Electronic device and method for wireless communication, and computer-readable storage medium

Abstract

An electronic device and method for wireless communication, and a computer-readable storage medium. The electronic device for wireless communication comprises at least one processor and at least one memory, wherein the at least one memory comprises a computer program code, and the at least one memory and the computer program code are configured to cause, by means of the at least one processor, the electronic device to determine, on the basis of a semantic communication error rate related to a user equipment for semantic communication, whether to update a semantic library for semantic communication of the user equipment and / or an inference model related to the semantic library.

Description

Electronic device and method for wireless communication, computer readable storage medium This application claims priority to the Chinese patent application No. 202410172862.6, filed on February 5, 2024, and entitled “Electronic device and method for wireless communication, computer readable storage medium”, the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of wireless communication, and in particular, to an electronic device and method for wireless communication. More specifically, the present disclosure relates to an electronic device and method for wireless communication that can improve the continuity and reliability of semantic communication. BACKGROUND

[0002] With the continuous development of networks, semantic communication has become a highly regarded communication method. For example, the Internet of Vehicles is a scenario involving voice communication. For example, communication between terminal user devices is also a scenario involving voice communication.

[0003] Taking the Internet of Vehicles as an example, vehicle communication can not only involve traditional mobile communication, but also include semantic communication, which is a unique communication mode. As an advanced communication method, semantic communication not only expands the diversity of communication, but also provides a profound transformation for vehicle communication and related fields in urban networks. It has become an important pillar of modern urban networks and plays a crucial role in building safer, more efficient, and intelligent urban transportation systems.

[0004] Firstly, semantic communication improves the efficiency and reliability of communication. By supporting different types of communication, such as voice, data, sensor information, etc., semantic communication enables vehicles to choose the most suitable communication method according to specific needs. This helps to improve the efficiency and reliability of information transmission, ensuring that vehicles can accurately and timely transmit and receive critical information. Secondly, semantic communication is the foundation of intelligent transportation systems. It enables vehicles to interact with the surrounding environment, other vehicles, and transportation infrastructure in real time. This real-time interaction helps to optimize traffic flow, improve traffic safety, reduce traffic congestion, and improve fuel efficiency. Therefore, semantic communication provides key support for the construction and development of intelligent transportation systems.

[0005] In urban networks, vehicles often need to pass through multiple semantic communication service areas, which are significantly different from traditional cellular network cells. In this context, a key problem has emerged: how to implement handover between different semantic communication cells, especially since these cells cannot simply rely on traditional signal power measurement methods. SUMMARY

[0006] The following presents a simplified summary of the application in order to provide a basic understanding of some aspects of the application. This summary is not an extensive overview of the application. It is not intended to identify key or critical elements of the application or to delineate the scope of the application. Its sole purpose is to present some concepts in a simplified form as a prelude to the more detailed description that is discussed later.

[0007] According to an aspect of the present disclosure, an electronic device for wireless communication is provided, comprising: at least one processor; and at least one memory including computer program codes, wherein the at least one memory and the computer program codes are configured to, with the at least one processor, cause the electronic device to perform: determining whether to update a semantic library for semantic communication and / or an inference model related to the semantic library of the electronic device based on a semantic communication error rate related to a user equipment for semantic communication.

[0008] According to an aspect of the present disclosure, an electronic device for wireless communication is provided, comprising: at least one processor; and at least one memory including computer program codes, wherein the at least one memory and the computer program codes are configured to, with the at least one processor, cause the electronic device to perform: calculating a semantic communication error rate related to semantic communication for a network side device to determine whether to update a semantic library for semantic communication and / or an inference model related to the semantic library of the electronic device.

[0009] According to an aspect of the present disclosure, an electronic device for wireless communication is provided, comprising: at least one processor; and at least one memory including computer program codes, wherein the at least one memory and the computer program codes are configured to, with the at least one processor, cause the electronic device to perform: transmitting a semantic communication error rate received from other electronic devices to a network side device for the network side device to determine whether to update a semantic library for semantic communication and / or an inference model related to the semantic library of the other electronic devices.

[0010] According to an aspect of the present disclosure, a method for wireless communication is provided, comprising: determining whether to update a semantic library for semantic communication and / or an inference model related to the semantic library of a user equipment based on a semantic communication error rate related to the user equipment for semantic communication.

[0011] According to an aspect of the present disclosure, a method for wireless communication is provided, comprising: calculating a semantic communication error rate related to semantic communication for a network side device to determine whether to update a semantic library for semantic communication and / or an inference model related to the semantic library of the electronic device.

[0012] According to one aspect of the present disclosure, a method for wireless communication is provided, comprising: transmitting a semantic communication error rate received from other electronic devices to a network side device for the network side device to determine whether to update a semantic library used for semantic communication and / or an inference model related to the semantic library of the other electronic devices.

[0013] According to other aspects of the present disclosure, there are also provided computer program codes and computer program products for implementing the above method, and a computer readable storage medium having the computer program codes for implementing the above method recorded thereon. BRIEF DESCRIPTION OF DRAWINGS

[0014] To further illustrate and describe the above and other advantages and features of the present application, a further specific description of the application is described below with reference to the accompanying drawings. The accompanying drawings form a part of this specification and are included to further illustrate the application and, together with the description, serve to explain the various principles and aspects of the application. Identical reference numerals in the figures indicate identical components. It will be appreciated that these drawings are only typical examples of the application and should not be viewed as limiting the scope of the application. In the drawings:

[0015] FIG. 1 shows a functional module block diagram of an electronic device for wireless communication according to one embodiment of the present disclosure;

[0016] FIG. 2 is a schematic diagram showing an example of a semantic library according to an embodiment of the present disclosure;

[0017] FIG. 3 is a schematic diagram showing an example of semantic information;

[0018] FIG. 4A is an example of a semantic communication cell switching scenario according to an embodiment of the present disclosure;

[0019] FIG. 4B is another example of a semantic communication cell switching scenario according to an embodiment of the present disclosure;

[0020] FIG. 5A shows an example of simulation results of semantic communication accuracy rate changes according to an embodiment of the present disclosure;

[0021] FIG. 5B shows another example of simulation results of semantic communication accuracy rate changes according to an embodiment of the present disclosure;

[0022] FIG. 6A is a first example of a flow of semantic communication cell switching according to an embodiment of the present disclosure;

[0023] FIG. 6B is a second example of a flow of semantic communication cell switching according to an embodiment of the present disclosure;

[0024] FIG. 7A is a third example of a flow of semantic communication cell switching according to an embodiment of the present disclosure;

[0025] FIG. 7B is a fourth example illustrating a flow of a semantic communication cell handover according to an embodiment of the disclosure;

[0026] FIG. 8A is a fifth example illustrating a flow of a semantic communication cell handover according to an embodiment of the disclosure;

[0027] FIG. 8B is a sixth example illustrating a flow of a semantic communication cell handover according to an embodiment of the disclosure;

[0028] FIG. 9 illustrates a functional module block diagram of an electronic device for wireless communication according to another embodiment of the disclosure;

[0029] FIG. 10 illustrates a functional module block diagram of an electronic device for wireless communication according to yet another embodiment of the disclosure;

[0030] FIG. 11 illustrates a flowchart of a method for wireless communication according to one embodiment of the disclosure;

[0031] FIG. 12 illustrates a flowchart of a method for wireless communication according to another embodiment of the disclosure;

[0032] FIG. 13 illustrates a flowchart of a method for wireless communication according to yet another embodiment of the disclosure;

[0033] FIG. 14 is a block diagram illustrating a first example of a schematic configuration of an eNB or a gNB to which the techniques of the present disclosure can be applied;

[0034] FIG. 15 is a block diagram illustrating a second example of a schematic configuration of an eNB or a gNB to which the techniques of the present disclosure can be applied;

[0035] FIG. 16 is a block diagram illustrating an example of a schematic configuration of a smartphone to which the techniques of the present disclosure can be applied;

[0036] FIG. 17 is a block diagram illustrating an example of a schematic configuration of a car navigation device to which the techniques of the present disclosure can be applied; and

[0037] FIG. 18 is a block diagram of an example of an exemplary structure of a general personal computer in which a method and / or apparatus and / or system according to an embodiment of the present application can be implemented. DETAILED DESCRIPTION

[0038] Exemplary embodiments of the present application will be described herein below with reference to the accompanying drawings. In the description, specific terminology and descriptions are set forth in order to provide a thorough understanding of the present application. However, it will be apparent to those skilled in the art that embodiments of the present application can be practiced without using the specific details set forth herein. In other instances, well-known methods, procedures, components, and networks have not been described in detail so as not to unnecessarily obscure aspects of the present application.

[0039] It is also to be noted that, in the drawings, only the structures and / or processing steps closely related to the solution according to the present application are shown, and other details not closely related to the present application are omitted in order not to obscure the present application with unnecessary details.

[0040] The present disclosure provides an electronic device 100 for wireless according to an embodiment of the present disclosure. The electronic device 100 comprises at least one processor and at least one memory including computer program code, wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the electronic device 100 to perform: determining whether to update a semantic library for semantic communication and / or an inference model related to the semantic library of a user device for semantic communication based on a semantic communication error rate related to the user device for semantic communication.

[0041] Fig. 1 shows a functional module block diagram of an electronic device 100 for wireless communication according to an embodiment of the present disclosure.

[0042] The electronic device 100 shown in Fig. 1 comprises a control unit 101 which controls, and a processing unit 103 which can be configured to determine whether to update a semantic library for semantic communication and / or an inference model related to the semantic library of a user device for semantic communication based on a semantic communication error rate related to the user device for semantic communication under the control of the control unit 101.

[0043] The control unit 101 and the processing unit 103 can be implemented as one or more processing circuits, such as a processor or a chip, and at least one memory, such as a RAM, a ROM, etc., for storing computer program code and data, etc. required for processing performed by the processing circuit. It should be understood that the various functional units of the electronic device 100 shown in Fig. 1 are merely logical modules divided according to the specific functions they implement, and are not intended to limit the specific implementation.

[0044] The electronic device 100 can be disposed at a base station side or communicatively connected to a base station, for example. For example, the electronic device 100 can operate as a base station itself, and can further include external devices such as a memory, a transceiver (not shown), and the like. The memory can be used to store programs and related data information required for the electronic device 100 to implement various functions. The transceiver can include one or more communication interfaces to support communication with different devices (e.g., UEs, base stations, and the like), and the implementation form of the transceiver is not specifically limited herein.

[0045] As an example, the base station can be an eNB or a gNB, for example.

[0046] The wireless communication system according to the present disclosure can be a 5G NR (New Radio) communication system, a 5G+ communication system, a 6G communication system. Further, the wireless communication system according to the present disclosure can include a Non-terrestrial network (NTN). Optionally, the wireless communication system according to the present disclosure can also include a Terrestrial network (TN). In addition, those skilled in the art can understand that the wireless communication system according to the present disclosure can also be a 4G or 3G communication system.

[0047] For example, the inference model related to the semantic library of the user equipment can be an encoder or a decoder at the user equipment side.

[0048] For example, the wireless communication system according to the present disclosure can be applied to a vehicle-to-everything scenario, and can also be applied to a scenario in which ordinary users perform semantic communication. Those skilled in the art can also think of other application scenarios, which are not listed here.

[0049] The semantic communication error rate can consider errors and packet loss in data transmission, and thus is an index that can accurately reflect the quality of semantic communication. The electronic device 100 according to the embodiments of the present disclosure can more intelligently determine whether to update the semantic library and / or the inference model related to the semantic library of the user equipment for semantic communication based on the semantic communication error rate, thereby ensuring that the user equipment maintains continuous and high-quality communication in semantic communication, i.e., the efficiency and reliability of semantic communication can be improved.

[0050] Hereinafter, for simplicity, unless otherwise specified, the vehicle-to-everything scenario is taken as an example for description, and more specifically, whether to update the semantic library and / or the inference model of the user equipment (which can also be referred to as semantic communication cell switching) in the vehicle-to-everything scenario is taken as an example for description. The cell switching proposed in 3GPP only considers cellular cell switching, and in the present disclosure, the switching of semantic communication cells is also considered.

[0051] For example, in the case of a vehicle driving in an urban network, it will experience multiple semantic communication service areas.

[0052] In traditional cellular network communication, whether a cell handover is needed is usually determined by measuring signal power. When a vehicle enters a new cell, the system will determine whether to switch according to the strength of the signal power. This method is effective to some extent, but it is not suitable for semantic communication because the characteristics of semantic communication make it not subject to traditional power measurement. Therefore, semantic communication cannot simply rely on power measurement to determine switching.

