Semantics and user feedback-based communication method, device and computer program product

Abstract

The present disclosure relates to a semantics and user feedback-based communication method, a device, and a computer program product. Various embodiments for performing communication on the basis of semantics and user feedback are described. In one embodiment, an electronic device for a central node is configured to: extract semantic information from a plurality of media objects to be transmitted and transmit corresponding semantic information of the plurality of media objects to one or more target nodes, wherein the semantic information comprises semantic features in corresponding media objects; receive corresponding feedback information from the one or more target nodes, wherein the feedback information is used for indicating one or more media objects, among the plurality of media objects, matching the interests of the corresponding target nodes; determine an importance ranking of the plurality of media objects on the basis of the corresponding feedback information of the one or more target nodes; and select the one or more media objects from among the plurality of media objects on the basis of the importance ranking, so as to perform transmission to the one or more target nodes.

Description

Communication method, device and computer program product based on semantics and user feedback TECHNICAL FIELD

[0001] The present disclosure generally relates to wireless communications, including a communication method, device and computer program product based on semantics and user feedback. BACKGROUND

[0002] With the continuous development and popularization of collection technologies for media information such as images, videos, audios, etc. and the Internet of Things, the demand of users for sharing and obtaining media information is largely met. With the continuous growth of media data volume and the diversification of user demand, it is a challenge to effectively transmit the required media information to users. Semantic communication is a new communication paradigm, which aims to effectively transmit content-aware and semantic-related information in a task-oriented manner.

[0003] It is desirable to meet the personalized needs of users for media information while ensuring the communication performance such as transmission delay and transmission rate of data, thereby improving communication efficiency and user experience. SUMMARY

[0004] A first aspect of the present disclosure relates to an electronic device for a center node, comprising at least one processor and at least one memory, the at least one memory storing program instructions which, when executed by the at least one processor, cause the electronic device to: extract semantic information from a plurality of media objects to be transmitted and transmit the corresponding semantic information of the plurality of media objects to one or more target nodes, wherein the semantic information comprises semantic features in the corresponding media objects; receive corresponding feedback information from the one or more target nodes, wherein the feedback information is used to indicate one or more media objects in the plurality of media objects that match the interest of the corresponding target node; determine an importance ranking of the plurality of media objects based on the corresponding feedback information of the one or more target nodes; and select one or more media objects from the plurality of media objects based on the importance ranking for transmission to the one or more target nodes.

[0005] A second aspect of the present disclosure relates to an electronic device for a target node, comprising at least one processor and at least one memory, the at least one memory storing program instructions that, when executed by the at least one processor, cause the electronic device to: receive, from a center node, respective semantic information of a plurality of media objects to be transmitted, wherein the semantic information comprises semantic features in respective media objects; determine one or more media objects of the plurality of media objects that match an interest of the target node; send, to the center node, feedback information, wherein the feedback information is used to indicate the one or more media objects that match the interest of the target node; and receive, from the center node, a media object, wherein the received media object is selected by the center node based at least in part on the one or more media objects that match the interest of the target node.

[0006] A third aspect of the present disclosure relates to a method for a center node, comprising: extracting semantic information from a plurality of media objects to be transmitted and transmitting, to one or more target nodes, respective semantic information of the plurality of media objects, wherein the semantic information comprises semantic features in respective media objects; receiving, from the one or more target nodes, respective feedback information, wherein the feedback information is used to indicate one or more media objects of the plurality of media objects that match an interest of a respective target node; determining, based on the respective feedback information of the one or more target nodes, an importance ranking of the plurality of media objects; and selecting, based on the importance ranking, one or more media objects from the plurality of media objects for transmission to the one or more target nodes.

[0007] A fourth aspect of the present disclosure relates to a method for a target node, comprising: receiving, from a center node, respective semantic information of a plurality of media objects to be transmitted, wherein the semantic information comprises semantic features in respective media objects; determining one or more media objects of the plurality of media objects that match an interest of the target node; sending, to the center node, feedback information, wherein the feedback information is used to indicate the one or more media objects that match the interest of the target node; and receiving, from the center node, a media object, wherein the received media object is selected by the center node based at least in part on the one or more media objects that match the interest of the target node.

[0008] A fifth aspect of the present disclosure relates to a computer-readable storage medium having stored thereon executable instructions that, when executed by one or more processors, implement a method according to embodiments of the present disclosure.

[0009] A sixth aspect of the present disclosure relates to a computer program product comprising instructions which, when executed by a computer, cause implementation of a method according to embodiments of the present disclosure.

[0010] The above summary is provided to summarize some example embodiments and to provide an initial understanding of the subject matter described herein. The above features are merely examples and should not be construed as limiting the scope or spirit of the subject matter described herein in any way. Other features, aspects, and advantages of the subject matter described herein will become apparent from the following detailed description, taken in conjunction with the accompanying drawings, which illustrate, by way of example, the principles of the subject matter described herein. BRIEF DESCRIPTION OF DRAWINGS

[0011] A better understanding of the present disclosure can be obtained from the following detailed description in conjunction with the following drawings, in which:

[0012] FIG. 1 illustrates an example block diagram of a wireless communication system according to embodiments of the present disclosure.

[0013] FIG. 2 illustrates an example electronic device for a center node according to embodiments of the present disclosure.

[0014] FIG. 3 illustrates an example electronic device for a target node according to embodiments of the present disclosure.

[0015] FIG. 4 illustrates an example flow of communication based on semantic information and user feedback according to embodiments of the present disclosure.

[0016] FIG. 5 illustrates an example of semantic features and an example of assigning transmission power to the semantic features according to embodiments of the present disclosure.

[0017] FIG. 6 illustrates an example of feedback information according to embodiments of the present disclosure.

[0018] FIG. 7 illustrates an example of importance ranking of multiple media objects according to embodiments of the present disclosure.

[0019] FIG. 8A illustrates an example operation for controlling a communication process according to embodiments of the present disclosure.

[0020] FIG. 8B illustrates an example of controlling the effect of the second stage based on a threshold according to embodiments of the present disclosure.

[0021] FIG. 9 illustrates an example method of communication based on semantic information and user feedback according to embodiments of the present disclosure.

[0022] FIG. 10 illustrates another example method of communication based on semantic information and user feedback according to embodiments of the present disclosure.

[0023] FIG. 11 illustrates an example block diagram of a computing device that can be configured as a center node or a target node according to embodiments of the present disclosure.

[0024] FIG. 12 is a block diagram illustrating an example of a schematic configuration of a smartphone to which the technology of the present disclosure can be applied.

[0025] FIG. 13 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.

[0026] While the embodiments described in the present disclosure can be susceptible to various modifications and alternative forms, specific embodiments thereof are shown by way of example in the drawings and are herein described in detail. It should be understood, however, that the drawings and detailed description thereto are not intended to limit the embodiments to the particular form disclosed, but on the contrary, the intention is to cover all modifications, equivalents and alternatives falling within the spirit and scope of the claims. DETAILED DESCRIPTION

[0027] The following description describes representative applications of aspects of devices and methods according to this disclosure. The description of these examples is merely intended to increase the understanding of the described embodiments. Thus, those skilled in the art will understand that the embodiments described below can be practiced without some or all of the specific details. In other instances, well known process steps have not been described in detail in order not to unnecessarily obscure the described embodiments. Other applications are possible, and the general principles of the present disclosure can be applied to other applications as well.

[0028] In general, all terms used herein are to be interpreted according to their ordinary meaning in the technical field, unless a different meaning is clearly given and / or is implied from the context of the application. Reference to an element or steps in the variation is meant to refer to at least one instance of the element or step. The operations of any of the methods disclosed herein do not have to be performed in the exact order disclosed. The operations of various methods disclosed herein need not be performed in the order in which they are described. Further, it is possible for operations to be performed in an order other than that which is described or otherwise is implied. Any subsequently described feature can be implemented independently of, or in conjunction with, any other described feature. Any feature described in relation to any one embodiment can be implemented with any other embodiment. Any feature described in relation to any embodiment can be implemented in any other embodiment. Any feature described in relation to any embodiment can be implemented in any other embodiment. Any feature described in relation to any embodiment can be implemented in any other embodiment. Any feature described in relation to any embodiment can be implemented in any other embodiment. Any advantage described in relation to any one embodiment can be implemented in any other embodiment. Any advantage described in relation to any embodiment can be implemented in any other embodiment. Other objects, features and advantages of the embodiments will become apparent from the following description.

