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

Abstract

Provided are an electronic device, a method for wireless communication, and a computer-readable storage medium. The electronic device may comprise at least one processor and at least one memory, wherein the at least one memory comprises computer program codes, and the at least one memory and the computer program codes are configured to, by means of the at least one processor, cause the electronic device to perform: extracting from environmental data a semantic slice related to vehicle driving; determining importance of the semantic slice; and sending, to a network side device, importance information indicating the importance.

Description

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

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on February 8, 2024, with application number 202410179009.7 and invention name “Electronic device, method for wireless communication and computer-readable storage medium”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the technical field of wireless communications, and more specifically, to an electronic device capable of being used for semantic communications related to vehicle driving or vehicle behavior decision-making, a method for wireless communications, and a computer-readable storage medium. Background Art

[0003] Semantic communication is a communication method designed to ensure that the sender and receiver of information accurately understand and share their meaning. This form of communication emphasizes the semantics of language and symbol systems—the importance of meaning, background knowledge, and context. Semantic communication goes beyond simply conveying the words or sounds of a message; it's crucial to ensure the receiver correctly understands the sender's intent and the message's meaning.

[0004] Semantic communication has attracted considerable attention because it can effectively extract information of interest to target applications, achieve efficient data compression, reduce the amount of data transmitted across communication networks, and alleviate communication bottlenecks caused by growing workloads. This communication method is of great significance in various fields, including interpersonal communication, computer science, artificial intelligence, and natural language processing. Summary of the Invention

[0005] A brief overview of the present disclosure is provided below to provide a basic understanding of certain aspects of the present disclosure. However, it should be understood that this overview is not an exhaustive overview of the present disclosure. It is not intended to identify key or important parts of the present disclosure, nor is it intended to limit the scope of the present disclosure. Its purpose is simply to present certain concepts of the present disclosure in a simplified form as a prelude to the more detailed description that will be given later.

[0006] An object of at least one aspect of the present disclosure is to provide an electronic device, a method for wireless communication, and a computer-readable storage medium, which are capable of performing semantic communication related to vehicle driving or vehicle behavior decision-making.

[0007] According to a first aspect of the present disclosure, an electronic device is provided, comprising at least one processor and at least one memory, wherein the at least one memory includes computer program code. The at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to: extract semantic slices related to vehicle driving from environmental data; determine the importance of the semantic slices; and transmit importance information indicating the importance to a network-side device.

[0008] According to the first aspect of the present disclosure, a method for wireless communication is also provided, which includes: extracting semantic slices related to vehicle driving (or vehicle behavior decision-making) from environmental data; determining the importance of the semantic slices; and sending importance information indicating the importance to a network side device.

[0009] According to a second aspect of the present disclosure, an electronic device is further provided, comprising at least one processor and at least one memory, wherein the at least one memory comprises computer program code. The at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute: receiving importance information from a vehicle-side device, the importance information indicating the importance of semantic slices extracted from environmental data and related to vehicle driving (or vehicle behavior decision-making).

[0010] According to a second aspect of the present disclosure, a method for wireless communication is also provided, the method comprising: receiving importance information from a vehicle-side device, the importance information indicating the importance of semantic slices related to vehicle driving extracted from environmental data.

[0011] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer program code is also provided. The computer program code enables the electronic device to execute the method for wireless communication provided according to the first or second aspect above through a processor included in the electronic device.

[0012] According to other aspects of the present disclosure, computer program codes and computer program products for implementing the above-mentioned method according to the present disclosure are also provided.

[0013] According to at least one aspect of the embodiments of the present disclosure, semantic communication related to vehicle driving or vehicle behavior decision-making can be performed, thereby alleviating communication bottleneck problems in scenarios such as the Internet of Vehicles with the help of emerging semantic communication technologies, and can help improve the overall performance of the network.

[0014] Other aspects of the embodiments of the present disclosure are given in the following description, wherein the detailed description is used to fully disclose the preferred embodiments of the embodiments of the present disclosure without imposing limitations thereon. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The drawings described herein are for illustrative purposes only of selected embodiments and not all possible implementations, and are not intended to limit the scope of the present disclosure. In the drawings:

[0016] FIG1 is a schematic diagram illustrating an example of a centralized vehicle network;

[0017] FIG2 is a schematic diagram illustrating an example of a distributed vehicle network;

[0018] 3 is a block diagram showing a configuration example of an electronic device according to a first embodiment of the present disclosure;

[0019] FIG4 is a flow chart illustrating an example signaling interaction between a vehicle side and a network side before semantic communication;

[0020] FIG5 is a schematic diagram for illustrating an example implementation of semantic extraction and semantic evaluation;

[0021] FIG6 is a flow chart illustrating an example signaling interaction between a vehicle side and a network side for semantic communication;

[0022] 7 is a block diagram showing a configuration example of an electronic device according to a second embodiment of the present disclosure;

[0023] FIG8 is a diagram illustrating an example implementation of allocating available communication resources based on semantic importance;

[0024] FIG9 is a schematic diagram for illustrating an example implementation of obtaining global semantic information based on semantic slices;

[0025] FIG10 is a schematic diagram for illustrating an example implementation of obtaining global semantic information using a semantic fusion network;

[0026] FIG11 is a schematic diagram for illustrating joint training optimization of a semantic evaluation network and an assignment evaluation network;

[0027] 12 is a flowchart showing a process example of a method for wireless communication according to the first embodiment of the present disclosure;

[0028] 13 is a flowchart illustrating a process example of a method for wireless communication according to a second embodiment of the present disclosure;

[0029] FIG14 is a block diagram illustrating an example of a schematic configuration of a server to which the technology of the present disclosure may be applied;

[0030] FIG15 is a block diagram showing a first example of a schematic configuration of an eNB to which the technology of the present disclosure may be applied;

[0031] FIG16 is a block diagram illustrating a second example of a schematic configuration of an eNB to which the technology of the present disclosure may be applied;

[0032] FIG17 is a block diagram showing an example of a schematic configuration of a smartphone to which the technology of the present disclosure can be applied;

[0033] FIG. 18 is a block diagram illustrating an example of a schematic configuration of a car navigation device to which the technology of the present disclosure can be applied.

[0034] While the present disclosure is susceptible to various modifications and alternative forms, specific embodiments thereof have been shown by way of example in the drawings and are described in detail herein. It should be understood, however, that the description of specific embodiments herein is not intended to limit the disclosure to the particular forms disclosed, but rather, the disclosure is intended to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the disclosure. It should be noted that throughout the several drawings, corresponding reference numerals indicate corresponding parts. DETAILED DESCRIPTION

[0035] Examples of the present disclosure will now be described more fully with reference to the accompanying drawings.The following description is merely exemplary in nature and is not intended to limit the present disclosure, application, or uses.

[0036] Example embodiments are provided so that the present disclosure will be exhaustive and will fully convey its scope to those skilled in the art. Numerous specific details such as examples of specific components, devices, and methods are set forth to provide a detailed understanding of the embodiments of the present disclosure. It will be apparent to those skilled in the art that specific details need not be used and that the example embodiments can be implemented in many different forms, none of which should be construed as limiting the scope of the present disclosure. In some example embodiments, well-known processes, well-known structures, and well-known technologies are not described in detail.

[0037] The description will be in the following order:

[0038] 1. Overview

[0039] 2. Configuration Example of Electronic Device of First Embodiment

[0040] 2.1 Configuration Example

[0041] 2.2 Example Processing

[0042] 3. Configuration Example of Electronic Device of Second Embodiment

[0043] 3.1 Configuration Example

[0044] 3.2 Example Processing

[0045] 3.3 Others (Joint training optimization of related networks)

[0046] 4. Method Examples

[0047] 5. Application Examples

[0048] <1. Overview>

[0049] In autonomous driving applications, vehicles may be equipped with a variety of devices for acquiring environmental information, such as LiDAR, millimeter-wave radar, optical cameras, and other sensors. These sensors provide a wealth of environmental information for autonomous vehicle decision-making. However, this environmental information contains a significant amount of redundant information, and much of it is irrelevant to the final behavioral decision. In connected vehicle applications, directly sharing raw sensor information presents significant challenges for communication transmission.

[0050] As previously mentioned, semantic communication can effectively extract information of interest to target applications, achieving efficient data compression. Given these characteristics of semantic communication, the inventors proposed the basic concept of this invention: applying semantic communication technology to IoV applications to extract semantic information of interest from raw sensor information (environmental information). This effectively reduces the amount of transmitted data, improves communication efficiency, and enhances the performance of IoV applications.

[0051] The above-mentioned inventive concept can be applied to both centralized and distributed vehicle networks.

[0052] FIG1 is a schematic diagram showing an example of a centralized Internet of Vehicles to which the technology of the present disclosure can be applied. As shown in FIG1 , the example of a centralized Internet of Vehicles may include a roadside station RSU and multiple vehicles V1, V2, V3, etc. that it serves. Each vehicle can, for example, use a pre-trained deep neural network to extract semantic information related to vehicle driving (vehicle behavior or vehicle behavior decision-making) (also referred to as semantic information related to Internet of Vehicles applications such as autonomous driving) from sensor data, i.e., raw environmental data, provided by basic sensors such as lidar, millimeter-wave radar, and optical cameras, and upload it to the roadside station RSU. In this way, the amount of data transmitted between the vehicle and the roadside station can be reduced and communication efficiency can be improved.

[0053] In the example shown in Figure 1, the roadside station (RSU) can optionally perform semantic fusion on the semantic information provided by individual vehicles to generate global semantic information. This global semantic information can then be used to make overall control or decisions related to the connected vehicle network. Optionally, the RSU can feed this global semantic information back to the individual vehicles it serves. Vehicles can then make behavioral decisions based on this global semantic information, providing an information advantage for their decision-making. For example, this can prevent individual vehicles from making inefficient decisions due to misleading local information, ultimately improving the performance of connected vehicle applications.

[0054] In the example of Figure 1, although vehicle V1 is used as the primary vehicle for simplicity, the diagram schematically illustrates vehicle V1 acquiring semantic information from an environment including vehicles V2 and V3 and receiving global semantic information from roadside stations (RSUs), it is understood that this perspective can be applied to individual vehicles in the connected vehicle network. Furthermore, although the control device of the central connected vehicle network is shown as a roadside station (RSU) in the example of Figure 1, it can be any suitable device that performs similar functions, such as a base station. It is understood that the functions of the control device in the centralized connected vehicle network described herein can be implemented by roadside stations and base stations, either individually or together, and will not be further described below.

