Communication method and device

Abstract

The present application relates to a communication method and device. The method comprises: a first communication device receives a system parameter corresponding to a semantic level, the semantic level being obtained on the basis of first information, and the system parameter being used for transmitting second information. By means of embodiments of the present application, the semantic level can be obtained by means of the first information, and the second information can be determined by means of the system parameter corresponding to the semantic level, thereby facilitating improvement of the transmission efficiency and transmission quality for semantic-related information in a communication system.

Description

Communication method and device TECHNICAL FIELD

[0001] The present application relates to the field of communication, and more particularly, to a communication method and device. BACKGROUND

[0002] In a wireless communication system, traditional communication mainly focuses on the accuracy and efficiency of bit information transmission. Semantic communication also focuses on the content and meaning of information, rather than simply transmitting raw data. The efficiency and quality of information transmission in the semantic communication scenario need to be considered.

[0003] SUMMARY

[0004] Embodiments of the present application provide a communication method, comprising:

[0005] The first communication device receives system parameters corresponding to a semantic level, the semantic level being obtained based on first information, and the system parameters being used for transmitting second information.

[0006] Embodiments of the present application provide a communication method, comprising:

[0007] The second communication device transmits system parameters corresponding to a semantic level, the semantic level being obtained based on first information, and the system parameters being used for transmitting second information.

[0008] Embodiments of the present application provide a first communication device, comprising:

[0009] The receiving unit is configured to receive system parameters corresponding to a semantic level, the semantic level being obtained based on first information, and the system parameters being used for transmitting second information.

[0010] Embodiments of the present application provide a second communication device, comprising:

[0011] The sending unit is configured to transmit system parameters corresponding to a semantic level, the semantic level being obtained based on first information, and the system parameters being used for transmitting second information.

[0012] Embodiments of the present application provide a communication device, comprising a transceiver, a processor and a memory. The memory is configured to store a computer program, the transceiver is configured to communicate with other devices, and the processor is configured to invoke and run the computer program stored in the memory, so that the communication device executes the above-mentioned communication method.

[0013] Embodiments of the present application provide a chip for implementing the above-mentioned communication method.

[0014] Specifically, the chip comprises a processor configured to invoke and run a computer program from a memory, so that a device installed with the chip executes the above-mentioned communication method.

[0015] The embodiment of the present application provides a computer readable storage medium, used for storing a computer program, which causes a device to perform the communication method when the computer program is run by the device.

[0016] The embodiment of the present application provides a computer program product, comprising computer program instructions, which causes a computer to perform the communication method.

[0017] The embodiment of the present application provides a computer program, which causes a computer to perform the communication method when the computer program is run by the computer.

[0018] The embodiment of the present application can obtain the semantic level through the first information, and can determine the second information through the system parameter corresponding to the semantic level, so that the transmission efficiency and the transmission quality of the communication system for the semantic related information are improved. BRIEF DESCRIPTION OF DRAWINGS

[0019] Fig. 1 is a schematic diagram of an application scenario according to the embodiment of the present application.

[0020] Fig. 2 is a schematic diagram of the whole working process of a wireless communication system.

[0021] Fig. 3 is a schematic diagram of the implementation process of semantic communication and a physical layer.

[0022] Fig. 4 is a schematic diagram of a neuron structure.

[0023] Fig. 5 is a schematic diagram of a fully connected neural network.

[0024] Fig. 6 is a schematic diagram of the basic mechanism of a convolutional neural network.

[0025] Fig. 7 is a schematic diagram of the basic LSTM unit structure.

[0026] Fig. 8 is a schematic flowchart of a communication method according to an embodiment of the present application.

[0027] Fig. 9 is a schematic flowchart of a communication method according to another embodiment of the present application.

[0028] Fig. 10 is a schematic flowchart of a communication method according to another embodiment of the present application.

[0029] Fig. 11 is a schematic flowchart of a communication method according to another embodiment of the present application.

[0030] Fig. 12 is a schematic flowchart of a communication method according to another embodiment of the present application.

[0031] Fig. 13 is a schematic flowchart of a communication method according to another embodiment of the present application.

[0032] Fig. 14 is a schematic flowchart of a communication method according to another embodiment of the present application.

[0033] FIG. 15 is a schematic flowchart of a communication method according to another embodiment of the application.

[0034] FIG. 16 is a schematic flowchart of a communication method according to another embodiment of the application.

[0035] FIG. 17 is a schematic flowchart of a communication method according to another embodiment of the application.

[0036] FIG. 18 is a schematic flowchart of a communication method according to another embodiment of the application.

[0037] FIG. 19 is a schematic flowchart of a communication method according to another embodiment of the application.

[0038] FIG. 20 is a schematic flowchart of a communication method according to another embodiment of the application.

[0039] FIG. 21 is a schematic flowchart of reporting of a semantic evaluation level according to example one of the application.

[0040] FIG. 22 is a schematic diagram of semantic evaluation based on AI according to example one of the application.

[0041] FIG. 23 is a schematic diagram of downlink transmission according to example two of the application.

[0042] FIG. 24 is a schematic diagram of semantic evaluation based on AI according to example two of the application.

[0043] FIG. 25 is a schematic diagram of uplink transmission according to example two of the application.

[0044] FIG. 26 is a schematic diagram of downlink transmission according to example three of the application.

[0045] FIG. 27 is a schematic diagram of uplink transmission according to example three of the application.

[0046] FIG. 28 is a schematic block diagram of a first communication device according to an embodiment of the application.

[0047] FIG. 29 is a schematic block diagram of a second communication device according to an embodiment of the application.

[0048] FIG. 30 is a schematic block diagram of a communication device according to an embodiment of the application.

[0049] FIG. 31 is a schematic block diagram of a chip according to an embodiment of the application.

[0050] FIG. 32 is a schematic block diagram of a communication system according to an embodiment of the application. DETAILED DESCRIPTION

[0051] The technical solutions in the embodiments of the application will be described below with reference to the accompanying drawings.

[0052] The technical solutions of the embodiments of the present application can be applied to various communication systems, for example, a Long Term Evolution (LTE) system, an Advanced long term evolution (LTE-A) system, a New Radio (NR) system, an evolved system of the NR system, an LTE-based access to unlicensed spectrum (LTE-U) system, an NR-based access to unlicensed spectrum (NR-U) system, a Non-Terrestrial Networks (NTN) system, a Universal Mobile Telecommunication System (UMTS), a Wireless Local Area Networks (WLAN), a Wireless Fidelity (WiFi), a 5th-Generation (5G) system, or other communication systems.

[0053] Generally, a conventional communication system supports a limited number of connections and is easy to implement. However, with the development of communication technology, a mobile communication system will not only support conventional communication, but also support, for example, Device to Device (D2D) communication, Machine to Machine (M2M) communication, Machine Type Communication (MTC), Vehicle to Vehicle (V2V) communication, or Vehicle to everything (V2X) communication, and the like. The embodiments of the present application can also be applied to these communication systems.

[0054] In an embodiment, the communication system in the embodiments of the present application can be applied to a Carrier Aggregation (CA) scenario, can also be applied to a Dual Connectivity (DC) scenario, and can also be applied to a Standalone (SA) network deployment scenario.

[0055] In an implementation, the communication system in embodiments of the present application can be applied to unlicensed spectrum, which can also be considered as shared spectrum, or the communication system in embodiments of the present application can also be applied to licensed spectrum, which can also be considered as unshared spectrum.

[0056] Embodiments of the present application describe various embodiments in combination with network devices and terminal devices, wherein the terminal device can also be referred to as user equipment (UE), access terminal, subscriber unit, subscriber station, mobile station, mobile, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent, or user device, etc.

[0057] The terminal device can be a station (STA) in a WLAN, and can be a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a wireless local loop (WLL) station, a Personal Digital Assistant (PDA) device, a handheld device with wireless communication function, a computing device, or other processing device connected to a wireless modem, a vehicle-mounted device, a wearable device, a terminal device in a next-generation communication system such as an NR network, or a terminal device in a future evolved Public Land Mobile Network (PLMN) network, etc.

[0058] In embodiments of the present application, the terminal device can be deployed on land, including indoor or outdoor, handheld, wearable or vehicle-mounted; can also be deployed on water surface (such as ships, etc.); and can also be deployed in the air (such as airplanes, balloons and satellites, etc.).

[0059] In embodiments of the present application, the terminal device can be a mobile phone, a tablet computer, a computer with wireless transceiver function, 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 treatment, a wireless terminal device in smart grid, a wireless terminal device in transportation safety, a wireless terminal device in smart city, or a wireless terminal device in smart home, etc.

[0060] By way of example and not limitation, in embodiments of the present application, the terminal device can also be a wearable device. The wearable device can also be referred to as a wearable smart device, which is a general term for devices that are designed and developed by applying wearable technology to daily wear, such as glasses, gloves, watches, clothing, and shoes. The wearable device is a portable device that is directly worn on the body or integrated into the clothes or accessories of the user. The wearable device is not only a hardware device, but also a device that realizes powerful functions through software support and data interaction and cloud interaction. The broad sense of wearable smart devices includes devices with full functions and large sizes that can realize complete or partial functions without relying on smart phones, such as smart watches or smart glasses, and devices that focus on a certain type of application function and need to be used in cooperation with other devices, such as smart phones, such as various smart wristbands and smart jewelry for monitoring vital signs.

[0061] In embodiments of the present application, the network device can be a device for communicating with the mobile device, and the network device can be an access point (Access Point, AP) in a WLAN, an evolved node B (Evolutional Node B, eNB or eNodeB) in LTE, or a relay station or an access point, or a vehicle-mounted device, a wearable device, and a network device in an NR network (gNB) or a future evolved PLMN network or a network device in an NTN network, etc.

[0062] By way of example and not limitation, in embodiments of the present application, the network device can have mobile characteristics, for example, the network device can be a mobile device. Alternatively, the network device can be a satellite, a balloon station. For example, the satellite can be a low earth orbit (low earth orbit, LEO) satellite, a medium earth orbit (medium earth orbit, MEO) satellite, a geostationary earth orbit (geostationary earth orbit, GEO) satellite, a high elliptical orbit (High Elliptical Orbit, HEO) satellite, etc. Alternatively, the network device can also be a base station arranged at a position on land, water, etc.

[0063] In the embodiments of the present application, the network device can serve a cell, and a terminal device communicates with the network device through a transmission resource (for example, a frequency domain resource, or a spectrum resource) used by the cell. The cell can be a cell corresponding to the network device (for example, a base station), and the cell can belong to a macro base station or a base station corresponding to a small cell (Small cell). The small cell can include a metro cell, a micro cell, a pico cell, a femto cell, and the like. The small cell has the characteristics of small coverage and low transmit power, and is suitable for providing high-speed data transmission services.

[0064] FIG. 1 illustrates a communication system 100. The communication system includes one network device 110 and two terminal devices 120. In an embodiment, the communication system 100 can include multiple network devices 110, and each network device 110 can include other numbers of terminal devices 120 within its coverage, which is not limited in the embodiments of the present application.

[0065] In an embodiment, the communication system 100 can further include a mobility management entity (MME), an access and mobility management function (AMF), and other network entities, which are not limited in the embodiments of the present application.

[0066] The network device can include an access network device and a core network device. That is, the wireless communication system further includes multiple core networks for communicating with the access network device. The access network device can be an evolved node B (eNB or e-NodeB) macro base station, a micro base station (also referred to as a “small base station”), a pico base station, an access point (AP), a transmission point (TP), or a new generation Node B (gNodeB) in a long-term evolution (LTE) system, a next radio (NR) system, or an authorized auxiliary access long-term evolution (LAA-LTE) system.