[0053] Semantic communication can cover a variety of communication methods, including voice calls, data transmission, sensor data, etc. This makes simple power measurement unable to fully reflect communication quality and demand. Because semantic communication can involve high-bandwidth data transmission, real-time voice communication, and large-scale sensor data processing, different communication types have different requirements for communication quality and reliability. This increases the complexity of semantic switching decisions.

[0054] In addition, the cell range of semantic communication is dynamic, which dynamically adjusts with time and location because it is greatly affected by environmental conditions. This is because semantic communication is affected by urban environmental conditions such as buildings, road topography, weather, etc. The dynamic adjustment of the cell range is to adapt to the changing communication needs and environmental conditions. Therefore, the traditional fixed cell management method is no longer applicable, and the problem of cell range judgment becomes more complex, requiring consideration of more dynamic factors.

[0055] The electronic device 100 according to the embodiments of the present disclosure determines the need for semantic communication cell switching based on the semantic communication error rate to better cope with the problem of cell management in semantic communication. The electronic device 100 according to the embodiments of the present disclosure can more intelligently determine whether to perform semantic cell switching based on the semantic communication error rate, thereby ensuring continuous and high-quality communication for vehicles between semantic communication service areas. The switching method based on the semantic communication error rate according to the embodiments of the present disclosure enables more intelligent switching of vehicles between different semantic communication cells, thereby improving the reliability and efficiency of semantic communication. A more intelligent and efficient cell management solution is provided for semantic communication of vehicles in urban networks to meet the growing demand for vehicle communication and ensure the reliability and quality of semantic communication services.

[0056] As an example, the semantic library includes at least one of a relationship mapping between data information and semantic information, a machine learning model for generating a relationship mapping between data information and semantic information, a deep learning model, a mapping table, and a matrix compression.

[0057] FIG. 2 is a schematic diagram illustrating an example of a semantic library according to an embodiment of the present disclosure.

[0058] In the following, the semantic library is also referred to as semantic communication database, database, knowledge base.

[0059] In FIG. 2, taking pictures as data information and “trees” as semantic information as an example, the semantic communication database includes a plurality of “picture-tree” relationship mappings, each of which is a part of the database. The role of the database is to generate the semantic information of the “tree” when the vehicle reads the “picture”. In addition, the semantic communication database can include an AI model for generating the “tree” from the “picture”. The AI model can include the network model shown in FIG. 2 (e.g., machine learning model, deep learning model, etc.), or a mapping table (i.e., table mapping), matrix compression, etc. algorithm that can extract picture information. The machine learning model can include support vector machines, etc., and the deep learning model can include CNN (convolutional neural network), RNN (recurrent neural network), etc.

[0060] The wireless communication system according to the present disclosure can use any data suitable for semantic communication, and in the Internet of Vehicles scenario, can include any data obtained by vehicle sensors, such as pictures obtained by vehicle-mounted cameras, vehicle-mounted radar sensing data, voice information obtained by vehicles, etc. These data can be used as inputs to the AI model. In the scenario of semantic communication by ordinary users, various information that can be obtained by mobile phone terminals and can be used as inputs to the AI model can be included.

[0061] The semantic extraction of semantic communication is usually achieved by analyzing and understanding the language or data of a specific field.

[0062] 1. Text / Speech / Image Input: The raw data can be text, speech, or other forms of language input. This can be human speech, computer-generated text, or language information extracted from speech signals.

[0063] 2. Semantic Analysis: The system will analyze the structure of the input data and identify the basic components of the sentence, such as subject, predicate, object, etc. This helps to understand the basic grammatical structure of the sentence. Semantic analysis is the interpretation of words and phrases in a text to understand their meaning in a specific context. This may involve analysis of lexical semantics, contextual context, word relationships, etc.

[0064] 3. Semantic Representation: Based on semantic analysis, the system will convert the extracted semantic information into a form that computers can understand, usually in the form of semantic representation, such as concise textual information, semantic graph, logical representation, etc.

[0065] Specific examples can refer to the "Picture-Tree" in FIG. 2, where the picture is the input image information, and the "Tree" is the extracted semantic information. The point cloud of a lidar or the image collected by an image sensor can be used as input information for semantic communication, and then the corresponding semantic information can be extracted through a network model such as that shown in FIG. 2.

[0066] In the Simultaneous Localization and Mapping (SLAM) technology, for example, a robot starts moving from an unknown position in an unknown environment, and during the movement, the robot performs self-localization based on the position and the map, and builds an incremental map based on the self-localization, to achieve autonomous positioning and navigation of the robot. In SLAM, the data collected by the robot can be used as input information for semantic communication, and then the corresponding semantic information can be extracted for communication.

[0067] As an example, the inference model is used to convert data information into semantic information. As described above, the inference model related to the semantic library of the user device can be an encoder or a decoder on the user device side. As an example, the inference model can be an AI model.

[0068] Semantic communication can be performed between the electronic device 100 and the user device, i.e., the electronic device 100 and the user device can be respectively used as the sending end and the receiving end of the semantic communication. Semantic communication can also be performed between the user device and other user devices. That is, the user device and the other user devices can be respectively used as the sending end and the receiving end of the semantic communication.

[0069] The semantic information transmitted between the sending end and the receiving end of the semantic communication is usually interacted in a structured format or representation form to ensure the consistency and interpretability of the information. The semantic representation of the scene has the following forms.

[0070] 1. Natural language: Although the goal of semantic communication is to achieve computer understanding of semantics, in the actual transmission process, text or natural language is still the main representation form. The sending end can use natural language to express intent, command or query, and the receiving end can use natural language processing technology to parse and understand the information.

[0071] 2. Semantic markup language: In order to more structurally represent semantic information, a semantic markup language such as XML (extensible Markup Language) or JSON (JavaScript Object Notation) can be used. These markup languages can be used to nest information to make it easier to parse and process.

[0072] 3. Semantic Graph: A semantic graph is a graphical representation where nodes represent entities or concepts and edges represent relationships between them. This representation helps to present the associations between entities, thus conveying semantic information more intuitively.

[0073] 4. Logical Expression: Logical expressions can be used to represent the logical structure of semantic information. For example, using first-order logic or description logic to express logical statements about relationships between entities.

[0074] 5. Semantic Network: Similar to a semantic graph, a semantic network represents entities and relationships in the form of nodes and edges. This representation helps to communicate complex semantic structures in communication.

[0075] The specific choice of representation depends on the application's requirements, the complexity of communication, and the available technology. In practical applications, multiple forms of semantic representation may be combined to convey rich semantic information more comprehensively.

[0076] In the field of semantic communication, AI models help achieve the goals of natural language understanding, semantic analysis, and interaction. Here are some examples of AI models that can be applied to semantic communication:

[0077] Natural Language Processing (NLP) Models:

[0078] BERT (Bidirectional Encoder Representations from Transformers): BERT is a pre-trained natural language processing model that improves performance in semantic tasks such as text classification, question answering, etc., by learning context information in both directions.

[0079] GPT (Generative Pre-trained Transformer): GPT series models are pre-trained models based on the Transformer architecture, which are pre-trained on large language models and are suitable for generative natural language tasks such as dialogue generation, text generation, etc.

[0080] Semantic Analysis Models:

[0081] Word Embeddings Models: Word Embeddings models (such as Word2Vec, GloVe) map words to high-dimensional vector spaces, capturing semantic relationships between words, and are used for semantic analysis and similarity matching.

[0082] ELMo (Embeddings from Language Models): ELMo generates dynamic representations of words using contextual information, which helps to address polysemy and context-sensitive semantic analysis tasks.

[0083] Entity Recognition Models:

[0084] BERT-based Entity Recognition Models: BERT-based models can be used to identify named entities in text, such as person names, location names, organization names, etc.

[0085] CRF (Conditional Random Fields): CRF is a sequence labeling model commonly used in entity recognition tasks, which takes into account the dependencies between context information and labels.

[0086] Sentiment Analysis Models:

[0087] LSTM (Long Short-Term Memory): LSTM is a variant of RNN (Recurrent Neural Network) that is suitable for processing sequence data, commonly used in sentiment analysis tasks, which can capture the sentiment changes in text.

[0088] BERT-based Sentiment Analysis Models: BERT-based models can better understand the sentiment of text by considering contextual information.

[0089] Graph Neural Networks (GNN):

[0090] Graph Neural Networks for Semantic Graph Representation: For semantic graphs in semantic communication, GNN can be used to learn the relationships between nodes and edges, improving the representation of entities and concepts in graph structures.

[0091] For example, models for generating relationship mappings between data information and semantic information, as well as inference models, can be based on the above AI models.

[0092] The information transmitted by semantic communication is the output layer of the AI model, and semantic communication can be generated using the above AI models to generate semantic information, and then interact using these semantic information.

[0093] The information of semantic communication (semantic information) can be divided into two categories: 1. Information that can be judged right or wrong; 2. Information that cannot be judged right or wrong. Using the above information classification, different semantic communication error rate calculation methods can be used.

[0094] Figure 3 is a schematic diagram showing an example of semantic information.

[0095] In FIG. 3, the front vehicle is driving in the cell, while the rear vehicle just enters the cell. The front vehicle can extract four pieces of semantic information according to, for example, its own network model: 1, there are 6 trees on the left. 2, there is 1 tree on the right. 3, there is 1 base station on the right. 4, there is an obstacle in front. When the rear vehicle receives the four pieces of information, the first three pieces of information are information that the rear vehicle can judge right or wrong, and the fourth piece of information is information that the rear vehicle cannot judge right or wrong.

[0096] As an example, the semantic communication error rate is calculated by the user equipment based on its original semantic library and / or original inference model, and is the proportion of incorrect information in the semantic information received from other user equipment within a predetermined time period (Method 1 for calculating the semantic communication error rate).

[0097] In Method 1, it is assumed that the user equipment receives N pieces of semantic information from other user equipment within a predetermined time period, and e[n] is used to represent whether the nth piece of semantic information is correct, where e[n] is 0 if the nth piece of semantic information is correct, and 1 otherwise.

[0098] The semantic communication error rate in Method 1 can be expressed as:

[0099]

[0100] The predetermined time period can be determined in advance by a person skilled in the art according to experience or application scenarios.

[0101] The user equipment (for example, a vehicle) continuously receives semantic information from other vehicles, and in this Method 1, the vehicle judges whether all received semantic information (including information that the vehicle can judge right or wrong and information that the vehicle cannot judge right or wrong) is correct according to its own original semantic library and / or original inference model. For example, the vehicle can judge that part of the information is incorrect. The vehicle dynamically calculates the proportion of incorrect information in the N pieces of information received recently as the semantic communication error rate.

[0102] For example, in combination with FIG. 3, because the base station can be made in the form of a telegraph pole or a tree in different environments, the rear vehicle can not include a database of this information. Therefore, if the rear vehicle judges that the third piece of information is “there are 0 base stations on the right” according to its own network model. Then this information is incorrect. Further, the semantic error rate calculated in Method 1 is:

[0103]

[0104] As an example, the semantic communication error rate is obtained by a user equipment based on its original semantic library and / or original inference model, calculating the proportion of incorrect information among the semantic information that the user equipment can judge to be correct, in the semantic information received from other user equipments within a predetermined time period (Method 2 for calculating the semantic communication error rate).

[0105] In Method 2, it is assumed that there are N pieces of semantic information that the user equipment can judge to be correct, among the semantic information received by the user equipment from other user equipments within a predetermined time period, e judge [n] is used to represent whether the nth piece of semantic information that the user equipment can judge to be correct is correct, where if the nth piece of semantic information is correct, e judge [n] is 0, otherwise 1.

[0106] The semantic communication error rate in Method 2 can be expressed as:

[0107]

[0108] The predetermined time period can be determined in advance by a person skilled in the art according to experience or application scenarios.

[0109] In Method 2, the vehicle judges whether the received information that it can judge to be correct is correct according to its own original semantic library and / or original inference model. For example, the vehicle dynamically calculates the proportion of incorrect information among the N pieces of information that it can judge to be correct received recently, as the semantic communication error rate.

[0110] For example, in combination with FIG. 3, if the rear vehicle judges the 3rd piece of information to be “0 base stations on the right” according to its own network model. Then the information is incorrect. Because the rear vehicle cannot judge whether the 4th piece of information is correct, it is not included in the calculation of the error rate. Further, the semantic error rate calculated in Method 2 is:

[0111]

[0112] As an example, the semantic communication error rate is obtained by a user equipment based on its original semantic library and / or original inference model, calculating the proportion of incorrect information among a predetermined number of flag information that the user equipment can obtain the correct semantics of in advance (Method 3 for calculating the semantic communication error rate).