[0029] Example Wireless Communication System

[0030] FIG. 1 illustrates an example block diagram of a wireless communication system according to embodiments of the present disclosure. Note that FIG. 1 illustrates only one of the many types and possible arrangements of a wireless communication system; features of the present disclosure can be implemented in any of a variety of systems as desired.

[0031] As shown in FIG. 1, the communication system 100 includes a central node 120 and a plurality of target nodes 110A, 110B, through 110N. In this document, when it is not necessary to distinguish the target nodes, any one or more of the target nodes 110A, 110B, through 110N can be referred to as the target node 110. In the communication system 100, the central node 120 and the target nodes 110 form a star network topology, and the central node 120 communicates with each target node 110 bi-directionally. Optionally, the target nodes 110 can also communicate bi-directionally.

[0032] In one embodiment, the central node 120 can be operated by a base station, and the target nodes 110 can be operated by terminal devices. In this way, the central node 120 and each target node 110 can communicate through uplink and downlink, and the target nodes 110 can communicate through sidelink. In one embodiment, the central node 120 and the target nodes 110 can be operated by terminal devices. In this way, the central node 120 and each target node 110 can communicate through sidelink, and the target nodes 110 can also communicate through sidelink.

[0033] In this document, the base station can be a 5G NR base station or a 5G LTE-A base station, such as a gNB and an ng-eNB. The gNB can provide NR user plane and control plane protocols that are terminated with terminal devices, and the ng-eNB is a node defined for compatibility with 4G LTE communication systems, which can be an upgrade of an evolved Node B (eNB) of an LTE wireless access network, providing evolved universal terrestrial radio access (E-UTRA) user plane and control plane protocols that are terminated with UEs. In addition, examples of the base station can include, but are not limited to, at least one of a base transceiver station (BTS) and a base station controller (BSC) in a GSM system; at least one of a radio network controller (RNC) and a Node B in a WCDMA system; an access point (AP) in a WLAN, WiMAX system; and a corresponding network node in a communication system to be developed or developed. Part of the base station in this document can also be implemented as an entity having a control function for communication in a D2D, M2M, and V2X scenario, or as an entity having a spectrum coordination function in a cognitive radio communication scenario.

[0034] In this document, a terminal device can have all the breadth of its ordinary meaning, e.g., a terminal device can be a mobile station (MS), user equipment (UE), etc. A terminal device can be implemented as, for example, a mobile phone, a handheld device, a media player, a computer, a laptop, a tablet, an on board unit (OBU) or vehicle, a road side unit (RSU), a wearable device, an Internet of Things (IoT) device, or almost any type of wireless device. In some cases, a terminal device can communicate using multiple wireless communication technologies. For example, a terminal device can be configured to communicate using one or more of GSM, UMTS, CDMA2000, WiMAX, LTE, LTE-A, WLAN, NR, Bluetooth, etc.

[0035] In embodiments of the present disclosure, the center node 120 can transmit media objects that it collects or otherwise obtains to the target nodes 110. The media objects include, for example, images, videos, or audios, etc. The center node 120 can provide the target nodes 110 with respective semantic information of a plurality of media objects to be transmitted, so that the target nodes 110 are able to determine and feed back to the center node 120 one or more media objects of the plurality of media objects that match their interests. Further, the center node 120 can synthesize the feedback information of the plurality of target nodes 110 and accordingly select media objects to be broadcast to the target nodes 110. Compared with the center node 120 determining the media objects that match the interests of the plurality of target nodes 110, performing this operation by each target node 110 can significantly reduce the energy consumption and processing load of the center node 120.

[0036] In embodiments of the present disclosure, the center node 120 can importance rank the plurality of media objects based on the feedback information of the plurality of target nodes 110 for the media objects that match the interests. The importance ranking includes forming a specific ranking of the plurality of media objects according to how many target nodes that match the interests of the respective media objects, so that the transmission priority of the respective media objects can be represented based on the specific ranking.

[0037] In embodiments of the present disclosure, the central node 120 can control the communication procedure with the target node 110, so as to properly allocate the respective time durations of the three stages of semantic information transmission, feedback information collection / media object importance ranking and media object transmission in a single transmission period. For example, the time duration for performing feedback information collection / media object importance ranking can be properly reduced, so as to ensure more time for media object transmission. In this example, higher throughput of media object transmission can be achieved, which helps to guarantee the communication performance such as transmission delay and transmission rate. For another example, the time duration for performing feedback information collection / media object importance ranking can be properly increased, and the time for media object transmission can be correspondingly reduced. In this example, the matching degree of the media objects transmitted to the target node with the interests of the target node can be improved, which helps to improve the user experience.

[0038] Example electronic device

[0039] FIG. 2 shows an example electronic device for a central node according to embodiments of the present disclosure. The electronic device 200 can include various units to implement embodiments of the semantic and user feedback based communication according to the present disclosure. In the example of FIG. 2, the electronic device 200 includes a transceiving unit 202 and a control unit 204. The various operations described below in connection with the central node or in connection with the semantic and user feedback based communication can be implemented by the units 202-204 of the electronic device 200 or other possible units.

[0040] Generally, the transceiving unit 202 can be configured to perform various signaling and messaging with the target node, and the control unit 204 can be configured to process the signaling and messages and control the communication procedure.

[0041] In one embodiment, the control unit 204 can be configured to extract semantic information from a plurality of media objects to be transmitted, the semantic information can include semantic features in the respective media objects. The data amount of the semantic information is much smaller than that of the media objects. Accordingly, the transceiving unit 202 can be configured to transmit the respective semantic information of the plurality of media objects to one or more target nodes. Further, the transceiving unit 202 can be configured to receive respective feedback information from the one or more target nodes, the feedback information being indicative of one or more media objects of the plurality of media objects that match the interests of the respective target node. The control unit 204 can be configured to determine an importance ranking of the plurality of media objects based on the respective feedback information of the one or more target nodes. Accordingly, the transceiving unit 202 can be configured to select one or more media objects from the media objects to be transmitted based on the importance ranking, so as to be transmitted to the one or more target nodes.

[0042] In an embodiment, the electronic device 200 can be implemented at a chip level, or can also be implemented at a device level by including other external components (e.g., a radio frequency chain, an antenna, etc.). The electronic device 200 can work as a communication device as a whole. For example, the electronic device 200 can include components (e.g., a camera, a video camera, a microphone, etc.) for collecting media objects (e.g., images, videos, audio, etc.) in real time.

[0043] FIG. 3 illustrates an example electronic device for a target node according to an embodiment of the present disclosure. The electronic device 300 can include various units to facilitate implementing embodiments of the semantic and user feedback based communication according to the present disclosure. In the example of FIG. 3, the electronic device 300 includes a transceiving unit 302 and a processing unit 304. The various operations described below in connection with a target node or in connection with the semantic and user feedback based communication can be implemented by the units 302-304 of the electronic device 300 or other possible units.

[0044] Generally, the transceiving unit 302 can be configured to perform various signaling and messaging with the center node, and the processing unit 304 can be configured to process the signaling and messages and control their transceiving.

[0045] In one embodiment, the transceiving unit 302 can be configured to receive, from the center node, respective semantic information of a plurality of media objects to be transmitted, the semantic information including semantic features in the respective media objects. The processing unit 304 can be configured to determine one or more media objects of the plurality of media objects that match the interest of the target node (or the electronic device 300). Accordingly, the transceiving unit 302 can be configured to send, to the center node, feedback information indicating the one or more media objects that match the interest of the target node. Further, the transceiving unit 302 can be configured to receive, from the center node, media objects, wherein the received media objects are selected by the center node based at least in part on the one or more media objects that match the interest of the target node.

[0046] In an embodiment, the electronic device 300 can be implemented at a chip level, or can also be implemented at a device level by including other external components (e.g., a radio frequency chain, an antenna, etc.). The electronic device 300 can work as a communication device as a whole.