[0067] It should be understood that the devices with communication function in the network / system in the embodiments of the present application can be referred to as communication devices. For example, the communication system shown in FIG. 1, the communication devices can include network devices and terminal devices with communication function, which can be specific devices in the embodiments of the present application, and details are not described herein again; the communication devices can also include other devices in the communication system, such as network controllers, mobile management entities and other network entities, which are not limited in the embodiments of the present application.

[0068] It should be understood that the terms "system" and "network" are often used interchangeably herein. The term "and / or" herein is only used to describe the association relationship of the associated objects. For example, A and / or B can represent three cases: A exists alone, A and B exist together, and B exists alone. In addition, the character " / " generally represents an "or" relationship between the associated objects.

[0069] It should be understood that the "indication" mentioned in the embodiments of the present application can be direct indication, indirect indication, or can represent an associated relationship. For example, A indicates B, which can mean that B can be obtained by A directly; it can also mean that A indirectly indicates B, for example, A indicates C, and B can be obtained by C; it can also mean that A and B have an associated relationship.

[0070] In the description of the embodiments of the present application, the term "corresponding" can represent a direct or indirect corresponding relationship between the two, can also represent an associated relationship between the two, or can represent an indication and being indicated, configuration and being configured, etc.

[0071] In order to facilitate the understanding of the technical solutions of the embodiments of the present application, the related technologies of the embodiments of the present application are described as follows. The following related technologies can be combined with the technical solutions of the embodiments of the present application in any way, and all belong to the protection scope of the embodiments of the present application.

[0072] I. Wireless communication system

[0073] In the wireless communication system, the basic working process can include the following steps, as shown in FIG. 2.

[0074] Source (also referred to as information source, information source, etc.) coding: source coding compresses data by removing the redundancy in the data to reduce the bandwidth required for transmission.

[0075] Channel coding: To enhance the error detection and correction capability during transmission, channel coding improves the reliability of data by adding extra check bits to the received data, such as the source bit stream. Common coding techniques include convolutional codes, error correction (Turbo) codes, and low-density parity check (LDPC) codes, etc.

[0076] Modulation: Modulation maps the encoded data onto specific signal waveforms. Common modulation techniques include quadrature amplitude modulation (QAM), phase shift keying (PSK), and frequency-shift keying (FSK), etc.

[0077] Signal transmission: After modulation, the pilot signal can be inserted, and then the signal is transmitted. Signal transmission involves power amplification and filtering before transmission to ensure signal quality and compliance with transmission standards.

[0078] Through the channel: During transmission, the signal will be affected by various wireless propagation environments, such as attenuation, multipath effect, interference, and noise.

[0079] Signal reception: The antenna and receiver at the receiving end capture the signal transmitted through the channel. These signals may be weak and accompanied by noise before reaching the receiver.

[0080] Channel estimation: In the received signal, the receiver needs to estimate the characteristics of the channel to support correct demodulation, often using known pilot signals to complete.

[0081] Symbol detection: Based on the results of channel estimation, the receiver performs symbol detection on the received analog signal, i.e., attempts to determine the digital data represented by each signal waveform.

[0082] Demodulation: Demodulation converts the detected symbols into a received bit stream, which is used for subsequent channel decoding.

[0083] Channel decoding: Using the check information of channel coding, the receiver can detect and correct errors that may occur during transmission.

[0084] Source decoding: Restores the data compressed by source encoding, restoring the original data (such as restoring the bit stream).

[0085] The above process is a simple illustration, and there are other modules not listed in traditional communication systems, such as resource mapping, precoding, interference cancellation, channel state information (CSI) measurement, etc. These modules can be designed and implemented separately, and then integrated into a complete wireless communication system.

[0086] II. Semantic Communication and Physical Layer Implementation

[0087] Traditional communication mainly focuses on accurately and efficiently transmitting each bit. Semantic communication focuses on the content and meaning of information, emphasizing the transmission of the meaning part of the information rather than simply transmitting raw data. The goal of this approach is to enable the receiving party to understand the sender's intention and the semantic content of the information, even in poor channel conditions or limited data transmission. The implementation of semantic communication usually relies on advanced artificial intelligence (AI) algorithms to identify, extract, and process semantic information in the source, so that even if there is a loss or miscommunication of transmitted bit information, the receiving end can still reconstruct and understand the basic meaning of the original information.

[0088] Implementing semantic communication at the physical layer means that in the most basic signal processing and transmission process, not only the physical properties of the signal are considered, but also the semantic content of the information. Semantic encoding and decoding are mainly added, as shown in Figure 3, as follows:

[0089] Semantic encoding: based on AI models, semantic analysis and encoding of image, video or text data, etc. to convert key information into a transmittable bit stream or directly into a transmittable symbol.

[0090] Traditional communication system transmission: transmit bit stream or symbol through conventional wireless communication system.

[0091] Semantic decoding: based on AI models, semantic decoding of received bit stream or symbol to recover the core semantic content of the original information.

[0092] III. Neural Networks

[0093] A neural network is an operation model composed of multiple neuron nodes connected to each other, where the connection between nodes represents the weighted value from input signal to output signal, called weight; each node performs weighted summation on different input signals and outputs through a specific activation function. An example of a neuron structure is shown in Figure 4.

[0094] An example of a simple fully connected neural network is shown in FIG. 5, which includes an input layer, a hidden layer and an output layer. Different connections, weights and activation functions of multiple neurons can produce different outputs, thereby fitting the mapping relationship from input to output. Each upper node is connected to all lower nodes.

[0095] Next, a convolutional neural network is introduced. The basic structure of the convolutional neural network includes an input layer, multiple convolutional layers, multiple pooling layers, a fully connected layer and an output layer, as shown in FIG. 6. Each neuron of the convolutional kernel in the convolutional layer is locally connected to its input, and the maximum value or average value feature of a local layer is extracted by introducing the pooling layer, effectively reducing the parameters of the network and mining local features, so that the convolutional neural network can quickly converge and obtain excellent performance.

[0096] Finally, a recurrent neural network is introduced. The recurrent neural network is a neural network for modeling sequence data, and has achieved remarkable results in natural language processing fields such as machine translation and speech recognition. Specifically, the network memorizes information at past time and uses it in the calculation of the current output, i.e., the nodes between the hidden layers are no longer unconnected but connected, and the input of the hidden layer includes not only the input layer but also the output of the hidden layer at the previous time. Long Short-Term Memory (LSTM) is a commonly used recurrent neural network, which includes a basic LSTM unit structure shown in FIG. 7. Unlike the recurrent neural network which only considers the recent state, the cell state of the LSTM determines which state should be left and which state should be forgotten, solving the defects of the traditional recurrent neural network in long-term memory.

[0097] In the semantic communication scenario, due to the introduction of the AI-based joint source channel coding module, the semantic source is visible in the physical layer system. The transmission strategy of the related physical layer system does not consider adapting to the semantics of the source itself, has low system flexibility, and further reduces the transmission efficiency and transmission quality of the semantic source.

[0098] FIG. 8 is a schematic flowchart of a communication method 800 according to an embodiment of the present application. The method can optionally be applied to the system shown in FIG. 1, but is not limited thereto. The method includes at least part of the following content.

[0099] S810, the first communication device receives a system parameter corresponding to a semantic level, the semantic level being obtained based on the first information, and the system parameter being used for transmitting the second information.

[0100] In the embodiments of the present application, the first communication device can be a terminal device, and the second communication device can be a network device. The first communication device can determine the semantic level based on the first information and then send the semantic level to the second communication device. The first communication device can also send the first information to the second communication device, and the second communication device can determine the semantic level based on the first information. The semantic level can also be referred to as a semantic grade, a semantic evaluation grade, a semantic grouping, a semantic group, etc. The semantic level and the system parameter can have a corresponding relationship (or a mapping relationship). The second communication device can find the system parameter corresponding to the semantic level in the mapping relationship, and then send the system parameter corresponding to the semantic level to the first communication device. The system parameter can be used for transmitting the second information. The second information can be semantic information of uplink or semantic information of downlink. For example, the first communication device can determine the semantic information of uplink based on the system parameter, and then send the semantic information of uplink to the second communication device. For another example, the second communication device can determine the semantic information of downlink based on the system parameter, and then send the semantic information of downlink to the first communication device.

[0101] In the embodiments of the present application, the first information and the second information can be different or the same. For example, after determining the system parameter based on the semantic category of the first information, the first information (the same as the second information) can be transmitted based on the system parameter. For another example, after determining the system parameter based on the semantic category of the first information, other information (different from the first information) can be transmitted based on the system parameter.

[0102] In the embodiments of the present application, the semantic level can be obtained through the first information, and the second information can be determined through the system parameter corresponding to the semantic level, which is beneficial to improving the transmission efficiency and the transmission quality of the semantic related information of the communication system.

[0103] In some examples, the system parameter can be related to coding, for example, related to source coding, or related to source-channel joint coding. The source-channel joint coding can include semantic source-channel joint coding.

[0104] In an implementation, the semantic level and the system parameter have a mapping relationship.

[0105] In an implementation, the system parameter includes at least one of the following: a modulation and coding scheme (MCS); a transport block size (TBsize); a number of physical resource blocks (PRBS); a transmission power level; a number of retransmissions of a hybrid automatic repeat request (HARQ); a semantic coding model identifier; a semantic coding model.

[0106] The mapping relationship between the semantic level and the system parameter can be saved in a table or the like. See the following table for an example:

[0107] The above table is only an example and is not limiting. The mapping relationship between the semantic level and the system parameter can also be saved in multiple tables, for example,

[0108] One table saves the mapping relationship between the semantic level and one or more of MCS, TBsize, PRBS, power level, and HARQ retransmission times. One table saves the mapping relationship between the semantic level and the model ID. One table saves the mapping relationship between the semantic level and the model parameters, structure, and the like.

[0109] FIG. 9 is a schematic flowchart of a communication method 900 according to another embodiment of the present application. The method can include one or more features of the above-described methods. In an implementation, the method further includes:

[0110] S910, the first communication device obtains a semantic level based on the first information;

[0111] S920, the first communication device transmits the semantic level.

[0112] In an implementation, the method further includes that the first communication device transmits the second information.

[0113] In an implementation, the method further includes that the first communication device receives the second information.

[0114] In an implementation, in Example One, the first information is first semantic information, and the second information is second semantic information. The method further includes that the first communication device transmits the second semantic information. In the embodiment of the present application, after the first communication device performs S910 and S920, it can perform S810, and then transmit the second information. For example, after the first communication device obtains a semantic level based on the first semantic information, it can transmit the semantic level to the second communication device. After the second communication device finds the mapping relationship and determines the system parameter corresponding to the semantic level, it can transmit the system parameter to the first communication device. After the first communication device receives the system parameter, it can transmit second semantic information to the second communication device based on the system parameter.

[0115] In an implementation, the semantic level is obtained based on at least one of the following rules: the type of the first semantic information; the transmission importance of the first semantic information; the transmission urgency of the first semantic information; the source of the first semantic information; the content of the first semantic information; the context of the first semantic information; and the content format of the first semantic information.

[0116] In the embodiments of the present application, the first communication device can evaluate the semantic level of the first information according to a preset rule. The preset rule can include a plurality of rules, such as a rule based on information type, a rule based on information source, a rule based on information content, a rule based on context, a rule based on content format, etc. The information type can include, for example, text, image, video, etc. The information source can include official channels, experts, user-defined, etc. The information content can include various keywords, and the semantic level can be evaluated according to the keywords. The context can include information received before or after the first information. The content format can include the writing format of the text, the image format, the video format, etc.