[0055] FIG2 is a schematic diagram showing an example of a distributed Internet of Vehicles to which the technology of the present disclosure can be applied. As shown in FIG2 , a plurality of vehicles are divided into a plurality of clusters C1 and C2 according to the transmission distance of the on-board communication equipment. Vehicles divided into the same cluster, for example, periodically elect a cluster head node or cluster head vehicle CHV1 or CHV2. The election of the cluster head node can be based on the computing power, communication capability and fairness principle of each vehicle. In addition to being able to obtain semantic information as a vehicle itself, each cluster head node also performs processing similar to the roadside station RSU in the example of FIG1 , that is, it optionally performs semantic fusion on the semantic information provided by each vehicle in the cluster to obtain global semantic information and feeds back the global semantic information to each vehicle in the cluster, etc. Therefore, hereinafter, the roadside station RSU of FIG1 and the cluster heads CHV1 and CHV2 of FIG2 are also collectively referred to as network-side devices (also referred to as control side or control devices).

[0056] In the aforementioned semantic communication model framework, the importance of semantic information obtained by each vehicle to driving or behavioral decisions may vary. Understanding this importance on the network side facilitates overall control and can also allocate appropriate physical communication resources for the transmission of semantic information based on this importance. In light of this, the inventors proposed a further inventive concept: determining the importance of semantic information in environmental data and sharing it between the vehicle and network sides.

[0057] Next, we will describe device / method embodiments based on the above-described inventive concepts, as well as various preferred examples and processes, primarily with reference to the centralized IoV example in Figure 1. Note that while the detailed description primarily utilizes a centralized IoV as an example scenario, those skilled in the art will appreciate, based on this disclosure, that the embodiments of this disclosure can be similarly applied to distributed IoV scenarios, and therefore will not be further elaborated upon here.

[0058] <2. Configuration Example of Electronic Device of First Embodiment>

[0059] [2.1 Configuration Example]

[0060] FIG. 3 is a block diagram showing a configuration example of an electronic device according to the first embodiment of the present disclosure.

[0061] As shown in Figure 3, the electronic device 300 may include one or more processors 310 and one or more memories 320 including computer program code, and optionally include a transceiver 330. The memory 320 and the computer program code included therein may be configured to cause the electronic device 300 to perform relevant processing or operations through the processor 310. Optionally, the memory 320 may also be configured to store various data and information. The transceiver 330 is used, for example, to send information to or receive information from another device. It may include one or more communication interfaces to support communication with different devices, and may perform corresponding processing or operations under the control of the memory 320, the computer program code included therein, and the processor 310.

[0062] In the context of the present disclosure, when necessary, the processing and operations performed by the electronic device 300 can be implemented with the aid of other components in the electronic device 300 in addition to the processor 310 and the memory 320 (such as the optional transceiver 330), but the implementation details of these other components are not the focus of the present invention and will not be described in detail.

[0063] Here, each component of the electronic device 300 (such as but not limited to a processor, memory and / or transceiver, etc.) can be included in a processing circuit. It should be noted that the electronic device 300 can include one processing circuit or multiple processing circuits. Furthermore, the processing circuit can include various discrete functional units to perform various functions and / or operations. It should be noted that these functional units can be physical entities or logical entities, and units with different names may be implemented by the same physical entity.

[0064] In addition, although FIG3 schematically shows an example in which the electronic device 300 includes a processor 310, a memory 320, and a transceiver 330, the functional configuration of the electronic device 300 is not limited thereto. For example, the electronic device 300 may include a processing unit, a storage unit, and / or a communication unit to replace the aforementioned processor, memory, and / or transceiver, respectively, and each of them has the same or similar functions and / or configurations as the processor, memory, and / or transceiver described herein, and will not be described in detail here.

[0065] In this embodiment, electronic device 300 is a vehicle-side or vehicle-end device. The vehicle-end device referred to herein can more generally refer to various user devices located on a vehicle and capable of accessing various sensors. For example, electronic device 300 can be installed or carried on a vehicle in a connected vehicle network, such as vehicle V1 in Figure 1 and vehicles other than cluster head vehicles CHV1 and CHV2 in Figure 2.

[0066] According to an embodiment of the present disclosure, the memory 320 of the electronic device 300 and the computer program code included therein can be configured to enable the electronic device 300 to perform a series of processing for semantic communication (semantic communication processing) through the processor 310, which processing may include: extracting semantic slices related to vehicle driving (or vehicle behavior decision) from environmental data; determining the importance of the semantic slices (semantic importance); and sending importance information indicating the importance to the network side device (semantic slice importance information).

[0067] Here, optionally, the memory 320 and the computer program code included therein may be configured to enable the electronic device 300 to obtain environmental data from sensor devices installed on the vehicle (on-board sensors) or nearby roadside infrastructure, etc., through the processor 310. As an example, these sensor devices may be used to sense the surrounding environment, traffic conditions, etc., and may include but are not limited to image sensors, lidars, millimeter-wave radars, optical cameras, and other sensors, and the various types of data obtained by them may be collectively referred to as environmental data.

[0068] Note that in order to perform semantic slice extraction and semantic importance evaluation, before semantic communication processing, the memory 320 and the computer program code included therein can be configured to cause the electronic device 300 to perform a series of preprocessing through the processor 310 to (optionally) report device capabilities to the network-side device and receive information related to semantic slice extraction and semantic importance evaluation from the network-side device. Here, the network-side device can be a device installed or carried by a roadside station (such as the RSU in Figure 1) or a cluster head vehicle (CHV1, CHV2, etc. in Figure 2) in the vehicle network.

[0069] As an example, FIG4 shows an example signaling interaction between the electronic device 300 on the vehicle side and the network side, such as a roadside station RSU, before semantic communication is performed. As shown in FIG4 , as an optional process, the vehicle-side device can feedback its device capabilities when accessing the roadside station, such as computing capabilities measured in FLOPS (floating-point operations per second). The roadside station can evaluate the computing capabilities of the vehicle-side device. As shown in (A) in FIG4 , when the device capability of the vehicle-side device is greater than or equal to a predetermined threshold (such as a computing capability threshold βFLOPS), the roadside station can allow the vehicle to access the semantic communication framework and send a confirmation message ACK and information related to semantic slice extraction (semantic extraction) and semantic importance evaluation (semantic evaluation) to the vehicle-side device. Here, the information related to semantic slice extraction and semantic importance evaluation includes, but is not limited to, parameters of the neural network (semantic extraction network) used for semantic slice extraction, predetermined rules (semantic evaluation rules) for semantic importance evaluation, parameters of the neural network (semantic evaluation network) used for semantic importance evaluation, and the like. In addition, as shown in (B) in FIG4 , when the device capability of the vehicle-side device is lower than a predetermined threshold, the roadside station may deny the vehicle access to the semantic communication framework and send a negative message NAK to the vehicle-side device.

[0070] Note that although the example in Figure 4 shows that the roadside station determines whether to allow the vehicle-side device to access semantic communication based on the device capabilities of the vehicle-side device, this determination step can be omitted, that is, the roadside station can send information related to semantic slice extraction and semantic importance evaluation based on the access request of the vehicle-side device or directly to all vehicle-side devices in the vehicle network, which will not be repeated here.

[0071] The memory 320 of the electronic device 300 on the vehicle side and the computer program code included therein can be configured to enable the electronic device 300 to extract N semantic slices (N is a natural number) from the environmental data obtained by various sensors using the semantic extraction network based on the parameters of the semantic extraction network obtained from the network side device through the processor 310, and to determine the importance of each extracted semantic slice using the semantic evaluation network based on the parameters of the semantic evaluation network obtained from the network side device, that is, to obtain corresponding N semantic importances, as shown in the example in Figure 5.

[0072] Here, the semantic extraction network obtained and used by the electronic device 300 from the network-side device can be a multimodal model based on a neural network (such as a convolutional neural network), which can extract high-dimensional vectors with a unified form as semantic slices from a variety of raw sensor data, such as various semantic categories of interest or concern in vehicle network applications. As an example, the semantic category of concern can correspond to the type of detection target of concern, that is, the type of object present in the environment around the vehicle (such as a road environment), such as pedestrians, other vehicles, lane lines, sky, etc. In this way, the extracted semantic slices can contain environmental semantics corresponding to the detection target of the specified type in the original environmental data. Note that the type of detection target is only given as an example of the semantic category of concern. In the context of the present disclosure, the semantic slices extracted by the semantic extraction network only need to contain specific (category) environmental semantics in the original environmental data, and will not be described in detail here.

[0073] For the network side, the different semantic slices obtained by each vehicle may contain different types of local information of each vehicle, and their importance to tasks in the Internet of Vehicles, such as vehicle driving or vehicle behavior decision-making, is different. Therefore, the network-side device hopes that each vehicle-side device can evaluate the importance of semantic slices with a unified semantic evaluation network or rule. For example, the semantic evaluation network provided by the network-side device to the electronic device 300 on the vehicle side, such as shown in Figure 5, can be a deep network model (such as a convolutional neural network) obtained through joint training optimization (described later), whose input is a semantic slice in the form of a unified high-dimensional vector, and the output is semantic importance in the form of a scalar value.

[0074] As an alternative, the electronic device 300 on the vehicle side can also use the semantic evaluation rules obtained from the network side to determine the importance of the semantic slices. The predetermined semantic evaluation rules give importance metrics to the environmental semantics of each category in an artificially designed manner, and can, for example, be in the form of a corresponding list of specified environmental semantics and semantic importance (scores). For example, it can be specified that the importance of the semantic slices (environmental semantics) corresponding to the environmental data of important targets such as pedestrians, vehicles, and lane lines is higher than the semantic slices (environmental semantics) corresponding to the environmental data of the sky is detected, and the importance of the semantic slices (environmental semantics) corresponding to the environmental data of a larger number of important targets is higher than the semantic slices (environmental semantics) corresponding to the environmental data of a smaller number of important targets is detected, and so on.

[0075] Regardless of whether a semantic evaluation network or semantic evaluation rules are used to determine the importance of semantic slices, the memory 320 of the electronic device 300 on the vehicle side and the computer program code included therein can be configured to cause the electronic device 300 to perform the following processing through the processor 310: extract a first semantic slice from first environmental data, the environmental information included in the first environmental data having a greater impact on vehicle driving than the environmental information included in the second environmental data; and determine a first importance of the first semantic slice, which is higher than the second importance of the second semantic information extracted from the second environmental data. In other words, the semantic evaluation network and semantic evaluation rules provided by the network side can specify that semantic slices extracted from environmental data that include environmental information that has a greater impact on vehicle driving or vehicle behavior decision-making have higher semantic importance. This evaluation principle can be applied to various semantic slices obtained at different times and from different vehicles.

[0076] Through the above processing, the electronic device 300 on the vehicle side can extract semantic slices from the environmental data and determine their semantic importance accordingly, and can send semantic slice importance information to the network side device so that the network side is aware of this importance, which is beneficial for its subsequent processing and physical communication resource allocation for semantic transmission.