[0047] It should be understood that each of the units described above is a logical module according to the specific function implemented by it, and is not intended to limit the specific implementation manner, for example, it can be implemented in software, hardware or a combination of software and hardware. In actual implementation, each of the units described above can be implemented as an independent physical entity, or can be implemented by a single entity (for example, a processor (CPU or DSP, etc.), an integrated circuit, etc.). Among them, the processing circuitry can refer to various implementations of digital circuitry, analog circuitry or mixed signal (combination of analog and digital) circuitry that performs functions in a computing system. The processing circuitry can include, for example, circuits such as integrated circuits (ICs), application-specific integrated circuits (ASICs), parts or circuits of individual processor cores, entire processor cores, individual processors, programmable hardware devices such as field-programmable gate arrays (FPGAs), and / or systems including multiple processors.

[0048] Example communication flow based on semantic information and user feedback

[0049] FIG. 4 shows an example flow of communication based on semantic information and user feedback according to embodiments of the present disclosure. The example flow 400 involves the operation of a center node 402 and target nodes 404, 406, 408 during a single transmission cycle. The transmission cycle advances over time, and the operations in the example flow 400 can be repeated. It should be understood that the center node can perform this communication flow with any number of target nodes based on actual application or need, and the present disclosure has no limitation in this regard.

[0050] As shown in FIG. 4, at 410, the center node 402 transmits semantic information of a plurality of media objects (e.g., images) to each of the target nodes 404, 406, 408. For example, during each transmission cycle, the center node 402 can collect a plurality of media objects in real time through a collection device (e.g., a camera) or in other appropriate manners, and extract corresponding semantic information from the plurality of media objects, for example, by the control unit 204. Then, the center node 402 transmits the semantic information to the target nodes 404, 406, 408 in a broadcast manner. After receiving the semantic information, the target nodes 404, 406, 408 can each determine one or more images in the plurality of images that match their own interests. In the present disclosure, the operation of the center node 402 at 410 can be regarded as a first stage in a single transmission cycle, also referred to as a semantic information transmission stage.

[0051] In the example procedure 400, the center node 402 can request feedback information from all or part of the target nodes one by one in a certain order, the feedback information being used to indicate the interest matching results of the corresponding target nodes. As shown in FIG. 4, at 412, the center node 402 transmits a message for requesting feedback information to the target node 404. Accordingly, at 414, the target node 404 transmits feedback information to the center node 402. Then, in the order, at 422-424, the center node 402 requests and receives feedback information from the target node 406; at 432-434, the center node 402 requests and receives feedback information from the target node 408. It should be understood that the certain order can be determined by the center node 402 in advance or in real time based on one or more factors, such as the quality of the wireless channel of the target node, the importance of the target node in a specific application or task, etc.

[0052] Simultaneously or in parallel with receiving the feedback information from the target nodes, the center node 402 can determine the importance ranking of the plurality of media objects to be transmitted based on the interest matching results that have been received (e.g., by the control unit 204). The importance ranking is, for example, a ranking formed according to the number of target nodes that are interested in the corresponding media objects. Further, the center node 402 can select one or more media objects from the media objects to be transmitted based on the importance ranking, so as to be transmitted to the target nodes.

[0053] In the present disclosure, the operations of the center node 402 at 412-434 can be regarded as a second phase in a single transmission cycle, also referred to as a feedback information collection / media object importance ranking phase. In one or more embodiments, based on the confidence indicator of the importance ranking satisfying a confidence threshold or upon reaching a maximum duration of the second phase, the center node 402 can determine to stop receiving the feedback information and end the importance ranking operation of the plurality of media objects.

[0054] As shown in FIG. 4, at 450, the center node 402 can broadcast the selected one or more media objects to the target nodes. In one embodiment, the center node 402 can transmit only the one or more media objects with a higher importance ranking to the target nodes within a certain time period. In the present disclosure, the operation of the center node 402 at 450 can be regarded as a third phase in a single transmission cycle, also referred to as a media object transmission phase.

[0055] With the development and popularization of unmanned aerial vehicle (UAV) technology, the role of UAVs in various applications is increasingly prominent. As an example scenario, a UAV can be employed as a center node configured to transmit media objects (e.g., images) to target nodes. The schemes of the present disclosure can be used for UAV-aware task-oriented semantic communication (UTSC) to leverage the image retrieval, image recognition, image transmission, and image encoding characteristics of UAVs to provide intelligent services across regions for users. As a complex cross-mode intelligent task with multiple users and multiple needs, UTSC can be used in various intelligent scenarios in daily life and industry, such as providing a bird’s eye view for vehicles in autonomous driving scenarios. In embodiments of the present disclosure, the determination of media objects matching the own interests by each target node 404-408 can significantly reduce the energy consumption and processing load of the center node 402. This will be advantageous for UAVs that can be limited in energy or computing power.

[0056] Semantic information extraction and transmission

[0057] In embodiments of the present disclosure, the center node can be configured to extract semantic information from a plurality of media objects. The plurality of media objects can be collected in real time by the center node itself or obtained in other appropriate manners, and have identification information. The media objects include, for example, images, videos, or audio, etc. For example, the semantic information extraction can be performed by the control unit 204 for the media objects.

[0058] For a single media object, the semantic information can include one or more semantic features. Each semantic feature can be represented by a semantic triple consisting of a subject, a predicate, and an object. Taking an image as an example, two steps can be used to extract its semantic information. First, the target features are extracted using Faster R-CNN. Then, a scene graph generation method is applied to obtain the corresponding semantic / textual information. Considering that the center node such as a UAV can be limited in computing power, alternatively, a lightweight pre-trained model such as RelTR (Relation Transformer for Scene Graph Generation) can be used to directly filter objects from the image and obtain the relationships between the objects, thereby directly obtaining the subject-predicate-object semantic triples expressing the semantic information.

[0059] FIG. 5 illustrates an example of semantic features and an example of assigning transmission power to the semantic features according to an embodiment of the present disclosure. As shown in FIG. 5, the semantic information extracted from one image includes four semantic features (the four semantic features are associated with the image through image identification), which are respectively expressed by the following semantic triples, i.e., "man wearing a jacket", "woman wearing pants", "vehicle having wheels", and "building having windows". Compared with the original image, the semantic triples express the information in the image through much less amount of data, thereby reducing the communication resources required for broadcasting to the target nodes.

[0060] Upon extracting the semantic information, the center node (e.g., 402) can be configured to transmit the respective semantic information of the plurality of media objects to one or more target nodes. In this way, the respective target nodes (e.g., 404 to 408) can determine one or more media objects in the plurality of media objects that match their interests based at least in part on the semantic information. It should be appreciated that successful transmission of the semantic information to the target nodes is important for the respective target objects to determine the interest matching results. Therefore, in one embodiment, for a plurality of semantic features in a single media object, an importance ranking of the plurality of semantic features can be determined. For example, the plurality of semantic features can be ranked based on historical knowledge at the center node or based on a specific task or application scenario. Then, the power for transmitting the respective semantic features of the media object to the one or more target nodes can be assigned based on the importance ranking of the plurality of semantic features.

[0061] As shown in FIG. 5, the semantic triples "man wearing a jacket", "woman wearing pants", "vehicle having wheels", and "building having windows" decrease in importance in turn, and the transmission power assigned to them in turn accounts for 60%, 30%, 10%, and 0% of the total transmission power for the semantic information of the image. In this way, even in the case of wireless channel fading, the transmission success rate of the semantic features with higher importance can still be guaranteed, thereby avoiding the loss of important semantic information. It should be appreciated that the transmission power allocation proportions in FIG. 5 are only examples. Depending on the system configuration or user selection, the allocation proportions can be fixed, or can be proportionally adjusted based on the relative importance between the semantic triples.

[0062] In the example of FIG. 5, the transmission power allocated to the semantic triple "building has window" accounts for 0% of the total transmission power. This means that the semantic feature does not need to be transmitted to multiple target nodes, i.e., only the first three semantic features are transmitted. This can reduce the time for transmitting semantic information of a single media object to some extent, thereby reducing the time of the first stage in a single transmission cycle described in conjunction with FIG. 4. This allows more time in a single transmission cycle for the second and third stages. It should be appreciated that increasing the time of the second or third stage is advantageous for selecting media objects with higher interest matching degree or for guaranteeing the communication performance of transmitting media objects.