[0113] For example, semantic communication switching flag areas are set in each area in the city, which are used by vehicles to judge whether the information extracted from the flag areas (which is an example of flag information) is correct, where for example, the flag area can be composed of multiple “input information-correct semantic output” similar to the “picture-tree” shown in FIG. 2.

[0114] Alternatively, after the vehicle enters a region, the base station of the region can send test information (which is another example of the sign information) to the vehicle.

[0115] In method 3, assuming a predetermined number is N, e[n] is used to represent whether the nth piece of sign information is correct, where e[n] is 0 if the nth piece of sign information is correct, and 1 otherwise.

[0116] The semantic communication error rate in method 3 can be expressed as:

[0117]

[0118] The predetermined number can be predetermined by the person skilled in the art according to experience or application scenarios.

[0119] For example, the sign region can be a region where a predetermined sign image (Chinese sign, English sign, safety information, etc.) is placed at each intersection. When the vehicle passes through the sign region, the semantic communication error rate can be calculated without interacting with surrounding vehicles. Assuming that 100 pieces of sign information are set in the sign region, the vehicle can obtain the sign information through a camera sensor or the like. Then the vehicle uses its own network model to judge 100 pieces of "input information (sign information)", and then compares the judgment result with the "correct semantic output". In this way, the semantic communication error rate can be calculated. Among them, the vehicle can directly extract the correct semantic output from the sign region for comparison with the above-mentioned judgment result. As an example, in the sign region, the vehicle can obtain the correct semantic output from the road side unit. And the vehicle can obtain surrounding information by using radar, camera, etc.

[0120] As an example, the processing unit 103 can be configured to determine whether to update the semantic library and / or the inference model of the user equipment based on a comparison of the semantic communication error rate with an error tolerance or error rate threshold of the semantic communication. Wherein, the higher the error tolerance, the higher the error rate threshold; and the lower the error tolerance, the lower the error rate threshold. For example, the error rate threshold can be pre-set by the person skilled in the art according to experience or application scenarios.

[0121] As an example, the error tolerance of the semantic communication is determined based on at least one of the following: road congestion degree, vehicle driving speed, road type and scene, weather condition, intersection and complex intersection, driver familiarity, application scenario and purpose, traffic event and construction area, network connection quality, vehicle type and driving mode, traffic regulations and local regulations.

[0122] In semantic communication, examples of factors affecting error rate tolerance under different road conditions are as follows.

[0123] Road congestion level: In highly congested urban traffic, the error tolerance of semantic communication can be lower. For example, when traffic is congested, information delivery in emergency situations can require higher accuracy to ensure accurate traffic navigation or traffic control.

[0124] Vehicle speed: In high-speed driving situations, such as on highways, the error tolerance of semantic communication can be relatively lower due to shorter reaction times. In this case, navigation instructions, traffic information, and the like need to be more accurate to ensure that the driver can quickly and safely respond. In low-speed driving situations, such as on low-speed limit roads, the error tolerance of semantic communication can be relatively higher.

[0125] Road type and scenario: On highways, the error tolerance of semantic communication can be lower because high-speed driving involves higher risks. In contrast, in low-speed scenarios such as low-speed limit roads or parking lots, there can be more tolerance for errors in semantic communication.

[0126] Weather conditions: Adverse weather conditions, such as rain, snow, fog, and the like, can increase the error rate of semantic communication. In this case, the driver's demand for navigation instructions, traffic information, and the like can be more urgent, so the error tolerance of semantic communication can be reduced.

[0127] Intersections and complex junctions: At complex intersections or roundabouts, the error tolerance of semantic communication can be lower. Accurate navigation and traffic information are crucial for safely crossing intersections.

[0128] Driver familiarity: For drivers familiar with the road, the error tolerance of semantic communication can be higher. However, for unfamiliar roads or novice drivers, accurate semantic information can be more important, so the error tolerance of semantic communication can be lower.

[0129] Application scenarios and purposes: In emergency rescue scenarios, the error tolerance of semantic communication can be lower because incorrect information can lead to serious consequences. In contrast, in entertainment navigation scenarios, the error tolerance can be higher.

[0130] Traffic events and construction areas: When encountering traffic accidents, road construction, or other emergencies, the error tolerance of semantic communication can decrease. Accurate information becomes crucial for avoiding danger or choosing the appropriate detour path.

[0131] Network connection quality: In areas with unstable network connections, such as remote areas or tunnels, the error tolerance of semantic communication can be affected. In this case, the system can need more powerful error correction mechanisms or caching strategies to cope with packet loss or delays.

[0132] Vehicle type and driving mode: Different types of vehicles (e.g., autonomous cars, traditional cars, motorcycles) can have different expectations for error tolerance of semantic communication. For example, autonomous cars can have higher requirements for accurate maps and navigation information.

[0133] Traffic laws and local regulations: In some areas, traffic laws can impose higher requirements on the accuracy of semantic communication, and the error tolerance of semantic communication can be reduced. For example, in some countries or cities, regulations can require navigation systems to provide specific types of information or warnings.

[0134] The above examples show that the error tolerance of semantic communication can be affected by various factors in different road conditions. Therefore, when designing a semantic communication system, user needs and safety requirements in different situations need to be considered to determine appropriate error tolerance values or error rate thresholds. For example, electronic device 100 sets the value of error tolerance or error rate threshold by understanding the communication situation in the surrounding area.

[0135] As described above, the semantic communication error rate is calculated at the user equipment (sending end), and the sending end sends the signaling or uplink information containing the error rate to the electronic device 100 (receiving end).

[0136] As an example, the signaling for indicating whether to update the semantic library of the user equipment and / or the inference model related to the semantic library is contained in the PDCCH (Physical Downlink Control Channel), which is composed of a field in the PDCCH for coordinating scheduling downlink resources, thereby completing the update of the semantic library and / or the inference model.

[0137] In the case that the communication link between the user equipment and the electronic device 100 newly entering its communication service range is good, the user equipment can directly communicate with the electronic device 100.

[0138] As an example, the processing unit 103 can be configured to receive the semantic communication error rate directly from the user equipment.

[0139] As an example, the processing unit 103 can be configured to directly send the signaling for indicating whether to update to the user equipment.

[0140] As an example, the processing unit 103 can be configured to directly send the updated semantic library and / or inference model to the user equipment in the case that the update is needed.

[0141] FIG. 4A is an example of a semantic communication cell handover scenario according to an embodiment of the present disclosure.

[0142] In FIG. 4A, vehicles Veh#1 and Veh#2, and base stations BS#1 and BS#2 are shown. Assume that the system state is: 1. The communication link between Veh#1 and BS#2 is good. 2. The communication link between Veh#2 and BS#2 is good or poor. 2. The communication link between Veh#1 and Veh#2 is good or poor. Among them, the base station BS#2 is an example of the electronic device 100 in this embodiment, and the vehicle Veh#1 is an example of the user equipment in this embodiment.

[0143] The semantic communication flow in FIG. 4A is as follows:

[0144] 1. Veh#1 will perform semantic communication with other vehicles in the vicinity during driving. The scope of the semantic library changes dynamically over time and region, so Veh#1 needs to calculate the error rate of semantic communication in real time to determine whether to perform semantic communication.

[0145] 2. In the case where Veh#1 enters the service range of BS#2 from the service range of BS#1, Veh#1 can receive a large amount of semantic communication information in the new environment, and Veh#1 can also judge whether part of the information is correct or not because it can observe the surrounding environment.

[0146] 3. Veh#1 dynamically judges whether the semantic information is correct or not, and calculates the semantic communication error rate ε.

[0147] 4. Veh#1 establishes uplink / downlink with BS#2.

[0148] 5. Veh#1 transmits the semantic communication error rate ε to the nearest BS#2, and BS#2 judges whether Veh#1 is suitable for performing semantic communication in the current region (the region within the service range of BS#2 that Veh#1 has newly entered) based on the semantic communication error rate ε.

[0149] 6. In the case where the semantic communication error rate ε is greater than the error rate threshold (which can be referred to as a threshold for short), BS#2 judges to update the semantic library and / or the reasoning model of Veh#1. If the semantic communication error rate ε is less than the threshold, BS#2 decides to let Veh#1 continue semantic communication (i.e., not to update the semantic library and / or the reasoning model of Veh#1).

[0150] 7. BS#2 transmits signaling SC (taking the values of yes or no, which is included in the PDCCH for example as described above) to Veh#1 to indicate whether to perform the update.

[0151] 8. Veh#1 receives the signaling, and in the case of needing to update, BS#2 transmits the updated semantic library and / or inference model (the semantic library and / or inference model of the area) to Veh#1 to update the semantic library and / or inference model of Veh#1.

[0152] 9. Then, the uplink / downlink between Veh#1 and BS#2 is released. Thus, channel resources can be saved.

[0153] In the example of FIG. 4A, the communication link between Veh#1 and BS#2, which newly enters the service range of Veh#1, is good, so Veh#1 can directly communicate with BS#2. In this way, Veh#1 can directly send the semantic communication error rate calculated by it to BS#2, BS#2 can directly transmit the signaling SC indicating whether to update to Veh#1, and in the case of needing to update, BS#2 can directly transmit the updated semantic library and / or inference model to Veh#1.

[0154] In the case that the communication link between the user equipment and the electronic device 100, which newly enters the communication service range of the user equipment, is poor, the user equipment cannot directly communicate with the electronic device 100.

[0155] As an example, the processing unit 103 can be configured to receive the semantic communication error rate of the user equipment forwarded via the other user equipment.

[0156] As an example, the processing unit 103 can be configured to send the signaling indicating whether to update to the other user equipment for the other user equipment to forward the signaling to the user equipment.

[0157] As an example, the processing unit 103 can be configured to, in the case of needing to update, send the updated semantic library and / or inference model to the other user equipment for the other user equipment to forward the updated semantic library and / or inference model to the user equipment.

[0158] FIG. 4B is another example illustrating a semantic communication cell switching scenario according to an embodiment of the present disclosure.

[0159] In FIG. 4B, it is assumed that the system state is: 1. The communication link between Veh#1 and BS#2 is poor (the communication link between Veh#1 and BS#2 is represented by a dashed line). 2. The communication link between Veh#2 and BS#2 is good. 3. The communication link between Veh#1 and Veh#2 is good. Wherein, the base station BS#2 is an example of the electronic device 100 in the present embodiment, and the vehicle Veh#1 is an example of the user equipment in the present embodiment.

[0160] The semantic communication flow in FIG. 4B is as follows:

[0161] 1. Veh#1 communicates with other vehicles in the vicinity during driving. The scope of the semantic library changes dynamically over time and region, so Veh#1 needs to calculate the error rate of semantic communication in real time to decide whether to perform semantic communication.

[0162] 2. In the case that Veh#1 enters the service range of BS#2 from the service range of BS#1, Veh#1 can receive a large amount of semantic communication information in the new environment. Since Veh#1 can observe the surrounding environment, it can determine whether part of the information is correct.

[0163] 3. Veh#1 dynamically determines whether the semantic information is correct and calculates the semantic communication error rate ε.

[0164] 4. Since the communication link between Veh#1 and BS#2 is poor, they cannot directly communicate. Since the communication link between Veh#1 and Veh#2 is good, a sidelink is established between Veh#1 and Veh#2.

[0165] 5. An uplink / downlink is established between Veh#2 and BS#2.

[0166] 6. Veh#1 transmits the semantic communication error rate ε to Veh#2, which then forwards it to the nearest BS#2. Based on the current semantic communication error rate ε, BS#2 determines whether Veh#1 is suitable for semantic communication in the current region.

[0167] 7. If the semantic communication error rate ε is greater than a threshold value, BS#2 determines to update the semantic library and / or reasoning model of Veh#1. If the semantic communication error rate ε is less than the threshold value, BS#2 determines to continue semantic communication of Veh#1 (i.e., not to update the semantic library and / or reasoning model of Veh#1).

[0168] 8. BS#2 transmits signaling SC (with values of yes or no, as described above, for example, included in PDCCH) to Veh#2 to indicate whether to perform the update.

[0169] 9. Veh#2 forwards the signaling SC to Veh#1 to indicate whether to perform the update.

[0170] 10. Veh#1 receives the signaling notification. If an update is needed, BS#2 transmits the updated semantic library and / or reasoning model (the semantic library and / or reasoning model of the region) to Veh#2, which then forwards it to Veh#1 through the sidelink. Alternatively, in the case that Veh#2 can perform semantic communication, the updated semantic library and / or reasoning model can be directly forwarded to Veh#1.

