Semantic communication method, device and system

Abstract

The invention provides a semantic communication method, device and system. A first device such as a sensing device can obtain at least one piece of task indication information sent in at least one area, and each piece of task indication information in the at least one piece of task indication information is sent in a corresponding area in the at least one area and indicates at least one task indication. Each task indication indicates a task type supported by the respective region. Then, the first device can select one region from the at least one region according to the task type of interest and the at least one piece of task indication information. Therefore, only the task type supported by each region and the task type of interest are considered, and for selecting one region, all task types do not need to be measured, so that task delay or power consumption can be reduced.

Description

[0001] Cross-reference to related applications

[0002] This application claims priority to U.S. Provisional Patent Application No. 63 / 509,421, filed June 21, 2023, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This invention relates to the field of semantic communication technology, and more specifically, to a communication method, apparatus, and system. Background Technology

[0004] Sensing capabilities will be integrated into the 6th generation (6G) system. A large number of sensing user equipment (UE) devices will be densely deployed in cities, factories, farms, and other locations. In addition to mobile phones, sensing devices will also become an important type of UE or device that heralds the arrival of the IoT era.

[0005] Just like internet search engines, 6G will bring corresponding Internet of Things (IoT) search engines to the real physical world. In fact, billions of IoT-based applications, such as self-driving cars, automated factories, smart cities, and autonomous farms, will rely heavily on efficient, real-time search engines in our physical world.

[0006] In recent years, artificial intelligence (AI) has made breakthroughs in various knowledge and cognitive domains. Some AIs are exploring cutting-edge knowledge in fields such as chemistry, gaming, mathematics, and genetic engineering. Others are providing human-level question-and-answer platforms in the digital world. The area AI has yet to conquer is the real-time physical world. AI in the physical world may be built upon the ubiquitous IoT connectivity brought by 6G, in which AI technology will permeate every aspect of our society and lives.

[0007] More challenging than internet search engines are real-world search engines, which must search the physical world in real time over vast physical areas and process diverse types of data and information (some novel, others yet to be invented). Furthermore, green technology, low energy consumption, and low emissions have been identified as key characteristics of 6G. Sensing devices can be battery-powered and / or entirely powered by solar and wind energy. Requiring all sensing devices on a large scale to simultaneously report what they are sensing is costly and impractical. On one hand, frequent sensing and transmission consume significant amounts of energy from sensing devices, shortening their battery life; on the other hand, such high-density IoT deployments could clog uplink channels, especially since uplink (UL) bandwidth is more expensive than downlink (DL) bandwidth.

[0008] The purpose of providing this background is to reveal information which the applicant believes to be relevant to the present application, and not to admit or suggest that any of the above information constitutes prior art to the present application. SUMMARY

[0009] In a first aspect, the present application provides a communication method, comprising:

[0010] obtaining at least one task indication information sent in at least one area, each of the at least one task indication information is sent in a corresponding area of the at least one area and indicates at least one task indication, each task indication indicates a task type supported by the corresponding area;

[0011] selecting an area from the at least one area according to a task type of interest and the at least one task indication information.

[0012] Since the selection of the area is based on the task type of interest and the task type supported by each area, only the task type supported by each area and the task type of interest are considered, and no measurement is needed for all task types for selecting an area, which can reduce task delay or power consumption.

[0013] In a possible implementation manner of the first aspect, each of the at least one task indication comprises a reference signal for measurement.

[0014] Since each of the at least one task indication comprises a reference signal for measurement, after obtaining the task indication information indicating the at least one task indication, measurement can be performed on the at least one task indication to obtain a measurement result corresponding to the at least one task indication.

[0015] In a possible implementation manner of the first aspect, the method further comprises: determining the task type of interest according to a capability of the first device and / or a current state of the first device.

[0016] Since the task type of interest is determined according to the capability of the first device and / or the current state of the first device, when selecting an area from the at least one area, no task type beyond the capability of the first device and / or no task type not supported by the first device in the current state is considered, and no measurement is performed on these task types, thereby reducing power consumption.

[0017] In a possible implementation manner of the first aspect, the selecting one region from the at least one region according to the task type of interest and the at least one piece of task indication information comprises: measuring the task type of interest in one or more regions of the at least one region to obtain one or more measurement results respectively corresponding to the one or more regions of the at least one region, the corresponding piece of task indication information sent by the one or more regions of the at least one region indicating one or more task indications, the one or more task indications indicating the task type of interest; and selecting one region from the one or more regions of the at least one region, the selected region corresponding to a measurement result with a value higher than a threshold.

[0018] Since the region is selected from the one or more regions supporting the task type of interest, and the selected region corresponds to a measurement result with a value higher than a threshold, it is ensured that the selected region supports the task type of interest and has good signal quality. In addition, since the measurement is performed only for the task type of interest, the task delay or power consumption can be greatly reduced.

[0019] In a possible implementation manner of the first aspect, the at least one region comprises a first region and a second region, the at least one piece of task indication information comprises a first piece of task indication information sent in the first region and a second piece of task indication information sent in the second region, and the at least one first task indication indicated by the first piece of task indication information and the at least one second task indication indicated by the second piece of task indication information indicate different task types.

[0020] Since the at least one first task indication indicated by the first piece of task indication information sent in the first region and the at least one second task indication indicated by the second piece of task indication information sent in the second region indicate different task types, different regions can support different task types. By means of the task indications indicated by the task indication information sent in different regions, different task types supported by different regions can be effectively indicated, and after obtaining the task indication information sent in different regions, it can be known that the regions support different task types according to the task indication information.

[0021] In a possible implementation manner of the first aspect, the at least one task indication is scrambled by an identity of a region sending a piece of task indication information indicating the at least one task indication.

[0022] Since at least one task indication is scrambled by an identity of a region sending a piece of task indication information indicating the at least one task indication, i.e., the task indication is scrambled by an identity of a region supporting a task type indicated by the task indication, after obtaining at least one piece of task indication information sent in at least one region, a region supporting the task type can be determined according to an identity used to scramble the region indicating the task type.

[0023] In a possible implementation manner of the first aspect, the at least one region includes a first region and a second region, and time-frequency resources of one or more first task indications for a certain task type in the first region are the same as time-frequency resources of one or more second task indications for the same task type in the second region.

[0024] In a possible implementation manner of the first aspect, the at least one region includes a first region and a second region, and time-frequency resources of one or more first task indications for a certain task type in the first region are different from time-frequency resources of one or more second task indications for the same task type in the second region.

[0025] Since the time-frequency resources of one or more first task indications for a certain task type in the first region can be the same as or different from the time-frequency resources of one or more second task indications for the same task type in the second region, the time-frequency resources of the task indications for the certain task type can be flexibly configured.

[0026] In a possible implementation manner of the first aspect, the time-frequency resources of the one or more first task indications for the task type in the first region include time-frequency resources of one or more first reference signals for the task type in the first region, and the time-frequency resources of the one or more second task indications for the same task type in the second region include time-frequency resources of one or more second reference signals for the same task type in the second region.

[0027] Since the time-frequency resources of one or more first reference signals for a certain task type in the first region can be the same as or different from the time-frequency resources of one or more second reference signals for the same task type in the second region, the time-frequency resources of the reference signals for the certain task type can be flexibly configured.

[0028] In a possible implementation manner of the first aspect, the at least one task indication is represented by at least one pattern of at least one task type.

[0029] Since the at least one task indication is represented by at least one pattern of at least one task type, after the task indication information indicating the at least one task indication is acquired, the at least one task type can be easily read and learned.

[0030] In a possible implementation manner of the first aspect, different patterns are defined for different task types.

[0031] Since different patterns are defined for different task types, different patterns can be used to indicate different task types, and each task type can be determined according to its corresponding pattern, which provides an effective way to indicate the task types supported by each region.

[0032] In a possible implementation manner of the first aspect, the at least one task indication is configurable.

[0033] Since the at least one task indication is configurable, flexible configuration is achieved.

[0034] In a possible implementation manner of the first aspect, the different patterns are predefined in a specification and can be selected according to a current scenario.

[0035] Since the different patterns are predefined in a specification and can be selected according to a current scenario, transmission resources of pattern configuration can be saved, and patterns can be flexibly selected according to a current scenario.

[0036] In a possible implementation manner of the first aspect, the different patterns are broadcast, multicast or unicast through signaling.

[0037] In a possible implementation manner of the first aspect, the signaling is carried in radio resource control (RRC) signaling.

[0038] Since the different patterns are broadcast, multicast or unicast through RRC signaling or the like signaling, transmission of the patterns is more flexible.

[0039] In a possible implementation manner of the first aspect, different task types correspond to different task indications.

[0040] Since different task types correspond to different task indications, the task types indicated by the task indications can be easily learned.

[0041] In a possible implementation manner of the first aspect, a message for a task type is scrambled by a task identifier of the task type.

[0042] Since the message for a certain task type is scrambled with the task identifier of the task type, after receiving the message, the task type to which the message corresponds can be easily known.

[0043] In a possible implementation of the first aspect, the at least one task indication belongs to at least one group, each of the at least one task indication belongs to one of the at least one group, each of the at least one group corresponds to a respective different task type, and includes one or more task indications indicating the respective different task type.

[0044] Since the task indications are grouped according to the task types, each task type can correspond to a group of one or more task indications, and thus the task indication used to indicate the task type can be flexibly selected from the group according to actual conditions, and the indication of the task type can be more reliable when multiple task indications are used to indicate the task type.

[0045] In a possible implementation of the first aspect, each of the at least one area is a cell, or each of the at least one area is a paging area.

[0046] The area can be a cell or a paging area, that is, the method can be used to select a cell or a paging area, thereby implementing task-specific cell selection or task-specific paging area selection.

[0047] In a possible implementation of the first aspect, the first device is a sensing device.

[0048] In a second aspect, the present application provides a communication method, comprising:

[0049] Sending at least one task indication information in at least one area, each of the at least one task indication information is sent in a respective area of the at least one area and indicates at least one task indication, each task indication indicates a task type supported by the respective area.

[0050] Since each task indication indicates the task type supported by the respective area, when the device to which the task indication information is sent selects an area, it is not necessary to measure all task types, and the task delay or power consumption can be reduced.

[0051] In a possible implementation of the second aspect, each of the at least one task indication includes a reference signal for measurement.

[0052] Since each of the at least one task indication comprises a reference signal for measurement, a device receiving the task indication information indicating the at least one task indication can perform measurement on the at least one task indication to obtain a measurement result corresponding to the at least one task indication.

[0053] In a possible implementation of the second aspect, the at least one region comprises a first region and a second region, the at least one piece of task indication information comprises a first piece of task indication information sent in the first region and a second piece of task indication information sent in the second region, and the at least one first task indication indicated by the first piece of task indication information is of a different task type from the at least one second task indication indicated by the second piece of task indication information.

[0054] Since the at least one first task indication indicated by the first piece of task indication information sent in the first region is of a different task type from the at least one second task indication indicated by the second piece of task indication information sent in the second region, different regions can support different task types. The different task types supported by different regions can be effectively indicated to a device receiving the task indication information by the task indications indicated by the task indication information sent in different regions.

[0055] In a possible implementation of the second aspect, the at least one task indication is scrambled by an identity of a region sending a piece of task indication information indicating the at least one task indication.

[0056] Since the at least one task indication is scrambled by an identity of a region sending a piece of task indication information indicating the at least one task indication, that is, the task indication is scrambled by an identity of a region supporting a task type indicated by the task indication, the region supporting the task type can be determined according to the identity of the region used to scramble the task indication indicating the task type.

[0057] In a possible implementation of the second aspect, the at least one region comprises a first region and a second region, and time-frequency resources of one or more first task indications for a certain task type in the first region are the same as time-frequency resources of one or more second task indications for the same task type in the second region.

[0058] In a possible implementation of the second aspect, the at least one region comprises a first region and a second region, and time-frequency resources of one or more first task indications for a certain task type in the first region are different from time-frequency resources of one or more second task indications for the same task type in the second region.

[0059] Since the time-frequency resources of the one or more first task indications for a certain task type in the first region and the time-frequency resources of the one or more second task indications for the same task type in the second region can be the same or different, the time-frequency resources of the task indications for a certain task type can be flexibly configured.

[0060] In a possible implementation manner of the second aspect, the time-frequency resources of the one or more first task indications for the task type in the first region include time-frequency resources of one or more first reference signals for the task type in the first region, and the time-frequency resources of the one or more second task indications for the same task type in the second region include time-frequency resources of one or more second reference signals for the same task type in the second region.