[0063] Feedback information generation and transmission

[0064] In an embodiment of the disclosure, upon receiving the semantic information of the plurality of media objects from the center node, the target node can determine one or more media objects of the plurality of media objects that match the interest of the target node. The interest-matched media objects can be a part or all of the plurality of media objects to be transmitted by the center node. The target node can generate feedback information based on the identification of the one or more interest-matched media objects, for indicating the interest-matched media objects to the center node. For example, the feedback information can be generated by the processing unit 304.

[0065] In an embodiment, the interest-matched media objects can be determined based on the interest information of the target node. The interest information of the user can be stored at the target node in the form of semantic triples and vocabulary. For example, a media object whose semantic features coincide with the interest information of the target node to a degree satisfying a certain interest threshold can be determined as an interest-matched media object. Specifically, for a single media object, by comparing the semantic triples of the media object with the interest information of the user in the form of semantic triples, the target device can determine a matching score of the media object. The higher the matching score, the higher the matching degree of the semantic information contained in the media object with the user interest. If the matching score of the media object satisfies the interest threshold, the media object is determined to be interest-matched and its identification is included in the feedback information. As the target node performs the interest matching operation on more media objects, the identifications of more interest-matched media objects are included in the feedback information.

[0066] FIG. 6 shows an example of feedback information according to an embodiment of the disclosure. In this example, the center node has seven images to be transmitted in a single transmission cycle, e.g., identified as images 1 to 7. The center node transmits the semantic information of the seven images to three target nodes A, B and C. By performing the interest matching operation, the feedback information generated by the target node A includes images {1, 3, 5, 7}, the feedback information generated by the target node B includes images {1, 3, 6, 7}, and the feedback information generated by the target node C includes images {3, 7}.

[0067] It should be appreciated that the interest threshold can be configured by the center node or configured by the target node itself. In one embodiment, alternatively, one or more media objects that match the target node's interest are selected by a user of the target node.

[0068] After generating the feedback information, the target node can transmit the feedback information to the center node. In one embodiment, the target node transmits the feedback information to the center node in response to receiving a request message for the feedback information from the center node. In the example of FIG. 6, the center node can request the feedback information in the order of target nodes A, B, C, and receive the feedback information of target nodes A, B, C accordingly.

[0069] Media object selection

[0070] In the process of receiving the feedback information from the target nodes, the center node can determine or update the importance ranking of the plurality of media objects to be transmitted in real time based on the respective feedback information of one or more target nodes. In one embodiment, the importance ranking of the plurality of media objects can be a ranking formed from more to less in the cumulative number of target nodes that match the interest of the respective media object. For example, the importance ranking can be performed by the control unit 204.

[0071] FIG. 7 illustrates an example of the importance ranking of the plurality of media objects according to an embodiment of the present disclosure. The ranking process in FIG. 7 is described with reference to the example of the feedback information in FIG. 6. In a particular transmission period, the center node transmits the respective semantic information of seven media objects during a first stage. During the first stage, the order in which the three target nodes transmit the feedback information to the center node is target node A, target node B, and target node C. Simultaneously or in parallel with receiving the feedback information, the center node continuously determines or updates the number of target nodes that match the interest of the respective media object as the cumulative matching score of different media objects.

[0072] In particular, before receiving the feedback information, the vector representing the cumulative matching scores of the seven media objects is initialized to (0, 0, 0, 0, 0, 0, 0). In response to receiving the feedback information of target node A, the scores of the media objects that match the interest of target node A are incremented by 1. For example, in response to receiving the feedback information of target node A with matching result {1, 3, 5, 7}, the cumulative matching score vector is updated to (1, 0, 1, 0, 1, 0, 1). Then, in response to receiving the feedback information of target node B with matching result {1, 3, 6, 7}, the cumulative matching score vector is updated to (2, 0, 2, 0, 1, 1, 2). In response to further receiving the feedback information of target node C with matching result {3, 7}, the cumulative matching score vector is updated to (2, 0, 3, 0, 1, 1, 3). At this point, the second phase can end and the final determined cumulative matching score vector is (2, 0, 3, 0, 1, 1, 3).

[0073] It should be appreciated that each determined cumulative matching score vector corresponds to an importance ordering of the media objects. Taking the final determined cumulative matching score vector (2, 0, 3, 0, 1, 1, 3) as an example, the cumulative matching scores of media objects 3 and 7 are 3, which are the highest; the cumulative matching score of media object 1 is 2, which is the second highest; the cumulative matching scores of media objects 5 and 6 are 1, which are lower; and the cumulative matching scores of media objects 2 and 4 are 0, which are the lowest.

[0074] It should be appreciated that the second phase can end based on the confidence metric of the importance ordering of the media objects satisfying a confidence threshold or based on a maximum duration of the second phase having been reached, thereby ensuring that as much time as possible is used for transmitting the media objects.

[0075] Media object transmission

[0076] Upon determining the importance ranking of the plurality of media objects, the center node then starts the third phase of operation to transmit the selected media objects to the target nodes. Specifically, the center node can select one or more media objects from the media objects to be transmitted based on the importance ranking. For example, the media objects with higher importance ranking are selected first and broadcast to the target nodes. In one embodiment, the center node only broadcasts the media objects with higher importance ranking to the one or more target nodes within the maximum duration of the third phase. Taking the media object importance ranking of FIG. 7 as an example, the final determined cumulative matching score vector is (2, 0, 3, 0, 1, 1, 3), and the transmission order of the media objects is {3, 7, 1, 5, 6, 2, 4}. If the third phase only supports transmission of up to three media objects, the media objects transmitted are 1, 3, and 7. If the third phase can support transmission of up to five media objects, the media objects transmitted are 1, 3, 5, 6, and 7. In this way, it can be ensured that the media objects with higher importance are transmitted first within the limited transmission time.

[0077] Communication process control

[0078] As described herein, a single transmission cycle of media objects can be divided into three phases of semantic information transmission, feedback information collection / media object importance ranking, and media object transmission. The three phases can be referred to as the first phase, the second phase, and the third phase in sequence. In embodiments of the present disclosure, the center node can control the communication process of the single transmission cycle to appropriately allocate the respective durations of the three phases.

[0079] FIG. 8A illustrates an example operation for controlling the communication process according to embodiments of the present disclosure. The example operation 800 can be performed by the center node 120, the electronic device 200, or the center node 402.

[0080] At 802, the first phase of the current transmission cycle is started, including broadcasting the semantic information of the plurality of media objects to be transmitted in the current transmission cycle to the target nodes. At 804, before reaching the maximum duration T1 of the first phase, it is determined whether the transmission of the semantic information of the plurality of media objects has been completed by monitoring the semantic information transmission. If it is determined that the transmission has been completed, the operation 800 proceeds to 812 to start the second phase of the current transmission cycle. If it is determined that the transmission has not been completed, the operation 800 proceeds to 806 to further determine whether the maximum duration T1 has been reached. If yes, the operation 800 also proceeds to 812; otherwise, the operation 800 returns to 804 to continue monitoring the semantic information transmission.

[0081] At 812, a second phase of the current transmission cycle is started, including collecting the corresponding feedback information from the target nodes and ranking the importance of the media objects. At 814, before reaching a maximum duration T2 of the second phase, it is determined whether the ranking of the importance of the media objects has been completed by monitoring the ranking situation. In one embodiment, the ranking of the importance of the media objects can be considered to be completed if it has been formed based on the feedback information of all or most (e.g., 70%) of the target nodes. If it is determined that the ranking has been completed, the operation 800 proceeds to 822 to start a third phase of the current transmission cycle. If it is determined that the ranking has not been completed, the operation 800 proceeds to 816 to further determine whether the maximum duration T2 is reached. If yes, the operation 800 proceeds to 822 as well; otherwise, the operation 800 returns to 814 to continue monitoring the ranking situation of the media objects.

[0082] At 822, a third phase of the current transmission cycle is started, including selecting the media objects based on the ranking of the importance and broadcasting the selected media objects to the target nodes. The third phase, and accordingly the current transmission cycle, can be ended when the transmission of the selected media objects is completed, or when a maximum duration T3 of the third phase is reached. It should be understood that the operation 800 can be repeatedly performed to start a new transmission cycle.

