at least one of the following:

[0809] First semantic data;

[0810] The source data for the first semantic data;

[0811] Semantic redundancy data;

[0812] The third semantic data; the third semantic data is related to the transmission parameters of the first semantic data.

[0813] In some embodiments, the semantically redundant data includes at least one of the following:

[0814] Semantic knowledge base information;

[0815] Contextual information;

[0816] Multimodal information;

[0817] The fourth semantic data, wherein the semantic similarity between the fourth semantic data and the first semantic data reaches a third threshold;

[0818] Historical information is used to indicate the historical interaction records between the sending end and the receiving end.

[0819] In some embodiments, the first semantically related parameter information includes at least one of the following:

[0820] Semantic knowledge base information;

[0821] Semantic context information;

[0822] Semantic modal information;

[0823] Semantic importance information;

[0824] And / or, the second semantically related parameter information includes at least one of the following:

[0825] Semantic knowledge base information;

[0826] Semantic context information;

[0827] Semantic modal information;

[0828] Semantic importance information.

[0829] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0830] The methods involved in the embodiments of this disclosure will be further described below with reference to specific examples.

[0831] In some embodiments, the receiving end receives and monitors semantic communication performance based on semantic data and source data sent by the sending end. The source data may be sent by the sending end based on a sending cycle, a request from the receiving end, or a decision made by the sending end itself, for the purpose of monitoring semantic communication performance.

[0832] In some embodiments, the receiving end receives and performs semantic communication performance monitoring based on the semantic data and semantic verification information sent by the sending end.

[0833] In some embodiments, semantic performance monitoring includes at least one of the following methods:

[0834] Method 1: Channel decoding errors may not affect the accuracy of semantic decoding. The receiver directly determines that the semantic communication performance is poor only when the semantic similarity is lower than the first threshold or the task completion is lower than the second threshold, based on the result of the joint source-channel semantic decoder.

[0835] Method 2: The receiver performs semantic decoding only when the channel decoding is correct, and determines that the semantic communication performance is poor only when the semantic similarity is lower than the first threshold or the task completion is lower than the second threshold based on the semantic decoding result.

[0836] In some embodiments, if a channel decoding error occurs, the data is discarded directly without semantic decoding, and is handled only through a channel retransmission mechanism (such as ARQ).

[0837] The configuration of the first and second thresholds can be flexibly achieved through protocol agreements or signaling negotiation mechanisms based on parameters such as semantic features (type, importance, integrity), network environment (channel quality, load), application requirements (latency, security) and terminal capabilities (computing, storage resources).

[0838] In some embodiments, in response to determining poor semantic communication performance, the receiving end performs semantic data recovery error correction to improve communication performance. The semantic data recovery error correction includes at least one of the following:

[0839] 1) Decoder reconstruction, including the reselection or update of at least one of the semantic decoding model, semantic reasoning model, and semantic knowledge base.

[0840] For example, if the semantic similarity is low, it may be because the current semantic decoding model or semantic knowledge base is not suitable for the current communication scenario. The receiving end can try to reselect or update the semantic decoding model or update the semantic knowledge base to add more semantic information.

[0841] For example, if the task completion rate is low, it may be due to an imperfect semantic reasoning model. The receiving end can try to reselect or update the semantic reasoning model.

[0842] 2) Send the first indication information to the sending end. The first indication information is used to instruct the sending end to send semantic data again.

[0843] In some embodiments, the first indication information may indicate at least one of the following:

[0844] a) Semantic-related information parameters used by the receiver for semantic decoding; including semantic knowledge base information, semantic context information (including contextual information, historical semantic information, etc.), semantic modality information, semantic importance information, etc., which help the sender determine the cause of poor semantic performance based on the semantic-related information parameters of the sender and receiver for encoding and decoding, and thus take corresponding semantic data recovery and error correction mechanisms.