[0171] 11. Release sidelink between Veh#1 and Veh#2.

[0172] 12. Release uplink / downlink between Veh#2 and BS#2. Thus, channel resources can be saved.

[0173] In addition, those skilled in the art can understand that there is also a case that the semantic communication error rate rises due to semantic communication quality degradation, and the semantic library and / or inference model of the user equipment (for example, Veh#1) needs to be updated in the original cell range (for example, the service range of BS#1) even if the user equipment does not enter the service range (for example, the service range of BS#2) of other base stations.

[0174] FIG. 5A shows one example of simulation results of semantic communication accuracy rate changes according to an embodiment of the present disclosure, and FIG. 5B shows another example of simulation results of semantic communication accuracy rate changes according to an embodiment of the present disclosure. It is described in combination with Veh#1, BS#1 and BS#2 in FIG. 4A. The vertical coordinate in FIGS. 5A and 5B represents the semantic communication accuracy rate (labeled as “terminal own semantic communication accuracy rate” in the figure). The horizontal coordinate in FIG. 5A represents the number of semantic communication messages, the semantic communication error rate is calculated based on the above-mentioned calculation method 1, and the semantic communication accuracy rate is obtained based on the calculated semantic communication error rate. The horizontal coordinate in FIG. 5B represents the number of semantic communication messages that can be identified as correct or incorrect, the semantic communication error rate is calculated based on the above-mentioned calculation method 2, and the semantic communication accuracy rate is obtained based on the calculated semantic communication error rate.

[0175] The parameter settings in FIG. 5A are that the accuracy rate of AI model A of vehicle Veh#1 in the BS#1 cell is 99.05%, the accuracy rate of AI model B in the BS#2 cell is 98.88%, the accuracy rate of AI model A in the BS#2 cell is 79.75%, 20% of the data cannot be identified as correct or incorrect (i.e., semantic information that cannot be judged as correct), and the switching threshold is 92%. The parameter settings in FIG. 5B are that the accuracy rate of AI model A of vehicle Veh#1 in the BS#1 cell is 99.05%, the accuracy rate of AI model B in the BS#2 cell is 98.88%, the accuracy rate of AI model A in the BS#2 cell is 79.75%, 20% of the data cannot be identified as correct or incorrect, and the switching threshold is 85%.

[0176] As can be seen from FIGS. 5A and 5B, in the strategy of performing semantic communication cell switching according to the embodiments of the present disclosure (corresponding to the curve marked as “Accuracy change when performing switching” in the figure), it can be seen that after the semantic communication cell switching, the semantic communication accuracy returns to the normal level. In the strategy of not performing semantic communication cell switching in the prior art (corresponding to the curve marked as “Accuracy change when not performing switching” in the figure), it can be seen that due to not performing switching, the semantic communication accuracy after entering the new cell BS#2 is relatively low (i.e., the semantic communication error rate is relatively high).

[0177] In the following, examples of the flow of semantic communication cell switching according to the embodiments of the present disclosure are described in conjunction with FIGS. 6A, 6B, 7A, 7B, 8A, and 8B. In FIGS. 6A, 6B, 7A, 7B, 8A, and 8B, base stations (BSs) BS#1 to BS#3 and vehicles Veh#1 to Veh#7 are shown, wherein the vehicle Veh#5 is an example of the user equipment according to the embodiments of the present disclosure, the vehicle Veh#5 enters the cell of BS#3 from the cell of BS#2, and BS#3 is an example of the electronic device 100 according to the embodiments of the present disclosure.

[0178] FIG. 6A is a first example illustrating the flow of semantic communication cell switching according to the embodiments of the present disclosure. FIG. 6B is a second example illustrating the flow of semantic communication cell switching according to the embodiments of the present disclosure.

[0179] In FIGS. 6A and 6B, the BS side deploys an encoder and a decoder, and a large number of information acquisition devices, such as radars and cameras, are deployed on the BS side; a small number of information acquisition devices are deployed on the vehicle side, and the vehicle requests a decoder model (inference model) from the BS (the vehicle comprehensively performs semantic communication in combination with the global information and the local information of the BS).

[0180] In FIG. 6A, it is assumed that the vehicle Veh#5 can communicate with the base station BS#3 newly entering its cell.

[0181] A1 of FIG. 6A: BS#1 to BS#3 respectively collect the global information of the cell, and broadcast the global information processed by the encoder to all vehicles in the cell.

[0182] A2 of FIG. 6A: The vehicle Veh#2 requests a decoder model (which can be personified as an AI model) from the cell BS#1 for decoding the received global information, so as to realize semantic communication. Although not shown in the figure for clarity, it can be understood that the vehicle Veh#5 requests a decoder model from the BS#2 of the original cell for decoding the received global information, so as to realize semantic communication.

[0183] Figure 6A, A3: BS#1 distributes the decoder model or the compressed decoder model to vehicle Veh#2. Although not shown in the figure for clarity, it is understood that BS#2 distributes the decoder model or the compressed decoder model to vehicle Veh#5.

[0184] Figure 6A, A4: The semantic error rate calculation module is deployed on vehicles, e.g., it is shown that vehicle Veh#4 is deployed with the semantic error rate calculation module. However, although not shown in the figure for clarity, it is understood that vehicle Veh#5 is also deployed with the semantic error rate calculation module. After entering the cell of BS#3, vehicle Veh#5 sends the semantic communication error rate calculated based on the semantic information received in the cell of BS#3 to BS#3.

[0185] Figure 6A, A5: BS#3 compares the received semantic communication error rate with the error rate threshold to determine whether vehicle Veh#5 replaces the existing decoder model, and if so, BS#3 distributes the new decoder model or the compressed decoder model to vehicle Veh#5.

[0186] In Figure 6B, it is assumed that vehicle Veh#5 is unable to communicate with the newly entered base station BS#3.

[0187] Figure 6B, A1: BS#1 to BS#3 respectively collect the global information of the cell, and broadcast the global information processed by the encoder to all vehicles in the cell.

[0188] Figure 6B, A2: Vehicle Veh#2 requests the decoder model from the cell BS#1 for decoding the received global information to achieve semantic communication. Although not shown in the figure for clarity, it is understood that vehicle Veh#5 requests the decoder model from the BS#2 of the original cell for decoding the received global information to achieve semantic communication.

[0189] Figure 6B, A3: BS#1 distributes the decoder model or the compressed decoder model to vehicle Veh#2. Although not shown in the figure for clarity, it is understood that BS#2 distributes the decoder model or the compressed decoder model to vehicle Veh#5.

[0190] Figure 6B, A4: After entering the cell of BS#3, vehicle Veh#5 establishes a sidelink connection with vehicle Veh#6 in the cell of BS#3, and sends the semantic communication error rate calculated based on the semantic information received in the cell of BS#3 to the connected vehicle Veh#6.

[0191] Figure 6B, A5: The connected vehicle Veh#6 reports the semantic communication error rate to the base station BS#3.

[0192] Figure 6B A6: BS#3 compares the received semantic communication error rate with the error rate threshold to determine whether the vehicle Veh#5 replaces the existing decoder model, and if so, BS#3 issues the new decoder model or compressed decoder model to the connected vehicle Veh#6 connected to the vehicle Veh#5.

[0193] Figure 6B A7: The connected vehicle Veh#6 sends the received response (whether to replace the existing decoder model of the vehicle Veh#5) to the vehicle Veh#5, and if so, the connected vehicle Veh#6 also sends the received decoder model or compressed decoder model to the vehicle Veh#5.

[0194] Figure 7A is a third example of a flow of semantic communication cell switching according to an embodiment of the present disclosure. Figure 7B is a fourth example of a flow of semantic communication cell switching according to an embodiment of the present disclosure.

[0195] In Figures 7A and 7B, the BS side deploys an encoder and a semantic library, and the BS side deploys a large number of information acquisition devices; the vehicle side deploys a decoder, and the vehicle side deploys a small number of information acquisition devices, and the vehicle requests a semantic library from the BS.

[0196] In Figure 7A, it is assumed that the vehicle Veh#5 is able to communicate with the base station BS#3 newly entering its cell

[0197] A1 in Figure 7A: BS#1 to BS#3 respectively collect the global information of the cell, and broadcast the global information processed by the encoder to all vehicles in the cell.

[0198] A2 in Figure 7A: The vehicle Veh#2 requests a semantic library (for example, can be materialized as a mapping table, an AI model, a dataset, experience, etc.) from the BS#1 of the cell to assist the decoder in decoding the received global information, thereby realizing semantic communication. Although not shown in the figure for clarity, it can be understood that the vehicle Veh#5 requests a semantic library from the BS#2 of its original cell to assist the decoder in decoding the received global information, thereby realizing semantic communication.

[0199] A3 in Figure 7A: BS#1 issues the semantic library or compressed semantic library to the vehicle Veh#2. Although not shown in the figure for clarity, it can be understood that BS#2 issues the semantic library or compressed semantic library to the vehicle Veh#5.

[0200] A4 in FIG. 7A: The vehicle deploys a semantic error rate calculation module, for example, it is shown that the vehicle Veh#4 deploys a semantic error rate calculation module. However, although not shown in the figure for clarity, it can be understood that the vehicle Veh#5 also deploys a semantic error rate calculation module. After entering the cell of BS#3, the vehicle Veh#5 sends the semantic communication error rate calculated based on the semantic information received in the cell of BS#3 to BS#3.

[0201] A5 in FIG. 7A: BS#3 compares the received semantic communication error rate with the error rate threshold to determine whether the vehicle Veh#5 replaces the existing semantic library, and if so, BS#3 downloads a new semantic library or a compressed semantic library to the vehicle Veh#5. The vehicle Veh#5 trains its decoder based on the new semantic library or the compressed semantic library.

[0202] In FIG. 7B, it is assumed that the vehicle Veh#5 is unable to communicate with the base station BS#3 newly entering its cell.

[0203] A1 in FIG. 7B: BS#1 to BS#3 respectively collect the global information of the cell, and broadcast the global information processed by the encoder to all vehicles in the cell.

[0204] A2 in FIG. 7B: The vehicle Veh#2 requests a semantic library from the cell BS#1 to assist the decoder in decoding the received global information to achieve semantic communication. Although not shown in the figure for clarity, it can be understood that the vehicle Veh#5 requests a semantic library from the BS#2 of its original cell to assist the decoder in decoding the received global information to achieve semantic communication.

[0205] A3 in FIG. 7B: BS#1 downloads a semantic library or a compressed semantic library to the vehicle Veh#2. Although not shown in the figure for clarity, it can be understood that BS#2 downloads a semantic library or a compressed semantic library to the vehicle Veh#5.

[0206] A4 in FIG. 7B: After entering the cell of BS#3, the vehicle Veh#5 establishes a sidelink connection with the vehicle Veh#6 in the cell of BS#3, and sends the semantic communication error rate calculated based on the semantic information received in the cell of BS#3 to the connected vehicle Veh#6.

[0207] A5 in FIG. 7B: The connected vehicle Veh#6 reports the semantic communication error rate to the cell base station BS#3.

[0208] A6 in FIG. 7B: BS#3 compares the received semantic communication error rate with the error rate threshold to determine whether the vehicle Veh#5 replaces the existing semantic library, and if so, BS#3 issues a new semantic library or a compressed semantic library to the connected vehicle Veh#6 connected to the vehicle Veh#5.

[0209] A7 in FIG. 7B: The connected vehicle Veh#6 sends the received response to the vehicle Veh#5, and if the semantic library needs to be replaced, the connected vehicle Veh#6 also sends the received semantic library or compressed semantic library to the vehicle Veh#5.

[0210] FIG. 8A is a fifth example illustrating a flow of semantic communication cell switching according to an embodiment of the present disclosure. FIG. 8B is a sixth example illustrating a flow of semantic communication cell switching according to an embodiment of the present disclosure.

[0211] In FIGS. 8A and 8B, the BS side deploys a global encoder and a global decoder, and the BS side does not deploy any information acquisition device; the vehicle side deploys a local encoder, and the vehicle side deploys an information acquisition device, and the vehicle requests a global decoder.

[0212] In FIG. 8A, it is assumed that the vehicle Veh#5 is capable of communicating with the base station BS#3 newly entering its cell.

[0213] A1 in FIG. 8A: The vehicles Veh#1 to Veh#7 extract important local information and upload the local information to the BS of the cell, respectively.

[0214] A2 in FIG. 8A: The BSs #1 to #3 aggregate the local information of all vehicles in the cell into global information through a global encoder, and broadcast the global information to all vehicles in the cell.