[0077] [2.2 Example Processing]

[0078] Next, with reference to FIG6 , further example processes and related details will be described, which may be performed by the memory 320 of the electronic device 300 and the computer program code included therein, through the processor 310, enabling the electronic device 300 to interact with network-side devices. For ease of illustration, the interaction between vehicle-side devices V1 and V2, each of which may have the functionality of the electronic device 300, and a network-side device RSU, such as a roadside station, is illustrated.

[0079] As shown in Figure 6, electronic devices 300 such as V1 and V2 can first extract semantic slices (semantic extraction) from environmental data obtained by various sensors using the semantic extraction network based on the parameters of the semantic extraction network obtained from the network side device RSU via the example process of Figure 4, and determine the importance of each extracted semantic slice (semantic evaluation) using the semantic evaluation network based on the parameters of the semantic evaluation network obtained from the RSU via the example process of Figure 4, that is, obtain the corresponding semantic importance, and then send the semantic slice importance information (semantic importance information) to the RSU.

[0080] In addition, in a preferred embodiment, in order to facilitate the allocation of physical communication resources for semantic transmission on the network side, the memory 320 of the electronic device 300 such as V1 and V2 and the computer program code included therein can also be configured to enable the electronic device 300 to send quality information (channel quality information) about the channel quality of available communication resources to the network side device through the processor 310.

[0081] Here, the available communication resources may be physical communication resources such as time and frequency that the network side device can allocate to the electronic device 300, such as subcarriers, and without loss of generality, may also be referred to as time-frequency resource blocks or time-frequency blocks hereinafter. Electronic devices 300 such as V1 and V2 can determine the channel quality of available communication resources via various appropriate methods. For example, the electronic device 300 can use its various components to perform channel measurement on the reference signal (for example, a reference signal occupying the corresponding subcarrier) sent by the network side device corresponding to each available communication resource (such as each resource block or each subcarrier) through necessary interaction with the network side device to obtain the channel quality of each available communication resource, which will not be repeated here.

[0082] As shown in Figure 6, after receiving the semantic slice importance information of each semantic slice and the channel quality information of the available communication resources from multiple vehicle-side devices V1 and V2, the network-side device RSU can determine the communication resource allocation for the semantic slice based on this information. The resource allocation of the network-side device RSU can match the importance of the semantic slice with the quality of the available communication resources (including various measurement indicators such as capacity and reliability) to allocate high-quality communication resources to important semantic slices. Due to the limited communication resources, the network-side device RSU may only allocate communication resources to semantic slices of high importance. Further details of the communication resource allocation will be described later in the second embodiment of the network-side device.

[0083] As shown in Figure 6, the network side device RSU can send resource allocation information about communication resource allocation to the vehicle side devices V1 and V2 to indicate the correspondence between the allocated communication resources (resource blocks) and the semantic slices. As an example, the allocated corresponding resource blocks can be indicated to each vehicle side device through RRC signaling, DCI signaling or MAC CE signaling, and the correspondence between the allocated resource blocks and the semantic slices to be transmitted by the vehicle can be indicated by adding corresponding bytes in the RRC signaling, DCI signaling or MAC CE signaling. In other words, the electronic devices 300 such as V1 and V2 can receive resource allocation information for communication resource allocation for semantic slices from the network side device RSU, and the communication resource allocation is determined by the network side device based on the importance of the semantic slices and the channel quality of the available communication resources.

[0084] Next, as shown in FIG6 , the memory 320 of the electronic device 300 such as V1 and V2 and the computer program code included therein can be configured to enable the electronic device 300 to send corresponding semantic slices (i.e., those semantic slices to which communication resources are allocated) to the network side device using the allocated communication resources according to the received resource allocation information through the processor 310. Here, preferably, the electronic device 300 can send location information such as the current location of the vehicle on which the electronic device 300 is installed or carried together with the semantic slices for reference or use by the network side device in subsequent processing.

[0085] Optionally, the network-side device RSU can obtain global semantic information based on the semantic slices (and optional location information) received from multiple vehicle-side devices V1 and V2, and can send or broadcast the global semantic information to the multiple vehicle-side devices V1 and V2. As an example, the network-side device RSU can use a pre-trained semantic fusion network (which will be described in detail later in the second embodiment of the network-side device) to fuse the various semantic information to obtain the final global semantic information and send or broadcast it.

[0086] In other words, electronic devices 300 such as V1 and V2 can receive global semantic information obtained based on semantic slices received from multiple vehicle-side electronic devices from the network-side device RSU. Thereafter, although not shown in FIG6 , the memory 320 of electronic devices 300 such as V1 and V2 and the computer program code included therein can be configured to enable the electronic device 300 to make vehicle behavior decisions based on the received global semantic information through the processor 310. Compared with the semantic information extracted by a single vehicle from limited environmental data such as its position and viewing angle, the above-mentioned final global semantic information obtained by fusing important semantic slices of each vehicle can indicate more comprehensive environmental semantics in a wider area. Accordingly, each vehicle-side device can have an information advantage in making behavioral decisions using this global semantic information, avoiding each vehicle-side device from making inefficient decisions due to misleading local information, and ultimately improving the performance of Internet of Vehicles applications.

[0087] Note that in an alternative example, the vehicle-side devices V1 and V2, such as the electronic device 300, can obtain the parameters of the semantic fusion network from the network-side device RSU in advance (for example, in the example shown in FIG4 , the parameters can be obtained from the network-side device RSU as optional information together with the "information related to semantic slice extraction and semantic importance assessment"). In this case, the network-side device RSU can aggregate the individual semantic information (and optional location information) it receives as global semantic information and send or broadcast it, and the vehicle-side devices V1 and V2 can perform semantic fusion on their own to obtain the final global semantic information, which will not be described in detail here.

[0088] The configuration example of the electronic device 300 on the terminal side and example processing thereof of the first embodiment of the present disclosure have been described above.

[0089] In the above description, in addition to the electronic device 300 on the vehicle side, the network side device that interacts with the electronic device 300 on the terminal side (such as the roadside station RSU shown in Figures 1, 4, and 6, and which can also be represented by a cluster head CHV1 or CHV2 such as shown in Figure 2) and the processing or operation performed by the network side device are also described. In other words, according to the present disclosure, in addition to the electronic device on the vehicle side (first embodiment), an electronic device on the network side (second embodiment) is also proposed. The following will be based on the description of the electronic device 300 on the terminal side according to the first embodiment of the present disclosure, and a description of the electronic device 700 on the network side according to the second embodiment of the present disclosure will be given, and unnecessary details will be omitted.

[0090] <3. Configuration Example of Electronic Device of Second Embodiment>

[0091] [3.1 Configuration Example]

[0092] FIG. 7 is a block diagram illustrating a configuration example of an electronic device on the network side according to the second embodiment of the present disclosure.

[0093] As shown in Figure 7, the electronic device 700 may include one or more processors 710 and one or more memories 720 including computer program code, and optionally include a transceiver 730. The memory 720 and the computer program code included therein may be configured to cause the electronic device 700 to perform relevant processing or operations through the processor 710. Optionally, the memory 720 may also be configured to store various data and information. The transceiver 730 is used, for example, to send information to or receive information from another device. It may include one or more communication interfaces to support communication with different devices, and may perform corresponding processing or operations under the control of the memory 720, the computer program code included therein, and the processor 710.

[0094] In the context of the present disclosure, when necessary, the processing and operations performed by the electronic device 700 can be implemented with the aid of other components in the electronic device 700 in addition to the processor 710 and the memory 720 (such as an optional transceiver 730), but the implementation details of these other components are not the focus of the present invention and will not be described in detail.

[0095] Here, each component of the electronic device 700 (such as but not limited to a processor, memory and / or transceiver, etc.) can be included in a processing circuit. It should be noted that the electronic device 700 can include either one processing circuit or multiple processing circuits. Furthermore, the processing circuit can include various discrete functional units to perform various functions and / or operations. It should be noted that these functional units can be physical entities or logical entities, and units with different names may be implemented by the same physical entity.

[0096] In addition, although FIG7 schematically shows an example in which the electronic device 700 includes a processor 710, a memory 720, and a transceiver 730, the functional configuration of the electronic device 700 is not limited thereto. For example, the electronic device 700 may include a processing unit, a storage unit, and / or a communication unit to replace the aforementioned processor, memory, and / or transceiver, respectively, which respectively have functions and / or configurations identical or similar to those of the processor, memory, and / or transceiver described herein, and thus will not be described in detail here.

[0097] In this embodiment, the electronic device 700 is a network-side device, for example, it can be a roadside station in the Internet of Vehicles, such as the roadside station RSU discussed above in the detailed description of the first embodiment. In addition, the electronic device 700 can also be any appropriate device that performs similar functions, such as a base station device. In addition, the electronic device 700 can also be a device (such as a user device) installed or carried on a cluster head vehicle (such as CHV1 and CHV2 shown in Figure 2) in the Internet of Vehicles. The present disclosure does not limit the specific deployment of the electronic device 700, as long as it can implement the corresponding processing.

[0098] According to an embodiment of the present disclosure, the memory 720 of the network-side electronic device 700 and the computer program code included therein can be configured to enable the electronic device 700 to receive importance information (semantic slice importance information) from the vehicle-side device through the processor 710, wherein the importance information indicates the importance (semantic importance) of semantic slices related to vehicle driving (or vehicle behavior decision) extracted from environmental data.

[0099] As previously described with reference to FIG4 , before semantic communication is performed with the vehicle-side device, the memory 720 of the electronic device 700 and the computer program code included therein may be configured to enable the electronic device 700 to perform a series of preprocessing through the processor 710 to interact with the vehicle-side device V1. The above-mentioned processing may include: (optionally) receiving device capabilities from the vehicle-side device, comparing the device capabilities with a predetermined threshold to perform a device capability check, sending a corresponding confirmation or denial access message to the vehicle-side device based on the check result, and sending information related to semantic slice extraction and semantic importance evaluation to the vehicle-side device in the case of confirmation. Here, the information related to semantic slice extraction and semantic importance evaluation includes but is not limited to parameters of the semantic extraction network, semantic evaluation rules, parameters of the semantic evaluation network, and the like.

[0100] As mentioned above, the semantic extraction network provided by the electronic device 700 as a network-side device can be a multimodal model based on a neural network (such as a convolutional neural network), which can extract high-dimensional vectors with a unified form as semantic slices from a variety of original sensor data, such as various semantic categories of interest or concern in vehicle network applications. As an example, the semantic category of concern can correspond to the type of detection target of concern, that is, the type of object present in the environment around the vehicle (such as a road environment), such as pedestrians, other vehicles, lane lines, sky, etc. In this way, the semantic slices extracted by the vehicle-side device can contain environmental semantics corresponding to the detection target of the specified type in the original environmental data. The electronic device 700 can use sensor data (training data) with pre-labeled corresponding environmental semantics to obtain the above-mentioned semantic extraction network through various appropriate training methods and store it in the storage unit 720.