[0083] In embodiments of the present disclosure, the semantic information transmission can last for an amount of time up to Tl. Moreover, in the operation 800, by monitoring the semantic information transmission situation, the first phase can be ended early if the semantic information transmission has been completed, leaving more time for the operations of the second and third phases. In embodiments of the present disclosure, the feedback information collection and the ranking of the importance of the media objects can last for an amount of time up to T2. Moreover, in the operation 800, by monitoring the ranking situation, the second phase can be ended early if the ranking of the importance has been completed, leaving more time for the operation of the third phase. In embodiments of the present disclosure, the media object transmission can last for an amount of time up to T3.

[0084] Since the data amount of the semantic information is generally small, Tl can be set to a small value. The values of T2 and T3 can be set relatively to meet different requirements. For example, the value of T2 can be increased and the value of T3 can be decreased, so as to more accurately select the media objects matching the interests of the target nodes (this is because more time is used for the ranking of the importance of the media objects). For example, the value of T2 can be decreased and the value of T3 can be increased, so as to achieve a higher throughput of the media object transmission, which helps to ensure the communication performance such as transmission delay and transmission rate (this is because more time resources are used for the media object transmission).

[0085] In addition to setting different values of T2, in embodiments of the present disclosure, the duration of the second stage can also be adaptively adjusted based on a threshold value. It should be appreciated that in the case of a fixed single transmission cycle time, increasing or decreasing the duration of the second stage is equivalent to decreasing or increasing the duration of the third stage. As described above, when the importance ranking of the media objects has been formed based on feedback information from all or most of the target nodes, it can be considered that the importance ranking of the media objects has been completed. Alternatively, a confidence index can be defined for the importance ranking of the media objects. When the confidence index reaches or satisfies a certain confidence threshold, it can also be considered that the importance ranking of the media objects has been completed.

[0086] Let the confidence index be f(t2), which represents the confidence of the importance ranking determined when the second stage has been running for time t2. In one embodiment, the confidence index can be a function of the number of target nodes that match the interest of the corresponding media object. For example, f(t2) can be taken as

[0087] where p i is the number of target nodes that match the interest of the media object i, i.e., the cumulative matching score in FIG. 7. Equation 1 defines the highest matching score of the current time media object as the confidence index of the importance ranking. The confidence index can also have other forms of definition, e.g., using the first moment, second moment, etc. information of the cumulative matching scores of multiple media objects. In these definitions, the confidence index has the following intuitive property: the more target nodes that are interested in the same media object, i.e., the interest is concentrated in a small number of media objects, the higher the confidence index of the importance ranking.

[0088] In embodiments of the present disclosure, the confidence threshold can be a constant threshold value. For example, the confidence threshold can be 2, then the importance ranking determined based on target nodes A and B in the example of FIG. 7 can satisfy the threshold, so that the feedback information of target node C is not needed. If the confidence threshold is 3, then the importance ranking determined based on target nodes A, B and C can satisfy the threshold. Alternatively, the confidence threshold can be a function that decreases with the duration of the ranking operation of multiple media objects.

[0089] Let the threshold function be g(t2), which represents the confidence threshold when the second stage has been running for time t2. The threshold function has the following property, i.e., when t2 is equal to the maximum duration T 2,max that the second stage can occupy, the threshold function takes 0, i.e., g(T 2,max ) = 0. Based on this property, different forms of threshold functions can be defined, e.g., g1(t2) = T 2,max -t2, or FIG. 8B shows a schematic diagram of controlling the second stage based on a threshold value according to an embodiment of the present disclosure. In the two schematic diagrams in FIG. 8B, the horizontal axis represents time (i.e., 0 to T 2,max ), and the vertical axis represents the value of the threshold function g1(t2) and g2(t2) (i.e., 0 to 1). The two schematic diagrams can generally show the second stage stopping time corresponding to the two threshold functions at a selected confidence index. In the left diagram, after receiving the feedback information of four target nodes, the confidence index f(t2) exceeds the threshold g1(t2), and the second stage can stop. In the right diagram, after receiving the feedback information of five target nodes, the confidence index f(t2) exceeds the threshold g2(t2), and the second stage can stop. Accordingly, the threshold function g1(t2) can be used to improve the throughput / image transmission quantity of the third stage, or the threshold function g2(t2) can be used to achieve higher image selection accuracy.

[0090] Example method

[0091] FIG. 9 shows an example method of communication based on semantic information and user feedback according to an embodiment of the present disclosure. The example method 900 can be performed by the center node 120, the electronic device 200, or the center node 402.

[0092] As shown in FIG. 9, the method 900 can include extracting semantic information from a plurality of media objects to be transmitted and transmitting the corresponding semantic information of the plurality of media objects to one or more target nodes (902). The semantic information can include semantic features in the corresponding media objects. The method 900 can include receiving corresponding feedback information from the one or more target nodes (904). The feedback information is used to indicate one or more media objects in the plurality of media objects that match the interest of the corresponding target node. The method 900 can include determining an importance ranking of the plurality of media objects based on the corresponding feedback information of the one or more target nodes (906). The method 900 can also include selecting one or more media objects from the plurality of media objects based on the importance ranking for transmission to the one or more target nodes (908).

[0093] In one embodiment, a first media object in the plurality of media objects includes a plurality of semantic features, and the method further includes: determining an importance ranking of the plurality of semantic features; assigning power for transmitting the corresponding semantic features of the first media object to the one or more target nodes based on the importance ranking of the plurality of semantic features; and transmitting the corresponding semantic features of the first media object using the assigned power.

[0094] In one embodiment, the method further includes: determining an order of the plurality of target nodes; and receiving the corresponding feedback information from the plurality of target nodes based on the order.

[0095] In an embodiment, determining the importance ranking of the plurality of media objects comprises ranking the plurality of media objects according to a number of target nodes that match the respective media object interest.

[0096] In an embodiment, the method further comprises ending the transmission of the respective semantic information before or at the first time.

[0097] In an embodiment, the method further comprises ending the ranking of the plurality of media objects before the second time based on a confidence indicator of the importance ranking of the plurality of media objects satisfying a confidence threshold; or ending the ranking of the plurality of media objects at the second time.

[0098] In an embodiment, wherein the confidence indicator is a function of a number of target nodes that match the respective media object interest, and wherein the confidence threshold is a decreasing function of a duration of the ranking operation of the plurality of media objects.

[0099] In an embodiment, the method further comprises transmitting only one or more media objects of which the importance ranking is in the front to one or more target nodes within a certain time period.

[0100] In an embodiment, the media object comprises at least one of an image, a video or an audio, and the central node is implemented as a drone.

[0101] In an embodiment, wherein the central node and the one or more target nodes are implemented by terminal devices, and the communication between the central node and the one or more target nodes is implemented by sidelink; or wherein the central node is implemented by a base station, the one or more target nodes are implemented by terminal devices, and the communication between the central node and the one or more target nodes is implemented by uplink and downlink.

[0102] FIG. 10 shows another example method of communication based on semantic information and user feedback according to embodiments of the present disclosure. The example method 1000 can be performed by a target node 110, the electronic device 300, or the target nodes 404-408.

[0103] As shown in FIG. 10, the method 1000 can include receiving, from a center node, respective semantic information of a plurality of media objects to be transmitted (1002). The semantic information includes semantic features in the respective media objects. The method 1000 can include determining one or more media objects of the plurality of media objects that match an interest of the target node (1004). The method 1000 can include sending feedback information to the center node (1006). The feedback information is used to indicate the one or more media objects that match the interest of the target node. The method 1000 can also include receiving a media object from the center node (1008). The received media object is selected by the center node based at least in part on the one or more media objects that match the interest of the target node.

[0104] In one embodiment, the one or more media objects that match the interest of the target node are one or more media objects whose matching degree between the semantic information and interest information of the target node satisfies an interest threshold, wherein the interest threshold is configured by the center node or is configured by the target node itself; or the one or more media objects that match the interest of the target node are selected by a user.

[0105] In one embodiment, the method further includes: receiving a request message from the center node; and in response to receiving the request message, sending the feedback information to the center node.

[0106] In one embodiment, the media object includes at least one of an image, a video, or an audio, the center node is implemented as a drone. Wherein the center node and the one or more target nodes are implemented by terminal devices, and the communication between the center node and the one or more target nodes is implemented by sidelink; or wherein the center node is implemented by a base station, the one or more target nodes are implemented by terminal devices, and the communication between the center node and the one or more target nodes is implemented by uplink and downlink.