[0061] Since the time-frequency resources of the one or more first reference signals for a certain task type in the first region and the time-frequency resources of the one or more second reference signals for the same task type in the second region can be the same or different, the time-frequency resources of the reference signals for a certain task type can be flexibly configured.

[0062] In a possible implementation manner of the second aspect, the at least one task indication is represented by at least one pattern of at least one task type.

[0063] Since the at least one task indication is represented by at least one pattern of at least one task type, the at least one task type can be easily read and learned.

[0064] In a possible implementation manner of the second aspect, different patterns are defined for different task types.

[0065] Since different patterns are defined for different task types, different patterns can be used to indicate different task types, and each task type can be determined according to its corresponding pattern, which provides an effective way to indicate the task types supported by each region.

[0066] In a possible implementation manner of the second aspect, the at least one task indication is configurable.

[0067] Since the at least one task indication is configurable, flexible configuration is achieved.

[0068] In a possible implementation manner of the second aspect, the different patterns are predefined in a specification and can be selected according to a current scenario.

[0069] Since different patterns are predefined in the specification and can be selected according to the current scene, transmission resources of pattern configuration can be saved, and the pattern can be flexibly selected according to the current scene.

[0070] In a possible implementation of the second aspect, the different patterns are broadcast, multicast or unicast through signaling.

[0071] In a possible implementation of the second aspect, the signaling is carried in radio resource control (RRC) signaling.

[0072] Since the different patterns are broadcast, multicast or unicast through signaling such as RRC signaling, the transmission of the patterns is more flexible.

[0073] In a possible implementation of the second aspect, different task types correspond to different task indications.

[0074] Since different task types correspond to different task indications, the task type indicated by the task indication can be easily known.

[0075] In a possible implementation of the second aspect, a message for a task type is scrambled with a task identity of the task type.

[0076] Since the message for a task type is scrambled with the task identity of the task type, the device to which the message is sent can easily know which task type the message corresponds to.

[0077] In a possible implementation of the second aspect, the at least one task indication belongs to at least one group, each of the at least one task indication belongs to one of the at least one group, each of the at least one group corresponds to a respective different task type, and includes one or more task indications indicating the respective different task type.

[0078] Since the task indications are grouped according to the task types, each task type can correspond to a group of one or more task indications, so that the task indication used to indicate the task type can be flexibly selected from the group according to the actual situation, and when multiple task indications are used to indicate the task type, the indication of the task type can be more reliable.

[0079] In a possible implementation of the second aspect, each of the at least one region is a cell, or each of the at least one region is a paging area.

[0080] The area can be a cell or a paging area, i.e. the method can be used for selecting a cell or a paging area, thereby enabling task-specific cell selection or task-specific paging area selection.

[0081] In a possible implementation form of the second aspect, the at least one piece of task indication information is transmitted by the central device.

[0082] In a third aspect, the present application provides a first apparatus comprising various means for performing the communication method according to the first aspect or any of the implementation forms of the first aspect.

[0083] In a fourth aspect, the present application provides a second apparatus comprising various means for performing the communication method according to the second aspect or any of the implementation forms of the second aspect.

[0084] In a fifth aspect, the present application provides a third apparatus comprising processing circuitry for performing the communication method according to the first aspect or any of the implementation forms of the first aspect.

[0085] In a sixth aspect, the present application provides a fourth apparatus comprising processing circuitry for performing the communication method according to the second aspect or any of the implementation forms of the second aspect.

[0086] In a seventh aspect, the present application provides a wireless communication system comprising at least one first apparatus according to the third aspect or any of the implementation forms of the third aspect or at least one third apparatus according to the fifth aspect; and at least one second apparatus according to the fourth aspect or any of the implementation forms of the fourth aspect or at least one fourth apparatus according to the sixth aspect.

[0087] In an eighth aspect, the present application provides a wireless communication system comprising first processing circuitry for performing the communication method according to the first aspect or any of the implementation forms of the first aspect; and second processing circuitry for performing the communication method according to the second aspect or any of the implementation forms of the second aspect.

[0088] In a ninth aspect, the present application provides a computer readable medium storing computer-executable instructions which, when executed by a processor, cause the processor to perform the communication method according to the first aspect or any of the implementation forms of the first aspect, or the second aspect or any of the implementation forms of the second aspect.

[0089] In a tenth aspect, the present application provides a computer program product, the computer program product comprising computer-executable instructions that, when executed by a processor, cause the processor to perform the communication method according to the first aspect or any implementation manner of the first aspect, or the second aspect or any implementation manner of the second aspect.

[0090] The present application provides a communication method, apparatus and system, the communication method comprising: obtaining at least one piece of task indication information transmitted in at least one area, each piece of the at least one piece of task indication information being transmitted in a corresponding area of the at least one area and indicating at least one task indication, each task indication indicating a task type supported by the corresponding area; and selecting an area from the at least one area according to a task type of interest and the at least one piece of task indication information. Therefore, only the task type supported by each area and the task type of interest are considered, and for selecting an area, measurement on all task types is not required, which can reduce task delay or power consumption. BRIEF DESCRIPTION OF DRAWINGS

[0091] The accompanying drawings, which are included to provide a further understanding of the present application and are incorporated in and constitute a part of this application, illustrate embodiments of the present application and together with the description serve to explain the principles of the present application. In the drawings:

[0092] Figure 1 is a simplified schematic diagram of a communication system provided by one or more example embodiments of the present application.

[0093] Figure 2 is a schematic diagram of an example communication system provided by one or more example embodiments of the present application.

[0094] Figure 3 is a schematic diagram of a basic component structure of a communication system provided by one or more example embodiments of the present application.

[0095] Figure 4 is a block diagram of a device in a communication system provided by one or more example embodiments of the present application.

[0096] Figure 5 is a schematic diagram of a semantic communication scenario provided by one or more example embodiments of the present application.

[0097] Figure 6 is a schematic diagram of a plurality of sensing devices in a semantic communication scenario provided by one or more example embodiments of the present application.

[0098] Figure 7 is a schematic diagram of interaction between devices in a semantic communication scenario provided by one or more example embodiments of the present application.

[0099] Figure 8is another diagram of interactions between devices in a semantic communication scenario provided by one or more example embodiments of the invention.

[0100] Figure 9 is a diagram of a communication method provided by one or more example embodiments of the invention.

[0101] Figure 10 is a diagram of time-frequency resources for semantic / task indication provided by one or more example embodiments of the invention.

[0102] Figure 11 is another diagram of interactions between devices in a semantic communication scenario provided by one or more example embodiments of the invention.

[0103] Figure 12 is another diagram of interactions between devices in a semantic communication scenario provided by one or more example embodiments of the invention.

[0104] Figure 13 is a diagram of implementing a thought chain provided by one or more example embodiments of the invention.

[0105] Figure 14 is another diagram of interactions between devices in a semantic communication scenario provided by one or more example embodiments of the invention.

[0106] Figure 15 is another diagram of interactions between devices in a semantic communication scenario provided by one or more example embodiments of the invention.

[0107] Figure 16 is a diagram of generating a query message.

[0108] Figure 17 is a diagram of reversing semantics.

[0109] Figure 18 is a diagram of tokenizing a query semantic into query tokens.

[0110] Figure 19 is a diagram of responding to query tokens.

[0111] Figure 20 is a diagram of scoring relevance using tokens.

[0112] Figure 21 is another diagram of responding to query tokens.

[0113] Figure 22 is a diagram of scoring relevance using semantics.

[0114] Figure 23 is another diagram of responding to query tokens.

[0115] Figure 24 is an illustration of scoring relevance using wordpieces converted from semantics.

[0116] Figure 25 is an illustration of generating query wordpieces.

[0117] Figure 26 is an illustration of generating query semantics.

[0118] Figure 27 is an illustration of responding to two queries using one common semantic model and two wordpiece models.

[0119] Figure 28 is an illustration of responding to two queries using one common semantic model and one common wordpiece model.

[0120] Figure 29 is another illustration of responding to two queries using two semantic models and two wordpiece models.

[0121] Figure 30 is another illustration of responding to two queries using two semantic models and one common wordpiece model.

[0122] Figure 31 is an illustration of responding to two query semantics using one common semantic model and two different wordpiece models.

[0123] Figure 32 is an illustration of responding to two query semantics using one common semantic model and one common wordpiece model.

[0124] Figure 33 is an illustration of responding to two query semantics using two semantic models and two wordpiece models.

[0125] Figure 34 is an illustration of responding to two query semantics using two semantic models and one wordpiece model.

[0126] Figure 35 is an illustration of responding to two query semantics using one semantic model but not using wordpiece models.

[0127] Figure 36 is an illustration of responding to two query semantics using two semantic models but not using wordpiece models.

[0128] Figure 37 is an illustration of processing two perceptual semantics independently.

[0129] Figure 38 is an illustration of processing one perceptual semantic independently but using two tasks.

[0130] Figure 39 is a structural schematic diagram of a first apparatus provided by one or more example embodiments of the present application.

[0131] Figure 40 is a structural schematic diagram of a second apparatus provided by one or more example embodiments of the present application. DETAILED DESCRIPTION

[0132] In the following description, reference is made to the accompanying drawings which form a part hereof, and which are shown by way of illustration of specific aspects of embodiments of the present application or aspects of embodiments of the present application that can be used by or with embodiments of the present application. It is to be understood that embodiments of the present application can be used in other aspects as well, and that the description below is intended to be illustrative only and not restrictive. Therefore, specific aspects of embodiments of the present application should not be construed as limiting the scope of the application, which is defined by the appended claims.

[0133] To assist understanding of the present application, examples of a wireless communication system and devices are described below.

[0134] Examples of communication systems and devices

[0135] The present application takes the interaction and processing procedures between at least one UE (i.e. a sensing device, also referred to as a sensing node, in Figure 1 , marked as ED), at least one BS (i.e. a central device) and at least one GPT device as illustrative examples. The exchanged information and protocol flows can also be used between other network nodes, for example, between ED 110 and TRP 170, between ED 110 and the core network, between ED 110 and ED 110, between TRP 170 and TRP 170, between TRP 170 and GPT device 180. The UE in the processes described by the present application can be replaced by the sensing node mentioned below. The BS in the processes described by the present application can be replaced by a sensing coordinator. The sensing coordinator is a node in the network that can assist sensing operations. These nodes can be independent nodes dedicated only to sensing operations, or other nodes that perform sensing operations in parallel with communication transmission (for example, the TRP 170, ED 110 or core network nodes shown). Figure 1

[0136] With reference to Figure 1 , a simplified schematic diagram of a communication system according to one or more example embodiments of the present application is provided as an illustrative example but without limitation. The communication system 100 (which can be a part of a larger communication system) includes a plurality of UEs 110, a plurality of TRPs 170, a core network 190 and a GPT device 180. Figure 1 ​The wireless system (e.g., a 5G or a 6G system) includes a wireless access network 120. The wireless access network 120 can be a next generation (e.g., a sixth generation (6G) or beyond) wireless access network or a legacy (e.g., 5G, 4G, 3G, or 2G) wireless access network. One or more communication electric devices (EDs) 110a, 110b, 110c, 110d, 110e, 110f, 110g, 110h, 110i, 110j (collectively referred to as 110) can be interconnected with each other and / or to one or more network nodes (170a, 170b, collectively referred to as 170) in the wireless access network 120. A core network 130 can be part of the communication system and can be dependent on or independent of the radio access technology used in the communication system 100. In addition, the communication system 100 includes a public switched telephone network (PSTN) 140, the Internet 150, and other networks 160.

[0137] Uplink messages / data transmitted between a central device (e.g., a network node 170) and a sensing device (e.g., an ED 110) can be carried in high layer signaling such as RRC signaling or MAC layer signaling. Alternatively, they can be carried in physical layer signaling such as UCI. Alternatively, they can be carried in a combination of high layer signaling and physical signaling. It should be noted that a message in the present invention can be replaced by information, which can be carried in one single message or in more than one single message. Downlink messages / data transmitted between a central device and an ED 110 can be carried in high layer signaling such as RRC signaling or MAC layer signaling. Alternatively, they can be carried in physical layer signaling such as UCI. Alternatively, they can be carried in a combination of high layer signaling and physical signaling. It should be noted that a message in the present invention can be replaced by information, which can be carried in one single message or in more than one single message.