[0117] In an embodiment, the semantic level is obtained by processing the first semantic information by a first artificial intelligence model, input features of the first artificial intelligence model including at least one of the following: semantic content, context information, key element list; and output features of the first artificial intelligence model including the semantic level.

[0118] In the embodiments of the present application, the first communication device can evaluate the semantic level of the first information based on artificial intelligence (AI). For example, one or more of the semantic content, the context information, and the key element list of the first information are input into an AI model, such as a natural language processing (NLP) model. The NLP model is used to perform semantic analysis on the first information to obtain the semantic level of the first information.

[0119] FIG. 10 is a schematic flowchart of a communication method 1000 according to another embodiment of the present application. The method can include one or more features of the above-described methods. In an embodiment, in Example II, the first information includes third semantic information and fourth semantic information, the second information is fifth semantic information, and the method further includes:

[0120] S1010, the first communication device sends the third semantic information;

[0121] S1020, the first communication device receives the fourth semantic information, the fourth semantic information being obtained based on the third semantic information;

[0122] S1030, the first communication device sends the fifth semantic information.

[0123] In the embodiments of the present application, after the first communication device performs S1010 and S1020, it can perform S910 and S920, then perform S810, and then perform S1030 (S930).

[0124] In the process of uplink transmission of semantic information in Example Two, the first communication device sends third semantic information, such as text, image, video or other forms of data, to the second communication device through, for example, PUSCH. After receiving the third semantic information, the second communication device processes and analyzes the third semantic information, for example, re-encodes the received third semantic information to obtain fourth semantic information ready for feedback. Then the second communication device can send the fourth semantic information to the first communication device. After receiving the fourth semantic information, the first communication device can compare the third semantic information and the fourth semantic information, evaluate their similarity, and thus generate a semantic level. There are many ways to evaluate similarity, such as using a rule-based method (such as keyword consistency) or an AI-based method (such as measuring feature vector distance) to evaluate the similarity of different semantic information (symbol sequences or feature vectors) and thus generate a semantic level. The first communication device can report the semantic level to the second communication device. The second communication device can find the mapping relationship to obtain the system parameter corresponding to the semantic level, and send the system parameter to the first communication device. The first communication device can transmit fifth semantic information to the second communication device based on the system parameter.

[0125] FIG. 11 is a schematic flowchart of a communication method 1100 according to another embodiment of the present application. The method can include one or more features of the above-described methods. In one implementation, in Example Two, the first information includes third semantic information and fourth semantic information, and the second information is fifth semantic information, and the method further includes:

[0126] S1110, the first communication device receives third semantic information;

[0127] S1120, the first communication device obtains fourth semantic information based on the third semantic information;

[0128] S1130, the first communication device sends the fourth semantic information;

[0129] S1140, the first communication device receives the fifth semantic information.

[0130] In the embodiments of the present application, after the first communication device performs S1110, S1120 and S1130, it can perform S810, and then perform S1140.

[0131] In the process of transmitting the semantic information in the second example, after receiving the third semantic information from the second communication device, the first communication device processes and analyzes the third semantic information, for example, re-encodes the received third semantic information to obtain fourth semantic information ready for feedback. The first communication device can feed back the fourth semantic information to the second communication device. After receiving the fourth semantic information, the second communication device can compare the third semantic information and the fourth semantic information in terms of semantics, evaluate the similarity between the two, and thus generate a semantic level. Then, the second communication device can look up the mapping relationship to obtain the system parameter corresponding to the semantic level, and send the system parameter to the first communication device. The first communication device can receive the fifth semantic information transmitted by the second communication device based on the system parameter.

[0132] In an implementation, in the second example, the semantic level is obtained by processing the third semantic information and the fourth semantic information by a second artificial intelligence model, input features of the second artificial intelligence model include at least one of the third semantic information and the fourth semantic information, output features of the second artificial intelligence model include at least one of the first symbol sequence after encoding the third semantic information, the second symbol sequence after encoding the fourth semantic information, the similarity between the first symbol sequence and the second symbol sequence, the distance between the first symbol sequence and the second symbol sequence, and the semantic level.

[0133] In the second example of the embodiments of the present application, the second artificial intelligence model can be arranged in the first communication device and / or the second communication device. The second artificial intelligence model can include a semantic encoding model. After inputting the third semantic information and the fourth semantic information into the same semantic encoding model, the encoded symbol sequence (i.e., feature vector) can be obtained, and the similarity of the semantic information can be evaluated by measuring the distance between the feature vectors. In addition to using the AI model, a keyword matching algorithm can also be used to evaluate the similarity of the third semantic information and the fourth semantic information. Then, the semantic level can be generated based on the similarity. In addition, the distance between the feature vectors of the third semantic information and the fourth semantic information can be calculated by using the vector distance measurement method, and the semantic level can be generated based on the distance.

[0134] In some examples, the correspondence between the similarity and the semantic level can be pre-set. For example, when the similarity is above 0.9, the semantic level is 5; when the similarity is between 0.7 and 0.9, the semantic level is 4; when the similarity is between 0.5 and 0.7, the semantic level is 3; when the similarity is between 0.3 and 0.5, the semantic level is 2; and when the similarity is below 0.3, the semantic level is 1.

[0135] In some examples, the correspondence between the vector distance and the semantic level can be pre-set. For example, when the vector distance is below 10, the semantic level is 5; when the similarity is between 10 and 20, the semantic level is 4; when the similarity is between 20 and 30, the semantic level is 3; when the similarity is between 30 and 50, the semantic level is 2; and when the similarity is above 50, the semantic level is 1.

[0136] In an embodiment, the manner in which the first communication device and / or the second communication device obtains the fourth semantic information based on the third semantic information comprises at least one of:

[0137] re-source encoding the third semantic information or jointly encoding the third semantic information and a semantic source channel to obtain the fourth semantic information;

[0138] processing the symbol sequence before the decoding module of the third semantic information, the symbol sequence being the fourth semantic information.

[0139] In one example, after the first communication device receives the information source, e.g., the third semantic information, transmitted by the second communication device, it directly re-source encodes the information source, e.g., the third semantic information, and prepares to transmit the encoded information source, e.g., the fourth semantic information, as feedback information back to the second communication device.

[0140] In another example, after the first communication device receives the information source, e.g., the third semantic information, transmitted by the second communication device, it processes the symbol sequence before the decoding module of the third semantic information, and prepares to transmit the symbol sequence, e.g., the fourth semantic information, as feedback information back to the second communication device.

[0141] In another example, after the second communication device receives the information source, e.g., the third semantic information, transmitted by the first communication device, it directly re-source encodes the information source, e.g., the third semantic information, and prepares to transmit the encoded information source, e.g., the fourth semantic information, as feedback information back to the first communication device.

[0142] In another example, after the second communication device receives the information source, e.g., the third semantic information, transmitted by the first communication device, it processes the symbol sequence before the decoding module of the third semantic information, and prepares to transmit the symbol sequence, e.g., the fourth semantic information, as feedback information back to the first communication device.

[0143] FIG. 12 is a schematic flow chart of a communication method 1200 according to another embodiment of the present application. The method can include one or more features of the above-described methods. In one embodiment, in Example Three, the first information is semantic pilot information, and the second information is the sixth semantic information, the method further comprises:

[0144] S1210, the first communication device receives the semantic pilot information;

[0145] S1220, the first communication device receives the sixth semantic information.

[0146] In the embodiments of the present application, the semantic pilot information can be reference data known by both the first communication device and the second communication device in advance, used to ensure the consistency of the understanding and evaluation of the transmission content by both sides. For example, the second communication device sends a standard text or a predefined semantic sequence to the first communication device, and the information source has been pre-agreed between the first communication device and the second communication device before transmission.

[0147] In the embodiments of the present application, after the first communication device performs S1210, it can perform S910 and S920, and then perform S810, and then perform S1220.

[0148] In the process of downlink transmission of semantic information in Example Three, after the first communication device receives the semantic pilot information transmitted by the second communication device, it performs semantic comparison and evaluates the similarity between the semantic pilot information and the pre-stored reference data, thereby generating a semantic level. The first communication device can report the semantic level to the second communication device. The second communication device can find the mapping relationship to obtain the system parameter corresponding to the semantic level, and send the system parameter to the first communication device. The first communication device can receive the sixth semantic information transmitted by the second communication device based on the system parameter.

[0149] FIG. 13 is a schematic flowchart of a communication method 1300 according to another embodiment of the present application. The method can include one or more features of the above-mentioned methods. In one implementation, in Example Three, the first information is semantic pilot information, the second information is sixth semantic information, and the method further includes:

[0150] S1310, the first communication device sends semantic pilot information;

[0151] S1320, the first communication device sends the sixth semantic information.

[0152] In the embodiments of the present application, after the first communication device performs S1310, it can perform S810, and then perform S1320.

[0153] In the process of uplink transmission of semantic information in Example Three, after the first communication device sends the semantic pilot information to the second communication device, the second communication device performs semantic comparison on the received semantic pilot information, evaluates the similarity between the semantic pilot information and the pre-stored reference data, thereby generating a semantic level. The second communication device can find the mapping relationship to obtain the system parameter corresponding to the semantic level, and send the system parameter to the first communication device. The first communication device can transmit the sixth semantic information to the second communication device based on the system parameter.

[0154] In an embodiment, in Example Three, the semantic level is obtained by processing the semantic pilot information by a third artificial intelligence model, input features of the third artificial intelligence model include at least one of the received semantic pilot information and the predefined semantic pilot information, output features of the third artificial intelligence model include at least one of a third symbol sequence after encoding the received semantic pilot information, a fourth symbol sequence after encoding the predefined semantic pilot information, a similarity between the third symbol sequence and the fourth symbol sequence, a distance between the third symbol sequence and the fourth symbol sequence, and the semantic level.

[0155] In Example Three of the embodiments of the present application, the third artificial intelligence model can be arranged in the first communication device and / or the second communication device. The third artificial intelligence model can include a semantic encoding model. After inputting the third semantic information and the fourth semantic information into the same semantic encoding model, a symbol sequence (i.e., a feature vector) after encoding can be obtained, and measuring the distance between the feature vectors can evaluate the similarity of the semantic information.

[0156] In an embodiment, in the process of transmitting the semantic information in Example Two or in the process of transmitting the semantic information in Example Three, the semantic level can be obtained by the second communication device based on the first information. In an example, after the second communication device transmits the third semantic information and receives the fourth semantic information fed back by the first communication device, a rule-based method (such as keyword consistency) or an AI-based method (such as measuring the distance between feature vectors) can be used to evaluate the similarity between the two, and then generate the semantic level.

[0157] In another example, after the second communication device receives the semantic pilot information (an example of the first information), the received semantic pilot information can be compared with the predefined semantic pilot information, for example, comparing the received text with the predefined semantic pilot text, using a keyword matching algorithm to evaluate the consistency of the two, or using an AI model to calculate the semantic similarity of the two, or using a vector distance measurement method to measure the distance between the feature vectors of the two, and then generating the semantic level.

[0158] In an embodiment, in the case that the first communication device reports the semantic level to the second communication device, the semantic level is carried by at least one of the following: a scheduling request (SR); a radio resource control (RRC) message; a physical uplink control channel (PUCCH); and a physical random access channel (PRACH).

[0159] In an embodiment, the semantic level is carried by at least one of the following in case that the second communication device issues the semantic level to the first communication device: Downlink Control Information (DCI) format transmission scheduling information; RRC message; Medium Access Control Control Element (MAC-CE).