[0107] The above respectively describes each exemplary electronic device and method according to embodiments of the present disclosure. It should be understood that the operations or functions of these electronic devices can be combined with each other, thereby achieving more or less operations or functions than described. The operation steps of each method can also be combined with each other in any appropriate order, thereby similarly achieving more or less operations than described.

[0108] It should be appreciated that the machine executable instructions in the machine readable storage medium or program product according to embodiments of the present disclosure can be configured to perform operations corresponding to the above-described device and method embodiments. Embodiments of the machine readable storage medium or program product are apparent to those skilled in the art from the above description of the device and method embodiments, and thus are not described again. Machine readable storage media and program products for carrying or including the machine executable instructions described above also fall within the scope of the present disclosure. Such storage media can include, without limitation, a floppy disk, an optical disc, a magneto-optical disk, a memory card, a memory stick, and the like. In addition, it should be appreciated that the above-described series of processes and devices can also be implemented by software and / or firmware.

[0109] In addition, it should be appreciated that the above-described series of processes and devices can also be implemented by software and / or firmware. In the case of implementation by software and / or firmware, a program constituting the software is installed from a storage medium or a network to a computer having a dedicated hardware structure, such as the general-purpose computer 1300 shown in FIG. 11, which is capable of performing various functions when various programs are installed. FIG. 11 shows an example block diagram of a computing device that can be configured as a central node or a target node according to embodiments of the present disclosure.

[0110] In FIG. 11, a central processing unit (CPU) 1301 performs various processes according to a program stored in a read only memory (ROM) 1302 or a program loaded from a storage section 1308 to a random access memory (RAM) 1303. In the RAM 1303, data required when the CPU 1301 performs various processes and the like is also stored as necessary.

[0111] The CPU 1301, the ROM 1302, and the RAM 1303 are connected to each other via a bus 1304. An input / output interface 1305 is also connected to the bus 1304.

[0112] The following components are connected to the input / output interface 1305: an input section 1306 including a keyboard, a mouse, and the like; an output section 1307 including a display such as a cathode ray tube (CRT), a liquid crystal display (LCD), and the like, and a speaker and the like; a storage section 1308 including a hard disk and the like; and a communication section 1309 including a network interface card such as a LAN card, a modem, and the like. The communication section 1309 performs communication processing via a network such as the Internet.

[0113] A drive 1310 is also connected to the input / output interface 1305 as necessary. A removable medium 1311 such as a magnetic disk, an optical disc, a magneto-optical disk, a semiconductor memory, and the like is mounted on the drive 1310 as necessary, so that a computer program read therefrom is installed in the storage section 1308 as necessary.

[0114] In a case where the above series of processes are realized by software, a program constituting the software is installed from a network such as the Internet or a storage medium such as the detachable medium 1311.

[0115] It is to be understood by those skilled in the art that this storage medium is not limited to the detachable medium 1311 in which the program is stored, which is distributed separately from the apparatus to provide the program to the user, as illustrated in FIG. 11. Examples of the detachable medium 1311 include a magnetic disk (including a floppy® disk), a magneto-optical disk (including a mini disk (MD)®), and a semiconductor memory. Alternatively, the storage medium can be the ROM 1302, a hard disk included in the storage section 1308, or the like, in which the program is stored and which is distributed to the user together with the apparatus including them.

[0116] An application example according to the present disclosure will be described below with reference to FIGS. 12 to 13.

[0117] An application example of a terminal apparatus

[0118] First application example

[0119] FIG. 12 is a block diagram illustrating an example of a schematic configuration of a smartphone 1600 to which the technology according to the present disclosure can be applied. The smartphone 1600 includes a processor 1601, a memory 1602, a storage 1603, an external connection interface 1604, a camera 1606, a sensor 1607, a microphone 1608, an input device 1609, a display device 1610, a speaker 1611, a wireless communication interface 1612, one or more antenna switches 1615, one or more antennas 1616, a bus 1617, a battery 1618, and an auxiliary controller 1619. In one implementation, the smartphone 1600 (or the processor 1601) here can correspond to the electronic apparatus 300B described above.

[0120] The processor 1601 can be, for example, a CPU or a system on chip (SoC), and controls functions of an application layer and another layer of the smartphone 1600. The memory 1602 includes a RAM and a ROM, and stores a data and a program executed by the processor 1601. The storage 1603 can include a storage medium such as a semiconductor memory and a hard disk. The external connection interface 1604 is an interface for connecting an external device such as a memory card and a universal serial bus (USB) device to the smartphone 1600.

[0121] The camera 1606 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 1607 can include a set of sensors such as a measurement sensor, a gyro sensor, a geomagnetic sensor, and an acceleration sensor. The microphone 1608 converts a sound input to the smartphone 1600 into an audio signal. The input device 1609 includes, for example, a touch sensor configured to detect a touch on a screen of the display device 1610, a keypad, a keyboard, a button, or a switch, and receives an operation or information input from a user. The display device 1610 includes a screen such as a liquid crystal display (LCD) and an organic light emitting diode (OLED) display, and displays an output image of the smartphone 1600. The speaker 1611 converts an audio signal output from the smartphone 1600 into a sound.

[0122] The wireless communication interface 1612 supports any cellular communication scheme such as LTE and LTE-Advanced, and performs wireless communication. The wireless communication interface 1612 can include, for example, a BB processor 1613 and an RF circuit 1614, in general. The BB processor 1613 can perform, for example, encoding / decoding, modulation / demodulation, and multiplexing / demultiplexing, and perform various types of signal processing for wireless communication. Meanwhile, the RF circuit 1614 can include, for example, a mixer, a filter, and an amplifier, and transmit and receive a wireless signal via an antenna 1616. The wireless communication interface 1612 can be one chip module in which the BB processor 1613 and the RF circuit 1614 are integrated. As illustrated in FIG. 12, the wireless communication interface 1612 can include a plurality of BB processors 1613 and a plurality of RF circuits 1614. Although FIG. 12 illustrates an example in which the wireless communication interface 1612 includes a plurality of BB processors 1613 and a plurality of RF circuits 1614, the wireless communication interface 1612 can include a single BB processor 1613 or a single RF circuit 1614.

[0123] In addition, the wireless communication interface 1612 can support another type of wireless communication scheme in addition to the cellular communication scheme, such as a short-range wireless communication scheme, a near field communication scheme, and a wireless local area network (LAN) scheme. In this case, the wireless communication interface 1612 can include a BB processor 1613 and an RF circuit 1614 for each wireless communication scheme.

[0124] Each of the antenna switches 1615 switches a connection destination of the antenna 1616 between a plurality of circuits included in the wireless communication interface 1612, for example, circuits for different wireless communication schemes.

[0125] Each of the antennas 1616 includes a single or multiple antenna elements (such as a plurality of antenna elements included in a MIMO antenna), and is used for the wireless communication interface 1612 to transmit and receive wireless signals. As illustrated in FIG. 12, the smartphone 1600 can include a plurality of antennas 1616. While FIG. 12 illustrates an example in which the smartphone 1600 includes a plurality of antennas 1616, the smartphone 1600 can also include a single antenna 1616.

[0126] Furthermore, the smartphone 1600 can include an antenna 1616 for each wireless communication scheme. In this case, the antenna switch 1615 can be omitted from the configuration of the smartphone 1600.

[0127] The bus 1617 connects the processor 1601, the memory 1602, the storage 1603, the external connection interface 1604, the camera 1606, the sensor 1607, the microphone 1608, the input device 1609, the display device 1610, the speaker 1611, the wireless communication interface 1612, and the auxiliary controller 1619 to one another. The battery 1618 supplies power to the respective blocks of the smartphone 1600 illustrated in FIG. 12 via feed lines, which are partially illustrated as dotted lines in the figure. The auxiliary controller 1619 operates the minimum necessary functions of the smartphone 1600, for example, in a sleep mode.

[0128] Second Application Example

[0129] FIG. 13 is a block diagram illustrating an example of a schematic configuration of a car navigation device 1720 to which the technology of the present disclosure can be applied. The car navigation device 1720 includes a processor 1721, a memory 1722, a global positioning system (GPS) module 1724, a sensor 1725, a data interface 1726, a content player 1727, a storage medium interface 1728, an input device 1729, a display device 1730, a speaker 1731, a wireless communication interface 1733, one or more antenna switches 1736, one or more antennas 1737, and a battery 1738. In one implementation, the car navigation device 1720 (or the processor 1721) here can correspond to the electronic device 300B described above.