[0138] Further, the communication system 100 comprises at least one GPT device 180. The GPT device 180 can be located within one or more network nodes 170. The GPT device 180 can be a standalone device connected to the network 170, e.g. an ED 110 connected to a network node 170 over a Uu interface. The GPT device 180 can be a device connected to a network node 170 over the core network 130. When the GPT device 180 is an ED, uplink messages / data sent between a central device (e.g. a network node 170) and the GPT device 180 can be carried in higher layer signaling such as RRC signaling or MAC layer signaling. Alternatively, they can be carried in physical layer signaling such as UCI. Alternatively, they can be carried in a combination of higher layer signaling and physical signaling. It should be noted that messages in the present invention can be replaced by information, which can be carried in one single message or in more than one single message. Downlink messages / data sent between a central device and the GPT device 180 can be carried in higher layer signaling such as RRC signaling or MAC layer signaling. Alternatively, they can be carried in physical layer signaling such as UCI. Alternatively, they can be carried in a combination of higher layer signaling and physical signaling. It should be noted that messages in the present invention can be replaced by information, which can be carried in one single message or in more than one single message.

[0139] Figure 2 is a schematic diagram of an example communication system provided by one or more example embodiments of the present invention, wherein, Figure 2 An example communication system 100 is shown. Generally, the communication system 100 is capable of enabling multiple wireless or wireline elements to communicate data and other content. The communication system 100 can be used to provide voice, data, video, signaling, and / or text content, among other content, through broadcast, multicast, and unicast, among other techniques. The communication system 100 can operate by sharing resources, such as a carrier frequency bandwidth, among its constituent elements. The communication system 100 can include a terrestrial communication system and / or a non-terrestrial communication system. The communication system 100 can provide a wide range of communication services and applications (e.g., earth monitoring, remote sensing, passive sensing and positioning, navigation and tracking, autonomous delivery and mobility, among others). The communication system 100 can provide high availability and robustness through joint operation of the terrestrial communication system and the non-terrestrial communication system. For example, integrating the non-terrestrial communication system (or components thereof) into the terrestrial communication system can enable a heterogeneous network comprising multiple tiers. The heterogeneous network can achieve better overall performance compared to conventional communication networks through efficient multi-link joint operation, more flexible function sharing, and faster physical layer link switching between the terrestrial network and the non-terrestrial network.

[0140] The terrestrial communication system and the non-terrestrial communication system can be considered as subsystems of a communication system. In Figure 2In the illustrated example, the communication system 100 includes electronic devices (EDs) 110a, 110b, 110c, 1 lOd (collectively referred to as EDs 110), radio access networks (RANs) 120a and 120b, a non-terrestrial communication network 120c, a core network 130, a public switched telephone network (PSTN) 140, the Internet 150, and other networks 160. The RANs 120a and 120b include respective base stations (BSs) 170a and 170b, which can generally be referred to as terrestrial transmit and receive points (T-TRPs) 170a and 170b. The non-terrestrial communication network 120c includes an access node 172, which can generally be referred to as a non-terrestrial transmit and receive point (NT-TRP) 172.

[0141] Alternatively or additionally, any of the EDs 110 can be configured to connect to, access, or communicate with any of the T-TRPs 170a and 170b, the NT-TRP 172, the Internet 150, the core network 130, the PSTN 140, the other networks 160, or any combination of the foregoing. In some examples, the ED 110a can communicate uplink and / or downlink transmissions with the T-TRP 170a over a terrestrial air interface 190a. In some examples, the EDs 110a, 110b, 110c, and 1 lOd can also communicate directly with one another over one or more sidelink air interfaces 190b. In some examples, the ED 1 lOd can communicate uplink and / or downlink transmissions with the NT-TRP 172 over a non-terrestrial air interface 190c.

[0142] The air interfaces 190a and 190b can use similar communication techniques, for example, any suitable wireless access technique. For example, the communication system 100 can implement one or more channel access methods in the air interfaces 190a and 190b, such as code division multiple access (CDMA), space division multiple access (SDMA), time division multiple access (TDMA), frequency division multiple access (FDMA), orthogonal FDMA (OFDMA), Direct Fourier Transform spread OFDMA (DFT-OFDMA), or single-carrier FDMA (SC-FDMA). The air interfaces 190a and 190b can utilize other multi-dimensional signal spaces that can include combinations of orthogonal and / or non-orthogonal dimensions.

[0143] The non-terrestrial air interface 190c can enable communication between the ED 110d and one or more NT-TRPs 172 through a wireless link or simply a link. For some examples, the link is a dedicated connection for unicast transmission, a connection for broadcast transmission, or a connection between a group of EDs 110 and one or more NT-TRPs 172 for groupcast transmission.

[0144] The RANs 120a and 120b communicate with the core network 130 to provide the EDs 110a, 110b, and 110c with access to various services, such as voice, data, and other services. The RANs 120a and 120b and / or the core network 130 can communicate with one or more other RANs (not shown) that can or can not be directly attached to the core network 130, and that can or can not utilize the same radio access technology(s) as the RANs 120a, 120b, or both. The core network 130 can also serve as a gateway for the RANs 120a and 120b; or the EDs 110a, 110b, and 110c; or both, to other networks (such as the PSTN 140, the Internet 150, and the other networks 160) by providing an interface with those networks. In addition, some or all of the EDs 110a, 110b, and 110c can include functionality for communicating with different wireless networks over different wireless links using different wireless technologies and / or protocols. The EDs 110a, 110b, and 110c can communicate with a service provider or switch (not shown) and with the Internet 150 through wired communication channels, rather than or in addition to wireless communication. The PSTN 140 can include a circuit-switched telephone network for providing plain old telephone service (POTS). The Internet 150 can include a network of computers and / or sub-networks (intranets) and incorporate Internet Protocol (IP), Transmission Control Protocol (TCP), User Datagram Protocol (UDP), and / or other protocols. The EDs 110a, 110b, and 110c can be multi-mode devices capable of operating according to multiple wireless access technologies and incorporate multiple transceivers needed to support those technologies.

[0145] Basic component structure

[0146] Figure 3 is a schematic diagram of the basic component structure of a communication system provided by one or more example embodiments of the present invention, wherein Figure 3Another example of an ED 110 and base stations 170a, 170b, and / or 170c is shown. The ED 110 is used to connect people, objects, machines, etc. The ED 110 can be widely used in various scenarios, such as cellular communication, device-to-device (D2D), vehicle to everything (V2X), peer-to-peer (P2P), machine-to-machine (M2M), machine-type communication (MTC), Internet of things (IOT), virtual reality (VR), augmented reality (AR), mixed reality (MR), metaverse, digital twin, industrial control, autonomous driving, telemedicine, smart grid, smart home, smart office, smart wearable device, smart transportation, smart city, unmanned aerial vehicle, robot, remote sensing, passive sensing, positioning, navigation and tracking, automatic distribution, mobility, etc.

[0147] Each ED 110 represents any suitable end user device for wireless operation, which can include these devices as (or can be referred to as): user equipment / device (UE), wireless transmit / receive unit (WTRU), mobile station, fixed or mobile subscriber unit, cellular telephone, station (STA), machine type communication (MTC) device, personal digital assistant (PDA), smartphone, laptop, computer, tablet, wireless sensor, consumer electronics, smartbook, vehicle, car, truck, bus, train, or IoT device, watch, head-mounted device, glasses, etc. wearable device, industrial device, or means of the above devices (e.g., a communication module, modem, or chip), etc. Future generations of ED 110 can be referred to using other terms. Each base station 170a and 170b is a T-TRP, which will be referred to as T-TRP 170 hereinafter. Also in Figure 3As shown in FIG. 1, the NT-TRPs are hereinafter referred to as NT-TRPs 172. Each ED 110 connected to the T-TRPs 170 and / or the NT-TRPs 172 can be dynamically or semi-statically turned on (i.e., established, activated, or enabled), turned off (i.e., released, deactivated, or disabled), and / or configured in response to one or more of connection availability and connection necessity.

[0148] The ED 110 includes a transmitter 201 and a receiver 203 coupled to one or more antennas 204. Only one antenna 204 is shown in the figure. One, some or all of the antennas 204 can also be panels. The transmitter 201 and receiver 203 can be, for example, integrated as a transceiver. The transceiver is used to modulate data or other content for transmission by at least one antenna 204 or a network interface controller (NIC). The transceiver is also used to demodulate data or other content received by the at least one antenna 204. Each transceiver includes any suitable structure for generating a signal for wireless or wired transmission and / or for processing a signal received via wireless or wired transmission. Each antenna 204 includes any suitable structure for transmitting and / or receiving wireless or wired signals.

[0149] The ED 110 includes at least one memory 208. The memory 208 stores instructions and data used, generated, or collected by the ED 110. For example, the memory 208 could store software

[0150] instructions or modules used to implement part or all of the functionality described herein and executed by one or more processing units (e.g., a processor 210). Each memory 208 includes any suitable volatile and / or non-volatile storage and retrieval devices. Any suitable type of memory can be used, such as random access memory (RAM), read only memory (ROM), hard disk, optical disk, subscriber identity module (SIM) card, memory stick, secure digital (SD) memory card, processor cache, etc. Figure 1 The ED 110 can also include one or more input / output devices (not shown) or interfaces (e.g., wired interfaces to the Internet 150). The input / output devices enable interaction with a user or other devices or systems. Each input / output device includes any suitable structure for providing information to or receiving information from a user, such as an audible or visual display, a keyboard, a mouse, or a microphone. The input / output devices also include any suitable structure for communicating with another device or system, such as an antenna or other wireless transmitter or receiver.

[0151] ED 110 includes a processor 210 for performing operations including operations related to preparing uplink transmissions to be sent to NT-TRPs 172 and / or T-TRPs 170, operations related to processing downlink transmissions received from NT-TRPs 172 and / or T-TRPs 170, and operations related to processing sidelink transmissions to and from another ED 110. The processing operations related to preparing uplink transmissions to be sent can include operations such as encoding, modulating, transmit beamforming, and generating symbols for transmission. The processing operations related to processing downlink transmissions can include operations such as receive beamforming, demodulating received symbols, and decoding received symbols. According to embodiments, receiver 203 can receive a downlink transmission (possibly using receive beamforming), and processor 210 can extract signaling (e.g., by detecting and / or decoding the signaling) from the downlink transmission. For example, the signaling can be a reference signal transmitted by NT-TRPs 172 and / or T-TRPs 170. In some embodiments, processor 210 implements transmit beamforming and / or receive beamforming according to an indication of a beam direction, e.g., beam angle information (BAI), received from T-TRPs 170. In some embodiments, processor 210 can perform operations related to network access (e.g., initial access) and / or downlink synchronization, e.g., operations related to detecting synchronization sequences, decoding and acquiring system information, etc. In some embodiments, processor 210 can perform channel estimation using a reference signal received from NT-TRPs 172 and / or T-TRPs 170, for example.

[0152] Although not shown, processor 210 can form part of transmitter 201 and / or part of receiver 203. Although not shown, memory 208 can form part of processor 210.

[0153] Processor 210, processing components in transmitter 201, and processing components in receiver 203 can be respectively implemented by the same or different one or more processors for executing instructions stored in memory (e.g., memory 208). Alternatively, some or all of processor 210, processing components in transmitter 201, and processing components in receiver 203 can be implemented using a special-purpose circuitry, such as an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a graphical processing unit (GPU), a Central Processing Unit (CPU), or a special-purpose computer.

[0154] In some implementations, the ED 110 can be a communication module, a modem, a chip or a chipset, or the like device (may also be referred to as a component), including the at least one processor 210, an interface, or at least one pin. In such a scenario, the transmitter 201 and the receiver 203 can be replaced by the interface or the at least one pin, where the interface or the at least one pin is used to connect the device (e.g., a chip) and another device (e.g., a chip, a memory, or a bus). Thus, sending information to the NT-TRP 172 and / or the T-TRP 170 and / or another ED 110 can be referred to as sending information to the interface or the at least one pin, or as sending information to the NT-TRP 172 and / or the T-TRP 170 and / or another ED 110 through the interface or the at least one pin, and receiving information from the NT-TRP 172 and / or the T-TRP 170 and / or another ED 110 can be referred to as receiving information from the interface or the at least one pin, or as receiving information from the NT-TRP 172 and / or the T-TRP 170 and / or another ED 110 through the interface or the at least one pin. The information can include control signaling and / or data.

[0155] In some implementations, the T-TRP 170 can be referred to by other names, such as a base station, a base transceiver station (BTS), a wireless base station, a network node, a network device, a network-side device, a transmission-reception node, a NodeB, an evolved NodeB (eNodeB or eNB), a Home eNodeB, a Generation NodeB (gNB), a transmission point (TP), a site controller, an access point (AP), a wireless router, a relay, a radio remote, a ground node, a ground network device, a ground base station, a base band unit (BBU), a remote radio unit (RRU), an active antenna unit (AAU), a remote radio head (RRH), a central unit (CU), a distributed unit (DU), a positioning node, or the like. The T-TRP 170 can be a macro base station, a pico base station, a relay node, a host node, or the like, or a combination thereof. The T-TRP 170 can refer to a device as described above, or to a device (e.g., a communication module, a modem, or a chip) in the device as described above.