[0215] A3 in FIG. 8A: The vehicle Veh#2 requests a decoder model from the BS #1 of the cell for decoding the received global information to achieve semantic communication. Although not shown in the figure for clarity, it is understood that the vehicle Veh#5 requests a decoder model from the BS #2 of the original cell for decoding the received global information to achieve semantic communication.

[0216] A4 in FIG. 8A: The BS #1 issues the decoder model or a compressed decoder model to the vehicle Veh#2. Although not shown in the figure for clarity, it is understood that the BS #2 issues the decoder model or a compressed decoder model to the vehicle Veh#5.

[0217] A5 in FIG. 8A: The vehicle deploys a semantic error rate calculation module, for example, it is shown that the vehicle Veh#4 deploys a semantic error rate calculation module. However, although not shown in the figure for clarity, it can be understood that the vehicle Veh#5 also deploys a semantic error rate calculation module. After entering the cell of BS#3, the vehicle Veh#5 sends the semantic communication error rate calculated based on the semantic information received in the cell of BS#3 to BS#3.

[0218] A6 in FIG. 8A: BS#3 compares the received semantic communication error rate with the error rate threshold to determine whether the vehicle Veh#5 replaces the existing decoder model, and if so, BS#3 issues a new decoder model or a compressed decoder model to the vehicle Veh#5.

[0219] In FIG. 8B, it is assumed that the vehicle Veh#5 is unable to communicate with the newly entered base station BS#3 in its cell.

[0220] A1 in FIG. 8B: Vehicles Veh#1 to Veh#7 extract important local information and upload to the local base station respectively.

[0221] A2 in FIG. 8B: BS#1 to BS#3 aggregate the local information of all vehicles in the cell into global information through a global encoder, and broadcast the global information to all vehicles in the cell.

[0222] A3 in FIG. 8B: The vehicle Veh#2 requests a decoder model from the local base station BS#1 for decoding the received global information to achieve semantic communication. Although not shown in the figure for clarity, it can be understood that the vehicle Veh#5 requests a decoder model from the BS#2 of its original cell for decoding the received global information to achieve semantic communication.

[0223] A4 in FIG. 8B: BS#1 issues a decoder model or a compressed decoder model to the vehicle Veh#2. Although not shown in the figure for clarity, it can be understood that BS#2 issues a decoder model or a compressed decoder model to the vehicle Veh#5.

[0224] A5 in FIG. 8B: After entering the cell of BS#3, the vehicle Veh#5 establishes a sidelink connection with the vehicle Veh#6 in the cell of BS#3, and sends the semantic communication error rate calculated based on the semantic information received in the cell of BS#3 to the connected vehicle Veh#6.

[0225] A6 in FIG. 8B: The connected vehicle Veh#6 reports the semantic communication error rate to the local base station BS#3.

[0226] A7 in FIG. 8B: BS#3 compares the received semantic communication error rate with the error rate threshold to determine whether the vehicle Veh#5 replaces the existing decoder model, and if so, BS#3 sends the new decoder model or compressed decoder model to the connected vehicle Veh#6 connected to the vehicle Veh#5.

[0227] A8 in FIG. 8B: The connected vehicle Veh#6 sends the received response to the vehicle Veh#5, and if the decoder model needs to be replaced, the connected vehicle Veh#6 also sends the received decoder model or compressed decoder model to the vehicle Veh#5.

[0228] In the following, the electronic device 100 according to embodiments of the present disclosure is described in terms of a configuration of a unit module in another form.

[0229] The electronic device 100 can include an information acquisition unit configured to acquire a scheduling request, information data, and pilot signaling (e.g., including received semantic communication error rate signaling, signaling for indicating whether to perform knowledge base update) of a user equipment (UE) (e.g., a vehicle) during a process of vehicle semantic communication; a channel measurement unit configured to measure a channel state in real time and generate a generalized channel model; and an information sending unit configured to send scheduling signaling to the vehicle and perform resource allocation (e.g., including sending semantic communication error rate signaling, signaling for indicating whether to perform knowledge base update). Thus, the channel can be measured in real time according to the received signaling, and the resource can be configured according to the received scheduling strategy.

[0230] As an example, the information acquisition unit is deployed at the electronic device 100 to receive scheduling signaling. The unit is configured to receive a scheduling request to establish a downlink, a sidelink, etc.

[0231] As an example, the channel measurement unit acquires pilot information from the information acquisition unit and models the channel into a generalized channel model based on the pilot information. After modeling, the model is sent to the information sending unit. The unit is configured to estimate the channel model, which can be implemented based on deep learning, reinforcement learning, etc.

[0232] As an example, the information sending unit receives the state from the information acquisition unit and the channel measurement unit and sends the decision of the scheduling strategy to the vehicle user. The unit informs the vehicle user how to configure the channel resource and whether to perform data transmission.

[0233] The way of judging whether to perform update based on semantic communication error rate according to embodiments of the present disclosure provides strong support for the development of future smart city traffic and communication systems, and is expected to improve the efficiency and reliability of communication and promote the sustainable development of this field.

[0234] The present disclosure also provides an electronic device 9000 for wireless according to another embodiment of the present disclosure. The electronic device 9000 comprises at least one processor and at least one memory including computer program code, wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the electronic device 9000 to perform: calculating a semantic communication error rate related to semantic communication for a network-side device to determine whether to update a semantic library for semantic communication and / or an inference model related to the semantic library of the electronic device 9000.

[0235] FIG. 9 shows a functional module block diagram of an electronic device 9000 for wireless communication according to another embodiment of the present disclosure.

[0236] As shown in FIG. 9, the electronic device 9000 comprises a control unit 9001 which controls, and a processing unit 9003 which, under the control of the control unit 9001, calculates a semantic communication error rate related to semantic communication for a network-side device to determine whether to update a semantic library for semantic communication and / or an inference model related to the semantic library of the electronic device 9000.

[0237] The control unit 9001 and the processing unit 9003 can be implemented as one or more processing circuits, such as a processor or a chip, and at least one memory, such as a RAM, a ROM, etc., which can be used to store computer program code and data required for processing performed by the processing circuit. It should be understood that the various functional units in the electronic device 9000 shown in FIG. 9 are only logical modules divided according to the specific functions they implement, and are not intended to limit the specific implementation.

[0238] For example, the electronic device 9000 can work as a user equipment itself, and can further comprise external devices such as a memory, a transceiver (not shown), etc. The memory can be used to store programs and related data information required for the electronic device 9000 to implement various functions. The transceiver can comprise one or more communication interfaces to support communication with different devices (e.g., UE, base station, etc.), and the implementation of the transceiver is not specifically limited here.

[0239] As an example, the network-side device in the electronic device 9000 embodiment can be the electronic device 100 mentioned above. As an example, the electronic device 9000 can be a user equipment involved in the electronic device 100 embodiment above.

[0240] For example, the inference model related to the semantic library of the electronic device 9000 can be implemented by an encoder or a decoder at the electronic device 9000 end.

[0241] The electronic device 9000 according to the embodiments of the present disclosure calculates the semantic communication error rate, so that the network side device can more intelligently determine whether to update the semantic library and / or the inference model of the electronic device 9000 based on the semantic communication error rate, thereby ensuring that the electronic device 9000 maintains continuous and high-quality communication in semantic communication, i.e., the efficiency and reliability of semantic communication can be improved.

[0242] In the Internet of Vehicles scenario, the electronic device 9000 according to the embodiments of the present disclosure calculates the semantic communication error rate, so that the network side device can determine the need for semantic communication cell switching based on the semantic communication error rate, to better cope with the problem of cell management in semantic communication. Based on the semantic communication error rate, the network side device can more intelligently determine whether to perform semantic cell switching, thereby ensuring that the electronic device 9000 maintains continuous and high-quality communication between semantic communication service areas. The switching configuration based on the semantic communication error rate according to the embodiments of the present disclosure can realize more intelligent switching of vehicles between different semantic communication cells, thereby improving the reliability and efficiency of semantic communication. It provides a more intelligent and efficient cell management solution for semantic communication of vehicles in urban networks to meet the growing demand for vehicle communication and ensure the reliability and quality of semantic communication services.

[0243] As an example, the semantic library includes at least one of a relationship mapping between data information and semantic information, a machine learning model for generating a relationship mapping between data information and semantic information, a deep learning model, a mapping table, and a matrix compression.

[0244] For examples of the semantic library, see the corresponding parts described in the electronic device 100 embodiments in conjunction with FIG. 2, which will not be repeated here.

[0245] As an example, the inference model is used to transform data information and semantic information.

[0246] As an example, the processing unit 9003 can be configured to calculate the proportion of error information in the semantic information received from other electronic devices within a predetermined time period based on the original semantic library and / or the original inference model of the electronic device 9000, as the semantic communication error rate. For a description of this way of calculating the semantic communication error rate, see the corresponding part described in expression 1 in the electronic device 100 embodiments, which will not be repeated here.

[0247] As an example, the processing unit 9003 can be configured to calculate, as the semantic communication error rate, a proportion of error information in semantic information that the electronic device can determine to be correct among semantic information received from other electronic devices within a predetermined time period, based on the original semantic library and / or the original inference model of the electronic device 9000. For a description of this manner of calculating the semantic communication error rate, see the corresponding part described in expression 2 in the electronic device 100 embodiment, which will not be repeated here.

[0248] As an example, the processing unit 9003 can be configured to calculate, as the semantic communication error rate, a proportion of error information in a predetermined number of pieces of obtained flag information, based on the original semantic library and / or the original inference model of the electronic device 9000, wherein the flag information is information of which the electronic device can obtain correct semantics in advance. For a description of this manner of calculating the semantic communication error rate, see the corresponding part described in expression 3 in the electronic device 100 embodiment, which will not be repeated here.

[0249] As an example, the processing unit 9003 can be configured to directly send the semantic communication error rate to the network side device. As an example, the processing unit 9003 can be configured to directly receive signaling for indicating whether to update from the network side device. As an example, the processing unit 9003 can be configured to directly receive an updated semantic library and / or inference model from the network side device in the case where updating is needed. See the corresponding part described in combination with FIG. 4A in the electronic device 100 embodiment, which will not be repeated here.

[0250] As an example, the processing unit 9003 can be configured to send the semantic communication error rate to other electronic devices, so that the other electronic devices forward the semantic communication error rate to the network side device. As an example, the processing unit 9003 can be configured to receive signaling for indicating whether to update from the network side device via the other electronic devices. As an example, the processing unit 9003 can be configured to receive an updated semantic library and / or inference model from the network side device via the other electronic devices in the case where updating is needed. See the corresponding part described in combination with FIG. 4B in the electronic device 100 embodiment, which will not be repeated here.

[0251] The electronic device 1000 for wireless communication according to another embodiment of the present disclosure is also provided. The electronic device 1000 includes at least one processor and at least one memory including computer program codes, wherein the at least one memory and the computer program codes are configured to, with the at least one processor, cause the electronic device 1000 to perform: transmitting, to a network-side device, a semantic communication error rate received from another electronic device for the network-side device to determine whether to update a semantic library and / or an inference model related to the semantic library of the another electronic device for semantic communication.

[0252] FIG. 10 shows a functional module block diagram of the electronic device 1000 for wireless according to another embodiment of the present disclosure.

[0253] As shown in FIG. 10, the electronic device 1000 includes a control unit 1001 that controls, and a communication unit 1003 that transmits, to a network-side device, a semantic communication error rate received from another electronic device for the network-side device to determine whether to update a semantic library and / or an inference model related to the semantic library of the another electronic device for semantic communication under the control of the control unit 1001.

[0254] The control unit 1001 and the communication unit 1003 can be implemented as one or more processing circuits, such as a processor or a chip, and at least one memory, such as a RAM, a ROM, etc., for storing computer program codes and data required by the processing circuit to perform processing, etc. It should be understood that each functional unit in the electronic device 1000 shown in FIG. 10 is only a logical module divided according to the specific function it implements, and is not intended to limit the specific implementation manner.

[0255] For example, the electronic device 1000 can work as a user equipment itself, and can further include external devices such as a memory, a transceiver (not shown in the figure), etc. The memory can be used to store programs and related data information required by the user equipment to implement various functions. The transceiver can include one or more communication interfaces to support communication with different devices (e.g., a base station, other user equipment, etc.), and the implementation form of the transceiver is not specifically limited here.

[0256] As an example, the network-side device in the electronic device 1000 embodiment can be the electronic device 100 mentioned above, and the other electronic device in the electronic device 1000 embodiment can be the electronic device 9000 mentioned above. As an example, the electronic device 1000 can be the other user equipment involved in the electronic device 100 embodiment and the other electronic device involved in the electronic device 9000 embodiment.