[0130] The processor 1721 can be, for example, a CPU or a SoC, and controls a navigation function and another function of the car navigation device 1720. The memory 1722 includes a RAM and a ROM, and stores data and programs executed by the processor 1721.

[0131] The GPS module 1724 measures a position (such as latitude, longitude and altitude) of the car navigation device 1720 using GPS signals received from GPS satellites. The sensor 1725 can include a set of sensors such as a gyro sensor, a geomagnetic sensor and an air pressure sensor. The data interface 1726 is connected to, for example, an in-vehicle network 1741 via a terminal not shown, and acquires data generated by the vehicle such as vehicle speed data.

[0132] The content player 1727 reproduces content stored in a storage medium such as a CD and a DVD, which is inserted into the storage medium interface 1728. The input device 1729 includes, for example, a touch sensor configured to detect a touch on a screen of the display device 1730, a button or a switch, and receives an operation or information input from a user. The display device 1730 includes a screen such as an LCD or an OLED display, and displays an image of a navigation function or reproduced content. The speaker 1731 outputs a sound of a navigation function or reproduced content.

[0133] The wireless communication interface 1733 supports any cellular communication scheme such as LTE and LTE-Advanced, and performs wireless communication. The wireless communication interface 1733 can generally include, for example, a BB processor 1734 and an RF circuit 1735. The BB processor 1734 can perform, for example, encoding / decoding, modulation / demodulation and multiplexing / demultiplexing, and perform various types of signal processing for wireless communication. Meanwhile, the RF circuit 1735 can include, for example, a mixer, a filter and an amplifier, and transmit and receive wireless signals via an antenna 1737. The wireless communication interface 1733 can also be one chip module in which the BB processor 1734 and the RF circuit 1735 are integrated thereon. As shown in FIG. 13, the wireless communication interface 1733 can include a plurality of BB processors 1734 and a plurality of RF circuits 1735. Although FIG. 13 shows an example in which the wireless communication interface 1733 includes a plurality of BB processors 1734 and a plurality of RF circuits 1735, the wireless communication interface 1733 can also include a single BB processor 1734 or a single RF circuit 1735.

[0134] In addition, the wireless communication interface 1733 can support another type of wireless communication scheme in addition to the cellular communication scheme, such as a short-range wireless communication scheme, a near field communication scheme and a wireless LAN scheme. In this case, the wireless communication interface 1733 can include a BB processor 1734 and an RF circuit 1735 for each wireless communication scheme.

[0135] Each of the antenna switches 1736 switches a connection destination of the antenna 1737 between a plurality of circuits included in the wireless communication interface 1733, such as circuits for different wireless communication schemes.

[0136] Each of the antennas 1737 includes a single or multiple antenna elements (such as multiple antenna elements included in a MIMO antenna), and is used for the wireless communication interface 1733 to transmit and receive wireless signals. As illustrated in FIG. 13, the car navigation device 1720 can include multiple antennas 1737. While FIG. 13 illustrates an example in which the car navigation device 1720 includes multiple antennas 1737, the car navigation device 1720 can also include a single antenna 1737.

[0137] Further, the car navigation device 1720 can include an antenna 1737 for each wireless communication scheme. In this case, the antenna switch 1736 can be omitted from the configuration of the car navigation device 1720.

[0138] The battery 1738 supplies power to the various blocks of the car navigation device 1720 illustrated in FIG. 13 via feed lines, which are partially illustrated as dotted lines in the figure. The battery 1738 accumulates power supplied from the vehicle.

[0139] The technology of the present disclosure can also be implemented as an in-vehicle system (or vehicle) 1740 including the car navigation device 1720, an in-vehicle network 1741, and one or more blocks of a vehicle module 1742. The vehicle module 1742 generates vehicle data such as vehicle speed, engine speed, and fault information, and outputs the generated data to the in-vehicle network 1741.

[0140] It should be understood that the technical solutions of the present disclosure can be implemented by the following example embodiments.

[0141] 1. An electronic device for a central node, comprising:

[0142] at least one processor; and at least one memory storing program instructions, wherein the program instructions, when executed by the at least one processor, cause the electronic device to:

[0143] extract semantic information from a plurality of media objects to be transmitted and transmit corresponding semantic information of the plurality of media objects to one or more target nodes, wherein the semantic information comprises semantic features in corresponding media objects;

[0144] receive corresponding feedback information from the one or more target nodes, wherein the feedback information is used to indicate one or more media objects in the plurality of media objects that match the interest of a corresponding target node;

[0145] determine an importance ranking of the plurality of media objects based on the corresponding feedback information of the one or more target nodes; and

[0146]

[0147] selecting one or more media objects from the plurality of media objects based on the importance ranking for transmission to the one or more target nodes.

[0148] 2. The electronic device of example 1, wherein a first media object of the plurality of media objects comprises a plurality of semantic features, and the program instructions further cause the electronic device to:

[0149] determine an importance ranking of the plurality of semantic features;

[0150] assign power for transmission of respective semantic features of the first media object to the one or more target nodes based on the importance ranking of the plurality of semantic features; and

[0151] transmit the respective semantic features of the first media object using the assigned power.

[0152] 3. The electronic device of example 1, wherein the program instructions further cause the electronic device to determine an order of the plurality of target nodes; and

[0153] receive respective feedback information from the plurality of target nodes based on the order.

[0154] 4. The electronic device of example 1, wherein determining the importance ranking of the plurality of media objects comprises ranking the plurality of media objects by a number of target nodes that match an interest of a respective media object.

[0155] 5. The electronic device of example 2, wherein the program instructions further cause the electronic device to end transmission of the respective semantic information before a first time or upon reaching the first time.

[0156] 6. The electronic device of example 4, wherein the program instructions further cause the electronic device to end ranking of the plurality of media objects based on a confidence metric of the importance ranking of the plurality of media objects satisfying a confidence threshold before a second time; or

[0157] end ranking of the plurality of media objects upon reaching the second time.

[0158] 7. The electronic device of example 6, wherein the confidence metric is a function of the number of target nodes that match an interest of a respective media object, and wherein the confidence threshold is a function that decreases over a duration of the ranking operation of the plurality of media objects.

[0159] 8. The electronic device of example 6, wherein the program instructions further cause the electronic device to transmit only one or more media objects of a higher importance ranking to the one or more target nodes for a particular time period.

[0160] 9. The electronic device of example 1, wherein the media objects comprise at least one of an image, a video, or an audio, and the central node is implemented as a drone.

[0161] 10. The electronic device of example 1, wherein the central node and the one or more target nodes are implemented by terminal devices, and the communication between the central node and the one or more target nodes is implemented by sidelink; or

[0162] wherein the central node is implemented by a base station, the one or more target nodes are implemented by terminal devices, and the communication between the central node and the one or more target nodes is implemented by uplink and downlink.

[0163] 11. An electronic device for a target node, comprising:

[0164] at least one processor; and

[0165] at least one memory storing program instructions, wherein the program instructions, when executed by the at least one processor, cause the electronic device to:

[0166] receive, from a central node, respective semantic information of a plurality of media objects to be transmitted, wherein the semantic information comprises semantic features in respective media objects;

[0167] determine one or more media objects of the plurality of media objects that match an interest of the target node;

[0168] send feedback information to the central node, wherein the feedback information is used to indicate the one or more media objects that match the interest of the target node; and

[0169] receive a media object from the central node, wherein the received media object is selected by the central node based at least in part on the one or more media objects that match the interest of the target node.

[0170] 12. The electronic device of example 11, wherein:

[0171] the one or more media objects that match the interest of the target node are one or more media objects whose matching degree between the semantic information and interest information of the target node satisfies an interest threshold, wherein the interest threshold is configured by the central node or is configured by the target node itself; or

[0172] the one or more media objects that match the interest of the target node are selected by a user.

[0173] 13. The electronic device of example 11, wherein the program instructions further cause the electronic device to: receive a request message from the central node; and

[0174] in response to receiving the request message, transmit the feedback information to the central node.