[0156] In some embodiments, various portions of T-TRP 170 can be distributed. For example, some of the modules in T-TRP 170 can be remote from the device that houses the antennas 256 of T-TRP 170, and can be coupled to the device that houses the antennas 256 by a communication link (not shown), sometimes referred to as front-haul, such as common public radio interface (CPRI). Thus, in some embodiments, the term "T-TRP 170" can also refer to modules that perform the processing operations of ED 110 position determination, resource allocation (scheduling), message generation and encoding / decoding, etc. on the network side, which are not necessarily part of the device that houses the antennas 256 of T-TRP 170. These modules can also be coupled to other T-TRPs. In some embodiments, T-TRP 170 can actually be multiple T-TRPs that work together, e.g., by using coordinated multipoint transmission, to serve ED 110.

[0157] The T-TRP 170 includes at least one transmitter 252 and at least one receiver 254 coupled to one or more antennas 256. Only one antenna 256 is shown in the figure. One, some or all of the antennas 256 can also be panels. The transmitter 252 and receiver 254 can be integrated as a transceiver. The T-TRP 170 also includes a processor 260 for performing various operations, including operations related to preparing downlink transmissions to the ED 110, processing uplink transmissions received from the ED 110, preparing backhaul transmissions to the NT-TRP 172, and processing transmissions received from the NT-TRP 172 over the backhaul. Processing operations related to preparing a downlink transmission or a backhaul transmission can include operations such as encoding, modulation, precoding (e.g., multiple input multiple output (MIMO) precoding), transmit beamforming, and generating symbols for transmission. Processing operations related to processing received transmissions in the uplink or over the backhaul can include operations such as receive beamforming, demodulating received symbols, and decoding received symbols. The processor 260 can also perform operations related to network access (e.g., initial access) and / or downlink synchronization, such as generating content of a synchronization signal block (SSB), generating system information, etc. In some embodiments, the processor 260 also generates an indication of a beam direction, e.g., a BAI, which can be scheduled for transmission by the scheduler 253. The processor 260 performs other network-side processing operations described herein, e.g., determining a location of the ED 110, determining a location at which to deploy the NT-TRP 172, etc. In some embodiments, the processor 260 can generate signaling, e.g., to configure one or more parameters of the ED 110 and / or one or more parameters of the NT-TRP 172. Any signaling generated by the processor 260 is transmitted by the transmitter 252. It should be noted that “signaling” used herein can also be referred to as control signaling. Dynamic signaling can be transmitted in a control channel such as a physical downlink control channel (PDCCH), and static or semi-static higher layer signaling can be included in packets transmitted in a data channel such as a physical downlink shared channel (PDSCH).

[0158] The scheduler 253 can be coupled to the processor 260. The scheduler 253 can be included within the T-TRP 170 or can operate separately from the T-TRP 170. The scheduler 253 can schedule uplink, downlink, and / or backhaul transmissions, including issuing scheduling grants and / or configuring grant-free (“configured grant”) resources. The T-TRP 170 also includes memory 258 for storing information and data. The memory 258 stores instructions and data used, generated, or collected by the T-TRP 170. For example, the memory 258 can store software

[0159] Although not shown, the processor 260 can form part of the transmitter 252 and / or part of the receiver 254. Further, although not shown, the processor 260 can implement the scheduler 253. Although not shown, the memory 258 can form part of the processor 260.

[0160] The processor 260, the scheduler 253, processing components in the transmitter 252, and processing components in the receiver 254 can be respectively implemented by the same or different one or more processors that are used to execute instructions stored in a memory (e.g., the memory 258). Alternatively, some or all of the processor 260, the scheduler 253, processing components in the transmitter 252, and processing components in the receiver 254 can be implemented using FPGA, GPU, CPU, or ASIC, etc., special circuitry.

[0161] When the T-TRP 170 is an apparatus (also referred to as a component) in a device, a modem, a chip, or a chipset, etc., it includes at least one processor, an interface, or at least one pin. In this scenario, the transmitter 252 and the receiver 254 can be replaced by the interface or at least one pin, which is used to connect the apparatus (e.g., a chip) and another apparatus (e.g., a chip, a memory, or a bus). Thus, transmitting information to the NT-TRP 172 and / or the T-TRP 170 and / or the ED 110 can be referred to as transmitting information to the interface or at least one pin, and receiving information from the NT-TRP 172 and / or the T-TRP 170 and / or the ED 110 can be referred to as receiving information from the interface or at least one pin. The information can include control signaling and / or data.

[0162] Notably, while the NT-TRP 172 is exemplified as a drone, the NT-TRP 172 can be implemented using any suitable non-ground form, such as a high-altitude platform, a satellite, a high-altitude platform that is an international mobile telecommunications base station, and an unmanned flight vehicle, which are discussed below. Moreover, in some implementations, the NT-TRP 172 can go by other names, such as a non-ground node, a non-ground network device, or a non-ground base station. The NT-TRP 172 includes a transmitter 272 and a receiver 274 coupled to one or more antennas 280. Only one antenna 280 is shown in the figure. One, some, or all of the antennas can also be panels. The transmitter 272 and the receiver 274 can be integrated as a transceiver. The NT-TRP 172 also includes a processor 276 for performing various operations, including operations related to preparing downlink transmissions to the ED 110, processing uplink transmissions received from the ED 110, preparing backhaul transmissions to the T-TRP 170, and processing transmissions received from the T-TRP 170 over the backhaul. Processing operations related to preparing a downlink transmission or a backhaul transmission can include operations such as encoding, modulating, precoding (e.g., MIMO precoding), transmit beamforming, and generating symbols for transmission. Processing operations related to processing received transmissions in the uplink or over the backhaul can include operations such as receive beamforming, demodulating received symbols, and decoding received symbols. In some embodiments, the processor 276 implements transmit beamforming and / or receive beamforming in accordance with beam direction information (e.g., BAI) received from the T-TRP 170. In some embodiments, the processor 276 can generate signaling, such as for configuring one or more parameters of the ED 110. In some embodiments, the NT-TRP 172 implements physical layer processing but not higher layer functions such as functions of a medium access control (MAC) layer or a radio link control (RLC) layer. Since this is just one example, the NT-TRP 172 can generally implement higher layer functions in addition to physical layer processing.

[0163] The NT-TRP 172 also includes a memory 278 for storing information and data. Although not shown, the processor 276 can form part of the transmitter 272 and / or part of the receiver 274. Although not shown, the memory 278 can form part of the processor 276.

[0164] The processor 276, processing components in the transmitter 272, and processing components in the receiver 274 can be implemented by the same or different one or more processors that are used to execute instructions stored in a memory (e.g., the memory 278). Alternatively, some or all of the processor 276, processing components in the transmitter 272, and processing components in the receiver 274 can be implemented using programmed FPGAs, GPUs, CPUs, or ASICs, among other specialized circuits. In some embodiments, the NT-TRP 172 can actually be multiple NT-TRPs that work together, e.g., through coordinated multipoint transmission, to serve the ED 110.

[0165] When the NT-TRP 172 is a device (e.g., a communication module, modem, chip, or chip set) in an apparatus, at least one processor, interface, or at least one pin is included. In this scenario, the transmitter 272 and the receiver 257 can be replaced by an interface or at least one pin that is used to connect the device (e.g., a chip) and another device (e.g., a chip, memory, or bus). Thus, transmitting information to the T-TRP 170 and / or another NT-TRP 172 and / or the ED 110 can be referred to as transmitting information to the interface or at least one pin, and receiving information from the T-TRP 170 and / or another NT-TRP 172 and / or the ED 110 can be referred to as receiving information from the interface or at least one pin. The information can include control signaling and / or data.

[0166] It should be noted that “TRP” as used herein can refer to a T-TRP or an NT-TRP. A T-TRP can also be referred to as a terrestrial network TRP (TN TRP), and an NT-TRP can also be referred to as a non-terrestrial network TRP (NTN TRP).

[0167] The T-TRP 170, the NT-TRP 172, and / or the ED 110 can include other components, which for brevity, have been omitted.

[0168] Any or all of the EDs 110 and the BSs 170 can be sensing nodes in the system 100. A sensing node is a network entity that senses by transmitting and receiving sensing signals. Some sensing nodes are communication devices that simultaneously communicate and sense. However, it is also possible for some sensing nodes to not communicate, but rather to be dedicated to sensing. The sensing agent 174 is an example of a sensing node that is dedicated to sensing. Unlike the EDs 110 and the BSs 170, the sensing agent 174 does not transmit or receive communication signals. However, the sensing agent 174 can communicate configuration information, sensing information, signaling information, or other information within the communication system 100. The sensing agent 174 can communicate with the core network 130 to communicate information with the rest of the communication system 100. As an example, the sensing agent 174 can determine the location of the ED 110a and transmit that information to the base station 170a through the core network 130. Although only one sensing agent 174 is shown in Figure 2

[0169] A sensing node can combine sensing-based techniques with reference signal-based techniques to enhance UE pose determination. This type of sensing node can also be referred to as a sensing management function (SMF). In some networks, the SMF can also be referred to as a location management function (LMF). The SMF can be implemented as a physically separate entity located at the core network 130 that connects with multiple BSs 170. In other aspects of the application, the SMF can be implemented as a logical entity co-located within a BS 170 through logic executed by the processor 260.

[0170] Although not shown in Figure 3 , the GPT device 180 can be included, which has a similar structure as the ED 110, e.g., the GPT device 180 includes at least one processor, a transmitter, and a receiver.

[0171] Basic module structure

[0172] Figure 4 is a block diagram of a device in a communication system provided by one or more example embodiments of the application, in which, according to Figure 4 , one or more steps of the embodiment methods provided herein can be performed by corresponding units or modules. Figure 4 ​Units or modules in devices such as the ED 110, the T-TRP 170, the NT-TRP 172, or the GPT device 180 are shown. For example, a signal can be transmitted by a transmitting unit or a transmitting module. A signal can be received by a receiving unit or a receiving module. A signal can be processed by a processing unit or a processing module. Other steps can be performed by an artificial intelligence (AI) module or a machine learning (ML) module. The corresponding units or modules can be implemented using hardware, one or more components or devices executing software, or a combination thereof. For example, one or more of these units or modules can be an integrated circuit, such as a programmed FPGA, GPU, CPU, or ASIC. It will be understood that where modules are implemented using software for execution by a processor, such modules can be retrieved from storage as necessary, processed individually or together in a single or multiple instances by the processor, and the modules themselves can include instructions for further deployment and instantiation, as appropriate. Figure 3 The mentioned transmitter can be a specific implementation of a transmitting module. In conjunction with Figure 3 The mentioned receiver can be a specific implementation of a receiving module. In conjunction with Figure 3 The mentioned processor can be a specific implementation of a processing module.

[0173] Further details regarding the ED 110, the T-TRP 170, the NT-TRP 172, and the GPT device 180 are known to those skilled in the art. Therefore, these details are omitted here.

[0174] The details of the present application will be described in detail in the following description.

[0175] Figure 5 is a schematic diagram of a semantic communication scenario provided by one or more example embodiments of the present application.

[0176] In the present application, a wireless system is also referred to as a communication system, or a wireless communication system. Here, the wireless system comprises a plurality of devices, for example, the plurality of devices comprises at least one central device, a plurality of distributed sensing devices, and at least one GPT device (as described in the Figure 5

[0177] ​The GPT device is responsible for encoding or decoding the query message and the perception data. Specifically, it generates a query message containing one or more natural language goals for the center device; the center device semantizes the query message into a semantic vector, tokenizes the semantic vector into a goal semantic token (vector), and then broadcasts the goal token to the perception device. The perception device is triggered by receiving the goal semantic token, measures its perception data, and converts the perception data into a perception semantic token. The perception device compares the goal semantic token with the perception semantic token and scores the correlation between the goal semantic token and the perception semantic token, and only when the correlation score is higher than a threshold, the perception data is sent in the form of a semantic vector. The center device fuses the perception data into a semantic vector, and outputs the fused data to the GPT device, which will generate the next query message according to the fused input.

[0178] The center device can be a BS, such as a gNB or an eNB, or the center device can be an access point (AP).