[0160] FIG. 14 is a schematic flow chart of a communication method 1400 according to another embodiment of the present application. The method can optionally be applied to, but is not limited to, the system shown in FIG. 1. The method comprises at least part of the following.

[0161] S1410, the second communication device sends a system parameter corresponding to the semantic level, the semantic level being obtained based on the first information, the system parameter being used for transmission of the second information.

[0162] FIG. 15 is a schematic flow chart of a communication method 1500 according to another embodiment of the present application. The method can comprise one or more features of the above-mentioned methods. In an embodiment, the method further comprises:

[0163] S1510, the second communication device receives a semantic level, the semantic level being obtained by the first communication device based on the first information.

[0164] FIG. 16 is a schematic flow chart of a communication method 1600 according to another embodiment of the present application. The method can comprise one or more features of the above-mentioned methods. In an embodiment, the method further comprises:

[0165] S1610, the second communication device obtains a semantic level based on the first information.

[0166] In the embodiments of the present application, the second communication device can determine the semantic level of the first information by itself, or receive the semantic level of the first information from the first communication device. For example, the second communication device performs S1510 first, and then performs S1410. For another example, the second communication device performs S1610 first, and then performs S1410.

[0167] In an embodiment, after S1410, the method further comprises: the second communication device sends the second information.

[0168] In an embodiment, after S1410, the method further comprises: the second communication device receives the second information.

[0169] In an embodiment, in example one, the first information is first semantic information, and the second information is second semantic information, and the method further comprises: receiving, by the second communication device, the second semantic information. This step can be performed after S1410.

[0170] In an embodiment, the semantic level is based on at least one of the following rules: a type of the first semantic information; a transmission importance of the first semantic information; a transmission urgency of the first semantic information; a source of the first semantic information; a content of the first semantic information; a context of the first semantic information; a content format of the first semantic information.

[0171] In an embodiment, the semantic level is obtained by processing, by a first artificial intelligence model, the first semantic information, and an input feature of the first artificial intelligence model comprises at least one of the following: semantic content, context information, a list of key elements; and an output feature of the first artificial intelligence model comprises the semantic level.

[0172] FIG. 17 is a schematic flowchart of a communication method 1700 according to another embodiment of the present application. The method can comprise one or more features of the above-mentioned methods. In an embodiment, in the process of uplink transmission of semantic information in example two, the first information comprises third semantic information and fourth semantic information, the second information is fifth semantic information, and the method further comprises:

[0173] S1710, receiving, by the second communication device, the third semantic information;

[0174] S1720, sending, by the second communication device, the fourth semantic information, the fourth semantic information being obtained based on the third semantic information;

[0175] S1730, receiving, by the second communication device, the fifth semantic information.

[0176] In an embodiment of the present application, after the second communication device performs S1710 and S1720, the semantic level can be obtained by the first communication device based on the third semantic information and the fourth semantic information and then sent to the second communication device. After the second communication device continues to perform S1510 to receive the semantic level, it performs S1410 to send the system parameter to the first communication device based on the semantic level, and then performs S1730 to receive the fifth semantic information from the first communication device based on the system parameter.

[0177] FIG. 18 is a schematic flowchart of a communication method 1800 according to another embodiment of the present application. The method can comprise one or more features of the above-mentioned methods. In an embodiment, in the process of downlink transmission of semantic information in example two, the first information comprises third semantic information and fourth semantic information, the second information is fifth semantic information, and the method further comprises:

[0178] S1810, the second communication device sends third semantic information, the third semantic information being used to obtain the fourth semantic information;

[0179] S1820, the second communication device receives the fourth semantic information;

[0180] S1830, the second communication device sends the fifth semantic information.

[0181] In the embodiments of the present application, after the second communication device performs S1810, the fourth semantic information can be obtained by the first communication device based on the third semantic information and sent to the second communication device. After the second communication device performs S1820, it continues to perform S1610 to obtain the semantic level based on the third semantic information and the fourth semantic information. The second communication device continues to perform S1410 to send the system parameter to the first communication device based on the semantic level, and then performs S1830 to send the fifth semantic information to the first communication device based on the system parameter.

[0182] In an embodiment, in Example Two, the semantic level is obtained by processing the third semantic information and the fourth semantic information by a second artificial intelligence model, input features of the second artificial intelligence model including at least one of the third semantic information and the fourth semantic information, and output features of the second artificial intelligence model including at least one of the first symbol sequence after encoding the third semantic information, the second symbol sequence after encoding the fourth semantic information, the similarity of the first symbol sequence and the second symbol sequence, the distance of the first symbol sequence and the second symbol sequence, and the semantic level.

[0183] In an embodiment, in Example Two, the way of obtaining the fourth semantic information based on the third semantic information includes at least one of the following:

[0184] re-performing source encoding or semantic source channel joint encoding on the third semantic information to obtain the fourth semantic information;

[0185] processing the symbol sequence before the decoding module of the third semantic information, the symbol sequence being the fourth semantic information.

[0186] FIG. 19 is a schematic flowchart of a communication method 1900 according to another embodiment of the present application. The method can include one or more features of the above-mentioned methods. In an embodiment, in the process of transmitting semantic information in downlink in Example Three, the first information is semantic pilot information, the second information is sixth semantic information, and the method further includes:

[0187] S1910, the second communication device sends semantic pilot information;

[0188] S1920, the second communication device sends the sixth semantic information.

[0189] In an embodiment of the application, after the second communication device performs S1910, the semantic level can be obtained by the first communication device based on the semantic pilot information and sent to the second communication device. After the second communication device performs S1510 and receives the semantic level, it continues to perform S1410 and sends the system parameter to the first communication device based on the semantic level, and then performs S1920 and sends the sixth semantic information to the first communication device based on the system parameter.

[0190] FIG. 20 is a schematic flowchart of a communication method 2000 according to another embodiment of the application. The method can include one or more features of the above-mentioned methods. In an implementation, in the process of uplink transmission of semantic information in Example Three, the first information is semantic pilot information, the second information is sixth semantic information, and the method further includes:

[0191] S2010, the second communication device receives semantic pilot information;

[0192] S2020, the second communication device receives the sixth semantic information.

[0193] In an embodiment of the application, after the second communication device performs S2010, it can perform S1610 and obtain a semantic level based on the semantic pilot information, and then obtain a system parameter based on the semantic level, and perform S1410 and send the system parameter to the first communication device based on the semantic level. Then the first communication device sends the sixth semantic information to the second communication device based on the system parameter, and the second communication device performs S2020 and receives the sixth semantic information.

[0194] In an implementation, in Example Three, the semantic level is obtained by processing the semantic pilot information by a third artificial intelligence model, and the input features of the third artificial intelligence model include at least one of the following: received semantic pilot information, pre-defined semantic pilot information; and the output features of the third artificial intelligence model include at least one of the following: a third symbol sequence after encoding the received semantic pilot information, a fourth symbol sequence after encoding the pre-defined semantic pilot information, a similarity between the third symbol sequence and the fourth symbol sequence, a distance between the third symbol sequence and the fourth symbol sequence, and a semantic level.

[0195] In an implementation, the semantic level is carried by at least one of the following: SR; RRC message; PUCCH; PRACH.

[0196] In an implementation, the semantic level is carried by at least one of the following: DCI format transmission scheduling information; RRC message; MAC-CE.

[0197] In an embodiment, the semantic level has a mapping relationship with the system parameter, and the system parameter includes at least one of the following: MCS, transport block size, PRBS, transmission power level, retransmission number of HARQ, semantic coding model identifier, and semantic coding model.

[0198] The specific examples of the second communication device execution method 1400 to 2000 of the embodiment can refer to the related descriptions of the second communication device in the above methods 800 to 1300. For brevity, the details are not described herein.

[0199] The communication method of the embodiment can include a reporting method of a source semantic evaluation level. In the method, first, a definition and measurement method of the source semantic evaluation level are provided, including a rule-based or AI-based measurement method for a semantic information source or a semantic pilot information source. Second, a method of adjusting a physical layer transmission strategy according to the source semantic evaluation level is provided, including a corresponding signaling flow and a mapping method between the semantic evaluation level and the transmission strategy. By determining the optimal system parameter optimization resource allocation through semantic evaluation, high-priority information can be preferentially transmitted, system flexibility is improved, and the transmission efficiency and quality of semantic communication are improved.

[0200] Example 1: Reporting method of source semantic evaluation level, see FIG. 21.

[0201] S2101: UE side measures and reports the semantic evaluation level

[0202] The measurement method is optionally rule-based or AI-based, and specific examples are as follows:

[0203] 1.1 Rule-based:

[0204] In the rule based on the type of information, the system can evaluate according to the type of semantic information, such as text, image, video, to define different levels. Different types of information have different importance and urgency in transmission, so different semantic evaluation levels (or called semantic levels, semantic levels, etc.) can be defined. Among them, for example, the semantic evaluation level of voice is higher than that of data flow (picture or video). In the rule based on the source of information, the level of different sources can be different. For example, information obtained from official channels can be given a higher semantic evaluation level, user-generated content is given a lower semantic evaluation level, and information from experts in a particular field can be given a high level of semantic evaluation. In the rule based on the content of information, the system can evaluate according to the specific characteristics of the information content itself, such as keyword matching, that is, using a predefined keyword list to evaluate the content of semantic information. For example, if the text contains some high-frequency or key words, a higher semantic evaluation level can be given. In the rule based on the context, the UE side measures the relevance of the semantic information source (or called semantic information) to be sent to the current context or user demand. For example, if the terminal is looking for information on a certain topic before sending the semantic information source, and the to-be-transmitted information source is highly related to it, a higher semantic evaluation level can be given. In the rule based on the content format, the system can evaluate the importance according to the specific format or mark of the content. For example, a specific writing format (official document or letter) of the text can be given a higher semantic evaluation level.

[0205] 1.2 Based on AI:

[0206] Referring to FIG. 22, taking the semantic evaluation based on a natural language processing (NLP) model as an example. When the semantic information source to be transmitted is text information, the natural language processing model is used to perform semantic analysis on the text information to evaluate the semantic level of the source. The input and output of the NLP model can include the following:

[0207] The input of the model can include the following examples:

[0208] (1) Semantic content: complete text information to be transmitted;

[0209] (2) Context information: related context content can include historical records of sending, current session topics, etc.;

[0210] (3) Key element list: for example, a predefined keyword list, which assists the model in learning and identifying important information predefined in the list.

[0211] The output of the model can include: semantic evaluation level, such as 1-5 levels.

[0212] S2102: The UE side reports the semantic evaluation level

[0213] An example of the reporting form is as follows:

[0214] (1) Scheduling Request (SR): The semantic evaluation level information is attached in the scheduling request message, transmitted to the network side through the physical layer and the medium access control (MAC) layer. In implementation, the structure of the SR message needs to contain a special field for transmitting the semantic evaluation level. This field can be a simple numerical value (such as 1 to 5), or a complex parameter set describing more detailed evaluation information. The reporting in the scheduling request is more close to the function of reporting the semantic evaluation level.

[0215] (2) Radio Resource Control (RRC) message: The UE can report the semantic evaluation level when the RRC connection is established, reconfigured or released, and a special field in the RRC message can carry the semantic evaluation level information.

[0216] (3) Physical Uplink Control Channel (PUCCH): In addition to HARQ feedback and CSI, the UE can attach semantic evaluation level information in the PUCCH. For example, the UE attaches the reported semantic evaluation level when sending HARQ feedback; or an additional field is always included in the PUCCH message to indicate the transmission of the semantic evaluation level.