[0845] b) Reasons for retransmission at the sending end (such as poor channel quality, low semantic similarity, etc.);

[0846] c) Retransmission operations at the sending end (such as falling back to traditional communication methods, dynamically adjusting transmission parameters, adding redundant information, and processing based on channel retransmission mechanisms (such as ARQ)) are used by the sending end to determine and execute the corresponding semantic data recovery and error correction mentioned above.

[0847] In some embodiments, the retransmission operation includes at least one of the following:

[0848] a) If the receiver determines that the channel decoding is incorrect, it will discard the data directly without performing semantic decoding and instruct the sender to process it based on the channel retransmission mechanism (such as ARQ).

[0849] b) Revert to traditional communication methods, i.e., re-transmit data using non-semantic communication.

[0850] c) Dynamically adjust transmission parameters, such as transmission power, modulation method, and coding rate, based on channel conditions and network environment to optimize information transmission quality.

[0851] d) Add redundant information to improve decoding reliability. The redundant information includes at least one of the following:

[0852] Semantic knowledge base information is simply added as redundant information, including the knowledge base version, etc.

[0853] Contextual information refers to adding semantic information as redundant information. During the encoding stage, the background information of the semantic information (such as the sending time, location, and sender's identity) is encoded along with the semantic information. In this way, the receiving end can use this background information during decoding to help infer more accurate semantic information.

[0854] Multimodal information indicates the addition of other modal information as redundant information. For example, image features can be embedded in text information, or text features can be embedded in image information to help the receiver perform error correction during decoding.

[0855] Semantic similarity information indicates the addition of multiple semantic similarities within a certain threshold as redundant information. For example, if a word has multiple synonyms, these synonyms can be selected as redundant information during encoding to help the receiver correct errors during decoding.

[0856] Historical information refers to the information received by the receiver using historical interaction records between the sender and receiver to predict the possible content of the current message. For example, in a dialogue system, the semantics of the current message can be inferred from previous dialogue content.

[0857] In some embodiments, the above redundant information can be added based on the first indication information during retransmission encoding, or the sender can add it autonomously during the initial transmission or based on a request from the receiver or other network devices.

[0858] In some embodiments, before the receiving end performs semantic data recovery and error correction, the following steps may also be performed:

[0859] The receiving end sends a second indication message to the sending end. This second indication message requests the sending end to send semantically related information parameters of the semantic encoding to the receiving end. The receiving end uses these parameters, based on the semantically encoded and semantically decoded information, to determine the cause and / or operation of the poor semantic performance, and thus implements a corresponding semantic data recovery and error correction mechanism. For example, updating decoding-related parameters, or sending the first indication message to the sending end, etc.

[0860] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0861] In some embodiments of this disclosure, a communication system is provided, which may include a receiving end and a sending end, wherein the receiving end may execute the communication method executed by the receiving end in the foregoing embodiments of this disclosure; and the sending end may execute the communication method executed by the sending end in the foregoing embodiments of this disclosure.

[0862] This disclosure also provides an apparatus for implementing any of the above methods. For example, an apparatus is provided that includes units or modules for implementing the steps performed by the receiving end in any of the above methods. Alternatively, another apparatus is provided that includes units or modules for implementing the steps performed by the sending end (e.g., a terminal, access network equipment, core network functional node, core network equipment, etc.) in any of the above methods.

[0863] It should be understood that the division of units or modules in the above device is only a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, the units or modules in the device can be implemented by a processor calling software: for example, the device includes a processor connected to a memory containing instructions. The processor calls the instructions stored in the memory to implement any of the above methods or to implement the functions of the units or modules in the above device. The processor can be, for example, a general-purpose processor, such as a Central Processing Unit (CPU) or a microprocessor, and the memory can be internal or external to the device. Alternatively, the units or modules in the device can be implemented in the form of hardware circuits. The functionality of some or all of the units or modules can be achieved through the design of these hardware circuits, which can be understood as one or more processors. For example, in one implementation, the hardware circuit is an Application-Specific Integrated Circuit (ASIC), and the functionality of some or all of the units or modules is achieved through the design of the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented using a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), which can include a large number of logic gates. The connection relationships between the logic gates are configured through configuration files, thereby achieving the functionality of some or all of the units or modules. All units or modules of the above device can be implemented entirely through processor-called software, entirely through hardware circuits, or partially through processor-called software with the remaining parts implemented through hardware circuits.