[0101] In addition, the semantic evaluation network provided by the electronic device 700 on the network side can be a deep network model obtained through pre-joint training (described later), whose input is a semantic slice s in the form of a unified high-dimensional vector, and the output is a semantic importance in the form of a scalar value. The semantic evaluation network can have an architecture such as a convolutional neural network CNN, a recurrent neural network RNN, a transformer Transformer, etc., to obtain the importance of each semantic slice s as a semantic importance function v(s). As an alternative to the semantic evaluation network, the semantic evaluation rules can be manually designed to give importance metrics to the environmental semantics of each category, and for example, can be in the form of a corresponding list of specified environmental semantics and semantic importance (scores). For example, the importance of the semantic slice (environmental semantics) corresponding to the environmental data of important targets such as pedestrians, vehicles, and lane lines can be specified to be higher than the semantic slice (environmental semantics) corresponding to the environmental data of the sky, and the importance of the semantic slice (environmental semantics) corresponding to the environmental data of a larger number of important targets can be specified to be higher than the semantic slice (environmental semantics) corresponding to the environmental data of a smaller number of important targets, and so on.

[0102] The semantic evaluation network and semantic evaluation rules can make the semantic slices extracted from environmental data including environmental information that has a greater impact on Internet of Vehicles applications such as vehicle driving or vehicle behavior decision-making have higher semantic importance, and this evaluation principle can be applied to each semantic slice obtained at different times and from different vehicles.

[0103] As previously described with reference to Figure 6, the vehicle-side device V1 can, for example, extract semantic slices from environmental data and determine the importance of semantic slices based on the above-mentioned semantic extraction network, semantic evaluation network or semantic evaluation rules provided by the network side, and then send the semantic slice importance information to the network-side device.

[0104] In this way, the electronic device 700 on the network side can know the importance of each semantic slice obtained by the vehicle side device, so as to facilitate its subsequent processing and allocation of physical communication resources for semantic transmission.

[0105] [3.2 Example Processing]

[0106] Next, more example processes and related details that the memory 720 of the electronic device 700 and the computer program code included therein can enable the electronic device 700 to perform through the processor 710 will be described in combination with Figures 6 and 8 to 10 described above.

[0107] (Example of Communication Resource Allocation)

[0108] First, reference is made to Figure 6. As shown in Figure 6, in order to facilitate the allocation of physical communication resources for semantic transmission on the network side, in addition to the semantic slice importance information, the network-side electronic device 700 also receives quality information about the channel quality of available communication resources from the vehicle-side devices (e.g., multiple vehicle-side devices V1 and V2).

[0109] Here, the available communication resources can be physical communication resources such as time and frequency that the network-side electronic device 700 can allocate to the vehicle-side devices V1 and V2, such as subcarriers, which can also be referred to as time-frequency resource blocks or time-frequency blocks without loss of generality. For example, the electronic device 700 can use its various components to send a reference signal corresponding to each available communication resource (such as each resource block or each subcarrier) to the vehicle-side device through necessary interaction with the vehicle-side device (for example, a reference signal occupying the corresponding subcarrier) for the vehicle-side device to perform channel measurement to obtain the channel quality of each available communication resource, which will not be repeated here.

[0110] As shown in Figure 6, the memory 720 of the network-side electronic device 700 and the computer program code included therein can be configured to enable the electronic device 700 to determine the communication resource allocation for the semantic slice based on the importance of the semantic slice and the channel quality of the available communication resources after receiving the above information from multiple vehicle-side devices V1 and V2 through the processor 710. The above resource allocation can match the importance of the semantic slice with the quality of the available communication resources (including various measurement indicators such as capacity and reliability) to allocate high-quality communication resources to important semantic slices.

[0111] Next, an example implementation of allocating available communication resources based on semantic importance will be described with reference to the example of FIG. 8 .

[0112] In this example, the memory 720 and the computer program code included therein can be configured to enable the electronic device 700 to perform the following processing through the processor 710: determine the sum of allocation scores for multiple semantic slices for each alternative communication resource allocation method, wherein the allocation score for each semantic slice is a comprehensive score based on the importance of the semantic slice and the channel quality of the available communication resources (e.g., physical time-frequency resource blocks) to be allocated to the semantic slice; and determine the allocation method with the highest sum of allocation scores as the communication resource allocation to be used.

[0113] More specifically, in this example, let M n The number M of semantic slices extracted from the environmental data by all N vehicle-side devices n The sum of (the total number of semantic slices). Arrange all semantic slices into sequences For sorted semantic slices to represents the vehicle corresponding to this semantic slice. The number of physical time-frequency resource blocks available for semantic slice transmission by the network-side electronic device 700 is K, and r1, r2, …, r K are used to represent these K semantic slices respectively. To ensure the quality of service of vehicle networking applications, it is necessary to efficiently allocate the K resource blocks to N vehicle-side devices V1, V2,....., VN, so as to ensure that more important semantic slices are transmitted to the electronic device 700 using resource blocks with higher channel quality (with higher reliability, etc.). For example, when K < M, it is necessary to select the most important K semantic slices for transmission.

[0114] As shown in Figure 8, to achieve efficient allocation of resource blocks, the electronic device 700 can establish a bipartite graph, where the sets and the set R = {r1, r2, …, r K} represent the semantic slice vertex set and the resource block vertex set respectively. Between each semantic slice vertex and each resource block vertex r k a connecting edge is established to represent that the resource block r k can be allocated for the transmission of the semantic slice . Based on this, a complete bipartite graph can be established. The resource allocation performed by the electronic device 700 is to find a non-overlapping edge set (that is, any two edges have no common vertices) in , and this set is also called a matching of the bipartite graph . If k it means that the resource block r is allocated to the vehicle for the transmission of the semantic slice

[0115] The electronic device 700 can determine an optimal matching of the bipartite graph in the following way: for each matching of the bipartite graph (each alternative communication resource allocation method), calculate the sum of the allocation scores of each semantic slice as the overall system utility; based on the Hungarian algorithm, determine the matching method with the largest sum of allocation scores, that is, the system utility maximization, as the final communication resource allocation.

[0116] More specifically, in this example, the electronic device 700 can be based on the importance of the semantic slice and the channel quality of the available communication resources to be allocated to this semantic slice, that is, the channel quality of the vehicle on the resource block r k ​ Formula (1) is used to obtain the comprehensive score w(e) of semantic slice importance and channel quality. mk ), as resource block r k Assigned to semantic slices The allocation score of , to represent the system utility brought by the allocation:

[0117] in, is the channel quality function, which can be a vehicle In resource block r k Channel quality It can also be a function of the bit error rate, channel capacity, etc. calculated based on the channel quality. In other words, the electronic device 700 can directly use the channel quality of the available communication resources itself to determine the allocation score in the form of formula (1), or can use the bit error rate or channel capacity calculated based on the channel quality of the available communication resources as an indicator of the channel quality to determine the allocation score.

[0118] For example, when the electronic device 700 directly uses the channel quality in equation (1), When the bit error rate is used in equation (1), we can make Where α1 and α2 are constants related to the specific modulation mode in the communication transmission, and γ is the signal-to-noise ratio of the communication transmission. For example, for M-ary quadrature amplitude modulation, When the channel capacity is used in equation (1), we can make Where γ is the signal-to-noise ratio of communication transmission.

[0119] Preferably, the function w(e mk ) can be represented by a pre-trained distribution evaluation network, which can be obtained together with the semantic evaluation network using joint training optimization and can be stored in the memory 720 of the electronic device 700. The acquisition method will be described in detail later.

[0120] As an example, the electronic device 700 may also calculate the allocation score using formula (2) which is a simplified example implementation of formula (1):

[0121] Among them, w1 and w2 are weighting coefficients or weights. The distribution score w(e mk ) balances semantic importance and channel quality through weighting coefficients w1 and w2. In other words, the electronic device 700 can obtain each semantic slice Importance The channel quality of the available communication resources to be allocated to the semantic slice (vehicle In resource block r k Channel quality or its indicators The weighted sum of the weighted sum is used as the allocation score w(e mk The weighting coefficients or weights can be obtained by optimizing the distribution evaluation network (the parameters of the network) in a simplified form together with the semantic evaluation network using joint training, and can be stored in the memory 720 of the electronic device 700.

[0122] As an alternative example, the electronic device 700 can also calculate the assigned score by using a predefined matching rule implemented as another simplified example of formula (1). In other words, the electronic device 700 can obtain the assigned score of each semantic slice based on the predefined matching rule. Importance The channel quality of the available communication resources to be allocated to the semantic slice (vehicle In resource block r k Channel quality or its indicators The matching degree between them is used as the assigned score for the semantic slice. Here, the predefined matching rule can match between semantic importance of different values ​​and channel quality (or its indicator), and can be in the form of a corresponding list of semantic importance and matched channel quality (or its indicator), for example, and can be stored in the memory 720 of the electronic device 700.

[0123] In the example shown in FIG8 , according to each matching of the bipartite graph in the above manner (Each alternative communication resource allocation method) calculates the allocation score w(e) of each semantic slice mk ), the electronic device 700 can determine the matching method that maximizes the sum of the allocation scores, i.e., maximizes system utility, based on various appropriate algorithms, such as the Hungarian algorithm, as the final communication resource allocation. Here, as an example, subcarriers 1 to 5, i.e., K = 5 resource blocks, are allocated to five important semantic slices out of all M semantic slices of vehicle-side devices V1 to VN.

[0124] 6 . As shown in FIG6 , the memory 720 of the network-side electronic device 700, such as the RSU, and the computer program code included therein may be configured to cause the electronic device 700 to generate and transmit resource allocation information regarding the allocation of communication resources to the vehicle-side device through the processor 710, and receive from the vehicle-side device semantic slices transmitted using the allocated communication resources, and position information indicating the current position of the vehicle, which is optionally transmitted together with the semantic information.

[0125] The resource allocation information generated and transmitted by the electronic device 700 may indicate to the vehicle-side device the correspondence between the allocated communication resources (resource blocks) and the semantic slices. As an example, the electronic device 700 may indicate the allocated corresponding resource blocks to each vehicle-side device through RRC signaling, DCI signaling, or MAC CE signaling, and may indicate the correspondence between the allocated resource blocks and the semantic slices to be transmitted by the vehicle by adding corresponding bytes in the RRC signaling, DCI signaling, or MAC CE signaling.

[0126] In this way, a match is achieved between the importance of semantic information and the quality of communication resources for semantic transmission, thereby facilitating high-quality transmission of important semantic information.