[0257] The electronic device 1000 according to the embodiments of the present disclosure forwards the semantic communication error rate of the other electronic device to the network side device, so that the network side device can more intelligently determine whether to update the semantic library and / or the inference model of the other electronic device based on the semantic communication error rate, thereby ensuring that the other electronic device maintains continuous and high-quality communication in semantic communication, that is, the efficiency and reliability of semantic communication can be improved.

[0258] In the Internet of Vehicles scenario, the electronic device 1000 according to the embodiments of the present disclosure forwards the semantic communication error rate of the other electronic device to the network side device, so that the network side device can determine the need for semantic communication cell switching based on the semantic communication error rate, so as to better cope with the cell management problem in semantic communication. Based on the semantic communication error rate, the network side device can more intelligently determine whether to perform semantic cell switching, thereby ensuring that the vehicle maintains continuous and high-quality communication between semantic communication service areas.

[0259] As an example, the semantic library includes at least one of a relationship mapping between data information and semantic information, a machine learning model for generating a relationship mapping between data information and semantic information, a deep learning model, a mapping table, and a matrix compression.

[0260] For examples of the semantic library, see the corresponding parts described in the electronic device 100 embodiment in conjunction with FIG. 2, which will not be repeated here.

[0261] As an example, the inference model is used to convert data information and semantic information.

[0262] As an example, the communication unit 1003 is configured to forward the signaling received from the network side device for indicating whether to perform the update to the other electronic device, and in the case where the update is needed, forward the updated semantic library and / or inference model received from the network side device to the other electronic device. See the corresponding parts described in the electronic device 100 embodiment in conjunction with FIG. 4B, which will not be repeated here.

[0263] In the following, the electronic devices 9000 and 1000 according to the embodiments of the present disclosure are described in the form of a unit module in another form.

[0264] The electronic device 9000 and 1000 can include an information obtaining unit configured to obtain a scheduling request, information data, and pilot signaling (e.g., including receiving semantic communication error rate signaling, signaling for indicating whether to perform a knowledge base update) of a vehicle during a process of vehicle semantic communication; a channel measurement unit configured to measure a channel state in real time and generate a generalized channel model; an information sending unit configured to send scheduling signaling to other vehicles, base stations, and perform resource allocation (e.g., including sending semantic communication error rate signaling, signaling for indicating whether to perform a knowledge base update); and a semantic communication unit configured to extract semantic communication information and convert collected data into information of semantic communication. Thus, the channel can be measured in real time according to the signaling received by the vehicle, and the resource can be configured according to the user state.

[0265] As an example, the information obtaining unit is configured to receive scheduling signaling. The unit is configured to receive a scheduling request to establish a downlink, a sidelink, and the like.

[0266] As an example, the channel measurement unit obtains pilot information from the information obtaining unit and models the channel into a generalized channel model based on the pilot information. After modeling, the model is sent to the information sending unit. The unit is configured to estimate the channel model, for example, which can be implemented based on deep learning, reinforcement learning, and the like.

[0267] As an example, the information sending unit receives a state from the information obtaining unit and the channel measurement unit and sends a decision of a scheduling strategy to a base station and a vehicle user. The unit informs the base station and the vehicle user how to configure a channel resource and whether to perform data transmission.

[0268] As an example, the semantic communication unit can include a deep neural network to process data of the user itself and extract semantic communication information. The unit is configured to process semantic communication related information.

[0269] In the above embodiments, the processes of the electronic device 100, 9000, and 1000 are described, and some processes or methods are also disclosed. Hereinafter, a summary of the methods is given without repeating some details already discussed above, but it should be noted that although the methods are disclosed in the description of the processes of the above electronic device, the methods do not necessarily use or are not necessarily performed by those components described. For example, the above embodiments of the electronic device can be partially or completely implemented using hardware and / or firmware, and the methods discussed below can be completely implemented by computer executable programs, although the methods can also use hardware and / or firmware of the electronic device.

[0270] FIG. 11 shows a flow chart of a method S1100 for wireless communication according to an embodiment of the present disclosure. The method S1100 starts at step S1102. In step S1104, it is determined whether to update a semantic library for semantic communication of a user equipment and / or an inference model related to the semantic library based on a semantic communication error rate related to the user equipment for semantic communication. The method S1100 ends at step S1106.

[0271] The method can be performed by the electronic device 100 described above, for example, and details thereof can be found in the description of the related processing of the electronic device 100 above, which will not be repeated here.

[0272] FIG. 12 shows a flow chart of a method S1200 for wireless communication according to another embodiment of the present disclosure. The method S1200 starts at step S1202. In step S1204, a semantic communication error rate related to semantic communication is calculated for a network-side device to determine whether to update a semantic library for semantic communication of the electronic device 9000 and / or an inference model related to the semantic library. The method S1200 ends at step S1206.

[0273] The method can be performed by the electronic device 9000 described above, for example, and details thereof can be found in the description of the related processing of the electronic device 9000 above, which will not be repeated here.

[0274] FIG. 13 shows a flow chart of a method S1300 for wireless communication according to yet another embodiment of the present disclosure. The method S1300 starts at step S1302. In step S1304, a semantic communication error rate received from other electronic devices is transmitted to a network-side device for the network-side device to determine whether to update a semantic library for semantic communication of the other electronic devices and / or an inference model related to the semantic library. The method S1300 ends at step S1306.

[0275] The method can be performed by the electronic device 1000 described above, for example, and details thereof can be found in the description of the related processing of the electronic device 1000 above, which will not be repeated here.

[0276] The techniques of the present disclosure can be applied to various products.

[0277] The electronic device 100 can be provided at a base station side or connected to a base station. The base station can be implemented as any type of evolved Node B (eNB) or gNB (5G base station). The eNB includes, for example, a macro eNB and a small eNB. The small eNB can be an eNB for a small cell whose coverage is smaller than that of a macro cell such as a pico eNB, a micro eNB, and a home (femto) eNB. The same can be applied to the gNB. Instead, the base station can be implemented as any other type of base station such as a NodeB and a base transceiver station (BTS). The base station can include a main body (also referred to as a base station device) configured to control wireless communication, and one or more remote radio heads (RRHs) provided at a different place from the main body. In addition, various types of electronic devices can operate as a base station by temporarily or semi-persistently performing a base station function.

[0278] The electronic devices 9000 and 1000 can be implemented as various user devices. The user devices can be implemented as mobile terminals such as smartphones, tablet personal computers (PCs), notebook PCs, portable game terminals, portable / dongle type mobile routers, and digital camera devices, or in-vehicle terminals such as car navigation devices. The user devices can also be implemented as terminals that perform machine-to-machine (M2M) communication (also referred to as machine type communication (MTC) terminals). In addition, the user devices can be wireless communication modules such as integrated circuit modules including a single wafer installed on each of the above-described terminals.

[0279] [Application Examples Related to Base Station]

[0280] (First Application Example)

[0281] FIG. 14 is a block diagram illustrating a first example of a schematic configuration of an eNB or gNB to which the technology of the present disclosure can be applied. Note that the following description takes an eNB as an example, but the same can be applied to a gNB. The eNB 800 includes one or more antennas 810 and a base station device 820. The base station device 820 and each antenna 810 can be connected to each other via an RF cable.

[0282] Each of the antennas 810 includes a single or a plurality of antenna elements such as a plurality of antenna elements included in a multiple-input multiple-output (MIMO) antenna, and functions to transmit and receive wireless signals for the base station device 820. As illustrated in FIG. 14, the eNB 800 can include a plurality of antennas 810. For example, the plurality of antennas 810 can be compatible with a plurality of frequency bands used by the eNB 800. Although FIG. 14 illustrates an example in which the eNB 800 includes a plurality of antennas 810, the eNB 800 can also include a single antenna 810.

[0283] The base station device 820 includes a controller 821, a memory 822, a network interface 823, and a wireless communication interface 825.

[0284] The controller 821 can be, for example, a CPU or a DSP, and operates various functions of a higher layer of the base station device 820. For example, the controller 821 generates data packets from data in a signal processed by the wireless communication interface 825, and transfers the generated packets via the network interface 823. The controller 821 can bundle data from a plurality of baseband processors to generate bundled packets, and transfer the generated bundled packets. The controller 821 can have a logical function of performing control such as radio resource control, radio bearer control, mobility management, admission control, and scheduling. The control can be performed in conjunction with a nearby eNB or a core network node. The memory 822 includes a RAM and a ROM, and stores programs executed by the controller 821 and various types of control data such as a terminal list, transmission power data, and scheduling data.

[0285] The network interface 823 is a communication interface for connecting the base station device 820 to the core network 824. The controller 821 can communicate with a core network node or another eNB via the network interface 823. In this case, the eNB 800 and the core network node or the other eNB can be connected to each other by a logical interface such as an S1 interface and an X2 interface. The network interface 823 can also be a wired communication interface or a wireless communication interface for a wireless backhaul line. If the network interface 823 is a wireless communication interface, the network interface 823 can use a higher frequency band for wireless communication than a frequency band used by the wireless communication interface 825.

[0286] The wireless communication interface 825 supports any cellular communication scheme such as Long Term Evolution (LTE) and LTE-Advanced, and provides wireless connections to terminals located in a cell of the eNB 800 via the antenna 810. The wireless communication interface 825 can generally include, for example, a baseband (BB) processor 826 and an RF circuit 827. The BB processor 826 can perform, for example, encoding / decoding, modulation / demodulation, and multiplexing / demultiplexing, and perform various types of signal processing of layers (e.g., layer 1, medium access control (MAC), radio link control (RLC), and packet data convergence protocol (PDCP)). The BB processor 826 can have a part or all of the logical functions described above instead of the controller 821. The BB processor 826 can be a memory that stores a communication control program, or a module that includes a processor and related circuitry configured to execute the program. Updating the program can cause the functions of the BB processor 826 to change. The module can be a card or a blade that is inserted into a slot of the base station device 820. Alternatively, the module can also be a chip that is mounted on a card or a blade. Meanwhile, the RF circuit 827 can include, for example, a mixer, a filter, and an amplifier, and transmit and receive wireless signals via the antenna 810.

[0287] As illustrated in FIG. 14, the wireless communication interface 825 can include a plurality of BB processors 826. For example, the plurality of BB processors 826 can be compatible with a plurality of frequency bands used by the eNB 800. As illustrated in FIG. 14, the wireless communication interface 825 can include a plurality of RF circuits 827. For example, the plurality of RF circuits 827 can be compatible with a plurality of antenna elements. While FIG. 14 illustrates an example in which the wireless communication interface 825 includes a plurality of BB processors 826 and a plurality of RF circuits 827, the wireless communication interface 825 can also include a single BB processor 826 or a single RF circuit 827.

[0288] The electronic device 100 as illustrated in FIG. 1, when implemented as the eNB 800 as illustrated in FIG. 14, its transceiver can be implemented by the wireless communication interface 825. At least a part of the functions can also be implemented by the controller 821. For example, the controller 821 can be able to improve the continuity and reliability of semantic communication by performing the functions of the units in the electronic device 100.

[0289] (Second Application Example)

[0290] FIG. 15 is a block diagram illustrating a second example of a schematic configuration of an eNB or gNB to which the technology of the present disclosure can be applied. Note that, similarly, the following description takes the eNB as an example, but is equally applicable to the gNB. The eNB 830 includes one or plural antennas 840, a base station device 850, and RRHs 860. The RRHs 860 and each of the antennas 840 can be connected to each other via an RF cable. The base station device 850 and the RRHs 860 can be connected to each other via a high-speed line such as an optical fiber cable.

[0291] Each of the antennas 840 includes a single or plural antenna elements (such as plural antenna elements included in a MIMO antenna) and is used for the RRH 860 to transmit and receive a radio signal. As illustrated in FIG. 15, the eNB 830 can include plural antennas 840. For example, the plural antennas 840 can be compatible with plural frequency bands used by the eNB 830. Although FIG. 15 illustrates an example in which the eNB 830 includes plural antennas 840, the eNB 830 can also include a single antenna 840.

[0292] The base station device 850 includes a controller 851, a memory 852, a network interface 853, a wireless communication interface 855, and a connection interface 857. The controller 851, the memory 852, and the network interface 853 are the same as the controller 821, the memory 822, and the network interface 823 described with reference to FIG. 15.