[0864] In this embodiment, the processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a Central Processing Unit (CPU), a microprocessor, a Graphics Processing Unit (GPU) (which can be understood as a microprocessor), or a Digital Signal Processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. The logical relationships of the aforementioned hardware circuits are fixed or reconfigurable. For example, the processor is a hardware circuit implemented using an Application-Specific Integrated Circuit (ASIC) or a Programmable Logic Device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units or modules. In addition, it can also be hardware circuits designed for artificial intelligence, which can be understood as ASICs, such as Neural Network Processing Units (NPUs), Tensor Processing Units (TPUs), and Deep Learning Processing Units (DPUs).

[0865] Figure 4A is a schematic diagram of a receiving end according to an embodiment of this disclosure. As shown in Figure 4A, the receiving end 101 may include at least one of a transceiver module 4101, a processing module 4102, etc. In some embodiments, the processing module 4102 is configured to monitor semantic communication performance based on first information; the first information is semantically related information during semantic communication. Optionally, the transceiver module 4101 can be used to perform at least one of the communication steps such as sending and / or receiving performed by the receiving end 101 in any of the above methods (e.g., steps S2101, S2105, S2106, S2108, S2109, S2110, S2201, S2205, S2206, S2208, S2209, S2210, S2301, S2305, S2306, S2308, S2309, S2310, S2401, S2501, but not limited thereto), which will not be elaborated here. Optionally, the processing module 4102 can be used to execute at least one of the other steps executed by the receiving end 101 in any of the above methods (e.g., steps S2102, S2103, S2104, S2107, S2202, S2203, S2204, S2107, S2302, S2303, S2304, S2307, S2402, S2403, S2502, S2503, S2304, but not limited thereto), which will not be elaborated here.

[0866] In some embodiments, the transceiver module may include a transmitting module and / or a receiving module, which may be separate or integrated. Optionally, the transceiver module may be interchangeable with a transceiver.

[0867] In some embodiments, the processing module may be a single module or may include multiple sub-modules. Optionally, the multiple sub-modules may each perform all or part of the steps required by the processing module. Optionally, the processing module may be interchangeable with a processor.

[0868] Figure 4B is a schematic diagram of a transmitting end according to an embodiment of this disclosure. As shown in Figure 4B, the transmitting end 102 may include at least one of a transceiver module 4201, a processing module 4202, etc. In some embodiments, the transceiver module 4201 is configured to send first information to a receiving end; wherein the first information is used by the receiving end to monitor the semantic communication performance; the first information is semantically related information during the semantic communication process. Optionally, the transceiver module 4201 can be used to execute at least one of the communication steps (e.g., steps S2101, S2105, S2106, S2108, S2109, S2110, S2201, S2205, S2206, S2208, S2209, S2210, S2301, S2305, S2306, S2308, S2309, S2310, S2401, S2501, but not limited thereto) performed by the sending end 102 in any of the above methods, which will not be elaborated here. Optionally, the processing module 4202 can be used to execute at least one of the other steps performed by the sending end 102 in any of the above methods, which will not be elaborated here.

[0869] In some embodiments, the transceiver module may include a transmitting module and / or a receiving module, which may be separate or integrated. Optionally, the transceiver module may be interchangeable with a transceiver.

[0870] In some embodiments, the processing module may be a single module or may include multiple sub-modules. Optionally, the multiple sub-modules may each perform all or part of the steps required by the processing module. Optionally, the processing module may be interchangeable with a processor.