[0127] (Example of obtaining global semantic information)

[0128] 6 . As shown in FIG6 , the memory 720 and the computer program code included therein of the network-side electronic device 700 such as the RSU may be configured to enable the electronic device 700 to obtain global semantic information based on semantic slices (and optional location information) received from multiple vehicle-side devices through the processor 710, and to send the global semantic information to the multiple vehicle-side devices.

[0129] In a preferred example, the network-side electronic device 700 of the gNB, such as that shown in FIG9 , can utilize a pre-trained semantic fusion network to perform semantic fusion processing on multiple semantic information received from multiple vehicle-side devices V1, V2,....., VN to obtain final global semantic information, and send or broadcast it.

[0130] Next, a specific example of the electronic device 700 using a semantic fusion network to obtain global semantic information based on K semantic slices received from multiple vehicle devices will be described in conjunction with the example of Figure 10. As shown in Figure 10, the semantic fusion network used by the electronic device 700 can be implemented as a combination of a semantic decoding and fusion network and a semantic extraction network, and can be pre-stored in the storage unit 720. Here, the semantic extraction network is the semantic extraction network described previously, obtained through training and shared with the vehicle side. In addition, the semantic decoding and fusion network can be a combination of a semantic decoder and a fusion network corresponding to the semantic extraction network, wherein the semantic decoder decodes the input semantic slices into environmental data, and the fusion network uses global map information and the location information corresponding to each semantic slice to map these decoded environmental data onto the global map and fuse them. For example, the fusion network can achieve the above-mentioned fusion processing by removing duplicate environmental data and accumulating different environmental data at the same location.

[0131] Compared to the semantic information extracted by individual vehicles from limited environmental data such as their location and viewing angle, the final global semantic information obtained by fusing important semantic slices transmitted from various vehicle-side devices can provide a more comprehensive picture of environmental semantics across a wider area. Consequently, each vehicle-side device can leverage this global semantic information to make behavioral decisions, gaining an information advantage. This prevents each vehicle-side device from making inefficient decisions due to misleading local information, ultimately improving the performance of connected vehicle applications.

[0132] [3.3 Others (Joint training optimization of related networks)]

[0133] As mentioned above, the semantic evaluation network used by the vehicle-side device and the matching evaluation network used by the network-side device can be obtained through joint training optimization, and are respectively used by the vehicle-side device to determine the importance of semantic slices and by the network-side device to determine the matching score between semantic slices and available communication resources.

[0134] Next, the joint training optimization for obtaining the above-mentioned evaluation network will be briefly described with reference to the example of FIG11 .

[0135] (1) Data preparation:

[0136] Data sets such as semantic slices and channel quality can be collected and organized. These are not limited to pre-acquired labeled data, but can also be data obtained in real time during applications, such as the semantic slices and channel quality obtained by various vehicle-side devices in the Internet of Vehicles.

[0137] (2) Model design:

[0138] The CNN architecture can be designed separately for the semantic evaluation network and the allocation evaluation network, which may include convolutional layers, pooling layers, and fully connected layers. The input of the semantic evaluation network is the semantic slices obtained by each vehicle-side device, and the output is the importance of the semantic slices (the numerical value of the semantic importance). The input of the allocation evaluation network is the channel quality obtained by each vehicle-side device and the semantic importance output by the semantic evaluation network, and the output is the corresponding allocation score allocated between the two.

[0139] (3) Training optimization:

[0140] The output of the evaluation network can be directly used by related devices in the connected vehicle network. For example, network-side devices such as RSUs can directly determine the communication resource allocation for the semantic slices of each vehicle-side device based on the allocation scores output by the allocation evaluation network, as described in the "Example of Communication Resource Allocation" section of "3.2 Example Processing".

[0141] Furthermore, as shown in the figure, network-side devices such as RSUs can utilize the semantic slices of each vehicle transmitted based on this resource allocation, obtain global semantic information based on the fusion processing of the semantic fusion network, and send or broadcast it to each vehicle in the Internet of Vehicles, allowing each vehicle to make behavioral decisions based on the global semantic information. Furthermore, feedback information on the performance of the Internet of Vehicles (such as accident rate, congestion rate, etc.) can be obtained, and the feedback on the Internet of Vehicles performance can be used to optimize the semantic evaluation network and the distribution evaluation network, with the optimization goal of improving the performance of the Internet of Vehicles, such as reducing the accident rate and congestion rate. Specific optimization methods may include adjusting the network architecture or performing more training iterations. In the actual training or optimization process, the architecture and parameters of one evaluation network can be fixed first, and another evaluation network can be trained or optimized. Then, the architecture and parameters of the trained or optimized evaluation network can be fixed, and the remaining evaluation network can be trained and optimized. This will not be repeated here.

[0142] <4. Method Example>

[0143] Corresponding to the above-mentioned device embodiments, the present disclosure provides the following method embodiments.

[0144] FIG12 is a flowchart illustrating a process example of a method for wireless communication according to the first embodiment of the present disclosure.

[0145] As shown in FIG12 , in step S11, semantic slices related to vehicle driving may be extracted from environmental data. In step S12, the importance of the semantic slices may be determined. In step S13, importance information indicating the importance may be sent to a network-side device.

[0146] As an example, the method shown in FIG12 may be implemented by a device (such as a user device) installed or carried on a vehicle, and although not shown in the figure, the method may also include obtaining environmental data from a sensor installed on the vehicle.

[0147] Furthermore, in one example, in step S11, a first semantic slice may be extracted from the first environmental data, where environmental information included in the first environmental data has a greater impact on vehicle driving than environmental information included in the second environmental data. In step S12, a first importance of the first semantic slice may be determined, where the first importance is higher than a second importance of the second semantic information extracted from the second environmental data.

[0148] In addition, although not shown in the figure, optionally, the method may further include sending quality information about the channel quality of the available communication resources to the network side device.

[0149] In addition, although not shown in the figure, the method may optionally further include receiving resource allocation information for communication resource allocation for the semantic slice from a network-side device, wherein the communication resource allocation is determined by the network-side device based on the importance of the semantic slice and the channel quality of the available communication resources. Optionally, the method may further include transmitting the semantic slice to the network-side device using the allocated communication resources based on the resource allocation information.

[0150] In addition, although not shown in the figure, optionally, the method may also include receiving global semantic information obtained from a network side device based on semantic slices received from multiple electronic devices.

[0151] According to an embodiment of the present disclosure, the subject executing the above method may be the electronic device 300 according to the first embodiment of the present disclosure, and therefore all the above embodiments regarding the electronic device 300 are applicable hereto.

[0152] FIG13 is a flowchart illustrating a process example of a method for wireless communication according to the second embodiment of the present disclosure.

[0153] As shown in FIG. 13 , in step S21 , importance information may be received from a vehicle-side device, where the importance information indicates the importance of semantic slices related to vehicle driving extracted from environmental data.

[0154] As an example, the method shown in FIG13 may be implemented by a device installed or carried in a roadside station installed in the Internet of Vehicles or a device installed or carried in a cluster head vehicle.

[0155] In addition, although not shown in the figure, the method may optionally also include a communication resource allocation step for determining the communication resource allocation for the semantic slice based on the importance of the semantic slice and the channel quality of the available communication resources.

[0156] In one example, the above-mentioned resource allocation step may include the following processing: determining the sum of allocation scores for multiple semantic slices for each alternative communication resource allocation method, wherein the allocation score for each semantic slice is a comprehensive score based on the importance of the semantic slice and the channel quality of the available communication resources to be allocated to the semantic slice; and determining the allocation method with the highest sum of allocation scores as the communication resource allocation to be used.

[0157] In one example, a weighted sum of the importance of each semantic slice and the channel quality of the available communication resources to be allocated to the semantic slice can be obtained as the allocation score of the semantic slice. In an alternative example, based on a predefined matching rule, a matching degree between the importance of each semantic slice and the channel quality of the available communication resources to be allocated to the semantic slice can be obtained as the allocation score of the semantic slice.

[0158] As an example, in the process of calculating the above allocation score, the channel quality itself based on the available communication resources or the bit error rate or channel capacity calculated based on the channel quality of the available communication resources can be used as an indicator of the channel quality to determine the allocation score.

[0159] In addition, although not shown in the figure, the method may optionally further include: sending resource allocation information about the communication resource allocation to the vehicle side device; and receiving semantic slices sent using the allocated communication resources from the vehicle side device.

[0160] In addition, although not shown in the figure, the method may optionally further include: obtaining global semantic information based on semantic slices received from multiple vehicle-side devices; and sending the global semantic information to multiple vehicle-side devices.

[0161] According to an embodiment of the present disclosure, the subject that executes the above method may be the electronic device 700 according to the second embodiment of the present disclosure, and therefore all the embodiments regarding the electronic device 700 in the foregoing text are applicable hereto.

[0162] <5. Application Examples>

[0163] The technology of the present disclosure can be applied to various products.

[0164] The electronic device 300 according to the first embodiment implements the necessary control functions in the Internet of Vehicles and is therefore called a network-side device, but it can be implemented in a roadside station, a base station device, or a vehicle serving as a cluster head node, and thus it can be various types of devices, including but not limited to servers, base station devices, user devices, etc.

[0165] For example, the electronic device 300 can be implemented as any type of server, such as a tower server, a rack server, and a blade server. The electronic device 300 can be a control module installed on the server (such as an integrated circuit module including a single chip, and a card or blade inserted into a slot of a blade server).

[0166] In addition, the electronic device 300 can also be implemented as various base stations. The base station can be implemented as any type of evolved Node B (eNB) or gNB (5G base station). eNBs include, for example, macro eNBs and small eNBs. Small eNBs can be eNBs that cover cells smaller than macro cells, such as pico eNBs, micro eNBs, and home (femto) eNBs. Similar situations can also be encountered for gNBs. Alternatively, 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 may include: a main body (also referred to as a base station device) configured to control wireless communications; and one or more remote radio heads (RRHs) located at a different place from the main body. In addition, various types of user equipment can work as a base station by temporarily or semi-permanently performing base station functions.

[0167] Furthermore, electronic device 300 can be implemented as any type of TRP. The TRP can have both sending and receiving functions, for example, it can receive information from a terminal device and a base station device, and can also send information to a terminal device and a base station device. In a typical example, the TRP can provide services to the terminal device and be controlled by the base station device. Furthermore, the TRP can have a structure similar to that of the base station device, or it can only have the structures of the base station device related to sending and receiving information.

[0168] In addition, the electronic device 300 can be implemented as various user devices. The user device can be implemented as a mobile terminal (such as a smart phone, a tablet personal computer (PC), a notebook PC, a portable game terminal, a portable / dongle-type mobile router, and a digital camera) or a vehicle-mounted terminal (such as a car navigation device). The user device can also be implemented as a terminal that performs machine-to-machine (M2M) communication (also known as a machine type communication (MTC) terminal). In addition, the user device can be a wireless communication module (such as an integrated circuit module including a single chip) installed on each of the above-mentioned terminals.