[0179] The perception device is responsible for measuring and / or collecting local physical world data. It can be a perception UE, a perception device, an IoT device, a UE, a cell phone, a handset, or other devices. The perception device can be equipped with a perception gadget or component to measure the nearby local physical world data as perception data; the perception device encodes the perception data and sends it to the center device.

[0180] The GPT device can generate a series of query messages and receive fused perception messages from the center device. In the present invention, the GPT device can also be referred to as an AI agent device, a robot device, or an intelligent control device.

[0181] In some implementations, the perception device can be a UE, a cell phone, or a handset, assuming that any two perception devices are independent of each other; therefore, the perception device can be independently scheduled by the wireless system associated with the perception device; the perception data measured by the perception device can be an application level payload of the wireless system and protocol.

[0182] The above-mentioned scheme of scheduling the perception device is inefficient in terms of wireless bandwidth and energy consumption. For example, the perception device blindly sends its perception data to the center device all the time, regardless of whether the perception data is needed.

[0183] From a higher level perspective, it is better to wake up multiple sensing devices for measurement and transmission only when their sensing data will serve one or more targets; for example, when a generative pre-trained transformer (GPT) device such as a self-driving car can request information about obstacles in movement near itself, it is futile to always send irrelevant information to the self-driving car or send all moving obstacles near the car to the car when the car is parked at the roadside.

[0184] To avoid any possibility of losing information, the resources in the wireless system in the above implementation can be over-scheduled.

[0185] Figure 6 is a schematic diagram of multiple sensing devices in a semantic communication scenario provided by one or more example embodiments of the present invention.

[0186] Specifically, the multiple sensing devices here can be grouped or classified according to the type of sensing data. As shown in Figure 6 , a first group of sensing devices can measure a first type of sensing data (e.g., red, green, blue (RGB) images or videos), while a second group of sensing devices can measure a second type of sensing data (e.g., radio frequency (RF) point clouds or lidar point clouds).

[0187] Figure 7 is a schematic diagram of interaction between devices in a semantic communication scenario provided by one or more example embodiments of the present invention.

[0188] The central device actively requests or triggers the sensing devices to send their recent sensing data (as Figure 7 indicated in the middle). Accordingly, the sensing devices will send their sensing data.

[0189] The central device can send one or more first query messages to one or some sensing devices in one or more DL broadcast, groupcast or unicast channels, which can be in a physical broadcast channel, a shared channel or a dedicated channel.

[0190] After receiving the first query message, the sensing device decides whether to send its sensing data. Specifically, the sensing device decodes the first query message, measures its data, and decides whether to send its sensing data, which is called responding to the first query message. If the sensing device decides to respond to the first query message, the sensing device can encode / encapsulate the sensing data into a payload and then send it to the central device in one or more UL channels (which can be a physical UL shared channel or a dedicated UL channel).

[0191] After the central device of the wireless system receives all payloads from the sensing devices responding to the first query message, the central device can fuse all or part of the payloads into fused payloads. Optionally, the central device can input the fused payloads into GPT devices that can process them, and then generate the second query message.

[0192] The central device can send one or more second query messages to one or some sensing devices in one or more DL broadcast, groupcast or unicast channels.

[0193] The GPT devices send query messages to the central device to inform and configure the central device to schedule the time, manner, content of the sensing by the sensing devices, and select which sensing devices, and send their sensing data to the central device. The GPT devices can be implemented / located with the central device to achieve shorter latency, or the GPT devices can be implemented in a remote data center that the central device can access through the core network, or the GPT devices can be on other connected devices in the same wireless system as the central device. It should be noted that in the present application, the query messages (downlink messages) from the central device to the sensing devices can be carried in high layer signaling such as radio resource control (RRC) signaling or medium access control (MAC) layer signaling. Or, the query messages can be carried in physical layer signaling, e.g., downlink control information (DCI). Or, the query messages can be carried in a combination of high layer signaling and physical signaling. The same is true for other downlink messages / data sent from the central device to the sensing devices. Similarly, in the present application, for uplink messages / data, they can be carried in high layer signaling such as RRC signaling or MAC layer signaling. Or, they can be carried in physical layer signaling, e.g., uplink control information (UCI). Or, they can be carried in a combination of high layer signaling and physical signaling. It should be noted that messages in the present application can be replaced by information, which can be carried in one separate message, or in more than one separate message.

[0194] Figure 8 is another schematic diagram of the interaction between devices in a semantic communication scenario provided by one or more example embodiments of the present application.

[0195] As Figure 8As shown, the wireless system including the central device, the perception device and the GPT device can form a series of interactions, in which the GPT device generates a series of query messages for the perception device, the perception device collects and feeds back the perception data, and the central device fuses the perception data and inputs the perception data to the GPT device.

[0196] In some cases, some perception devices can actively send their perception data without receiving any query message from the central device. The perception devices sending the perception data can respond to some emergency queries, such as fire alarms or car accidents. In a sense, some query messages have been predefined and configured into the system by default.

[0197] Figure 9 is a schematic flowchart of a communication method provided by one or more example embodiments of the present application. The method can be implemented by a first device. Optionally, the first device can be a perception device or other device with similar functions (for example, the first device can be a chip), which is not limited herein. As shown, the method can include the following steps: Figure 9

[0198] S910: Obtain at least one piece of task indication information sent in at least one region, each piece of task indication information in the at least one piece of task indication information being sent in a corresponding region in the at least one region and indicating at least one task indication, each task indication indicating a task type supported by the corresponding region.

[0199] In an implementation manner, the first device such as the perception device can obtain one piece of task indication information from the central device, and the central device broadcasts the semantics / task indication of some specific task type (or query lexeme). The semantics / task indication can have two functions: being a task-specific indication, and also being used as a reference for measurement (for example, measuring signal quality). For example, each task indication in the at least one task indication includes a reference signal for measurement. Therefore, after obtaining one piece of task indication information indicating the at least one task indication, the at least one task indication can be measured to obtain a measurement result corresponding to the at least one task indication.

[0200] ​In an implementation, the at least one region includes a first region and a second region, the at least one piece of task indication information includes a first piece of task indication information sent in the first region and a second piece of task indication information sent in the second region, the at least one first task indication indicated by the first piece of task indication information indicates a different task type than the at least one second task indication indicated by the second piece of task indication information. Thus, different regions can support different task types, and the different task types supported by different regions can be effectively indicated by the task indications indicated by the pieces of task indication information sent in the different regions. After obtaining the pieces of task indication information sent in the different regions, the sensing device can learn that the different regions support different task types according to the pieces of task indication information.

[0201] Specifically, each of the at least one region can be a cell or a paging region, and different cells / paging regions can have or support different task types and broadcast corresponding semantics / task indications. Figure 10 is a schematic diagram of time-frequency resources for semantics / task indication provided by one or more example embodiments of the present application. As shown in Figure 10 Cell A / paging region A supports task types a, b, and c, while cell B / paging region B supports task types a, c, and d. Cell A / paging region A broadcasts reference signals or semantics / task indications of task types a, b, and c, while cell B / paging region B broadcasts reference signals or semantics / task indications of task types a, c, and d.

[0202] In a specific implementation, the at least one task indication is scrambled by an identity of a region sending a piece of task indication information indicating the at least one task indication, i.e., the task indication is scrambled by an identity of a region supporting a task type indicated by the task indication. In an example, a cell ID or a paging region ID can be used to scramble the broadcasted semantics / task indication. In this way, after obtaining the at least one piece of task indication information sent in the at least one cell / paging region, the sensing device can learn which cell / paging region supports the indicated task type.

[0203] In an implementation, the at least one region includes a first region and a second region, and the time-frequency resources of the one or more first task indications for a certain task type in the first region are the same as the time-frequency resources of the one or more second task indications for the same task type in the second region. In another implementation, the at least one region includes a first region and a second region, and the time-frequency resources of the one or more first task indications for a certain task type in the first region are different from the time-frequency resources of the one or more second task indications for the same task type in the second region. Since the time-frequency resources of the one or more first task indications for a certain task type in the first region can be the same as or different from the time-frequency resources of the one or more second task indications for the same task type in the second region, the time-frequency resources of the task indications for a certain task type can be flexibly configured.

[0204] In an implementation, the time-frequency resources of the one or more first task indications for the task type in the first region include the time-frequency resources of the one or more first reference signals for the task type in the first region, and the time-frequency resources of the one or more second task indications for the same task type in the second region include the time-frequency resources of the one or more second reference signals for the same task type in the second region. Thus, the time-frequency resources of the reference signals for a certain task type can be flexibly configured.

[0205] In an implementation, the at least one task indication can be represented by at least one pattern of at least one task type. For example, the pattern can be a sequence, and in some fields of the sequence, the task indications for the task type can be carried. Thus, after obtaining the task indication information indicating the at least one task indication, the at least one task type corresponding to the at least one task indication can be easily read and learned.

[0206] In an implementation, since different patterns can be defined for different semantics / task types, different patterns can be used to indicate different task types, and each task type can be easily determined according to its corresponding pattern, which provides an effective way to indicate the task types supported by each region.

[0207] The semantic / task indication is configurable. In one implementation, since at least one task indication is configurable, flexible configuration is achieved. In one example, the pattern can be predefined in the specification, selected in real time according to the scene, so that the transmission resource of the pattern configuration can be saved, and the pattern can be flexibly selected according to the current scene. In another example, the pattern can be signaled to the sensing device through some signaling messages (for example, in the radio resource control (RRC) signaling, or carried in some sequence) through the broadcast / multicast / unicast mode, so that the pattern transmission is more flexible.

[0208] Different types of tasks can have different semantics / task indications, so the type of task indicated by the task indication can be easily known. For example, the signaling can be scrambled by the semantic / task type ID, such as scrambling the message (configuration message or query message) of the task type by the task identification of the task type, so that after receiving the message, the type of the message can be easily known. In another example, all semantic / task indication sets can be divided into different subsets, different subsets are used for different semantics / tasks, for example, at least one task indication can belong to at least one group, each task indication in the at least one task indication belongs to one group in the at least one group, each group in the at least one group corresponds to a respective different task type, and includes one or more task indications indicating the respective different task type. Since each task type can correspond to a group of one or more task indications, the task indication used to indicate the task type can be flexibly selected from the group according to the actual situation, and when multiple task indications are used to indicate the task type, the indication of the task type can be more reliable.

[0209] S920: Selecting one area from the at least one area according to the task type of interest and the at least one piece of task indication information.

[0210] Figure 11 is another schematic flow chart of the communication method provided by one or more example embodiments of the present application. As shown in the figure, step S920 can include the following steps: Figure 11

[0211] S9201: Measuring the task type of interest in one or more areas in the at least one area to obtain one or more measurement results respectively corresponding to the one or more areas in the at least one area, and the corresponding piece of task indication information transmitted by the one or more areas in the at least one area indicates one or more task indications, and the one or more task indications indicate the task type of interest.

[0212] ​S9202: Select one region from one or more regions of the at least one region, wherein the value of the measurement result corresponding to the selected region is higher than the threshold.

[0213] For example, a sensing device can measure a task type of interest in one or more areas within at least one region (cell or paging area), obtaining one or more measurement results corresponding to each of those areas. A corresponding task indication message transmitted from each of those areas indicates one or more task indications, which in turn indicate the task type of interest. The sensing device can then select one area from the at least one area where the value of the measurement result corresponding to the selected area is higher than a threshold. Therefore, cell selection or paging area selection at the sensing device can comprehensively consider both task / semantic type and measurement results, unlike standards based on Reference Signal Received Power (RSRP). For example, because the measurement result for task m (the sensing device's task / target) is better, the sensing device can camp on cell A instead of cell B, which has a higher peak signal-to-noise ratio (PSNR). This ensures that the selected cell or paging area supports the task type of interest and has good signal quality. Furthermore, since only the task type of interest is measured, task latency or power consumption can be significantly reduced.

[0214] like Figure 11 As shown, before selecting a region from at least one region, the communication method may further include: S930: determining the type of task of interest based on the capabilities of the first device and / or the current state of the first device. For example, the sensing device may determine the type of task of interest based on the capabilities of the sensing device and / or the current state of the sensing device. For example, the current state may be the current location of the sensing device, the task being performed by the sensing device, or the power of the sensing device (e.g., when the sensing device runs out of power, it will not perform complex tasks). In this way, when selecting a region from at least one region, task types that are beyond the capabilities of the sensing device and / or task types that the sensing device does not support in the current state are not considered, and these task types are not measured, thereby reducing power consumption.

[0215] It should be noted that the sensing device does not need to measure all task / semantic types. It only measures task / semantic indications. This differs from traditional cell selection. By measuring only the semantic / task indications of interest / need, the task latency or power consumption of the sensing device can be significantly reduced. The sensing device selects the task / semantic type of interest based on its task / goal / current state, measures the corresponding semantic / task indications, and then camps on the selected cell or selects an appropriate paging area.