[0871] Figure 5A is a schematic diagram of the structure of the communication device 5100 proposed in an embodiment of this disclosure. The communication device 5100 can be a transmitting end, such as a network device (e.g., access network device, core network device, etc.), or a receiving end, such as a terminal (e.g., user equipment, etc.), or a chip, chip system, or processor that supports the first device in implementing any of the above methods, or a chip, chip system, or processor that supports the terminal in implementing any of the above methods. The communication device 5100 can be used to implement the methods described in the above method embodiments; for details, please refer to the descriptions in the above method embodiments.

[0872] As shown in Figure 5A, the communication device 5100 includes one or more processors 5101. The processor 5101 can be a general-purpose processor or a dedicated processor, such as a baseband processor or a central processing unit (CPU). The baseband processor can be used to process communication protocols and communication data, while the CPU can be used to control communication devices (e.g., base stations, baseband chips, IoT devices, IoT device chips, DUs or CUs, etc.), execute programs, and process program data. The communication device 5100 is used to execute any of the above methods.

[0873] In some embodiments, the communication device 5100 further includes one or more memories 5102 for storing instructions. Optionally, all or part of the memories 5102 may also be located outside the communication device 5100.

[0874] In some embodiments, the communication device 5100 further includes one or more transceivers 5103. When the communication device 5100 includes one or more transceivers 5103, the transceivers 5103 perform communication steps such as sending and / or receiving in the above method (e.g., steps S2101, S2105, S2106, S2108, S2109, S2110, S2201, S2205, S2206, S2208, S2209, S2210, S2301, S2305, S2306, S2308, S2309, S2310, ...). At least one of steps S2401 and S2501, but not limited thereto, the processor 5101 executes at least one of other steps (e.g., steps S2102, S2103, S2104, S2107, S2202, S2203, S2204, S2107, S2302, S2303, S2304, S2307, S2402, S2403, S2502, S2503, S2304, but not limited thereto).

[0875] In some embodiments, a transceiver may include a receiver and / or a transmitter, which may be separate or integrated. Optionally, the terms transceiver, transceiver unit, transceiver, transceiver circuit, etc., may be used interchangeably; the terms transmitter, transmitting unit, transmitter, transmitting circuit, etc., may be used interchangeably; and the terms receiver, receiving unit, receiver, receiving circuit, etc., may be used interchangeably.

[0876] In some embodiments, the communication device 5100 may include one or more interface circuits. Optionally, the interface circuit is connected to the memory 5102, and the interface circuit can be used to receive signals from the memory 5102 or other devices, and can be used to send signals to the memory 5102 or other devices. For example, the interface circuit can read instructions stored in the memory 5102 and send the instructions to the processor 5101.

[0877] The communication device 5100 described in the above embodiments may be a first device or an Internet of Things (IoT) device, but the scope of the communication device 5100 described in this disclosure is not limited thereto, and the structure of the communication device 5100 may not be limited by FIG. 5A. The communication device may be a standalone device or may be part of a larger device. For example, the communication device may be: (1) a standalone integrated circuit IC, or chip, or chip system or subsystem; (2) a collection of one or more ICs, optionally, the IC collection may also include storage components for storing data and programs; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a receiver, IoT device, smart IoT device, cellular phone, wireless device, handheld device, mobile unit, vehicle device, first device, cloud device, artificial intelligence device, etc.; (6) others, etc.

[0878] Figure 5B is a schematic diagram of the structure of chip 5200 according to an embodiment of this disclosure. For cases where the communication device 5100 can be a chip or a chip system, please refer to the schematic diagram of chip 5200 shown in Figure 5B, but it is not limited thereto.

[0879] Chip 5200 includes one or more processors 5201, which are used to perform any of the above methods.

[0880] In some embodiments, chip 5200 further includes one or more interface circuits 5203. Optionally, the interface circuit 5203 is connected to memory 5202, and the interface circuit 5203 can be used to receive signals from memory 5202 or other devices, and the interface circuit 5203 can be used to send signals to memory 5202 or other devices. For example, the interface circuit 5203 can read instructions stored in memory 5202 and send the instructions to processor 5201.