[0293] The wireless communication interface 855 supports any cellular communication scheme such as LTE and LTE-Advanced, and provides wireless communication to terminals located in a sector corresponding to the RRH 860 via the RRH 860 and the antennas 840. The wireless communication interface 855 can typically include, for example, a BB processor 856. The BB processor 856 is the same as the BB processor 826 described with reference to FIG. 15, except that the BB processor 856 is connected to the RF circuit 864 of the RRH 860 via the connection interface 857. As illustrated in FIG. 15, the wireless communication interface 855 can include plural BB processors 856. For example, the plural BB processors 856 can be compatible with plural frequency bands used by the eNB 830. Although FIG. 15 illustrates an example in which the wireless communication interface 855 includes plural BB processors 856, the wireless communication interface 855 can also include a single BB processor 856.

[0294] The connection interface 857 is an interface for connecting the base station device 850 (the wireless communication interface 855) to the RRH 860. The connection interface 857 can also be a communication module for communication in the above-described high-speed line for connecting the base station device 850 (the wireless communication interface 855) to the RRH 860.

[0295] The RRH 860 includes a connection interface 861 and a wireless communication interface 863.

[0296] The connection interface 861 is an interface for connecting the RRH 860 (wireless communication interface 863) to the base station apparatus 850. The connection interface 861 can also be a communication module for communication in the high-speed line described above.

[0297] The wireless communication interface 863 transmits and receives wireless signals via the antenna 840. The wireless communication interface 863 can generally include, for example, an RF circuit 864. The RF circuit 864 can include, for example, a mixer, a filter, and an amplifier, and transmits and receives wireless signals via the antenna 840. As illustrated in FIG. 15, the wireless communication interface 863 can include a plurality of RF circuits 864. For example, the plurality of RF circuits 864 can support a plurality of antenna elements. While FIG. 15 illustrates an example in which the wireless communication interface 863 includes a plurality of RF circuits 864, the wireless communication interface 863 can also include a single RF circuit 864.

[0298] The electronic device 100 as illustrated in FIG. 1, when implemented as the eNB 830 illustrated in FIG. 15, can have its transceiver implemented by the wireless communication interface 855. At least a portion of the functions can also be implemented by the controller 851. For example, the controller 851 can be able to improve continuity and reliability of semantic communication by performing the functions of the units in the electronic device 100.

[0299] [Application Examples with Respect to User Equipment]

[0300] (First Application Example)

[0301] FIG. 16 is a block diagram illustrating an example of a schematic configuration of a smartphone 900 to which the technology of the present disclosure can be applied. The smartphone 900 includes a processor 901, a memory 902, a storage 903, an external connection interface 904, a camera 906, a sensor 907, a microphone 908, an input device 909, a display device 910, a speaker 911, a wireless communication interface 912, one or more antenna switches 915, one or more antennas 916, a bus 917, a battery 918, and an auxiliary controller 919.

[0302] The processor 901 can be, for example, a CPU or a system on chip (SoC), and controls functions of the application layer and other layers of the smartphone 900. The memory 902 includes a RAM and a ROM, and stores data and programs executed by the processor 901. The storage 903 can include a storage medium such as a semiconductor memory and a hard disk. The external connection interface 904 is an interface for connecting an external device such as a memory card and a universal serial bus (USB) device to the smartphone 900.

[0303] The camera 906 includes an image sensor such as a charge coupled device (CCD) and a complementary metal oxide semiconductor (CMOS), and generates a captured image. The sensor 907 can include a set of sensors such as a measurement sensor, a gyro sensor, a geomagnetic sensor, and an acceleration sensor. The microphone 908 converts a sound input to the smartphone 900 into an audio signal. The input device 909 includes, for example, a touch sensor configured to detect a touch on a screen of the display device 910, a keypad, a keyboard, a button, or a switch, and receives an operation or information input from a user. The display device 910 includes a screen such as a liquid crystal display (LCD) and an organic light emitting diode (OLED) display, and displays an output image of the smartphone 900. The speaker 911 converts an audio signal output from the smartphone 900 into a sound.

[0304] The wireless communication interface 912 supports any cellular communication scheme such as LTE and LTE-Advanced, and performs wireless communication. The wireless communication interface 912 can generally include, for example, a BB processor 913 and an RF circuit 914. The BB processor 913 can perform, for example, encoding / decoding, modulation / demodulation, and multiplexing / demultiplexing, and perform various types of signal processing for wireless communication. Meanwhile, the RF circuit 914 can include, for example, a mixer, a filter, and an amplifier, and transmit and receive a wireless signal via an antenna 916. Note that, although a case in which one RF link is connected to one antenna is shown in the drawing, this is merely illustrative, and a case in which one RF link is connected to a plurality of antennas through a plurality of phase shifters is also included. The wireless communication interface 912 can be one chip module in which the BB processor 913 and the RF circuit 914 are integrated. As shown in FIG. 16, the wireless communication interface 912 can include a plurality of BB processors 913 and a plurality of RF circuits 914. Although FIG. 16 shows an example in which the wireless communication interface 912 includes a plurality of BB processors 913 and a plurality of RF circuits 914, the wireless communication interface 912 can also include a single BB processor 913 or a single RF circuit 914.

[0305] In addition, the wireless communication interface 912 can support another type of wireless communication scheme in addition to the cellular communication scheme, such as a short-range wireless communication scheme, a near field communication scheme, and a wireless local area network (LAN) scheme. In this case, the wireless communication interface 912 can include a BB processor 913 and an RF circuit 914 for each wireless communication scheme.

[0306] Each of the antenna switches 915 switches a connection destination of the antenna 916 between a plurality of circuits included in the wireless communication interface 912 (for example, circuits for different wireless communication schemes).

[0307] Each of the antennas 916 includes a single or multiple antenna elements (such as a plurality of antenna elements included in a MIMO antenna), and is used for the wireless communication interface 912 to transmit and receive wireless signals. As illustrated in FIG. 16, the smartphone 900 can include a plurality of antennas 916. Although FIG. 16 illustrates an example in which the smartphone 900 includes a plurality of antennas 916, the smartphone 900 can also include a single antenna 916.

[0308] Further, the smartphone 900 can include an antenna 916 for each wireless communication scheme. In this case, the antenna switch 915 can be omitted from the configuration of the smartphone 900.

[0309] The bus 917 connects the processor 901, the memory 902, the storage 903, the external connection interface 904, the camera 906, the sensor 907, the microphone 908, the input device 909, the display device 910, the speaker 911, the wireless communication interface 912, and the auxiliary controller 919 to each other. The battery 918 supplies power to the respective blocks of the smartphone 900 illustrated in FIG. 16 via a feed line, which is partially illustrated as a broken line in the figure. The auxiliary controller 919, for example, operates the minimum necessary functions of the smartphone 900 in a sleep mode.

[0310] When the electronic devices 9000 and 1000 are implemented as, for example, the smartphone 900 illustrated in FIG. 16 as a user device side, the transceivers of the electronic devices 9000 and 1000 can be implemented by the wireless communication interface 912. At least a part of the functions can also be implemented by the processor 901 or the auxiliary controller 919. For example, the processor 901 or the auxiliary controller 919 is able to improve the continuity and reliability of semantic communication by executing the functions of the units in the electronic devices 9000 and 1000 described above.

[0311] (Second Application Example)

[0312] FIG. 17 is a block diagram illustrating an example of a schematic configuration of a car navigation device 920 to which the technology of the present disclosure can be applied. The car navigation device 920 includes a processor 921, a memory 922, a global positioning system (GPS) module 924, a sensor 925, a data interface 926, a content player 927, a storage medium interface 928, an input device 929, a display device 930, a speaker 931, a wireless communication interface 933, one or more antenna switches 936, one or more antennas 937, and a battery 938.

[0313] The processor 921 can be, for example, a CPU or a SoC, and controls a navigation function and another function of the car navigation device 920. The memory 922 includes a RAM and a ROM, and stores data and programs executed by the processor 921.

[0314] The GPS module 924 measures a position (such as latitude, longitude, and altitude) of the car navigation device 920 using a GPS signal received from a GPS satellite. The sensor 925 can include a set of sensors such as a gyro sensor, a geomagnetic sensor, and an air pressure sensor. The data interface 926 is connected to, for example, an in-vehicle network 941 via a terminal not shown, and acquires data (such as vehicle speed data) generated by the vehicle.

[0315] The content player 927 reproduces content stored in a storage medium (such as a CD and a DVD) inserted into the storage medium interface 928. The input device 929 includes, for example, a touch sensor configured to detect a touch on a screen of the display device 930, a button, or a switch, and receives an operation or information input from a user. The display device 930 includes a screen such as an LCD or an OLED display, and displays an image of a navigation function or reproduced content. The speaker 931 outputs a sound of a navigation function or reproduced content.

[0316] The wireless communication interface 933 supports any cellular communication scheme (such as LTE and LTE-Advanced), and performs wireless communication. The wireless communication interface 933 can typically include, for example, a BB processor 934 and an RF circuit 935. The BB processor 934 can perform, for example, encoding / decoding, modulation / demodulation, and multiplexing / demultiplexing, and perform various types of signal processing for wireless communication. Meanwhile, the RF circuit 935 can include, for example, a mixer, a filter, and an amplifier, and transmit and receive a wireless signal via an antenna 937. The wireless communication interface 933 can also be one chip module in which the BB processor 934 and the RF circuit 935 are integrated. As shown in FIG. 17, the wireless communication interface 933 can include a plurality of BB processors 934 and a plurality of RF circuits 935. While FIG. 17 shows an example in which the wireless communication interface 933 includes a plurality of BB processors 934 and a plurality of RF circuits 935, the wireless communication interface 933 can also include a single BB processor 934 or a single RF circuit 935.

[0317] Furthermore, the wireless communication interface 933 can support another type of wireless communication scheme, such as a short-range wireless communication scheme, a near field communication scheme, and a wireless LAN scheme, in addition to the cellular communication scheme. In this case, the wireless communication interface 933 can include a BB processor 934 and an RF circuit 935 for each wireless communication scheme.

[0318] Each of the antenna switches 936 switches a connection destination of the antenna 937 between a plurality of circuits included in the wireless communication interface 933, such as circuits for different wireless communication schemes.

[0319] Each of the antennas 937 includes a single or a plurality of antenna elements, such as a plurality of antenna elements included in a MIMO antenna, and is used for the wireless communication interface 933 to transmit and receive wireless signals. As illustrated in FIG. 17, the car navigation device 920 can include a plurality of antennas 937. While FIG. 17 illustrates an example in which the car navigation device 920 includes a plurality of antennas 937, the car navigation device 920 can also include a single antenna 937.

[0320] Further, the car navigation device 920 can include an antenna 937 for each wireless communication scheme. In this case, the antenna switches 936 can be omitted from the configuration of the car navigation device 920.

[0321] The battery 938 supplies power to the respective blocks of the car navigation device 920 illustrated in FIG. 17 via feed lines, which are partially illustrated as dotted lines in the figure. The battery 938 accumulates power supplied from the vehicle.

[0322] When the electronic devices 9000 and 1000 as illustrated in FIGS. 9 and 10 are implemented as, for example, the car navigation device 920 as a user device side, for example, the car navigation device 920 illustrated in FIG. 17, respectively, the transceivers of the electronic devices 9000 and 1000 can be implemented by the wireless communication interface 933. At least a part of the functions can also be implemented by the processor 921. For example, the processor 921 is able to improve continuity and reliability of semantic communication by executing the functions of the units in the electronic devices 9000 and 1000 described above.

[0323] The technology of the present disclosure can also be implemented as an in-vehicle system (or a vehicle) 940 including one or more blocks of the car navigation device 920, the in-vehicle network 941, and the vehicle module 942. The vehicle module 942 generates vehicle data such as vehicle speed, engine speed, and failure information, and outputs the generated data to the in-vehicle network 941.

[0324] The basic principles of the present application are described above in connection with specific embodiments, but it is to be noted that, for those skilled in the art, it is understood that all or any steps or components of the method and apparatus of the present application can be implemented in any computing device (including a processor, a storage medium, etc.) or network of computing devices in the form of hardware, firmware, software, or a combination thereof, which can be implemented by those skilled in the art with their basic circuit design knowledge or basic programming skills upon reading the description of the present application.

[0325] Moreover, the present application also proposes a program product storing machine-readable instruction codes. The instruction codes are read and executed by a machine to perform the above-mentioned method according to the embodiments of the present application.

[0326] Correspondingly, a storage medium for carrying the above-mentioned program product storing machine-readable instruction codes is also included in the disclosure of the present application. The storage medium includes but is not limited to floppy disks, optical disks, magneto-optical disks, memory cards, memory sticks, and the like.

[0327] In the case of implementing the present application by software or firmware, programs constituting the software are installed from a storage medium or a network to a computer having a special hardware structure, such as a general-purpose computer 1800 shown in Fig. 18, which is capable of performing various functions and the like when various programs are installed.