[0169] The electronic device 700 according to the second embodiment can be installed or carried in a vehicle, and thus can be various types of user equipment.

[0170] The electronic device 700 may be implemented as various user devices. The user device may be implemented as a mobile terminal (such as a smartphone, a tablet personal computer (PC), a notebook PC, a portable game terminal, a portable / dongle-type mobile router, and a digital camera) or an in-vehicle terminal (such as a car navigation device). The user device may also be implemented as a terminal that performs machine-to-machine (M2M) communication (also known as a machine type communication (MTC) terminal). In addition, the user device may be a wireless communication module (such as an integrated circuit module including a single chip) installed on each of the above-mentioned terminals.

[0171] [Application examples for servers]

[0172] 14 is a block diagram illustrating an example of a schematic configuration of a server 1700 to which the technology of the present disclosure may be applied. The server 1700 includes a processor 1701 , a memory 1702 , a storage device 1703 , a network interface 1704 , and a bus 1706 .

[0173] The processor 1701 may be, for example, a central processing unit (CPU) or a digital signal processor (DSP), and controls the functions of the server 1700. The memory 1702 includes a random access memory (RAM) and a read-only memory (ROM), and stores data and programs executed by the processor 1701. The storage device 1703 may include a storage medium such as a semiconductor memory and a hard disk.

[0174] The network interface 1704 is a wired communication interface for connecting the server 1700 to the wired communication network 1705. The wired communication network 1705 may be a core network such as an evolved packet core (EPC) or a packet data network (PDN) such as the Internet.

[0175] The bus 1706 connects the processor 1701, the memory 1702, the storage device 1703, and the network interface 1704 to each other. The bus 1706 may include two or more buses each having a different speed (such as a high-speed bus and a low-speed bus).

[0176] In the server 1700 shown in FIG14 , the transceiver 330 in the electronic device 300 described above with reference to FIG3 can be implemented via the network interface 1704. At least some of the functions of the processor 310 in the electronic device 300 can be implemented via the processor 1701. The functions of the memory 320 in the electronic device 300 can be implemented via the memory 1702 or the storage device 1703. For example, the processor 1701 can implement at least some of the functions of the processor 310 by executing instructions stored in the memory 1702 or the storage device 1703.

[0177] [Application examples for base stations]

[0178] (First application example)

[0179] 15 is a block diagram showing a first example of a schematic configuration of an eNB to which the technology of the present disclosure can be applied. The eNB 1800 includes one or more antennas 1810 and a base station device 1820. The base station device 1820 and each antenna 1810 can be connected to each other via an RF cable.

[0180] Each of the antennas 1810 includes a single or multiple antenna elements (such as multiple antenna elements included in a multiple-input multiple-output (MIMO) antenna) and is used for base station device 1820 to transmit and receive wireless signals. As shown in FIG15 , eNB 1800 may include multiple antennas 1810. For example, multiple antennas 1810 may be compatible with multiple frequency bands used by eNB 1800. Although FIG15 shows an example in which eNB 1800 includes multiple antennas 1810, eNB 1800 may also include a single antenna 1810.

[0181] The base station device 1820 includes a controller 1821 , a memory 1822 , a network interface 1823 , and a wireless communication interface 1825 .

[0182] The controller 1821 may be, for example, a CPU or a DSP, and operates various functions of the higher layers of the base station device 1820. For example, the controller 1821 generates data packets based on the data in the signal processed by the wireless communication interface 1825, and transmits the generated packets via the network interface 1823. The controller 1821 may bundle data from multiple baseband processors to generate bundled packets, and transmit the generated bundled packets. The controller 1821 may have logic functions for performing the following controls: the control may be radio resource control, radio bearer control, mobility management, admission control, and scheduling. The control may be performed in conjunction with a nearby eNB or core network node. The memory 1822 includes RAM and ROM, and stores programs executed by the controller 1821 and various types of control data (such as a terminal list, transmission power data, and scheduling data).

[0183] The network interface 1823 is a communication interface for connecting the base station device 1820 to the core network 1824. The controller 1821 can communicate with the core network node or another eNB via the network interface 1823. In this case, the eNB 1800 and the core network node or other eNB can be connected to each other through a logical interface (such as an S1 interface and an X2 interface). The network interface 1823 can also be a wired communication interface or a wireless communication interface for a wireless backhaul line. If the network interface 1823 is a wireless communication interface, the network interface 1823 can use a higher frequency band for wireless communication than the frequency band used by the wireless communication interface 1825.

[0184] The wireless communication interface 1825 supports any cellular communication scheme, such as Long Term Evolution (LTE) and LTE-Advanced, and provides wireless connectivity to terminals located in the cell of the eNB 1800 via the antenna 1810. The wireless communication interface 1825 may typically include, for example, a baseband (BB) processor 1826 and RF circuitry 1827. The BB processor 1826 can perform various signal processing functions, such as encoding / decoding, modulation / demodulation, and multiplexing / demultiplexing, and performs various types of signal processing for layers such as Layer 1 (L1), Medium Access Control (MAC), Radio Link Control (RLC), and Packet Data Convergence Protocol (PDCP). In place of the controller 1821, the BB processor 1826 may perform some or all of the aforementioned logical functions. The BB processor 1826 may be a memory that stores communication control programs, or a module including a processor configured to execute programs and associated circuitry. Program updates can modify the functionality of the BB processor 1826. This module may be a card or blade inserted into a slot in the base station device 1820. Alternatively, the module may be a chip mounted on the card or blade. Meanwhile, the RF circuit 1827 may include, for example, a mixer, a filter, and an amplifier, and transmit and receive wireless signals via the antenna 1810 .

[0185] As shown in FIG15 , the wireless communication interface 1825 may include multiple BB processors 1826. For example, multiple BB processors 1826 may be compatible with multiple frequency bands used by the eNB 1800. As shown in FIG15 , the wireless communication interface 1825 may include multiple RF circuits 1827. For example, multiple RF circuits 1827 may be compatible with multiple antenna elements. Although FIG15 illustrates an example in which the wireless communication interface 1825 includes multiple BB processors 1826 and multiple RF circuits 1827, the wireless communication interface 1825 may also include a single BB processor 1826 or a single RF circuit 1827.

[0186] In the eNB 1800 shown in FIG15 , the transceiver in the electronic device 300 described previously with reference to FIG3 may be implemented via a wireless communication interface 1825 and an optional antenna 1810. At least some of the functions of the processor in the electronic device 300 may be implemented by a controller 1821. The functions of the memory in the electronic device 300 may be implemented by a memory 1822. For example, the controller 1821 may implement at least some of the functions of the processor by executing instructions stored in the memory 1822.

[0187] (Second application example)

[0188] FIG16 is a block diagram illustrating a second example of a schematic configuration of an eNB to which the techniques of this disclosure may be applied. An eNB 1930 includes one or more antennas 1940, a base station 1950, and an RRH 1960. The RRH 1960 and each antenna 1940 may be connected to each other via an RF cable. The base station 1950 and the RRH 1960 may be connected to each other via a high-speed line such as an optical fiber cable.

[0189] Each of the antennas 1940 includes a single or multiple antenna elements (such as multiple antenna elements included in a MIMO antenna) and is used for RRH 1960 to transmit and receive wireless signals. As shown in FIG16 , eNB 1930 may include multiple antennas 1940. For example, multiple antennas 1940 may be compatible with multiple frequency bands used by eNB 1930. Although FIG16 shows an example in which eNB 1930 includes multiple antennas 1940, eNB 1930 may also include a single antenna 1940.

[0190] Base station device 1950 includes a controller 1951, a memory 1952, a network interface 1953, a wireless communication interface 1955, and a connection interface 1957. Controller 1951, memory 1952, and network interface 1953 are the same as controller 1821, memory 1822, and network interface 1823 described with reference to FIG.

[0191] The wireless communication interface 1955 supports any cellular communication scheme (such as LTE and LTE-Advanced) and provides wireless communication to terminals located in the sector corresponding to the RRH 1960 via the RRH 1960 and the antenna 1940. The wireless communication interface 1955 may generally include, for example, a BB processor 1956. The BB processor 1956 is identical to the BB processor 1826 described with reference to FIG. 15 , except that the BB processor 1956 is connected to the RF circuit 1964 of the RRH 1960 via a connection interface 1957. As shown in FIG. 16 , the wireless communication interface 1955 may include multiple BB processors 1956. For example, multiple BB processors 1956 may be compatible with multiple frequency bands used by the eNB 1930. Although FIG. 16 illustrates an example in which the wireless communication interface 1955 includes multiple BB processors 1956, the wireless communication interface 1955 may also include a single BB processor 1956.

[0192] The connection interface 1957 is an interface for connecting the base station device 1950 (wireless communication interface 1955) to the RRH 1960. The connection interface 1957 may also be a communication module for connecting the base station device 1950 (wireless communication interface 1955) to the RRH 1960 for communication in the high-speed line.

[0193] The RRH 1960 includes a connection interface 1961 and a wireless communication interface 1963 .

[0194] The connection interface 1961 is an interface for connecting the RRH 1960 (wireless communication interface 1963) to the base station device 1950. The connection interface 1961 may also be a communication module for communication in the above-mentioned high-speed line.

[0195] The wireless communication interface 1963 transmits and receives wireless signals via the antenna 1940. The wireless communication interface 1963 may generally include, for example, an RF circuit 1964. The RF circuit 1964 may include, for example, a mixer, a filter, and an amplifier, and transmits and receives wireless signals via the antenna 1940. As shown in FIG16 , the wireless communication interface 1963 may include multiple RF circuits 1964. For example, the multiple RF circuits 1964 may support multiple antenna elements. Although FIG16 shows an example in which the wireless communication interface 1963 includes multiple RF circuits 1964, the wireless communication interface 1963 may also include a single RF circuit 1964.

[0196] In the eNB 1930 shown in FIG16 , the transceiver in the electronic device 300 described previously with reference to FIG3 may be implemented, for example, via the wireless communication interface 1963 and the optional antenna 1940. At least some of the functions of the processor in the electronic device 300 may be implemented by the controller 1951. The functions of the memory in the electronic device 300 may be implemented by the memory 1952. For example, the controller 1951 may implement at least some of the functions of the processor by executing instructions stored in the memory 1952.