[0881] In some embodiments, the interface circuit 5203 performs communication steps such as sending and / or receiving in the above method (e.g., steps S2101, S2105, S2106, S2108, S2109, S2110, S2201, S2205, S2206, S2208, S2209, S2210, S2301, S2305, S2306, S2308, S2309, S2310, S2401, ...). At least one of S2501, but not limited to, and at least one of other steps (e.g., steps S2102, S2103, S2104, S2107, S2202, S2203, S2204, S2107, S2302, S2303, S2304, S2307, S2402, S2403, S2502, S2503, S2304, but not limited to) is performed by the processor 5201.

[0882] In some embodiments, the terms interface circuit, interface, transceiver pin, transceiver, etc., can be used interchangeably.

[0883] In some embodiments, chip 5200 further includes one or more memories 5202 for storing instructions. Optionally, all or part of the memories 5202 may be located outside of chip 5200.

[0884] This disclosure also proposes a storage medium storing instructions that, when executed on the communication device 5100, cause the communication device 5100 to perform any of the above methods. Optionally, the storage medium is an electronic storage medium. Optionally, the storage medium is a computer-readable storage medium, but is not limited thereto; it may also be a storage medium readable by other devices. Optionally, the storage medium may be a non-transitory storage medium, but is not limited thereto; it may also be a temporary storage medium.

[0885] This disclosure also provides a program product that, when executed by the communication device 5100, causes the communication device 5100 to perform any of the above methods. Optionally, the program product may be a computer program product.

[0886] This disclosure also proposes a computer program that, when run on a computer, causes the computer to perform any of the above methods.

Claims

1. A communication method, characterized in that, The method, executed by the receiving end, includes: The performance of semantic communication is monitored based on the first information; the first information is semantically related information during the semantic communication process.

2. The method according to claim 1, characterized in that, The first information includes at least one of the following: First semantic data; The source data for the first semantic data; Channel decoding result; the channel decoding result is obtained by the receiving end after performing channel decoding on the first semantic data; The semantic verification information corresponding to the first semantic data; The semantic task information corresponding to the first semantic data; The first semantic data is the semantic data received by the receiving end from the sending end.

3. The method according to claim 2, characterized in that, The monitoring of semantic communication performance based on the first information includes at least one of the following: Based on the first information, determine the semantic similarity between the first semantic data and the source data; monitor the semantic communication performance based on the semantic similarity. Based on the first information, determine the task completion degree of the semantic task corresponding to the first semantic data; The semantic communication performance is monitored based on the task completion rate.

4. The method according to claim 3, characterized in that, Determining the semantic similarity between the first semantic data and the source data based on the first information includes at least one of the following: The semantic similarity is determined based on the first semantic data in the first information and the source data in the first information; If the channel decoding result determines that the channel decoding was successful, the semantic similarity is determined based on the first semantic data in the first information and the source data in the first information. Based on the first semantic data in the first information and the semantic verification information in the first information, the semantic similarity is determined; If the channel decoding result indicates that the channel decoding was successful, the semantic similarity is determined based on the first semantic data in the first information and the semantic verification information in the first information.

5. The method according to claim 3 or 4, characterized in that, Determining the task completion degree of the semantic task corresponding to the first semantic data based on the first information includes at least one of the following: Based on the first semantic data in the first information and the semantic task information in the first information, the task completion degree is determined; If the channel decoding result indicates that the channel decoding was successful, the task completion degree is determined based on the first semantic data and the semantic task information in the first information.

6. The method according to any one of claims 1-5, characterized in that, The monitoring of semantic communication performance based on the first information includes at least one of the following: If the semantic similarity between the first semantic data and the source data is lower than a first threshold, it is determined that the monitored semantic communication performance is substandard; the semantic similarity is determined by the receiving end based on the first information. If the task completion rate of the semantic task corresponding to the first semantic data is lower than the second threshold, it is determined that the monitored semantic communication performance is substandard; the task completion rate is determined by the receiving end based on the first information. If the channel decoding result in the first information is a channel decoding failure, it is determined that the monitored semantic communication performance is substandard.