[0217] (4) Physical Random Access Channel (PRACH): The UE attaches and sends the semantic evaluation level in Msg1 or Msg3 in the four-step random access process, or in MsgA in the two-step random access process.

[0218] S2103: The network side maps the system parameters or semantic coding model according to the semantic evaluation level. The semantic coding model can be considered as a kind of system parameter.

[0219] (1) The semantic evaluation level is associated with the mapping of MCS, TBsize, PRBS, power level, and HARO configuration retransmission times.

[0220] The semantic evaluation level is directly associated with the mapping of system parameters, including modulation and coding scheme (MCS), transport block size (TBsize), number of physical resource blocks (PRBS), transmission power level, and number of hybrid automatic repeat request (HARQ) retransmissions. The following is an example of a mapping table showing the association of semantic evaluation levels with MCS, TBsize, PRBS, power level, and HARQ retransmission number. In implementation, when the semantic information source to be transmitted is a live video source, for example, after the base station analyzes the semantic evaluation level 4, it selects the appropriate MCS (such as 22), larger TBsize (such as 10240 bytes), more PRBS (such as 80), higher power level (such as 20 dBm), and fewer HARQ retransmission times (such as 2 times) from the mapping table. The base station informs the UE to use these parameters through the RRC reconfiguration message, ensuring high-quality transmission and low delay of the video stream.

[0221] (2) The semantic evaluation level can be associated with the mapping of the semantic encoding model ID.

[0222] For example, by mapping different semantic evaluation levels to corresponding semantic encoding models, the system can select the most suitable encoding scheme according to the importance and urgency of the data, thereby optimizing transmission efficiency. The following is an example of a mapping table showing the association of semantic evaluation levels with semantic encoding model IDs.

[0223] S2104: The network side maps system parameters or semantic encoding models according to the semantic evaluation level and informs the UE (system parameter / model indication) downlink.

[0224] The scheduling information can be transmitted through the DCI format. The DCI format contains various information for resource allocation, such as MCS, resource block allocation, power control, etc. The RRC message, i.e., the RRC connection reconfiguration message, can also be used to add new fields to describe MCS, TBsize, HARQ configuration, and semantic encoding model. The above configurations can also be attached in MAC-CE.

[0225] S2105: The UE starts semantic information communication transmission based on the downlink indicated system parameters.

[0226] Example Two: Alternatively, the semantic evaluation level can be defined based on the comparison of the information source semantics and the feedback information source semantics

[0227] Example Two-1: As shown in FIG. 23, it is a schematic diagram of downlink transmission for Example Two, which can include the following steps:

[0228] S2301: Semantic information transmission (downlink)

[0229] In the downlink transmission process, the base station first transmits semantic information source (or called semantic information) to the UE, which can be text, image, video or other forms of data. The base station transmits the semantic information source through PDSCH, and also transmits the broadcast or paging type semantic information through BCH and PCH.

[0230] S2302: Semantic information receiving and processing (UE side)

[0231] After the UE receives the semantic information source transmitted by the base station, it processes and analyzes it. This includes re-encoding the received information source to prepare feedback, which can be traditional source encoding or semantic source channel joint encoding.

[0232] (1) Directly re-source encode the received information source to prepare feedback: After the UE receives the information source transmitted by the base station, it directly re-source encodes it and prepares to transmit the encoded information source back to the base station as feedback information. This method can use traditional source encoding or semantic source channel joint encoding to improve transmission efficiency and data accuracy.

[0233] (2) Prepare feedback for the symbol sequence before the received semantic decoding module: After the UE receives the information source transmitted by the base station, it processes the symbol sequence before the decoding module and prepares to transmit these symbol sequences back to the base station as feedback information.

[0234] S2303: Semantic information source feedback (uplink)

[0235] The UE transmits the processed semantic information source or symbol sequence back to the base station through the uplink to allow the base station to perform semantic comparison and evaluation. For example, it transmits the feedback information source through PUSCH, or for short and small feedback information through PUCCH.

[0236] S2304: Semantic evaluation level measurement (network side)

[0237] After the base station receives the feedback information source transmitted by the UE, it performs semantic comparison and evaluates its similarity to generate a semantic evaluation level. It can use a rule-based method (such as keyword consistency) or an AI-based method (such as measuring feature vector distance) to generate the semantic evaluation level.

[0238] Figure 24 shows an AI-based method for evaluating semantic levels. The semantic information to be compared is input into the same AI model, such as the same semantic encoding model, to obtain the encoded symbol sequences (i.e. feature vectors) V1 and V2. The L1 or L2 distance of V1 and V2 is measured to evaluate the similarity.

[0239] (1) Compare the information source obtained by feedback reception with the original information source, for example, the base station compares the original text sent with the re-encoded text fed back by the UE, uses a keyword matching algorithm to evaluate the consistency of the two, or uses an AI model to calculate the semantic similarity of the two, measures the feature vector distance (such as L1 / L2 distance), to generate a semantic evaluation level.

[0240] (2) Measure the vector distance between the symbol sequence obtained by feedback reception and the transmitted symbol sequence, use a vector distance measurement method (such as L1 distance or L2 distance) to calculate the distance between the two, and generate a semantic evaluation level based on the distance.

[0241] S2305: System parameter / semantic model indication (downlink)

[0242] The base station selects appropriate system parameters and semantic encoding models according to the generated semantic evaluation level, and notifies the UE through the downlink channel so that it transmits data according to the specified configuration. For example, the base station notifies the UE of the system parameters and semantic encoding model ID through PDCCH or RRC message. For example, the base station sends scheduling information containing system parameters and semantic encoding model ID through PDCCH to notify the UE to use specific parameters such as MCS, TBsize, PRBS, power level, and HARQ retransmission times.

[0243] S2306: The base station starts semantic information communication transmission based on system parameters

[0244] Example II-2: As shown in Figure 25, it is a schematic diagram for uplink transmission of Example II, which can include the following steps:

[0245] S2501: Semantic information transmission (uplink)

[0246] During uplink transmission, the UE first transmits the semantic information source to the base station, which can be text, image, video or other forms of data, for example, the semantic information source is transmitted through PUSCH.

[0247] S2502: Semantic information reception and processing (network side)

[0248] After the base station receives the semantic information source transmitted by the UE, it processes and analyzes it. For example, prepare feedback for the re-encoding of the received information source, which can be traditional source encoding or joint encoding of semantic source channel. For example:

[0249] (1) Directly re-encode the received information source to prepare feedback: After the base station receives the semantic information source transmitted by the UE, it directly re-encodes it and prepares to issue the encoded information source as feedback information to the UE. This method can use traditional source encoding or semantic source channel joint encoding to improve transmission efficiency and data accuracy.

[0250] (2) Prepare feedback for the symbol sequence before the received semantic decoding module: After the base station receives the semantic information source transmitted by the UE, it processes the symbol sequence before the decoding module and prepares to issue these symbol sequences as feedback information to the UE.

[0251] S2503: Semantic information source feedback (downlink)

[0252] The base station transmits the processed semantic information source or symbol sequence back to the UE through the downlink to allow the UE to perform semantic comparison and evaluation. For example, the feedback information source is transmitted through PDSCH or PDCCH.

[0253] S2504: Semantic evaluation level measurement (UE side)

[0254] After the UE receives the feedback information source transmitted by the base station, it performs semantic comparison and evaluates its similarity to generate a semantic evaluation level. Rule-based methods (such as keyword consistency) or AI-based methods (such as measuring feature vector distance) can be used to generate the semantic evaluation level. Examples include:

[0255] (1) Compare the information source obtained through feedback reception with the original transmitted information source. For example, compare the originally transmitted text with the re-encoded text fed back by the UE, use a keyword matching algorithm to evaluate the consistency of the two, or use an AI model to calculate the semantic similarity of the two and measure the feature vector distance (such as L1 / L2 distance) to generate a semantic evaluation level.

[0256] (2) Measure the vector distance between the symbol sequence obtained through feedback reception and the transmitted symbol sequence. Use a vector distance measurement method (such as L1 distance or L2 distance) to calculate the distance between the two and generate a semantic evaluation level based on the distance.

[0257] S2505: Semantic evaluation level reporting (uplink)

[0258] The UE reports the calculated semantic evaluation level to the base station, which selects appropriate system parameters and semantic encoding models based on the evaluation level.

[0259] S2506: System parameter / semantic model notification (system parameter / model indication) (downlink)

[0260] The base station selects appropriate system parameters and semantic encoding model according to the generated semantic evaluation level, and notifies the UE through the downlink channel so that it transmits data according to the specified configuration. For example, the base station notifies the UE of the system parameters and semantic encoding model ID through PDCCH or RRC message. For example, the base station sends scheduling information containing system parameters and semantic encoding model ID through PDCCH to notify the UE to use specific parameters such as MCS, TBsize, PRBS, power level, and HARQ retransmission times.

[0261] S2507: UE starts semantic information communication transmission based on the downlink indicated system parameters

[0262] Example Three: Optionally, wherein the semantic evaluation level can be defined based on a comparison of the semantic pilot information source known in advance by both ends

[0263] Example Three-1: As shown in FIG. 26, it is a schematic diagram of downlink transmission for Example Three, which can include the following steps:

[0264] S2601: Semantic pilot information transmission (downlink)

[0265] The base station first transmits semantic pilot information sources (which can be referred to as semantic pilot information) to the UE. These semantic pilot information sources are reference data known in advance by both ends, which are used to ensure consistency of both parties in understanding and evaluating the transmission content. For example, the base station sends a standard text or a predefined semantic sequence, and these information sources have been pre-agreed between the base station and the UE before transmission.

[0266] S2602: Semantic evaluation level measurement (UE side)

[0267] After the UE receives the semantic pilot information sources transmitted by the base station, it performs semantic comparison and evaluates the similarity to generate a semantic evaluation level. Rule-based methods (such as keyword consistency) or AI-based methods (such as measuring feature vector distance) can be used to generate the semantic evaluation level. For example, the received information source is compared with the predefined semantic pilot information source, for example, the received text is compared with the predefined semantic pilot text, and the consistency of the two is evaluated using a keyword matching algorithm, or the semantic similarity of the two is calculated using an AI model, and the feature vector distance (such as L1 / L2 distance) is measured to generate the semantic evaluation level.

[0268] S2603: Semantic evaluation level reporting (uplink)

[0269] The UE reports the calculated semantic evaluation level to the base station, and the base station selects appropriate system parameters and semantic encoding model according to the evaluation level.

[0270] S2604: System parameter model notification (system parameter / model indication) (downlink)

[0271] The base station selects appropriate system parameters and semantic encoding models according to the generated semantic evaluation level, and notifies the UE (system parameter / model indication) through the downlink channel, so that it transmits data according to the specified configuration. For example, the base station notifies the UE of the system parameters and semantic encoding model ID through PDCCH or RRC message. For example, the base station sends scheduling information containing system parameters and semantic encoding model ID through PDCCH to notify the UE to use specific parameters such as MCS, TBsize, PRBS, power level, and HARQ retransmission times.

[0272] S2605: The base station starts semantic information communication transmission based on system parameters.

[0273] Example Three-2: As shown in FIG. 27, it is a schematic diagram for uplink transmission of Example Three, which can include the following steps:

[0274] S2701: Semantic pilot information transmission (uplink)

[0275] The UE first transmits semantic pilot information sources to the base station. These semantic pilot information sources are double-end known reference data in advance, which are used to ensure the consistency of the understanding and evaluation of the transmission content by both parties. For example, the UE sends a standard text or a predefined semantic sequence, and these information sources have been pre-agreed between the base station and the UE before transmission.