[0197] [Application examples for terminal devices]

[0198] (First application example)

[0199] 17 is a block diagram showing an example of a schematic configuration of a smartphone 2000 to which the technology of the present disclosure can be applied. The smartphone 2000 includes a processor 2001, a memory 2002, a storage device 2003, an external connection interface 2004, a camera 2006, a sensor 2007, a microphone 2008, an input device 2009, a display device 2010, a speaker 2011, a wireless communication interface 2012, one or more antenna switches 2015, one or more antennas 2016, a bus 2017, a battery 2018, and an auxiliary controller 2019.

[0200] The processor 2001 may be, for example, a CPU or a system on a chip (SoC), and controls the functions of the application layer and other layers of the smartphone 2000. The memory 2002 includes RAM and ROM, and stores data and programs executed by the processor 2001. The storage device 2003 may include storage media such as semiconductor memories and hard disks. The external connection interface 2004 is an interface for connecting external devices (such as memory cards and universal serial bus (USB) devices) to the smartphone 2000.

[0201] The camera 2006 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 2007 may include a group of sensors such as a measurement sensor, a gyroscope sensor, a geomagnetic sensor, and an acceleration sensor. The microphone 2008 converts the sound input to the smart phone 2000 into an audio signal. The input device 2009 includes, for example, a touch sensor, a keypad, a keyboard, a button, or a switch configured to detect a touch on the screen of the display device 2010, and receives an operation or information input from the user. The display device 2010 includes a screen (such as a liquid crystal display (LCD) and an organic light emitting diode (OLED) display) and displays the output image of the smart phone 2000. The speaker 2011 converts the audio signal output from the smart phone 2000 into sound.

[0202] The wireless communication interface 2012 supports any cellular communication scheme (such as LTE and LTE-Advanced) and performs wireless communication. The wireless communication interface 2012 may generally include, for example, a BB processor 2013 and an RF circuit 2014. The BB processor 2013 may perform, for example, encoding / decoding, modulation / demodulation, and multiplexing / demultiplexing, and perform various types of signal processing for wireless communication. Meanwhile, the RF circuit 2014 may include, for example, a mixer, a filter, and an amplifier, and transmit and receive wireless signals via an antenna 2016. The wireless communication interface 2012 may be a chip module on which the BB processor 2013 and the RF circuit 2014 are integrated. As shown in FIG17 , the wireless communication interface 2012 may include multiple BB processors 2013 and multiple RF circuits 2014. Although FIG17 shows an example in which the wireless communication interface 2012 includes multiple BB processors 2013 and multiple RF circuits 2014, the wireless communication interface 2012 may also include a single BB processor 2013 or a single RF circuit 2014.

[0203] In addition, in addition to the cellular communication scheme, the wireless communication interface 2012 can support other types of wireless communication schemes, 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 2012 can include a BB processor 2013 and an RF circuit 2014 for each wireless communication scheme.

[0204] Each of the antenna switches 2015 switches the connection destination of the antenna 916 between a plurality of circuits (eg, circuits for different wireless communication schemes) included in the wireless communication interface 2012 .

[0205] Each of the antennas 2016 includes a single or multiple antenna elements (such as multiple antenna elements included in a MIMO antenna) and is used for transmitting and receiving wireless signals via the wireless communication interface 2012. As shown in FIG17 , the smartphone 2000 may include multiple antennas 2016. Although FIG17 shows an example in which the smartphone 2000 includes multiple antennas 2016, the smartphone 2000 may also include a single antenna 2016.

[0206] In addition, the smartphone 2000 may include an antenna 2016 for each wireless communication scheme. In this case, the antenna switch 2015 may be omitted from the configuration of the smartphone 2000.

[0207] The bus 2017 connects the processor 2001, the memory 2002, the storage device 2003, the external connection interface 2004, the camera 2006, the sensor 2007, the microphone 2008, the input device 2009, the display device 2010, the speaker 2011, the wireless communication interface 2012, and the auxiliary controller 2019. The battery 2018 supplies power to the various blocks of the smartphone 2000 shown in FIG17 via feeders, which are partially shown as dotted lines in the figure. The auxiliary controller 2019 operates the minimum necessary functions of the smartphone 2000, for example, in sleep mode.

[0208] In the smartphone 2000 shown in FIG17 , the transceiver in the electronic device 300 described previously with reference to FIG3 or the electronic device 700 described previously with reference to FIG7 can be implemented via the wireless communication interface 2012 and the optional antenna 2016. At least some of the functions of the processor in the electronic device 300 or 700 can be implemented by the processor 2001 or the auxiliary controller 2019. The functions of the memory in the electronic device 300 or 700 can be implemented by the memory 2002 or the storage device 2003. For example, the processor 2001 or the auxiliary controller 2019 can implement at least some of the functions of the processor by executing instructions stored in the memory 2002 or the storage device 2003.

[0209] (Second application example)

[0210] 18 is a block diagram showing an example of a schematic configuration of a car navigation device 2120 to which the technology of the present disclosure can be applied. The car navigation device 2120 includes a processor 2121, a memory 2122, a global positioning system (GPS) module 2124, a sensor 2125, a data interface 2126, a content player 2127, a storage medium interface 2128, an input device 2129, a display device 2130, a speaker 2131, a wireless communication interface 2133, one or more antenna switches 2136, one or more antennas 2137, and a battery 2138.

[0211] The processor 2121 may be, for example, a CPU or an SoC, and controls a navigation function and other functions of the car navigation device 2120. The memory 2122 includes a RAM and a ROM, and stores data and programs executed by the processor 2121.

[0212] The GPS module 2124 uses GPS signals received from GPS satellites to measure the position (such as latitude, longitude, and altitude) of the car navigation device 2120. The sensor 2125 may include a group of sensors such as a gyroscope sensor, a geomagnetic sensor, and an air pressure sensor. The data interface 2126 is connected to, for example, the vehicle network 2141 via a terminal not shown, and acquires data generated by the vehicle (such as vehicle speed data).

[0213] The content player 2127 reproduces content stored in a storage medium (such as a CD or DVD) inserted into the storage medium interface 2128. The input device 2129 includes, for example, a touch sensor, button, or switch configured to detect a touch on the screen of the display device 2130, and receives an operation or information input from the user. The display device 2130 includes a screen such as an LCD or OLED display and displays an image of a navigation function or reproduced content. The speaker 2131 outputs the sound of the navigation function or the reproduced content.

[0214] The wireless communication interface 2133 supports any cellular communication scheme (such as LTE and LTE-Advanced) and performs wireless communication. The wireless communication interface 2133 may generally include, for example, a BB processor 2134 and an RF circuit 2135. The BB processor 2134 may perform, for example, encoding / decoding, modulation / demodulation, and multiplexing / demultiplexing, and perform various types of signal processing for wireless communication. Meanwhile, the RF circuit 2135 may include, for example, a mixer, a filter, and an amplifier, and transmit and receive wireless signals via an antenna 2137. The wireless communication interface 2133 may also be a chip module on which the BB processor 2134 and the RF circuit 2135 are integrated. As shown in Figure 18, the wireless communication interface 2133 may include multiple BB processors 2134 and multiple RF circuits 2135. Although Figure 18 shows an example in which the wireless communication interface 2133 includes multiple BB processors 2134 and multiple RF circuits 2135, the wireless communication interface 2133 may also include a single BB processor 2134 or a single RF circuit 2135.

[0215] In addition, in addition to the cellular communication scheme, the wireless communication interface 2133 can support other types of wireless communication schemes, such as a short-range wireless communication scheme, a near field communication scheme, and a wireless LAN scheme. In this case, for each wireless communication scheme, the wireless communication interface 2133 can include a BB processor 2134 and an RF circuit 2135.

[0216] Each of the antenna switches 2136 switches the connection destination of the antenna 2137 between a plurality of circuits included in the wireless communication interface 2133 , such as circuits for different wireless communication schemes.

[0217] Each of the antennas 2137 includes a single or multiple antenna elements (such as multiple antenna elements included in a MIMO antenna) and is used for transmitting and receiving wireless signals via the wireless communication interface 2133. As shown in FIG18, the car navigation device 2120 may include multiple antennas 2137. Although FIG18 shows an example in which the car navigation device 2120 includes multiple antennas 2137, the car navigation device 2120 may also include a single antenna 2137.

[0218] Furthermore, the car navigation device 2120 may include an antenna 2137 for each wireless communication scheme. In this case, the antenna switch 2136 may be omitted from the configuration of the car navigation device 2120.

[0219] The battery 2138 supplies power to the respective blocks of the car navigation device 2120 shown in Fig. 18 via a feeder line, which is partially shown as a dotted line in the figure. The battery 2138 accumulates the power supplied from the vehicle.

[0220] In the car navigation device 2120 shown in FIG18 , the transceiver in the electronic device 300 described previously with reference to FIG3 or the electronic device 700 described previously with reference to FIG7 can be implemented via the wireless communication interface 2133 and the optional antenna 2137. At least some of the functions of the processor in the electronic device 300 or 700 can be implemented by the processor 2121. The functions of the memory in the electronic device 300 or 700 can be implemented by the memory 2122. For example, the processor 2121 can implement at least some of the functions of the processor by executing instructions stored in the memory 2122.

[0221] The technology of the present disclosure can also be implemented as an in-vehicle system (or vehicle) 2140 including a car navigation device 2120, an in-vehicle network 2141, and one or more blocks of a vehicle module 2142. The vehicle module 2142 generates vehicle data (such as vehicle speed, engine speed, and fault information) and outputs the generated data to the in-vehicle network 2141.

[0222] The preferred embodiments of the present disclosure are described above with reference to the accompanying drawings, but the present disclosure is of course not limited to the above examples. Those skilled in the art may obtain various changes and modifications within the scope of the appended claims, and it should be understood that these changes and modifications will naturally fall within the technical scope of the present disclosure.

[0223] For example, the units shown in dotted boxes in the functional block diagrams shown in the accompanying drawings all indicate that the functional units are optional in the corresponding device, and the various optional functional units can be combined in an appropriate manner to achieve the required functions.

[0224] For example, a plurality of functions included in one unit in the above embodiments may be implemented by separate devices. Alternatively, a plurality of functions implemented by a plurality of units in the above embodiments may be implemented by separate devices, respectively. In addition, one of the above functions may be implemented by a plurality of units. Needless to say, such a configuration is included in the technical scope of the present disclosure.

[0225] In this specification, the steps described in the flowchart include not only processing executed in time series in the order described, but also processing executed in parallel or individually rather than necessarily in time series. In addition, even in the steps processed in time series, it goes without saying that the order can be changed as appropriate.

[0226] Furthermore, the present disclosure may have configurations as described below.

[0227] 1. An electronic device comprising:

[0228] at least one processor; and

[0229] at least one memory including computer program code, wherein the at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute:

[0230] Extracting semantic slices related to vehicle driving from environmental data;

[0231] determining the importance of the semantic slice; and

[0232] Importance information indicating the importance is sent to the network side device.