7. The method according to claim 6, characterized in that, The first threshold is determined by at least one of the following parameters: The semantic features of the first semantic data; The network environment during semantic communication; Application requirements; Semantic device capability, wherein the semantic device includes at least one of a transmitter, the receiver, and a network device; And / or, the second threshold is determined by at least one of the following parameters: The semantic features of the first semantic data; The network environment during semantic communication; Application requirements; Semantic device capability, wherein the semantic device includes at least one of the sending end, the receiving end, and the network device.

8. The method according to any one of claims 1-7, characterized in that, The method further includes: If the monitored semantic communication performance fails to meet the standard, the first semantic data is discarded.

9. The method according to any one of claims 1-8, characterized in that, Before monitoring the semantic communication performance based on the first information, the method further includes: Receive the first information sent by the sending end.

10. The method according to any one of claims 1-9, characterized in that, The method further includes: If the monitored semantic communication performance is substandard, a first operation is performed; the first operation is used to improve the semantic communication performance.

11. The method according to claim 10, characterized in that, The execution of the first operation includes at least one of the following: Update semantic decoding related parameters; the semantic decoding related parameters include at least one of the following: semantic decoding model, semantic reasoning model, and semantic knowledge base; Send the first indication information to the sending end; The first indication information is used to instruct the sending end to send second semantic data, the second semantic data being the same as or related to the first semantic data; Send first semantic related parameter information to the sending end, the first semantic related parameter information including semantic related parameters used by the receiving end to decode the first semantic data; Send a second instruction message to the sending end; The second indication information is used to instruct the sending end to send second semantic related parameter information, which includes semantic related parameters used by the sending end to encode the source data.

12. The method according to claim 11, characterized in that, The first indication information carries at least one of the following: The third indication information indicates the reason why the sending end sends the second semantic data; The fourth indication information indicates the manner in which the sending end transmits the second semantic data.

13. The method according to claim 12, characterized in that, The third instruction information includes at least one of the following: The second piece of information is used to indicate channel quality information; The third piece of information is used to indicate semantic similarity information; The fourth piece of information is used to indicate the progress of the task. The fifth piece of information is used to indicate the monitoring results of the semantic communication performance.

14. The method according to claim 12 or 13, characterized in that, The fourth instruction information includes at least one of the following: The sixth piece of information is used to instruct the sending end to send the second semantic data based on the channel retransmission mechanism; The seventh piece of information is used to instruct the sending end to send the second semantic data through non-semantic communication. The eighth piece of information is used to instruct the sending end to send the second semantic data based on the adjusted transmission parameters; the adjusted transmission parameters are obtained by the sending end after adjusting them based on at least one of the channel conditions and network environment during the semantic communication process. The ninth piece of information is used to instruct the sending end to send the second semantic data and semantic redundancy data associated with the second semantic data.

15. The method according to any one of claims 11-14, characterized in that, The second semantic data includes at least one of the following: First semantic data; The source data for the first semantic data; Semantic redundancy data; The third semantic data; the third semantic data is related to the transmission parameters of the first semantic data.

16. The method according to claim 14 or 15, characterized in that, The semantically redundant data includes at least one of the following: Semantic knowledge base information; Contextual information; Multimodal information; The fourth semantic data, wherein the semantic similarity between the fourth semantic data and the first semantic data reaches a third threshold; Historical information is used to indicate the historical interaction records between the sending end and the receiving end.

17. The method according to any one of claims 11-16, characterized in that, The first semantically related parameter information includes at least one of the following: Semantic knowledge base information; Semantic context information; Semantic modal information; Semantic importance information; And / or, the second semantically related parameter information includes at least one of the following: Semantic knowledge base information; Semantic context information; Semantic modal information; Semantic importance information.

18. The method according to any one of claims 11-17, characterized in that, The method further includes: Receive the second semantic related parameter information sent by the sending end.