[0175] 14. The electronic device of example 11, wherein the media objects comprise at least one of an image, a video, or an audio, the central node is implemented as a drone;

[0176] wherein the central node and the one or more target nodes are implemented by terminal devices, and the communication between the central node and the one or more target nodes is implemented by sidelinks; or

[0177] wherein the central node is implemented by a base station, the one or more target nodes are implemented by terminal devices, and the communication between the central node and the one or more target nodes is implemented by uplink and downlink.

[0178] 15. A method for communication, comprising:

[0179] by a central node:

[0180] extracting semantic information from a plurality of media objects to be transmitted and transmitting respective semantic information of the plurality of media objects to one or more target nodes, wherein the semantic information comprises semantic features in respective media objects;

[0181] receiving respective feedback information from the one or more target nodes, wherein the feedback information is used to indicate one or more media objects of the plurality of media objects that match interests of respective target nodes;

[0182] determining an importance ranking of the plurality of media objects based on respective feedback information of the one or more target nodes; and

[0183] selecting one or more media objects from the plurality of media objects based on the importance ranking for transmission to the one or more target nodes.

[0184] 16. A method for communication, comprising:

[0185] by a target node:

[0186] receiving respective semantic information of a plurality of media objects to be transmitted from a central node, wherein the semantic information comprises semantic features in respective media objects;

[0187] determining one or more media objects of the plurality of media objects that match interests of the target node;

[0188] sending feedback information to the central node, wherein the feedback information is used to indicate the one or more media objects that match the target node interest; and

[0189] receiving a media object from the central node, wherein the received media object is selected by the central node based at least in part on the one or more media objects that match the target node interest.

[0190] 17. A computer program product comprising instructions which, when executed by a computer, cause the implementation of the method according to any one of the examples 15 to 16.

[0191] The exemplary 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. Various changes and modifications can be made by those skilled in the art within the scope of the appended claims, and it should be understood that such changes and modifications naturally fall within the technical scope of the present disclosure.

[0192] For example, a plurality of functions included in one unit in the above-described embodiments can be implemented by separate apparatuses. Alternatively, a plurality of functions implemented by a plurality of units in the above-described embodiments can be implemented by separate apparatuses, respectively. In addition, one of the above-described functions can be implemented by a plurality of units. Needless to say, such a configuration is included in the technical scope of the present disclosure.

[0193] In this specification, the steps described in the flowcharts described in the flowcharts include not only processes performed in time series according to the order described in the flowcharts, but also processes performed in parallel or individually rather than in time series. Furthermore, even if the steps are processed in time series, needless to say, the order can be changed appropriately.

[0194] While the present disclosure and its advantages have been disclosed in detail, it should be understood that various changes, substitutions and alterations can be made herein without departing from the spirit and scope of the disclosure as defined by the appended claims. Moreover, the scope of the present disclosure is not intended to be limited to the particular embodiments of the process, machine, manufacture, composition of matter, means, methods and steps described in the specification. Accordingly, the disclosure of this patent application is intended to be illustrative, but not limiting, of the scope of the present disclosure, which is set forth in the following claims.

Claims

1. An electronic device for a central node, comprising: at least one processor; and at least one memory storing program instructions that, when executed by the at least one processor, cause the electronic device to: extract semantic information from a plurality of media objects to be transmitted and transmit corresponding semantic information of the plurality of media objects to one or more target nodes, wherein the semantic information comprises semantic features in a corresponding media object; receive corresponding feedback information from the one or more target nodes, wherein the feedback information is used to indicate one or more media objects of the plurality of media objects that match interest of a corresponding target node; determine an importance ranking of the plurality of media objects based on the corresponding feedback information of the one or more target nodes; and select one or more media objects from the plurality of media objects based on the importance ranking for transmission to the one or more target nodes. 2.The electronic device of claim 1, wherein a first media object of the plurality of media objects comprises a plurality of semantic features, and the program instructions further cause the electronic device to: determine an importance ranking of the plurality of semantic features; assign power for transmitting corresponding semantic features of the first media object to the one or more target nodes based on the importance ranking of the plurality of semantic features; and transmit the corresponding semantic features of the first media object using the assigned power. 3.The electronic device of claim 1, wherein the program instructions further cause the electronic device to: determine an order of a plurality of target nodes; and receive the corresponding feedback information from the plurality of target nodes based on the order. 4.The electronic device of claim 1, wherein determining the importance ranking of the plurality of media objects comprises ranking the plurality of media objects by a number of target nodes that match interest of a corresponding media object. 5.The electronic device of claim 2, wherein the program instructions further cause the electronic device to: end transmission of the corresponding semantic information before a first time or when the first time is reached. 6.The electronic device of claim 4, wherein the program instructions further cause the electronic device to: end ranking of the plurality of media objects based on a confidence indicator of the importance ranking of the plurality of media objects satisfying a confidence threshold before a second time; or end ranking of the plurality of media objects when the second time is reached. 7.The electronic device of claim 6, wherein the confidence indicator is a function of the number of target nodes that match interest of a corresponding media object, and wherein the confidence threshold is a function that decreases with duration of the ranking operation of the plurality of media objects. 8.The electronic device of claim 6, wherein the program instructions further cause the electronic device to: transmit only one or more media objects of the importance ranking in front to the one or more target nodes within a certain time period. ​ ​ ​ 9.The electronic device of claim 1, wherein the media object comprises at least one of an image, a video, or an audio, and the center node is implemented as a drone. 10.The electronic device of claim 1, wherein the center node and the one or more target nodes are implemented by terminal devices, and the communication between the center node and the one or more target nodes is implemented by sidelink; or wherein the center node is implemented by a base station, the one or more target nodes are implemented by terminal devices, and the communication between the center node and the one or more target nodes is implemented by uplink and downlink. 11.An electronic device for a target node, comprising: at least one processor; and at least one memory storing program instructions, wherein the program instructions, when executed by the at least one processor, cause the electronic device to: receive, from a center node, respective semantic information of a plurality of media objects to be transmitted, wherein the semantic information comprises semantic features in respective media objects; determine one or more media objects of the plurality of media objects that match an interest of the target node; send, to the center node, feedback information, wherein the feedback information is used to indicate the one or more media objects that match the interest of the target node; and receive, from the center node, a media object, wherein the received media object is selected by the center node based at least in part on the one or more media objects that match the interest of the target node. 12.The electronic device of claim 11, wherein: the one or more media objects that match the interest of the target node are one or more media objects whose matching degree between the semantic information and interest information of the target node satisfies an interest threshold, wherein the interest threshold is configured by the center node or is configured by the target node itself; or the one or more media objects that match the interest of the target node are selected by a user. 13.The electronic device of claim 11, wherein the program instructions further cause the electronic device to: receive a request message from the center node; and in response to receiving the request message, send the feedback information to the center node. 14.The electronic device of claim 11, wherein the media object comprises at least one of an image, a video, or an audio, and the center node is implemented as a drone; wherein the center node and the one or more target nodes are implemented by terminal devices, and the communication between the center node and the one or more target nodes is implemented by sidelink; or wherein the center node is implemented by a base station, the one or more target nodes are implemented by terminal devices, and the communication between the center node and the one or more target nodes is implemented by uplink and downlink. 15.A method for communication, comprising: by a center node: extracting semantic information from a plurality of media objects to be transmitted and transmitting, to one or more target nodes, respective semantic information of the plurality of media objects, wherein the semantic information comprises semantic features in respective media objects; ​ receiving, from the one or more target nodes, respective feedback information, wherein the feedback information is used to indicate one or more media objects of the plurality of media objects that match interests of the respective target nodes; determining, based on the respective feedback information of the one or more target nodes, an importance ranking of the plurality of media objects; and selecting, based on the importance ranking, one or more media objects from the plurality of media objects for transmission to the one or more target nodes.

16. A method for communication, comprising: by a target node: receiving, from a central node, respective semantic information of a plurality of media objects to be transmitted, wherein the semantic information comprises semantic features in respective media objects; determining one or more media objects of the plurality of media objects that match interests of the target node; sending, to the central node, feedback information, wherein the feedback information is used to indicate the one or more media objects that match interests of the target node; and receiving, from the central node, a media object, wherein the received media object is selected by the central node based at least in part on the one or more media objects that match interests of the target node.

17. A computer program product comprising instructions which, when executed by a computer, cause the implementation of the method of any of claims 15 to 16. ​ ​

Images