[0233] 2. The electronic device of configuration 1, wherein the at least one memory and the computer program code are further configured to, through the at least one processor, cause the electronic device to execute:

[0234] extracting a first semantic slice from the first environmental data, where environmental information included in the first environmental data has a greater impact on vehicle driving than environmental information included in the second environmental data; and

[0235] A first importance of the first semantic slice is determined, the first importance being higher than a second importance of second semantic information extracted from the second environment data.

[0236] 3. The electronic device of configuration 1, wherein the at least one memory and the computer program code are further configured to, through the at least one processor, cause the electronic device to execute:

[0237] Quality information about the channel quality of available communication resources is sent to the network side device.

[0238] 4. The electronic device of configuration 1, wherein the at least one memory and the computer program code are further configured to, through the at least one processor, cause the electronic device to execute:

[0239] Resource allocation information for communication resource allocation for the semantic slice is received from a network side device, where the communication resource allocation is determined by the network side device based on the importance of the semantic slice and the channel quality of available communication resources.

[0240] 5. The electronic device according to configuration 4, wherein the at least one memory and the computer program code are further configured to, through the at least one processor, cause the electronic device to execute:

[0241] According to the resource allocation information, the semantic slice is sent to the network side device using the allocated communication resources.

[0242] 6. The electronic device of configuration 5, wherein the at least one memory and the computer program code are further configured to, through the at least one processor, cause the electronic device to execute:

[0243] Global semantic information obtained based on semantic slices received from multiple electronic devices is received from the network side device.

[0244] 7. The electronic device of configuration 1, wherein the electronic device is installed in a vehicle, and the at least one memory and the computer program code are further configured to, through the at least one processor, cause the electronic device to execute:

[0245] Environmental data is obtained from sensors mounted on the vehicle.

[0246] 8. An electronic device comprising:

[0247] at least one processor; and

[0248] at least one memory including computer program code, wherein the at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute:

[0249] Importance information is received from a vehicle-side device, where the importance information indicates the importance of semantic slices related to vehicle driving extracted from environmental data.

[0250] 9. The electronic device of configuration 8, wherein the at least one memory and the computer program code are further configured to, through the at least one processor, cause the electronic device to execute:

[0251] Quality information on channel quality of available communication resources is received from the vehicle-side device.

[0252] 10. The electronic device of configuration 8, wherein the at least one memory and the computer program code are further configured to, through the at least one processor, cause the electronic device to execute:

[0253] Communication resource allocation for the semantic slices is determined based on the importance of the semantic slices and the channel quality of the available communication resources.

[0254] 11. The electronic device of configuration 10, wherein the at least one memory and the computer program code are further configured to, through the at least one processor, cause the electronic device to execute:

[0255] Determining, for each alternative communication resource allocation method, a sum of allocation scores for the plurality of semantic slices, wherein the allocation score for each semantic slice is a comprehensive score based on the importance of the semantic slice and the channel quality of the available communication resources to be allocated to the semantic slice; and

[0256] The allocation method with the highest sum of allocation scores is determined as the communication resource allocation to be used.

[0257] 12. The electronic device of configuration 11, wherein the at least one memory and the computer program code are further configured to, through the at least one processor, cause the electronic device to execute:

[0258] The bit error rate or channel capacity calculated based on the channel quality of the available communication resources is used as an indicator of the channel quality to determine the allocation score.

[0259] 13. The electronic device of configuration 11, wherein the at least one memory and the computer program code are further configured to, through the at least one processor, cause the electronic device to execute:

[0260] A weighted sum of the importance of each semantic slice and the channel quality of the available communication resources to be allocated to the semantic slice is obtained as the allocation score of the semantic slice.

[0261] 14. The electronic device of configuration 11, wherein the at least one memory and the computer program code are further configured to, through the at least one processor, cause the electronic device to execute:

[0262] Based on the predefined matching rules, the matching degree between the importance of each semantic slice and the channel quality of the available communication resources to be allocated to the semantic slice is obtained as the allocation score of the semantic slice.

[0263] 15. The electronic device of configuration 11, wherein the at least one memory and the computer program code are further configured to, through the at least one processor, cause the electronic device to execute:

[0264] transmitting resource allocation information regarding the communication resource allocation to a vehicle-side device; and

[0265] Receive semantic slices sent from the vehicle-side device using the allocated communication resources.

[0266] 16. The electronic device of configuration 15, wherein the at least one memory and the computer program code are further configured to, through the at least one processor, cause the electronic device to execute:

[0267] Obtaining global semantic information based on semantic slices received from a plurality of vehicle-side devices; and

[0268] The global semantic information is sent to multiple vehicle-side devices.

[0269] 17. The electronic device according to configuration 8, wherein the electronic device is installed in a roadside station in a connected vehicle network.

[0270] 18. A method for wireless communication, comprising:

[0271] Extracting semantic slices related to vehicle driving from environmental data;

[0272] determining the importance of the semantic slice;

[0273] Importance information indicating the importance is sent to the network side device.

[0274] 19. A method for wireless communication, comprising:

[0275] Importance information is received from a vehicle-side device, where the importance information indicates the importance of semantic slices related to vehicle driving extracted from environmental data.

[0276] 20. A non-transitory computer-readable storage medium storing computer program code, wherein the computer program code causes a processor included in an electronic device to cause the electronic device to execute the method according to configuration 18 or 19.

[0277] Although the embodiments of the present disclosure have been described in detail above with reference to the accompanying drawings, it should be understood that the embodiments described above are merely illustrative of the present disclosure and are not intended to limit the present disclosure. Those skilled in the art will appreciate that various modifications and variations can be made to the above embodiments without departing from the spirit and scope of the present disclosure. Therefore, the scope of the present disclosure is solely defined by the appended claims and their equivalents.

Claims

1. An electronic device comprising: at least one processor; as well as at least one memory including computer program code, wherein the at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute: Extracting semantic slices related to vehicle driving from environmental data; determining the importance of the semantic slice; and Importance information indicating the importance is sent to the network side device.

2. The electronic device according to claim 1, wherein The at least one memory and the computer program code are further configured to, through the at least one processor, cause the electronic device to execute: extracting a first semantic slice from the first environmental data, where environmental information included in the first environmental data has a greater impact on vehicle driving than environmental information included in the second environmental data; as well as A first importance of the first semantic slice is determined, the first importance being higher than a second importance of second semantic information extracted from the second environment data.

3. The electronic device according to claim 1, wherein The at least one memory and the computer program code are further configured to, through the at least one processor, cause the electronic device to execute: Quality information about the channel quality of available communication resources is sent to the network side device.

4. The electronic device according to claim 1, wherein The at least one memory and the computer program code are further configured to, through the at least one processor, cause the electronic device to execute: Resource allocation information for communication resource allocation for the semantic slice is received from a network side device, where the communication resource allocation is determined by the network side device based on the importance of the semantic slice and the channel quality of available communication resources.

5. The electronic device according to claim 4, wherein: The at least one memory and the computer program code are further configured to, through the at least one processor, cause the electronic device to execute: According to the resource allocation information, the semantic slice is sent to the network side device using the allocated communication resources.

6. The electronic device according to claim 5, wherein: The at least one memory and the computer program code are further configured to, through the at least one processor, cause the electronic device to execute: Global semantic information obtained based on semantic slices received from multiple electronic devices is received from the network side device.

7. The electronic device according to claim 1, wherein The electronic device is installed on a vehicle, and the at least one memory and the computer program code are further configured to, through the at least one processor, cause the electronic device to execute: Environmental data is obtained from sensors mounted on the vehicle.

8. An electronic device comprising: at least one processor; as well as at least one memory including computer program code, wherein the at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute: Importance information is received from a vehicle-side device, where the importance information indicates the importance of semantic slices related to vehicle driving extracted from environmental data.

9. The electronic device according to claim 8, wherein: The at least one memory and the computer program code are further configured to, through the at least one processor, cause the electronic device to execute: Quality information on channel quality of available communication resources is received from the vehicle-side device.

10. The electronic device according to claim 8, wherein The at least one memory and the computer program code are further configured to, through the at least one processor, cause the electronic device to execute: Communication resource allocation for the semantic slices is determined based on the importance of the semantic slices and the channel quality of the available communication resources.

11. The electronic device according to claim 10, wherein: The at least one memory and the computer program code are further configured to, through the at least one processor, cause the electronic device to execute: Determining, for each alternative communication resource allocation mode, a sum of allocation scores for the plurality of semantic slices, wherein the allocation score for each semantic slice is a comprehensive score based on the importance of the semantic slice and the channel quality of the available communication resources to be allocated to the semantic slice; as well as The allocation method with the highest sum of allocation scores is determined as the communication resource allocation to be used.

12. The electronic device according to claim 11, wherein The at least one memory and the computer program code are further configured to, through the at least one processor, cause the electronic device to execute: The bit error rate or channel capacity calculated based on the channel quality of the available communication resources is used as an indicator of the channel quality to determine the allocation score.

13. The electronic device according to claim 11, wherein The at least one memory and the computer program code are further configured to, through the at least one processor, cause the electronic device to execute: A weighted sum of the importance of each semantic slice and the channel quality of the available communication resources to be allocated to the semantic slice is obtained as the allocation score of the semantic slice.

14. The electronic device according to claim 11, wherein The at least one memory and the computer program code are further configured to, through the at least one processor, cause the electronic device to execute: Based on the predefined matching rules, the matching degree between the importance of each semantic slice and the channel quality of the available communication resources to be allocated to the semantic slice is obtained as the allocation score of the semantic slice.

15. The electronic device according to claim 11, wherein The at least one memory and the computer program code are further configured to, through the at least one processor, cause the electronic device to execute: transmitting resource allocation information regarding the communication resource allocation to a vehicle-side device; and Receive semantic slices sent from the vehicle-side device using the allocated communication resources.

16. The electronic device according to claim 15, wherein The at least one memory and the computer program code are further configured to, through the at least one processor, cause the electronic device to execute: Obtaining global semantic information based on semantic slices received from a plurality of vehicle-side devices; and The global semantic information is sent to multiple vehicle-side devices.

17. The electronic device according to claim 8, wherein: The electronic device is installed in a roadside station in the vehicle network.

18. A method for wireless communication, comprising: Extracting semantic slices related to vehicle driving from environmental data; determining the importance of the semantic slice; Importance information indicating the importance is sent to the network side device.

19. A method for wireless communication, comprising: Importance information is received from a vehicle-side device, where the importance information indicates the importance of semantic slices related to vehicle driving extracted from environmental data.

20. A non-transitory computer-readable storage medium storing computer program code, wherein: The computer program code enables the electronic device to execute the method according to claim 18 or 19 through a processor included in the electronic device.

Images