[0216] For low-latency scenarios or sensing devices with specific capabilities, a novel design is proposed to reduce task latency or power consumption. Task-specific / semantic-specific cell selection is defined. The sensing device detects and selects a cell or paging area only based on its specific task / semantic meaning. Using the communication method provided by this invention, a first device, such as a sensing device, acquires at least one task indication message transmitted in at least one area. Each of these task indication messages is transmitted in a corresponding area within the at least one area and indicates at least one task indication, each indicating a task type supported by the corresponding area. The sensing device can then select an area from the at least one area based on the task type of interest and the at least one task indication message. Therefore, by considering only the task types supported by each area and the task type of interest, it is not necessary to measure all task types for selecting an area, thus reducing task latency or power consumption. It should be noted that the above method is also applicable to cell reselection / paging area reselection.

[0217] The above combination Figures 9 to 11 The communication method of the present invention has been described from the perspective of a first device (e.g., a sensing device). The following will combine... Figure 12 The communication method of the present invention is described from the perspective of a second device (e.g., a central device).

[0218] Figure 12 This is another illustrative flowchart of a communication method provided in one or more exemplary embodiments of the present invention. The method can be implemented by a second device. Optionally, the second device can be a central device or other devices with similar functions (e.g., the second device can be a chip), and there are no limitations herein. Figure 12 As shown, the method may include the following steps:

[0219] S1210: Send at least one task instruction message in at least one area, wherein each task instruction message in the at least one area is sent and indicates at least one task instruction in the corresponding area of ​​the at least one area, and each task instruction indicates the task type supported by the corresponding area.

[0220] In an implementation, a second device such as a central device can send a piece of task indication information to a perception device, e.g., the central device can broadcast a semantic / task indication of some specific task type (or query token). The semantic / task indication can have two functions: be a task-specific indication, and also be used as a reference for measurement (e.g., measure signal quality). For example, each of the at least one task indication includes a reference signal for measurement. Thus, a perception device receiving the task indication information indicating the at least one task indication can measure the at least one task indication to obtain a measurement result corresponding to the at least one task indication.

[0221] In an implementation, the at least one region includes a first region and a second region, and the at least one piece of task indication information includes a first piece of task indication information sent in the first region and a second piece of task indication information sent in the second region, the at least one first task indication indicated by the first piece of task indication information indicates a different task type from the at least one second task indication indicated by the second piece of task indication information. In this way, different regions can support different task types, and the task indications indicated by the task indication information sent in different regions can effectively indicate the different task types supported by the different regions to the perception devices receiving the task indication information.

[0222] Specifically, each of the at least one region can be a cell or a paging region, and different cells / paging regions can have or support different task types and broadcast corresponding semantics / task indications. As shown in Figure 10 Cell A / paging region A supports task types a, b, and c, while cell B / paging region B supports task types a, c, and d. Cell A / paging region A broadcasts reference signals or semantics / task indications of task types a, b, and c, while cell B / paging region B broadcasts reference signals or semantics / task indications of task types a, c, and d.

[0223] In a specific implementation, the at least one task indication is scrambled by an identity of a region sending the piece of task indication information indicating the at least one task indication, i.e., the task indication is scrambled by an identity of a region supporting a task type indicated by the task indication. In an example, the broadcasted semantics / task indication can be scrambled by a cell ID or a paging region ID. Thus, the region supporting a task type can be determined according to the identity of the region used to scramble the task indication indicating the task type.

[0224] In an implementation, the at least one region includes a first region and a second region, and the time-frequency resources of the one or more first task indications for a certain task type in the first region are the same as the time-frequency resources of the one or more second task indications for the same task type in the second region. In another implementation, the at least one region includes a first region and a second region, and the time-frequency resources of the one or more first task indications for a certain task type in the first region are different from the time-frequency resources of the one or more second task indications for the same task type in the second region. Since the time-frequency resources of the one or more first task indications for a certain task type in the first region can be the same as or different from the time-frequency resources of the one or more second task indications for the same task type in the second region, the time-frequency resources of the task indications for a certain task type can be flexibly configured.

[0225] In an implementation, the time-frequency resources of the one or more first task indications for the task type in the first region include the time-frequency resources of the one or more first reference signals for the task type in the first region, and the time-frequency resources of the one or more second task indications for the same task type in the second region include the time-frequency resources of the one or more second reference signals for the same task type in the second region. Thus, the time-frequency resources of the reference signals for a certain task type can be flexibly configured.

[0226] In an implementation, the at least one task indication is represented by at least one pattern of at least one task type. For example, the pattern can be a sequence, and the task indications for the task type can be carried in some fields of the sequence. Thus, the at least one task type corresponding to the at least one task indication can be easily read and learned.

[0227] In an implementation, since different patterns can be defined for different semantics / task types, different patterns can be used to indicate different task types, and each task type can be easily determined according to its corresponding pattern, which provides an effective way to indicate the task types supported by each region.

[0228] The semantics / task indication is configurable. In an implementation, since the at least one task indication is configurable, flexible configuration is achieved. In one example, the pattern can be predefined in the specification, and selected in real time according to the scene, so that the transmission resources of the pattern configuration can be saved, and the pattern can be flexibly selected according to the current scene. In another example, the pattern can be signaled to the sensing device through some signaling messages (for example, in the Radio Resource Control (RRC) signaling, or carried in some sequence) in a manner of broadcast / multicast / unicast, so that the transmission of the pattern is more flexible.

[0229] Different types of tasks can have different semantics / task indications, so the task type indicated by the task indication can be easily known. For example, the signaling can be scrambled with semantics / task type IDs, such as scrambling the message (configuration message or query message) of the task type with the task identification of the task type, so that the perception device to which the message is sent can easily know which task type the message corresponds to after receiving the message. In another example, all semantics / task indications can be divided into different subsets, different subsets are used for different semantics / tasks, for example, at least one task indication belongs to at least one group, each of the at least one task indication belongs to one of the at least one group, each of the at least one group corresponds to a respective different task type, and includes one or more task indications indicating the respective different task type. Since each task type can correspond to a group of one or more task indications, the task indication used to indicate the task type can be flexibly selected from the group as needed, and the indication of the task type can be more reliable when multiple task indications are used to indicate the task type.

[0230] With the communication method provided by the application, the second device such as the center device can send at least one task indication information in at least one area, each of the at least one task indication information is sent in a corresponding area in the at least one area and indicates at least one task indication, and each task indication indicates a task type supported by the corresponding area. Since each task indication indicates a task type supported by the corresponding area, when the device to which the task indication information is sent selects an area, it is not necessary to measure all task types, which can reduce task delay or power consumption.

[0231] Figure 13 is a schematic diagram for implementing a thought chain provided by one or more example embodiments of the application, which shows how the thought chain is implemented through a generative AI model and embodied through a series of query messages in a possible implementation.

[0232] The GPT device can generate a series of query messages according to previous perception messages, wherein the previous perception messages are received and / or fused by the center device. The GPT device can infer one or more generative AI models. The generative AI model or one or more model infer deep neural network (DNN) outputs one or more query messages. The GPT device generates a series of query messages by interacting with a series of fused perception messages, called "thought chain", and the center device fuses the response perception data sent by the perception device into the series of fused perception messages, as shown in Figure 13 .

[0233] A query message generated by a GPT device can convey semantic goals, tasks, or purposes. For example, the query message "locate an oncoming pedestrian" explicitly sets a semantic goal for a sensing device, causing the sensing device to focus on nearby pedestrians and prevent the sensing device from being distracted by other things. Since the query message conveys one or more semantic goals, a query message sent by a central device to a sensing device can trigger goal-oriented sensing tasks at each responding sensing device that receives and responds to the query message. Note that a message can convey multiple goals. For example, the message "find a moving pedestrian wearing a white coat" conveys two semantic goals or tasks: a moving pedestrian and a pedestrian wearing a white coat.

[0234] Figure 14 is another diagram of interactions between devices in a semantic communication scenario provided by one or more embodiments of the present invention. In one possible implementation, as shown in Figure 14 , a central device can broadcast a series of query messages because individually scheduling sensing devices can be too costly or even prohibited in a wireless system that includes such a high density of sensing devices. Thus, once a sensing device receives a query message, the sensing device can wake up but have little idea whether its sensing data is sufficiently relevant to the goal conveyed by the query message. As a result, the sensing device can enable its sensing widget to sense its surrounding environment into sensing data and compare the sensing data to the query message. If the sensing device informs that the sensing data is sufficiently relevant to the query message, the sensing device encodes the sensing data and sends the sensing data to the central device (sensing device #1 in Figure 14 ). Otherwise, the sensing device can not respond to the query message at all (sensing device #2 in Figure 14 ). In this sense, the wireless system does not schedule individual sensing devices but schedules a common task in a collection of sensing devices. Figure 15 is another diagram of interactions between devices in a semantic communication scenario provided by one or more embodiments of the present invention. In one possible implementation, as shown in Figure 15 , a central device can receive multiple sensing data from some or all sensing devices that respond to a query message at the end of a predefined response time interval. The central device can fuse all sensing data into one sensing message and input the sensing message to a GPT device, which will generate a next query message according to the sensing message, as shown in Figure 15 . Because only those sensing devices that respond to the query message will send sensing data, a large amount of wireless resources can be saved compared to a one-to-one scheduling algorithm.

[0235] Figure 16is a schematic diagram of generating a query message, which shows that in one possible implementation, the GPT device generates a query message using a generative AI model, and then translates the query message into query semantics using a semanticization model. Figure 17 is a schematic diagram of reversing semantics, which shows that in one possible implementation, semantics are reversible, meaning that if there is a de-semanticization model, the query message can be recovered from the query semantics.

[0236] The sequence of query messages generated by the GPT device and broadcast by the central device are in natural language, i.e., human-readable. The GPT device can use a large language model (LLM) to reason on the fused perception message (also in natural language) input to generate new query messages. The LLM model can be a “standard” base model, such as a transformer, or a “customized” model built for a narrow vocabulary and specific scenario. For example, a customized LLM for handling Industry 4.0 or a customized LLM for handling wireless communication signaling and protocols. The GPT device can change, update, shrink, enlarge, replace one or more of its LLMs at any time as needed. It should be noted that broadcasting, multicasting, or unicasting can be implemented.

[0237] The query messages generated by the GPT device are in natural language. Due to the randomness of generation, two different query messages can convey very similar semantic goal(s). For example, “find pedestrian” and “locate walking person” can have the same semantic goal. Therefore, the GPT device can semanticize the query message into query semantics, referred to as “embedding”, “semanticizing”, “encoding”, “natural language to machine translation”, etc. The GPT device can translate the query message into query semantics, which can include vectors, matrices, or scalar tensors. The translation can be implemented by a deep neural network or other classical functions. The query semantics can retain all the key semantic goals conveyed by the query message, so that the query semantics can be properly translated (de-semanticized) back to the query message. Optionally, the GPT device can send the query semantics to the central device instead of the query message, as shown in Figure 16 It should be noted that if all LLMs output in a common natural language (e.g., English), these LLMs are referred to as being aligned in natural language; in this way, whatever LLM is used, it can be seamlessly connected to the GPT device and work normally in the wireless system.

[0238] Figure 18 is a schematic diagram of tokenizing query semantics into query tokens, which shows that in one possible implementation, how the GPT device tokenizes the query semantics into query tokens.

[0239] In an implementation, the center device can also tokenizes the query semantics into query tokens. Query tokens are fixed length semantics, but include scalar vectors, which are more convenient for transmission and comparison purposes. The wireless system can pre-specify multiple lengths for query tokens. Thus, when the center device tokenizes the query semantics, it can choose an appropriate token length according to the size range of the query semantics. Tokenization can be a very strict function to prevent the perception devices from recovering the complete query message from the query tokens. Tokenization can provide a certain privacy protection for the query message. Tokenization can be implemented through a deep neural network or other classical functions, as shown in Figure 18 .

[0240] Optionally, the center device receives the query semantics from the GPT device, and then the center device converts the query semantics into fixed length query tokens; the center device can broadcast the query tokens of this length to all perception devices; the center device can save the query semantics in its own memory or storage device to check the feedback perception data.