19. A communication method, characterized in that, The method, executed by the sending end, includes: Send the first message to the receiving end; The first information is used by the receiving end to monitor the semantic communication performance; the first information is semantic-related information during the semantic communication process.

20. The method according to claim 19, characterized in that, The first information includes at least one of the following: First semantic data; The source data for the first semantic data; Channel decoding result; the channel decoding result is obtained by the receiving end after performing channel decoding on the first semantic data; The semantic verification information corresponding to the first semantic data; The semantic task information corresponding to the first semantic data; The first semantic data is the semantic data received by the receiving end from the sending end.

21. The method according to claim 19 or 20, characterized in that, The method further includes at least one of the following: Send second semantic data to the receiving end; the second semantic data is sent by the sending end after receiving the first indication information sent by the receiving end; The receiver receives first semantic related parameter information sent by the receiving end, the first semantic related parameter information including semantic related parameters used by the receiving end to decode the first semantic data; The sending end sends second semantic related parameter information to the receiving end; the second semantic related parameter information is sent by the sending end after receiving the second indication information sent by the receiving end; the second semantic related parameter information includes semantic related parameters used by the sending end to encode the source data.

22. The method according to claim 21, characterized in that, The first indication information carries at least one of the following: The third indication information indicates the reason why the sending end sends the second semantic data; The fourth indication information indicates the manner in which the sending end transmits the second semantic data.

23. The method according to claim 22, characterized in that, The third instruction information includes at least one of the following: The second piece of information is used to indicate channel quality information; The third piece of information is used to indicate semantic similarity information; The fourth piece of information is used to indicate the progress of the task. The fifth piece of information is used to indicate the monitoring results of the semantic communication performance.

24. The method according to claim 22 or 23, characterized in that, The fourth instruction information includes at least one of the following: The sixth piece of information is used to instruct the sending end to send the second semantic data based on the channel retransmission mechanism; The seventh piece of information is used to instruct the sending end to send the second semantic data through non-semantic communication. The eighth piece of information is used to instruct the sending end to send the second semantic data based on the adjusted transmission parameters; the adjusted transmission parameters are obtained by the sending end after adjusting them based on at least one of the channel conditions and network environment during the semantic communication process. The ninth piece of information is used to instruct the sending end to send the second semantic data and semantic redundancy data associated with the second semantic data.

25. The method according to any one of claims 21-24, characterized in that, The second semantic data includes at least one of the following: First semantic data; The source data for the first semantic data; Semantic redundancy data; The third semantic data; the third semantic data is related to the transmission parameters of the first semantic data.

26. The method according to claim 24 or 25, characterized in that, The semantically redundant data includes at least one of the following: Semantic knowledge base information; Contextual information; Multimodal information; The fourth semantic data, wherein the semantic similarity between the fourth semantic data and the first semantic data reaches a third threshold; Historical information is used to indicate the historical interaction records between the sending end and the receiving end.

27. The method according to any one of claims 21-26, characterized in that, The first semantically related parameter information includes at least one of the following: Semantic knowledge base information; Semantic context information; Semantic modal information; Semantic importance information; And / or, the second semantically related parameter information includes at least one of the following: Semantic knowledge base information; Semantic context information; Semantic modal information; Semantic importance information.

28. A communication device, characterized in that, The communication device is used to perform the communication method according to any one of claims 1-18 or any one of claims 19-27.

29. A communication system, characterized in that, It includes a receiving end and a sending end, wherein the receiving end is configured to implement the communication method of any one of claims 1-18, and the sending end is configured to implement the communication method of any one of claims 19-27.

30. A storage medium storing instructions, characterized in that, When the instruction is executed on the communication device, it causes the communication device to perform the communication method as described in any one of claims 1-18 or any one of claims 19-27.

31. A program product comprising at least one of a program and instructions, characterized in that, When at least one of the programs or instructions is executed by a communication device, it implements the steps of the method described in any one of claims 1-18 or any one of claims 19-27.

Images