[0276] S2702: Semantic comparison to obtain evaluation level (network side)

[0277] After the base station receives the semantic pilot information sources transmitted by the UE, it performs semantic comparison and evaluates the similarity to generate a semantic evaluation level. Rule-based methods (such as keyword consistency) or AI-based methods (such as measuring feature vector distance) can be used to generate the semantic evaluation level. For example, the received information source is compared with the predefined semantic pilot information source. For example, the received text is compared with the predefined semantic pilot text, and the consistency of the two is evaluated using a keyword matching algorithm, or the semantic similarity of the two is calculated using an AI model, and the feature vector distance (such as L1 / L2 distance) is measured to generate the semantic evaluation level.

[0278] S2703: System parameter model notification (system parameter / model indication) (downlink)

[0279] The base station selects appropriate system parameters and semantic coding model according to the generated semantic evaluation level, and notifies the UE through a downlink channel so that the UE transmits data according to the specified configuration. For example, the base station notifies the UE of the system parameters and semantic coding model ID through a PDCCH or an RRC message. For example, the base station sends scheduling information containing the system parameters and semantic coding model ID through a PDCCH to notify the UE to use specific parameters such as MCS, TBsize, PRBS, power level, and HARQ retransmission times.

[0280] S2704: The UE starts semantic information communication transmission based on the system parameters indicated by the downlink

[0281] The embodiments of the present application can improve transmission efficiency: optimal resource allocation can be optimized based on the determination of optimal system parameters and coding model. The embodiments of the present application can also improve transmission quality: high-priority semantic information can be ensured to be transmitted first, and the delay and error rate can be reduced. The embodiments of the present application can also improve system flexibility: transmission strategies can be dynamically adjusted based on real-time semantic evaluation to adapt to different application scenarios.

[0282] FIG. 28 is a schematic block diagram of a first communication device 2800 according to an embodiment of the present application. The first communication device 2800 can include:

[0283] The receiving unit 2810 is configured to receive system parameters corresponding to a semantic level, the semantic level being obtained based on first information, and the system parameters being used for transmitting second information.

[0284] In an embodiment, the first communication device further includes:

[0285] The processing unit 2820 is configured to obtain the semantic level based on the first information.

[0286] The sending unit 2830 is configured to send the semantic level.

[0287] In an embodiment, the first information is first semantic information, and the second information is second semantic information. The sending unit is further configured to send the second semantic information.

[0288] In an embodiment, the semantic level is obtained based on at least one of the following rules: a type of the first semantic information; a transmission importance of the first semantic information; a transmission urgency of the first semantic information; a source of the first semantic information; a content of the first semantic information; a context of the first semantic information; and a content format of the first semantic information.

[0289] In an implementation, the semantic level is obtained by processing the first semantic information by a first artificial intelligence model, input features of the first artificial intelligence model comprising at least one of: semantic content, context information, a list of key elements; output features of the first artificial intelligence model comprising: the semantic level.

[0290] In an implementation, the first information comprises third semantic information and fourth semantic information, the second information is fifth semantic information, the sending unit 2830 is further configured to send the third semantic information; the receiving unit 2810 is further configured to receive the fourth semantic information, the fourth semantic information being obtained based on the third semantic information; the sending unit 2830 is further configured to send the fifth semantic information.

[0291] In an implementation, the first information is semantic pilot information, the second information is sixth semantic information, the receiving unit 2801 is further configured to receive the semantic pilot information; receive the sixth semantic information.

[0292] In an implementation, the semantic level is obtained by a second communication device based on the first information.

[0293] In an implementation, the first information comprises third semantic information and fourth semantic information, the second information is fifth semantic information, the receiving unit 2810 is further configured to receive the third semantic information; the processing unit 2820 is further configured to obtain the fourth semantic information based on the third semantic information; the sending unit 2830 is further configured to send the fourth semantic information; the receiving unit 2810 is further configured to receive the fifth semantic information.

[0294] In an implementation, the first information is semantic pilot information, the second information is sixth semantic information, the sending unit 2830 is further configured to send the semantic pilot information; send the sixth semantic information.

[0295] In an implementation, the manner of obtaining the fourth semantic information based on the third semantic information comprises at least one of:

[0296] re-source encoding or semantic source channel joint encoding is performed on the third semantic information to obtain the fourth semantic information;

[0297] processing a symbol sequence before a decoding module of the third semantic information, the symbol sequence being the fourth semantic information.

[0298] In an implementation, the semantic level is obtained by processing the third semantic information and the fourth semantic information by a second artificial intelligence model, input features of the second artificial intelligence model comprising at least one of the third semantic information and the fourth semantic information, output features of the second artificial intelligence model comprising at least one of the first symbol sequence after encoding the third semantic information, the second symbol sequence after encoding the fourth semantic information, the similarity between the first symbol sequence and the second symbol sequence, the distance between the first symbol sequence and the second symbol sequence, and the semantic level.

[0299] In an implementation, the semantic level is obtained by processing the semantic pilot information by a third artificial intelligence model, input features of the third artificial intelligence model comprising at least one of the received semantic pilot information and the predefined semantic pilot information, output features of the third artificial intelligence model comprising at least one of the third symbol sequence after encoding the received semantic pilot information, the fourth symbol sequence after encoding the predefined semantic pilot information, the similarity between the third symbol sequence and the fourth symbol sequence, the distance between the third symbol sequence and the fourth symbol sequence, and the semantic level.

[0300] In an implementation, the semantic level is carried by at least one of the following: SR; RRC message; PUCCH; PRACH.

[0301] In an implementation, the semantic level is carried by at least one of the following: DCI format transmission scheduling information; RRC message; MAC-CE.

[0302] In an implementation, the semantic level has a mapping relationship with the system parameter, the system parameter comprising at least one of the following: MCS; transport block size; PRBS; transmission power level; number of retransmissions of HARQ; semantic encoding model identifier; semantic encoding model.

[0303] The first communication device 2800 of the embodiments of the present application can realize the corresponding functions of the first communication device in the foregoing method embodiments. The corresponding processes, functions, implementation manners, and beneficial effects of each module (sub-module, unit, or component, etc.) in the first communication device can be referred to the corresponding description in the foregoing method embodiments, which will not be described here. It should be noted that the functions described with respect to each module (sub-module, unit, or component, etc.) in the first communication device of the embodiments of the present application can be realized by different modules (sub-modules, units, or components, etc.), or by the same module (sub-module, unit, or component, etc.).

[0304] FIG. 29 is a schematic block diagram of a second communication device 2900 according to an embodiment of the present application. The second communication device 2900 can include:

[0305] The sending unit 2910 is configured to send a system parameter corresponding to a semantic level, the semantic level being obtained based on the first information, and the system parameter being used for transmission of the second information.

[0306] In an embodiment, the second communication device further includes:

[0307] The receiving unit 2920 is configured to receive the semantic level, the semantic level being obtained by the first communication device based on the first information.

[0308] In an embodiment, the first information is first semantic information, the second information is second semantic information, and the receiving unit 2920 is further configured to receive the second semantic information.

[0309] In an embodiment, the semantic level is obtained based on at least one of the following rules: a type of the first semantic information; a transmission importance of the first semantic information; a transmission urgency of the first semantic information; a source of the first semantic information; a content of the first semantic information; a context of the first semantic information; a content format of the first semantic information.

[0310] In an embodiment, the semantic level is obtained by processing the first semantic information by a first artificial intelligence model, and an input feature of the first artificial intelligence model includes at least one of the following: semantic content, context information, a list of key elements; and an output feature of the first artificial intelligence model includes the semantic level.

[0311] In an embodiment, the first information includes third semantic information and fourth semantic information, the second information is fifth semantic information, the receiving unit 2920 is further configured to receive the third semantic information; the sending unit 2910 is further configured to send the fourth semantic information, the fourth semantic information being obtained based on the third semantic information; and the receiving unit 2920 is further configured to receive the fifth semantic information.

[0312] In an embodiment, the first information is semantic pilot information, the second information is sixth semantic information, the sending unit 2910 is further configured to send the semantic pilot information; and the sixth semantic information is sent.

[0313] In an embodiment, the second communication device further includes:

[0314] The processing unit 2930 is configured to obtain the semantic level based on the first information.

[0315] In an embodiment, the first information comprises third semantic information and fourth semantic information, the second information is fifth semantic information, the sending unit 2910 is further configured to send the third semantic information, the third semantic information is used to obtain the fourth semantic information; the receiving unit 2920 is further configured to receive the fourth semantic information; the sending unit 2910 is further configured to send the fifth semantic information.

[0316] In an embodiment, the first information is semantic pilot information, the second information is sixth semantic information, the receiving unit 2920 is further configured to receive the semantic pilot information; receive the sixth semantic information.

[0317] In an embodiment, the manner of obtaining the fourth semantic information based on the third semantic information comprises at least one of the following:

[0318] Re-source encoding or semantic source channel joint encoding of the third semantic information to obtain the fourth semantic information;

[0319] Processing a symbol sequence before a decoding module of the third semantic information, the symbol sequence being the fourth semantic information.

[0320] In an embodiment, the semantic level is obtained by processing the third semantic information and the fourth semantic information by a second artificial intelligence model, input features of the second artificial intelligence model comprising at least one of the following: the third semantic information and the fourth semantic information; output features of the second artificial intelligence model comprising at least one of the following: a first symbol sequence after encoding of the third semantic information, a second symbol sequence after encoding of the fourth semantic information, a similarity of the first symbol sequence and the second symbol sequence, a distance of the first symbol sequence and the second symbol sequence, a semantic level.

[0321] In an embodiment, the semantic level is obtained by processing semantic pilot information by a third artificial intelligence model, input features of the third artificial intelligence model comprising at least one of the following: received semantic pilot information, predefined semantic pilot information; output features of the third artificial intelligence model comprising at least one of the following: a third symbol sequence after encoding of the received semantic pilot information, a fourth symbol sequence after encoding of the predefined semantic pilot information, a similarity of the third symbol sequence and the fourth symbol sequence, a distance of the third symbol sequence and the fourth symbol sequence, a semantic level.

[0322] In an embodiment, the semantic level is carried by at least one of the following: SR; RRC message; PUCCH; PRACH.

[0323] In an embodiment, the semantic level is carried by at least one of the following: DCI format transmission scheduling information; RRC message; MAC-CE.

[0324] In an embodiment, the semantic level has a mapping relationship with the system parameter, and the system parameter includes at least one of the following: MCS, transport block size, PRBS, transmission power level, retransmission number of HARQ, semantic coding model identifier, and semantic coding model.

[0325] The second communication device 2900 of the embodiment of the application can realize the corresponding functions of the second communication device in the foregoing method embodiments. The corresponding processes, functions, implementation manners, and beneficial effects of each module (sub-module, unit, or component, etc.) in the second communication device 2900 can be referred to the corresponding description in the foregoing method embodiments, which will not be described here again. It should be noted that the functions described with respect to each module (sub-module, unit, or component, etc.) in the second communication device of the embodiment of the application can be realized by different modules (sub-modules, units, or components, etc.), or by the same module (sub-module, unit, or component, etc.).

[0326] FIG. 30 is a schematic structural diagram of a communication device 3000 according to an embodiment of the application. The communication device 3000 includes a processor 3010. The processor 3010 can call and run a computer program from a memory to enable the communication device 3000 to implement the method in the embodiment of the application.