[0241] Figure 19 is a schematic diagram of responding to query tokens, which shows how the perception devices respond to query tokens in one possible implementation. Figure 20 is a schematic diagram of scoring relevance using tokens, which shows how the perception devices score relevance using tokens in one possible implementation. Figure 21 is another schematic diagram of responding to query tokens, which shows how the perception devices respond to query tokens in one possible implementation. Figure 22 is a schematic diagram of scoring relevance using semantics, which shows how the perception devices score relevance using semantics in one possible implementation. Figure 23 is another schematic diagram of responding to query tokens, which shows how the perception devices respond to query tokens in one possible implementation. Figure 24 is a schematic diagram of scoring relevance using tokens converted from semantics, which shows how the perception devices score relevance using tokens converted from semantics in one possible implementation.

[0242] The perception device can compare its perception data with the query message; the perception device is woken up upon receiving the query token (its length or its length indication) so that its perception widget can measure the nearby physical environment as perception data; the perception device can be equipped with one or more LLMs as semanticization models, input the perception data into the semanticization models to output perception semantics; optionally, the perception device can select a suitable length and format of the perception semantics; the perception device can continue to tokenize the perception semantics into perception tokens of the same length as the query token that the perception device has received; the perception device compares the query message with the perception data or scores the relevance between the query message and the perception data according to the content that has been received.

[0243] Alternative #1 (Query Token) Figure 19 and Figure 20 ): The perception device receives a query token and a scoring function; compare the query token with the perception token and score the relevance between the query token and the perception token; if the relevance score is greater than or equal to a predefined threshold, the perception device will tell that the perception data is sufficiently relevant to the query message from the center device.

[0244] Alternative #2 (Query Semantics) Figure 21 and Figure 22 ): The perception device receives a query semantics and a scoring function; if the size and format of the query semantics and the perception semantics are similar, compare the query semantics with the perception semantics and score the relevance between the query semantics and the perception semantics; if the relevance score is greater than or equal to a predefined threshold, the perception device will tell that the perception data is sufficiently relevant to the query message from the center device.

[0245] Alternative #3 (Query Semantics) Figure 23 and Figure 24 ): The perception device receives a query semantics and a scoring function; first convert the query semantics into query tokens through a local tokenization model; compare the query token with the perception token and score the relevance between the query token and the perception token; if the relevance score is greater than or equal to a predefined threshold, the perception device will tell that the perception data is sufficiently relevant to the query message from the center device.

[0246] If the relevance score is greater than or equal to a predefined threshold, the perception device can send information including the perception data and the optional relevance score to the center device. Here are some alternatives for the content in the sent information:

[0247] Alternative #1: Raw perception data

[0248] Alternative #2: Perception semantics

[0249] Alternative #3: Semi-raw perception data (e.g., exact value or number) + perception semantics

[0250] Alternative Option #4: Raw Perception Data + Relevance Score

[0251] Alternative Option #5: Perceptual Semantics + Relevance Score

[0252] Alternative #6: Semi-raw perceptual data (e.g., precise values ​​or numbers) + perceptual semantics + relevance score.

[0253] The sensing device may be equipped with one or more semantic models to generate perceptual semantics from perceptual (raw) data, may be equipped with a lexicalization model to generate perceptual lexicals from perceptual semantics, and may be configured with a scoring function. Unlike GPT devices, the LLM, lexicalization model, and scoring function that the sensing device may use are configured by a central device. The central device may configure a common LLM and / or lexicalization model and scoring function from the beginning or at runtime and inform the sensing device.

[0254] Multiple sensing devices of one or more types can simultaneously serve one or more tasks; sensing devices can be triggered once in an effective manner to serve as many tasks as possible.

[0255] A wireless system may include two GPT devices, or a single GPT device capable of performing two independent tasks; in the following disclosure, two GPT devices are used as an example. Two GPT devices can be easily expanded into a single GPT device performing two independent tasks.

[0256] Although the two GPT devices have their own independent tasks, they may trigger the same sensing devices simultaneously; for example, an autonomous vehicle GPT device and a traffic light GPT device may trigger the same roadside camera sensing device. However, although the same sensing device may be triggered by the two GPT devices at the same time interval, the query message from the first GPT device may be different from the query message from the second GPT device; for example, the autonomous vehicle GPT device may broadcast a query message about "moving obstacles," while the traffic light GPT device may broadcast a query message about "traffic density." The two may be related to some extent but not similar.

[0257] Figure 25 This is a schematic diagram illustrating how a GPT device generates query terms in one possible implementation. Figure 26 This is a schematic diagram illustrating how a GPT device generates query semantics in one possible implementation.

[0258] The first GPT device generates the first query semantics against the central device, and the second GPT device generates the second query semantics against the central device. There are two options, as shown below:

[0259] Alternative #1: As shown in Figure 25 , the central device can tokenizes the first query message into first query tokens and the second query message into second query tokens; the central device can use a first tokenization model to tokenize the first query message and a second tokenization model to tokenize the second query message, or the central device can use a common tokenization model to tokenize the first query message and the second query message; then the central device can broadcast in the DL channel in a multiplexed manner the first query tokens, the length of the first tokens, the first scoring function related to the first tokens and the first threshold related to the first scoring function, and the second query tokens, the length of the second tokens, the second scoring function related to the second tokens and the second threshold related to the second scoring function.

[0260] Alternative #2: As shown in Figure 26 , the central device can not tokenize, the central device can broadcast in the DL channel in a multiplexed manner the first query semantics, the length and format of the first semantics, the first scoring function related to the first semantics and the first threshold related to the first scoring function, and the second query message, the length of the second message, the second scoring function related to the second message and the second threshold related to the second scoring function.

[0261] Figure 27 is a diagram of responding to two queries using one common semantic model and two tokenization models, which shows how, in one possible implementation, a perception device responds to two queries using one common semantic model and two tokenization models. Figure 28 is a diagram of responding to two queries using one common semantic model and one common tokenization model, which shows how, in one possible implementation, a perception device responds to two queries using one common semantic model and one common tokenization model. Figure 29 is another diagram of responding to two queries using two semantic models and two tokenization models, which shows how, in one possible implementation, a perception device responds to two queries using two semantic models and two tokenization models. Figure 30 is another diagram of responding to two queries using two semantic models and one common tokenization model, which shows how, in one possible implementation, a perception device responds to two queries using two semantic models and one common tokenization model.

[0262] The perception device can receive the first query tokens and the second query tokens, wake up to cause its perception widgets to perceive the physical world around itself as perception data. There are two options, as follows:

[0263] Alternative 1: The perception device can convert the perception data into a common perception semantics through one or more LLMs; the perception device can then tokenizes the perception semantics into a first perception token according to the length of the first query token, and tokenizes the perception semantics into a second perception token according to the length of the second query token; wherein the perception device can use a first tokenization model to tokenize the perception semantics into the first perception token, and use a second tokenization model to tokenize the perception semantics into the second perception token (as shown in Figure 27 ), or can use a common tokenization model to tokenize the perception semantics into the first perception token and the second perception token (as shown in Figure 28 ); the perception device can score the relevance between the first query token and the first perception token, and the relevance between the second query token and the second perception token; if the first relevance score is greater than or equal to a first threshold, the perception device can inform whether the perception data provides sufficient relevance to the first query token, and if the second relevance score is greater than or equal to a second threshold, the perception device can inform whether the perception data provides sufficient relevance to the second query token; if it is determined that the first relevance score is high enough, the perception device can send at least one of the perception data, the perception semantics, or the first relevance score; if it is determined that the second relevance score is high enough, the perception device can send at least one of the perception data, the perception semantics, or the second relevance score.

[0264] Alternative #2: As shown in Figure 28 , the perception device can convert the perception data into a first perception semantics through one or more LLMs, and convert the same perception data into a second perception semantics through one or more LLMs; the perception device can then tokenize the first perception semantics into a first perception token according to the length of the first query token, and tokenize the second perception semantics into a second perception token according to the length of the second query token; wherein the perception device can use a first tokenization model to tokenize the first perception semantics into the first perception token, and use a second tokenization model to tokenize the second perception semantics into the second perception token (as shown in Figure 29 ), or can use a common tokenization model to tokenize the perception semantics into the first perception token and the second perception token (as shown in Figure 30The perception device can score the relevance between the first query token and the first perceived token and the relevance between the second query token and the second perceived token; the perception device can inform whether the perception data provides sufficient relevance to the first query token if the first relevance score is greater than or equal to a first threshold and whether the perception data provides sufficient relevance to the second query token if the second relevance score is greater than or equal to a second threshold; the perception device can send at least one of the perception data, the first perceived semantics, or the first relevance score if it is determined that the first relevance score is sufficiently high; the perception device can send at least one of the perception data, the second perceived semantics, or the second relevance score if it is determined that the second relevance score is sufficiently high.

[0265] Figure 31 is a diagram of responding to two query semantics using one common semanticization model and two different tokenization models, showing how, in one possible implementation, a perception device can respond to two query semantics using one common semanticization model and two different tokenization models. Figure 32 is a diagram of responding to two query semantics using one common semanticization model and one common tokenization model, showing how, in one possible implementation, a perception device can respond to two query semantics using one common semanticization model and one common tokenization model. Figure 33 is a diagram of responding to two query semantics using two semanticization models and two tokenization models, showing how, in one possible implementation, a perception device can respond to two query semantics using two semanticization models and two tokenization models. Figure 34 is a diagram of responding to two query semantics using two semanticization models and one tokenization model, showing how, in one possible implementation, a perception device can respond to two query semantics using two semanticization models and one tokenization model. Figure 35 is a diagram of responding to two query semantics using one semanticization model but not using tokenization models, showing how, in one possible implementation, a perception device can respond to two query semantics using one semanticization model but not using tokenization models. Figure 36 is a diagram of responding to two query semantics using two semanticization models but not using tokenization models, showing how, in one possible implementation, a perception device can respond to two query semantics using two semanticization models but not using tokenization models.

[0266] The perception device can receive a first query semantics and a second query semantics, wake up to cause its perception widget to perceive the physical world around itself as perception data. There are several options, as follows:

[0267] Alternative #1: The perception device can convert the perception data into a common perception semantics through one or more LLMs; the perception device can then tokenizes the perception semantics into a first perception token and tokenizes the first query semantics into a first query token, both tokens having a same first length determined by the perception device, while the perception device can tokenizes the perception semantics into a second perception token and tokenizes the second query semantics into a second query token, both tokens having a same second length determined by the perception device, wherein the perception device can use a first tokenization model to tokenize the perception semantics into the first perception token and use a second tokenization model to tokenize the perception semantics into the second perception token ( Figure 31 ), or can use a common tokenization model to tokenize the perception semantics into both the first perception token and the second perception token ( Figure 32 ); the perception device can score a relevance between the first query token and the first perception token and a relevance between the second query token and the second perception token; the perception device can inform whether the perception data provides sufficient relevance to the first query token if the first relevance score is greater than or equal to a first threshold, and can inform whether the perception data provides sufficient relevance to the second query token if the second relevance score is greater than or equal to a second threshold; the perception device can send at least one of the perception data, the perception semantics, or the first relevance score if it is determined that the first relevance score is sufficiently high, and can send at least one of the perception data, the perception semantics, or the second relevance score if it is determined that the second relevance score is sufficiently high.

[0268] Alternative #2: The perception device can convert the perception data into a first perception semantics through one or more LLMs and convert the same perception data into a second perception semantics through one or more LLMs; the perception device tokenizes the first perception semantics into a first perception token and tokenizes the first query semantics into a first query token, both tokens having a same first length determined by the perception device, while the perception device can tokenizes the second perception semantics into a second perception token and tokenizes the second query semantics into a second query token, both tokens having a same second length determined by the perception device, wherein the perception device can use a first tokenization model to tokenize the first perception semantics into the first perception token and use a second tokenization model to tokenize the second perception semantics into the second perception token ( Figure 33 ), or can use a common tokenization model to tokenize both the first and second perception semantics into the first perception token and the second perception token ( Figure 34); the perception device can score a relevance between the first query token and the first perception token and a relevance between the second query token and the second perception token; the perception device can inform whether the perception data provides sufficient relevance to the first query token if the first relevance score is greater than or equal to a first threshold, and whether the perception data provides sufficient relevance to the second query token if the second relevance score is greater than or equal to a second threshold; the perception device can send at least one of the perception data, the first perception semantics, or the first relevance score if the first relevance score is determined to be sufficiently high, and at least one of the perception data, the second perception semantics, or the second relevance score if the second relevance score is determined to be sufficiently high.