[0328] In Fig. 18, a central processing unit (CPU) 1801 performs various processes according to programs stored in a read-only memory (ROM) 1802 or programs loaded from a storage section 1808 to a random access memory (RAM) 1803. In the RAM 1803, data required when the CPU 1801 performs various processes and the like is also stored as necessary. The CPU 1801, the ROM 1802, and the RAM 1803 are connected to each other via a bus 1804. An input / output interface 1805 is also connected to the bus 1804.

[0329] The following components are connected to the input / output interface 1805: an input section 1806 (including a keyboard, a mouse, and the like), an output section 1807 (including a display such as a cathode ray tube (CRT), a liquid crystal display (LCD), and the like, and a speaker, and the like), a storage section 1808 (including a hard disk, and the like), and a communication section 1809 (including a network interface card such as a LAN card, a modem, and the like). The communication section 1809 performs communication processing via a network such as the Internet. A drive 1810 can also be connected to the input / output interface 1805 as necessary. A removable medium 1811 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, and the like is installed in the drive 1810 as necessary, so that computer programs read therefrom are installed in the storage section 1808 as necessary.

[0330] In the case of implementing the above-mentioned series of processes by software, programs constituting the software are installed from a network such as the Internet or a storage medium such as the removable medium 1811.

[0331] It is understood by those skilled in the art that such storage media are not limited to the removable media 1811 shown in Fig. 18 in which the programs are stored and distributed separately from the apparatus to provide the programs to users. Examples of the removable media 1811 include magnetic disks (including floppy disks (registered trademark)), optical disks (including compact disc read only memory (CD-ROM) and digital versatile disk (DVD)), magneto-optical disks (including mini disks (MD) (registered trademark)), and semiconductor memories. Alternatively, the storage media can be the ROM 1802, the hard disk included in the storage section 1808, or the like in which the programs are stored and distributed to users together with the apparatuses including them.

[0332] It is also to be noted that in the apparatus, method and system of the present application, each component or step can be decomposed and / or recombined. Such decomposition and / or recombination should be considered as equivalents of the present application. Also, the steps of performing the above series of processes can naturally be executed in time series according to the order of explanation, but do not necessarily have to be executed in time series. Some steps can be executed in parallel or independently of each other.

[0333] Finally, it is to be noted that the terms "comprising", "including", or any other variant thereof are intended to cover non-exclusive inclusions, so that processes, methods, articles or apparatuses including a series of elements not only include those elements, but also include other elements not explicitly listed or inherent to such processes, methods, articles or apparatuses. In addition, the element defined by the phrase "including a" does not exclude the presence of additional identical elements in the process, method, article or apparatus including the element.

[0334] Although the embodiments of the present application have been described in detail above with reference to the accompanying drawings, it is to be understood that the above-described embodiments are merely for illustration of the present application and do not constitute limitations on the present application. Various modifications and changes can be made to the above-described embodiments without departing from the spirit and scope of the present application. Therefore, the scope of the present application is only limited by the appended claims and their equivalents.

[0335] The present technology can also be implemented as follows. Scheme 1. An electronic device for wireless communication, comprising: at least one processor; and at least one memory including computer program code, wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the electronic device to perform: determining whether to update a semantic library for semantic communication and / or an inference model related to the semantic library of the electronic device based on a semantic communication error rate related to the electronic device for semantic communication. Scheme 2. The electronic device of scheme 1, wherein the semantic library comprises at least one of a relationship mapping between data information and semantic information, a machine learning model for generating the relationship mapping between data information and semantic information, a deep learning model, a mapping table, and a matrix compression. Scheme 3. The electronic device of scheme 1 or 2, wherein the inference model is used to convert data information into semantic information. Scheme 4. The electronic device of any one of schemes 1 to 3, wherein the semantic communication error rate is calculated by the electronic device based on an original semantic library and / or an original inference model of the electronic device, and is a proportion of incorrect information among semantic information received from other electronic devices within a predetermined time period. Scheme 5. The electronic device of any one of schemes 1 to 3, wherein the semantic communication error rate is calculated by the electronic device based on an original semantic library and / or an original inference model of the electronic device, and is a proportion of incorrect information among semantic information received from other electronic devices within a predetermined time period, for which the electronic device can determine the correctness. Scheme 6. The electronic device of any one of schemes 1 to 3, wherein the semantic communication error rate is calculated by the electronic device based on an original semantic library and / or an original inference model of the electronic device, and is a proportion of incorrect information among a predetermined number of flag information obtained, wherein the flag information is information for which the electronic device can obtain correct semantics in advance. Scheme 7. An electronic device for wireless communication, comprising: at least one processor; and at least one memory including computer program code, wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the electronic device to perform: calculating a semantic communication error rate related to semantic communication for a network-side device to determine whether to update a semantic library for semantic communication and / or an inference model related to the semantic library of the electronic device. Scheme 8. The electronic device of scheme 7, wherein the semantic library comprises at least one of a relationship mapping between data information and semantic information, a machine learning model for generating the relationship mapping between data information and semantic information, a deep learning model, a mapping table, and a matrix compression. Scheme 9. The electronic device of scheme 7 or 8, wherein the inference model is used to convert data information into semantic information.Scheme 10. The electronic device according to any one of schemes 7 to 9, wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the electronic device to perform: calculating, based on the original semantic library and / or original inference model of the electronic device, a proportion of incorrect information among semantic information received from other electronic devices within a predetermined time period as the semantic communication error rate. Scheme 11. The electronic device according to any one of schemes 7 to 9, wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the electronic device to perform: calculating, based on the original semantic library and / or original inference model of the electronic device, a proportion of incorrect information among semantic information that the electronic device can judge the correctness of among semantic information received from other electronic devices within a predetermined time period as the semantic communication error rate. Scheme 12. The electronic device according to any one of schemes 7 to 9, wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the electronic device to perform: calculating, based on the original semantic library and / or original inference model of the electronic device, a proportion of incorrect information among a predetermined number of obtained landmark information as the semantic communication error rate, wherein the landmark information is information whose correct semantics can be obtained in advance by the electronic device. Scheme 13. An electronic device for wireless communication, comprising: at least one processor; and at least one memory including computer program code, wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the electronic device to perform: transmitting a semantic communication error rate received from other electronic devices to a network side device for the network side device to judge whether to update a semantic library used for semantic communication and / or an inference model related to the semantic library of the other electronic device. Scheme 14. The electronic device according to scheme 13, wherein the semantic library comprises at least one of a relationship mapping between data information and semantic information, a machine learning model used to generate a relationship mapping between data information and semantic information, a deep learning model, a mapping table, and a matrix compression. Scheme 15. The electronic device according to scheme 13 or 14, wherein the inference model is used to convert data information and semantic information. Scheme 16. The electronic device according to any one of schemes 13 to 15, wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the electronic device to perform: forwarding signaling received from the network side device for indicating whether to perform the update to the other electronic device, and forwarding an updated semantic library and / or inference model received from the network side device to the other electronic device in the case where the update is needed.Scheme 17. A method for wireless communication, comprising: determining whether to update a semantic library for semantic communication and / or an inference model related to the semantic library of a user equipment for semantic communication based on a semantic communication error rate related to the user equipment. Scheme 18. A method for wireless communication, comprising: calculating a semantic communication error rate related to semantic communication for a network-side device to determine whether to update a semantic library for semantic communication and / or an inference model related to the semantic library of the electronic device. Scheme 19. A method for wireless communication, comprising: transmitting a semantic communication error rate received from other electronic devices to a network-side device for the network-side device to determine whether to update a semantic library for semantic communication and / or an inference model related to the semantic library of the other electronic devices. Scheme 20. A computer-readable storage medium having computer-executable instructions stored thereon that, when executed, perform the method according to any one of schemes 17-19.

Claims

1. An electronic device for wireless communication, comprising: at least one processor; and at least one memory including computer program codes, wherein the at least one memory and the computer program codes are configured to, with the at least one processor, cause the electronic device to perform: determining whether to update a semantic library for semantic communication and / or an inference model related to the semantic library of the electronic device based on a semantic communication error rate related to a user device for semantic communication. The semantic library comprises at least one of a relationship mapping between data information and semantic information, a machine learning model for generating a relationship mapping between data information and semantic information, a deep learning model, a mapping table, and matrix compression. 2.The electronic device of claim 1, wherein, 3.The electronic device of claim 1 or 2, wherein The inference model is used to convert data information into semantic information. 4.The electronic device of any one of claims 1 to 3, wherein The semantic communication error rate is calculated by the user device based on its original semantic library and / or original inference model, and is the proportion of incorrect information in the semantic information received from other user devices within a predetermined time period. 5.The electronic device of any one of claims 1 to 3, wherein The semantic communication error rate is calculated by the user device based on its original semantic library and / or original inference model, and is the proportion of incorrect information in the semantic information received from other user devices within a predetermined time period, which the user device can determine to be correct. 6.The electronic device of any one of claims 1 to 3, wherein The semantic communication error rate is calculated by the user device based on its original semantic library and / or original inference model, and is the proportion of incorrect information in a predetermined number of flag information obtained by the user device, Wherein the flag information is information whose correct semantics can be obtained in advance by the user device. 7.An electronic device for wireless communication, comprising: at least one processor; and at least one memory including computer program codes, wherein the at least one memory and the computer program codes are configured to, with the at least one processor, cause the electronic device to perform: calculating a semantic communication error rate related to semantic communication for a network side device to determine whether to update a semantic library for semantic communication and / or an inference model related to the semantic library of the electronic device. The semantic library comprises at least one of a relationship mapping between data information and semantic information, a machine learning model for generating a relationship mapping between data information and semantic information, a deep learning model, a mapping table, and matrix compression. 9.The electronic device of claim 7 or 8, wherein 8. The electronic device of claim 7, wherein, The inference model is used to convert data information into semantic information. The at least one memory and the computer program codes are configured to, with the at least one processor, cause the electronic device to perform: ​ 10. The electronic device of any of claims 7 to 9, wherein, ​ calculate, based on the original semantic library and / or original inference model of the electronic device, a proportion of incorrect information in semantic information received from other electronic devices within a predetermined time period as the semantic communication error rate.

11. The electronic device of any of claims 7 to 9, wherein, The at least one memory and the computer program code are configured to, with the at least one processor, cause the electronic device to perform: calculate, based on the original semantic library and / or original inference model of the electronic device, a proportion of incorrect information in semantic information received from other electronic devices within a predetermined time period as the semantic communication error rate.

12. The electronic device of any of claims 7 to 9, wherein, The at least one memory and the computer program code are configured to, with the at least one processor, cause the electronic device to perform: calculate, based on the original semantic library and / or original inference model of the electronic device, a proportion of incorrect information in the obtained predetermined number of flag information as the semantic communication error rate, The flag information is information of which correct semantics can be obtained in advance by the electronic device.

13. An electronic device for wireless communication, comprising: at least one processor; and at least one memory including computer program code, wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the electronic device to perform: transmit the semantic communication error rate received from other electronic devices to a network side device for the network side device to determine whether to update a semantic library for semantic communication and / or an inference model related to the semantic library of the other electronic devices.

14. The electronic device of claim 13, wherein, The semantic library comprises at least one of a relationship mapping between data information and semantic information, a machine learning model for generating a relationship mapping between data information and semantic information, a deep learning model, a mapping table, and a matrix compression.

15. The electronic device of claim 13 or 14, wherein The inference model is used to convert data information and semantic information.

16. The electronic device of any of claims 13-15, wherein, The at least one memory and the computer program code are configured to, with the at least one processor, cause the electronic device to perform: forward signaling received from the network side device indicating whether the update is performed to the other electronic devices, and in the case where the update needs to be performed, forward the updated semantic library and / or inference model received from the network side device to the other electronic devices.

17. A method for wireless communication, comprising: determine whether to update a semantic library for semantic communication and / or an inference model related to the semantic library of a user equipment for semantic communication based on a semantic communication error rate related to the user equipment.

18. A method for wireless communication, comprising: calculate a semantic communication error rate related to semantic communication for a network side device to determine whether to update a semantic library for semantic communication and / or an inference model related to the semantic library of the electronic device.

19. A method for wireless communication, comprising: The semantic communication error rate received from other electronic devices is transmitted to a network side device for the network side device to determine whether to update a semantic library used for semantic communication and / or an inference model related to the semantic library of the other electronic devices.

20. A computer-readable storage medium having stored thereon computer- executable instructions which, when executed, perform a method according to any one of claims 17 to 19.

Images