[0327] In an embodiment, the communication device 3000 can further include a memory 3020. The processor 3010 can call and run a computer program from the memory 3020 to enable the communication device 3000 to implement the method in the embodiment of the application.

[0328] The memory 3020 can be a separate device independent of the processor 3010, or can be integrated in the processor 3010.

[0329] In an embodiment, the communication device 3000 can further include a transceiver 3030. The processor 3010 can control the transceiver 3030 to communicate with other devices. Specifically, the transceiver 3030 can send information or data to other devices, or receive information or data sent by other devices.

[0330] The transceiver 3030 can include a transmitter and a receiver. The transceiver 3030 can further include an antenna, and the number of antennas can be one or more.

[0331] In an embodiment, the communication device 3000 can be the first communication device of the embodiment of the application, and the communication device 3000 can realize the corresponding processes realized by the first communication device in each method of the embodiment of the application. For brevity, details will not be described here again.

[0332] In an embodiment, the communication device 3000 can be a second communication device of the embodiments of the present application, and the communication device 3000 can implement the corresponding procedures implemented by the second communication device in the various methods of the embodiments of the present application. For brevity, details are not repeated here.

[0333] FIG. 31 is a schematic structural diagram of a chip 3100 according to an embodiment of the present application. The chip 3100 includes a processor 3110, which can call and run a computer program from a memory to implement the methods in the embodiments of the present application.

[0334] In an embodiment, the chip 3100 can further include a memory 3120. The processor 3110 can call and run a computer program from the memory 3120 to implement the methods performed by the first communication device or the second communication device in the embodiments of the present application.

[0335] The memory 3120 can be a separate device independent of the processor 3110, or can be integrated in the processor 3110.

[0336] In an embodiment, the chip 3100 can further include an input interface 3130. The processor 3110 can control the input interface 3130 to communicate with other devices or chips, and specifically, can obtain information or data sent by other devices or chips.

[0337] In an embodiment, the chip 3100 can further include an output interface 3140. The processor 3110 can control the output interface 3140 to communicate with other devices or chips, and specifically, can output information or data to other devices or chips.

[0338] In an embodiment, the chip can be applied to the first communication device in the embodiments of the present application, and the chip can implement the corresponding procedures implemented by the first communication device in the various methods of the embodiments of the present application. For brevity, details are not repeated here.

[0339] In an embodiment, the chip can be applied to the second communication device in the embodiments of the present application, and the chip can implement the corresponding procedures implemented by the second communication device in the various methods of the embodiments of the present application. For brevity, details are not repeated here.

[0340] The chip applied to the first communication device and the second communication device can be the same chip or different chips.

[0341] It should be understood that the chip mentioned in the embodiments of the present application can also be referred to as a system-level chip, a system chip, a chip system, or a system-on-chip chip, etc.

[0342] The aforementioned processor can be a general-purpose processor, a digital signal processor (DSP), a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), or other programmable logic device, transistor logic device, discrete hardware component, etc. Among them, the aforementioned general-purpose processor can be a microprocessor or any conventional processor, etc.

[0343] The aforementioned memory can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable ROM (PROM), an erasable PROM (EPROM), an electrically EPROM (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM).

[0344] It should be understood that the aforementioned memory is an exemplary but non-limiting description, for example, the memory in the embodiments of the present application can also be a static RAM (SRAM), a dynamic RAM (DRAM), a synchronous DRAM (SDRAM), a double data rate SDRAM (DDR SDRAM), an enhanced SDRAM (ESDRAM), a synch link DRAM (SLDRAM), and a direct memory bus random access memory (Direct Rambus RAM, DR RAM), etc. That is, the memory in the embodiments of the present application is intended to include but not limited to these and any other suitable type of memory.

[0345] FIG. 32 is a schematic block diagram of a communication system 3200 according to an embodiment of the present application. The communication system 3200 includes a first communication device 3210 and a second communication device 3220.

[0346] The first communication device 3210 is configured to receive a system parameter corresponding to a semantic level, the semantic level being obtained based on the first information, and the system parameter being used for transmitting the second information.

[0347] The second communication device 3220 is configured to send a system parameter corresponding to a semantic level.

[0348] The first communication device 3210 can be configured to implement the corresponding functions of the first communication device in the above-described method, and the second communication device 3220 can be configured to implement the corresponding functions of the second communication device in the above-described method. For brevity, they will not be described here.

[0349] In the above embodiments, all or part of them can be realized by software, hardware, firmware, or any combination thereof. When realized by software, all or part of them can be realized in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed by a computer, all or part of them generate a flow or function according to the embodiments of the present application. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another, for example, the computer instructions can be transferred from one website, computer, server or data center to another through wired (such as coaxial cable, optical fiber, digital subscriber line (Digital Subscriber Line, DSL)) or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media. The available medium can be a magnetic medium (for example, floppy disk, hard disk, magnetic tape), an optical medium (for example, DVD), or a semiconductor medium (for example, solid state disk (Solid State Disk, SSD)) and the like.

[0350] It should be understood that in various embodiments of the present application, the size of the sequence number of each process described above does not mean the order of execution, and the execution order of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0351] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0352] The above merely provides the specific implementation of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of the changes or replacements within the technical range disclosed by the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for communication, comprising: receiving, by a first communication device, a system parameter corresponding to a semantic level, the semantic level being derived based on first information, the system parameter being used for transmitting second information.

2. The method of claim 1, wherein, The method further comprises: deriving, by the first communication device, the semantic level based on the first information; transmitting, by the first communication device, the semantic level.

3. The method of claim 2, wherein, The first information is first semantic information, and the second information is second semantic information, and the method further comprises: transmitting, by the first communication device, the second semantic information.

4. The method of claim 3, wherein, The semantic level is derived based on at least one of the following rules: a type of the first semantic information; a transmission importance of the first semantic information; a transmission urgency of the first semantic information; a source of the first semantic information; a content of the first semantic information; a context of the first semantic information; a content format of the first semantic information. The semantic level is derived by processing the first semantic information by a first artificial intelligence model, and input features of the first artificial intelligence model comprise at least one of the following: semantic content, context information, a list of key elements.

5. The method of claim 3 or 4, wherein, Output features of the first artificial intelligence model comprise the semantic level. The first information comprises third semantic information and fourth semantic information, and the second information is fifth semantic information, and the method further comprises:

6. The method of claim 2, wherein, transmitting, by the first communication device, the third semantic information; receiving, by the first communication device, the fourth semantic information, the fourth semantic information being derived based on the third semantic information; transmitting, by the first communication device, the fifth semantic information. The first information is semantic pilot information, and the second information is sixth semantic information, and the method further comprises:

7. The method of claim 2, wherein, receiving, by the first communication device, the semantic pilot information; receiving, by the first communication device, the sixth semantic information. The semantic level is derived by a second communication device transmitting the system parameter based on first information.

8. The method of claim 1, wherein, The first information comprises third semantic information and fourth semantic information, and the second information is fifth semantic information, and the method further comprises:

9. The method of claim 8, wherein, receiving, by the first communication device, the third semantic information; deriving, by the first communication device, the fourth semantic information based on the third semantic information; transmitting, by the first communication device, the fourth semantic information; receiving, by the first communication device, the fifth semantic information. The first information is semantic pilot information, and the second information is sixth semantic information, and the method further comprises:

10. The method of claim 8, wherein, transmitting, by the first communication device, the semantic pilot information; transmitting, by the first communication device, the sixth semantic information. The way of deriving the fourth semantic information based on the third semantic information comprises at least one of the following:

11. The method of claim 6 or 9, wherein, re-performing source coding or semantic source channel joint coding on the third semantic information to derive the fourth semantic information; processing a symbol sequence before a decoding module of the third semantic information, the symbol sequence being the fourth semantic information. ​ 12. The method of claim 6 or 9 or 11, wherein, The semantic level is obtained by processing the third semantic information and the fourth semantic information by a second artificial intelligence model, input features of the second artificial intelligence model include at least one of the third semantic information and the fourth semantic information, output features of the second artificial intelligence model include at least one of a first symbol sequence after encoding the third semantic information, a second symbol sequence after encoding the fourth semantic information, a similarity between the first symbol sequence and the second symbol sequence, a distance between the first symbol sequence and the second symbol sequence, and the semantic level.

13. The method of claim 7 or 10, wherein, The semantic level is obtained by processing semantic pilot information by a third artificial intelligence model, input features of the third artificial intelligence model include at least one of received semantic pilot information and predefined semantic pilot information, and output features of the third artificial intelligence model include at least one of a third symbol sequence after encoding the received semantic pilot information, a fourth symbol sequence after encoding the predefined semantic pilot information, a similarity between the third symbol sequence and the fourth symbol sequence, a distance between the third symbol sequence and the fourth symbol sequence, and the semantic level.

14. The method of any one of claims 1 to 7, wherein, The semantic level is carried by at least one of a scheduling request (SR), a radio resource control (RRC) message, a physical uplink control channel (PUCCH), and a physical random access channel (PRACH).

15. The method of any one of claims 1, 8 to 13, wherein, The semantic level is carried by at least one of a downlink control information (DCI) format transmission scheduling information, an RRC message, and a medium access control control element (MAC-CE).

16. The method of any one of claims 1 to 15, wherein, The semantic level has a mapping relationship with system parameters, and the system parameters include at least one of a modulation and coding scheme (MCS), a transport block size, a number of physical resource blocks (PRBS), a transmission power level, a number of hybrid automatic repeat request (HARQ) retransmissions, a semantic encoding model identifier, and a semantic encoding model.

17. A communication method, comprising: A second communication device transmits system parameters corresponding to a semantic level, the semantic level being obtained based on first information, and the system parameters being used for transmitting second information.

18. The method of claim 17, wherein, The method further comprises: The second communication device receives the semantic level, which is obtained by a first communication device based on the first information.

19. The method of claim 18, wherein, The first information is first semantic information, and the second information is second semantic information, and the method further comprises: The second communication device receives the second semantic information.

20. The method of claim 19, wherein, The semantic level is obtained based on at least one of the following rules: a type of the first semantic information, a transmission importance of the first semantic information, a transmission urgency of the first semantic information, a source of the first semantic information, a content format of the first semantic information. The semantic level is obtained by processing the first semantic information by a first artificial intelligence model, input features of the first artificial intelligence model include at least one of semantic content, context information, and a list of key elements.

21. The method of claim 19 or 20, wherein, Output features of the first artificial intelligence model include the semantic level. ​ 22. The method of claim 18, wherein, The first information comprises third semantic information and fourth semantic information, the second information is fifth semantic information, and the method further comprises: The second communication device receives the third semantic information; The second communication device sends the fourth semantic information, which is obtained based on the third semantic information; The second communication device receives the fifth semantic information.

23. The method of claim 18, wherein, The first information is semantic pilot information, and the second information is sixth semantic information, and the method further comprises: The second communication device sends the semantic pilot information; The second communication device sends the sixth semantic information.

24. The method of claim 17, wherein, The method further comprises: The second communication device obtains the semantic level based on the first information.

25. The method of claim 24, wherein, The first information comprises third semantic information and fourth semantic information, the second information is fifth semantic information, and the method further comprises: The second communication device sends the third semantic information, which is used to obtain the fourth semantic information; The second communication device receives the fourth semantic information; The second communication device sends the fifth semantic information.

26. The method of claim 24, wherein, The first information is semantic pilot information, and the second information is sixth semantic information, and the method further comprises: The second communication device receives the semantic pilot information; The second communication device receives the sixth semantic information.

27. The method of claim 22 or 25, wherein, The manner of obtaining the fourth semantic information based on the third semantic information comprises at least one of the following: The third semantic information is re-encoded or jointly encoded with a semantic source channel to obtain the fourth semantic information; A symbol sequence before a decoding module of the third semantic information is processed, and the symbol sequence is the fourth semantic information.

28. The method of claim 22 or 25 or 27, wherein, The semantic level is obtained by processing the third semantic information and the fourth semantic information by a second artificial intelligence model, input features of the second artificial intelligence model comprise at least one of the following: the third semantic information and the fourth semantic information, output features of the second artificial intelligence model comprise at least one of the following: a first symbol sequence after encoding of the third semantic information, a second symbol sequence after encoding of the fourth semantic information, a similarity of the first symbol sequence and the second symbol sequence, a distance of the first symbol sequence and the second symbol sequence, and a semantic level.

29. The method of claim 23 or 26, wherein, The semantic level is obtained by processing the semantic pilot information by a third artificial intelligence model, input features of the third artificial intelligence model comprise at least one of the following: received semantic pilot information and predefined semantic pilot information, and output features of the third artificial intelligence model comprise at least one of the following: a third symbol sequence after encoding of the received semantic pilot information, a fourth symbol sequence after encoding of the predefined semantic pilot information, a similarity of the third symbol sequence and the fourth symbol sequence, a distance of the third symbol sequence and the fourth symbol sequence, and a semantic level.

30. The method of any one of claims 17 to 23, wherein, The semantic level is carried by at least one of the following: SR; RRC message; PUCCH; and PRACH.

31. The method of any one of claims 17, 24-29, wherein, The semantic level is carried by at least one of the following: DCI format transmission scheduling information; RRC message; and MAC-CE.

32. The method of any one of claims 17-31, wherein, The semantic level has a mapping relationship with the system parameter, and the system parameter includes at least one of the following: MCS, transport block size, PRBS, transmission power level, retransmission number of HARQ, semantic coding model identifier, and semantic coding model.

33. A first communication device, comprising: a receiving unit configured to receive a system parameter corresponding to a semantic level, the semantic level being obtained based on first information, and the system parameter being used for transmitting second information.

34. The first communication device of claim 33, wherein, The first communication device further comprises: a processing unit configured to obtain the semantic level based on the first information; a sending unit configured to send the semantic level.

35. The first communication device of claim 34, wherein, The first information is first semantic information, and the second information is second semantic information, and the sending unit is further configured to send the second semantic information.

36. The first communication device of claim 35, wherein The semantic level is obtained based on at least one of the following rules: type of the first semantic information, transmission importance of the first semantic information, transmission urgency of the first semantic information, source of the first semantic information, and content of the first semantic information. Context of the first semantic information, and content format of the first semantic information.

37. A first communications device according to claim 35 or 36, wherein, The semantic level is obtained by processing the first semantic information by a first artificial intelligence model, and input features of the first artificial intelligence model include at least one of the following: semantic content, context information, and key element list. Output features of the first artificial intelligence model include the semantic level.

38. The first communication device of claim 34, wherein, The first information includes third semantic information and fourth semantic information, the second information is fifth semantic information, and the first communication device further comprises: The sending unit is further configured to send the third semantic information. The receiving unit is further configured to receive the fourth semantic information, and the fourth semantic information is obtained based on the third semantic information. The sending unit is further configured to send the fifth semantic information.

39. The first communication device of claim 34, wherein, The first information is semantic pilot information, the second information is sixth semantic information, and the receiving unit is further configured to: receive the semantic pilot information; receive the sixth semantic information.

40. The first communication device of claim 35, wherein, The semantic level is obtained by a second communication device based on first information.

41. The first communication device of claim 40, wherein, The first information includes third semantic information and fourth semantic information, the second information is fifth semantic information, and the first communication device further comprises: The receiving unit is further configured to receive the third semantic information. The processing unit is further configured to obtain the fourth semantic information based on the third semantic information. The sending unit is further configured to send the fourth semantic information. The receiving unit is further configured to receive the fifth semantic information.

42. The first communication device of claim 40, wherein, The first information is semantic pilot information, the second information is sixth semantic information, and the first communication device further comprises: The first communication device sends the semantic pilot information. The first communication device sends the sixth semantic information.

43. The first communication device as claimed in claim 38 or 41, wherein, The way of obtaining the fourth semantic information based on the third semantic information includes at least one of the following: The third semantic information is re-encoded by a source or jointly encoded by a semantic source channel to obtain the fourth semantic information. The symbol sequence before the decoding module of the third semantic information is processed, and the symbol sequence is the fourth semantic information.

44. The first communication device as claimed in claim 38 or 41 or 43, wherein, The semantic level is obtained by processing the third semantic information and the fourth semantic information by a second artificial intelligence model, input features of the second artificial intelligence model include at least one of the third semantic information and the fourth semantic information, and output features of the second artificial intelligence model include at least one of the first symbol sequence after encoding of the third semantic information, the second symbol sequence after encoding of the fourth semantic information, the similarity of the first symbol sequence and the second symbol sequence, the distance of the first symbol sequence and the second symbol sequence, and the semantic level.

45. The first communication device of claim 39 or 42, wherein, The semantic level is obtained by processing semantic pilot information by a third artificial intelligence model, input features of the third artificial intelligence model include at least one of received semantic pilot information and predefined semantic pilot information, and output features of the third artificial intelligence model include at least one of a third symbol sequence after encoding of the received semantic pilot information, a fourth symbol sequence after encoding of the predefined semantic pilot information, the similarity of the third symbol sequence and the fourth symbol sequence, the distance of the third symbol sequence and the fourth symbol sequence, and the semantic level.

46. The first communication device of any one of claims 33 to 39, wherein, The semantic level is carried by at least one of SR, an RRC message, a PUCCH, and a PRACH.

47. The first communication device according to any one of claims 33, 40 to 45, wherein, The semantic level is carried by at least one of DCI format transmission scheduling information, an RRC message, and MAC-CE.

48. A first communications device according to any one of claims 33 to 47, wherein, The semantic level has a mapping relationship with system parameters, and the system parameters include at least one of MCS, a transport block size, a PRBS, a transmission power level, the number of retransmissions of HARQ, a semantic encoding model identifier, and a semantic encoding model. 49.A second communication device, comprising: a sending unit configured to send system parameters corresponding to a semantic level, the semantic level being obtained based on first information, and the system parameters being used for transmitting second information.

50. A second communications device according to Claim 49 wherein, The second communication device further comprises: a receiving unit configured to receive the semantic level, the semantic level being obtained by a first communication device based on the first information.

51. The second communication device of claim 50, wherein, The first information is first semantic information, and the second information is second semantic information, and the second communication device further comprises: The receiving unit is further configured to receive the second semantic information.

52. The second communication device of claim 51, wherein, The semantic level is obtained based on at least one of the following rules: the type of the first semantic information, the transmission importance of the first semantic information, the transmission urgency of the first semantic information, the source of the first semantic information, the content of the first semantic information, the context of the first semantic information, and the content format of the first semantic information. The semantic level is obtained by processing the first semantic information by a first artificial intelligence model, input features of the first artificial intelligence model include at least one of semantic content, context information, and a list of key elements, and output features of the first artificial intelligence model include the semantic level.

53. The second communication device of claim 51 or 52, wherein, The semantic level is obtained by processing the first semantic information by a first artificial intelligence model, input features of the first artificial intelligence model include at least one of semantic content, context information, and a list of key elements, and output features of the first artificial intelligence model include the semantic level. ​ 54. The second communication device of claim 50, wherein, The first information comprises third semantic information and fourth semantic information, the second information is fifth semantic information, and the second communication device further comprises: The receiving unit is further configured to receive the third semantic information; The sending unit is further configured to send the fourth semantic information, which is obtained based on the third semantic information; The receiving unit is further configured to receive the fifth semantic information.

55. The second communication device of claim 50, wherein, The first information is semantic pilot information, and the second information is sixth semantic information, and the second communication device further comprises: The sending unit is further configured to send the semantic pilot information; The sending unit is further configured to send the sixth semantic information.

56. The second communication device of claim 49, wherein, The second communication device further comprises: The processing unit is configured to obtain the semantic level based on the first information.

57. The second communication device of claim 56, wherein, The first information comprises third semantic information and fourth semantic information, the second information is fifth semantic information, and the second communication device further comprises: The sending unit is further configured to send the third semantic information, which is used to obtain the fourth semantic information; The receiving unit is further configured to receive the fourth semantic information; The sending unit is further configured to send the fifth semantic information.

58. The second communication device of claim 56, wherein, The first information is semantic pilot information, and the second information is sixth semantic information, and the second communication device further comprises: The receiving unit is further configured to receive the semantic pilot information; The receiving unit is further configured to receive the sixth semantic information.

59. A second communications device according to claim 54 or 57, wherein, The manner in which the fourth semantic information is obtained based on the third semantic information comprises at least one of the following: The third semantic information is re-encoded or jointly encoded with a semantic source channel to obtain the fourth semantic information; A symbol sequence before a decoding module of the third semantic information is processed, and the symbol sequence is the fourth semantic information.

60. A second communications device according to claim 54 or 57 or 59, wherein, The semantic level is obtained by processing the third semantic information and the fourth semantic information by a second artificial intelligence model, input features of the second artificial intelligence model comprise at least one of the following: the third semantic information and the fourth semantic information, output features of the second artificial intelligence model comprise at least one of the following: a first symbol sequence after encoding of the third semantic information, a second symbol sequence after encoding of the fourth semantic information, a similarity between the first symbol sequence and the second symbol sequence, a distance between the first symbol sequence and the second symbol sequence, and a semantic level.

61. The second communication device of claim 55 or 58, wherein, The semantic level is obtained by processing semantic pilot information by a third artificial intelligence model, input features of the third artificial intelligence model comprise at least one of the following: received semantic pilot information and predefined semantic pilot information, and output features of the third artificial intelligence model comprise at least one of the following: a third symbol sequence after encoding of the received semantic pilot information, a fourth symbol sequence after encoding of the predefined semantic pilot information, a similarity between the third symbol sequence and the fourth symbol sequence, a distance between the third symbol sequence and the fourth symbol sequence, and a semantic level.

62. A second communications device according to any one of claims 49 to 55, wherein, The semantic level is carried by at least one of the following: an SR; an RRC message; a PUCCH; and a PRACH.

63. A second communications device according to any one of claims 49, 56 to 61 wherein, The semantic level carries at least one of the following: DCI format transmission scheduling information; RRC message; MAC-CE.

64. A second communications device according to any one of claims 49 to 63, wherein, The semantic level has a mapping relationship with the system parameter, and the system parameter includes at least one of the following: MCS; transport block size; PRBS; transmission power level; HARQ retransmission number; semantic coding model identifier; semantic coding model.

65. A communication device, comprising: A transceiver, a processor and a memory, the memory is used to store a computer program, the transceiver is used to communicate with other devices, and the processor is used to call and run the computer program stored in the memory, so that the communication device executes the method as claimed in any one of claims 1-32.

66. A chip comprising: A processor is used to call and run a computer program from a memory, so that a device installed with the chip executes the method as claimed in any one of claims 1-32.

67. A computer readable storage medium for storing a computer program which, when executed by a device, causes the device to perform the method as claimed in any one of claims 1-32.

68. A computer program product comprising computer program instructions which cause a computer to perform the method as claimed in any one of claims 1-32.

69. A computer program which causes a computer to perform the method as claimed in any one of claims 1-32.

70. A communication system comprising: A first communication device for performing the method as claimed in any one of claims 1-16; A second communication device for performing the method as claimed in any one of claims 17-32.

Images