[0269] Alternative #3 (Perception device converts perception data to a common perception semantics using one or more LLMs): Figure 35 ); the perception device can score a relevance between the first query semantics and the perception semantics and a relevance between the second query semantics and the perception semantics; the perception device can inform whether the perception data provides sufficient relevance to the first query semantics if the first relevance score is greater than or equal to a first threshold, and whether the perception data provides sufficient relevance to the second query semantics if the second relevance score is greater than or equal to a second threshold; the perception device can send at least one of the perception data, the perception semantics, or the first relevance score if the first relevance score is determined to be sufficiently high, and at least one of the perception data, the perception semantics, or the second relevance score if the second relevance score is determined to be sufficiently high.

[0270] Alternative #4 (Perception device converts perception data to first perception semantics using one or more LLMs, and converts the same perception data to second perception semantics using one or more LLMs): Figure 36 ); the perception device can score a relevance between the first query semantics and the first perception semantics and a relevance between the second query semantics and the second perception semantics; the perception device can inform whether the perception data provides sufficient relevance to the first query semantics if the first relevance score is greater than or equal to a first threshold, and whether the perception data provides sufficient relevance to the second query semantics if the second relevance score is greater than or equal to a second threshold; the perception device can send at least one of the perception data, the first perception semantics, or the first relevance score if the first relevance score is determined to be sufficiently high, and at least one of the perception data, the second perception semantics, or the second relevance score if the second relevance score is determined to be sufficiently high.

[0271] Figure 37is a schematic diagram of independently processing two perception semantics, which shows how the center device independently processes two perception semantics in a possible implementation.

[0272] If the center device receives multiple first perception semantics plus first correlation scores and multiple second perception semantics plus second correlation scores, the center device can fuse the first perception semantics into first fused perception semantics according to the first correlation scores of the first perception semantics, and the center device can fuse the second perception semantics into second fused perception semantics according to the second correlation scores of the second perception semantics; the center device can score the first fused perception semantics by measuring the correlation between the first fused perception semantics and the first query semantics, and score the second fused perception semantics by measuring the correlation between the second fused perception semantics and the second query semantics; the center device can send the first fused perception semantics with the first correlation score to the first GPT device, and send the second fused perception semantics with the second correlation score to the second GPT device, as shown in Figure 37 .

[0273] Figure 38 is a schematic diagram of independently processing one perception semantic but using two tasks, which shows how the center device independently processes one perception semantic but uses two tasks in a possible implementation.

[0274] If the center device receives multiple perception semantics plus first correlation scores and second correlation scores, the center device can fuse the perception semantics into first fused perception semantics according to the first correlation scores of the perception semantics, and the center device can fuse the second perception semantics into second fused perception semantics according to the second correlation scores of the second perception semantics; the center device can score the first fused perception semantics by measuring the correlation between the first fused perception semantics and the first query semantics, and score the second fused perception semantics by measuring the correlation between the second fused perception semantics and the second query semantics; the center device can send the first fused perception semantics with the first correlation score to the first GPT device, and send the second fused perception semantics with the second correlation score to the second GPT device, as shown in Figure 38 .

[0275] The first GPT device can receive the first fused perception semantics and the first correlation score related to the first query semantics; the first GPT device can de-semanticize the first fused perception semantics into a first perception message; the first GPT device can input the first perception message into the LLM for inference to generate a next first query message; optionally, the first GPT device can input the first perception message plus the first correlation score into the LLM.

[0276] The second GPT device can receive the second fused perceived semantics and a second relevance score related to the second query semantics; the second GPT device can de-semanticize the second fused perceived semantics into a second perceived message; the second GPT device can input the second perceived message into the LLM for inference to generate a next second query message; optionally, the second GPT device can input the second perceived message plus the second relevance score into the LLM.

[0277] Next, a product example related to the semantic communication method will be described.

[0278] Figure 39 is a structural diagram of a first device 3900 provided by one or more example embodiments of the present application.

[0279] As shown in Figure 39 , the first device 3900 can include:

[0280] The acquisition module 3910 is configured to acquire at least one piece of task indication information sent in at least one region, each piece of task indication information in the at least one piece of task indication information being sent in a corresponding region in the at least one region and indicating at least one task indication, each task indication indicating a task type supported by the corresponding region.

[0281] The selection module 3920 is configured to select a region from the at least one region according to a task type of interest and the at least one piece of task indication information.

[0282] In a possible implementation, each task indication in the at least one task indication includes a reference signal for measurement.

[0283] In a possible implementation, the first device further includes a determination module 3930 configured to determine the task type of interest according to a capability of the first device and / or a current state of the first device.

[0284] In a possible implementation, the selection module 3920 is configured to:

[0285] measure the task type of interest in one or more regions of the at least one region to obtain one or more measurement results respectively corresponding to the one or more regions of the at least one region, the corresponding piece of task indication information sent in the one or more regions of the at least one region indicating one or more task indications, the one or more task indications indicating the task type of interest;

[0286] select a region from the one or more regions of the at least one region, a value of a measurement result corresponding to the selected region being higher than a threshold value.

[0287] In a possible implementation, the at least one region includes a first region and a second region, the at least one piece of task indication information includes a first piece of task indication information sent in the first region and a second piece of task indication information sent in the second region, and the at least one first task indication indicated by the first piece of task indication information indicates a different task type from the at least one second task indication indicated by the second piece of task indication information.

[0288] In a possible implementation, the at least one task indication is scrambled by an identity of a region sending a piece of task indication information indicating the at least one task indication.

[0289] In a possible implementation, the at least one region includes a first region and a second region, and time-frequency resources of one or more first task indications for a certain task type in the first region are the same as time-frequency resources of one or more second task indications for the same task type in the second region.

[0290] In a possible implementation, the at least one region includes a first region and a second region, and time-frequency resources of one or more first task indications for a certain task type in the first region are different from time-frequency resources of one or more second task indications for the same task type in the second region.

[0291] In a possible implementation, the time-frequency resources of one or more first task indications for the task type in the first region include time-frequency resources of one or more first reference signals for the task type in the first region, and the time-frequency resources of one or more second task indications for the same task type in the second region include time-frequency resources of one or more second reference signals for the same task type in the second region.

[0292] In a possible implementation, the at least one task indication is represented by at least one pattern of at least one task type.

[0293] In a possible implementation, different patterns are defined for different task types.

[0294] In a possible implementation, the at least one task indication is configurable.

[0295] In a possible implementation, the different patterns are predefined in a specification and can be selected according to a current scenario.

[0296] In a possible implementation, the different patterns are broadcast, multicast, or unicast through signaling.

[0297] In a possible implementation, the signaling is carried in radio resource control (RRC) signaling.

[0298] In a possible implementation, different task types correspond to different task indications.

[0299] In a possible implementation, the message for the task type is scrambled with a task identity of the task type.

[0300] In a possible implementation, the at least one task indication belongs to at least one group, each of the at least one task indication belongs to one of the at least one group, each of the at least one group corresponds to a respective different task type, and comprises one or more task indications indicating the respective different task type.

[0301] In a possible implementation, each of the at least one area is a cell, or each of the at least one area is a paging area.

[0302] In a possible implementation, the first apparatus is a sensing apparatus.

[0303] The first apparatus can be applied to the above first device described in the above possible method implementation, for example, the sensing device. Those skilled in the art should understand that, in combination with the related description of the communication method in these possible implementations of the present application, the related description of the above modules in these possible implementations of the present application can be understood. The technical effects achieved by the above first apparatus are similar to those achieved by the above possible method implementation, which will not be repeated here.

[0304] Figure 40 FIG. 4 is a structural schematic diagram of a second apparatus 4000 provided by one or more example embodiments of the present application.

[0305] As shown in FIG. 4, the second apparatus 4000 can include: Figure 40 A sending module 4010 configured to send at least one piece of task indication information in at least one area, each piece of the at least one piece of task indication information being sent in a respective area of the at least one area and indicating at least one task indication, each task indication indicating a task type supported by the respective area.

[0306] In a possible implementation, each of the at least one task indication comprises a reference signal for measurement.

[0307]

[0308] ​In a possible implementation, the at least one region includes a first region and a second region, the at least one piece of task indication information includes a first piece of task indication information sent in the first region and a second piece of task indication information sent in the second region, and the at least one first task indication indicated by the first piece of task indication information indicates a different task type from the at least one second task indication indicated by the second piece of task indication information.

[0309] In a possible implementation, the at least one task indication is scrambled by an identity of a region sending a piece of task indication information indicating the at least one task indication.

[0310] In a possible implementation, the at least one region includes a first region and a second region, and time-frequency resources of one or more first task indications for a certain task type in the first region are the same as time-frequency resources of one or more second task indications for the same task type in the second region.

[0311] In a possible implementation, the at least one region includes a first region and a second region, and time-frequency resources of one or more first task indications for a certain task type in the first region are different from time-frequency resources of one or more second task indications for the same task type in the second region.

[0312] In a possible implementation, the time-frequency resources of one or more first task indications for the task type in the first region include time-frequency resources of one or more first reference signals for the task type in the first region, and the time-frequency resources of one or more second task indications for the same task type in the second region include time-frequency resources of one or more second reference signals for the same task type in the second region.

[0313] In a possible implementation, the at least one task indication is represented by at least one pattern of at least one task type.

[0314] In a possible implementation, different patterns are defined for different task types.

[0315] In a possible implementation, the at least one task indication is configurable.

[0316] In a possible implementation, the different patterns are predefined in a specification and can be selected according to a current scenario.

[0317] In a possible implementation, the different patterns are broadcast, multicast, or unicast through signaling.

[0318] In a possible implementation, the signaling is carried in radio resource control (RRC) signaling.

[0319] In a possible implementation, different task types correspond to different task indications.

[0320] In a possible implementation, the message for a task type is scrambled with a task identity of the task type.

[0321] In a possible implementation, the at least one task indication belongs to at least one group, each of the at least one task indication belongs to one of the at least one group, each of the at least one group corresponds to a respective different task type, and comprises one or more task indications indicating the respective different task type.

[0322] In a possible implementation, each of the at least one area is a cell, or each of the at least one area is a paging area.

[0323] In a possible implementation, the at least one piece of task indication information is sent by the central device.

[0324] The second device can be applied to the above-described second apparatus, e.g., the central apparatus, described in the above possible method implementation. Those skilled in the art should understand that, in combination with the related description of the communication method in these possible implementations of the present application, the related description of the above modules in these possible implementations of the present application can be understood. The technical effects achieved by the above second device are similar to those achieved by the above possible method implementation, which will not be repeated here.

[0325] A possible implementation of the present application provides a third device comprising processing circuitry for performing any of the above corresponding semantic communication methods on the first apparatus side, which will not be repeated here.

[0326] A possible implementation of the present application provides a fourth device comprising processing circuitry for performing any of the above corresponding semantic communication methods on the second apparatus side, which will not be repeated here.

[0327] A possible implementation of the present application provides a wireless communication system comprising: at least one first device for performing any of the above corresponding semantic communication methods on the first apparatus side or at least one third device for performing any of the above corresponding semantic communication methods on the first apparatus side; at least one second device for performing any of the above corresponding semantic communication methods on the second apparatus side or at least one fourth device for performing any of the above corresponding semantic communication methods on the second apparatus side. The above method will not be repeated here.

[0328] One possible implementation of the present application provides a wireless communication system, comprising: a first processing circuitry configured to perform any of the above corresponding semantic communication methods at a first device side; and a second processing circuitry configured to perform any of the above corresponding semantic communication methods at a second device side. The above methods are not repeated here.

[0329] One possible implementation of the present application provides a computer readable medium storing computer-executable instructions that, when executed by a processor, cause the processor to perform any of the above semantic communication methods, which are not repeated here.

[0330] One possible implementation of the present application provides a computer program product comprising computer-executable instructions that, when executed by a processor, cause the processor to perform any of the above semantic communication methods, which are not repeated here.

[0331] The present application provides a semantic / task-oriented unit selection method, device and system.

[0332] Some aspects of the present application relate to a scheme for managing and scheduling semantic-based communication of a large number of sensing devices, wherein the sensing devices can belong to different types. The query semantics are target-oriented, and only the sensing devices whose sensing data have sufficient relevance to the semantic message will respond and send their sensing data, which are preferably also in semantic form.

[0333] Some aspects of the present application relate to a scheme for scheduling based on collective semantic tokens on a large number of sensing devices rather than one-to-one individual scheduling.

[0334] Some aspects of the present application relate to a scheme for converting query data and sensing data into a common semantic domain using a large language model (LLM), on which the query data and the sensing data can be easily compared and fused with each other.

[0335] The above one or more aspects of the present application can have at least one of the following benefits:

[0336] The scheduling can be task-oriented or target-oriented; only the sensing devices that contribute to the scheduling task or target will respond and send their sensing data;

[0337] Privacy can be protected: the task, target or query and sensing data are well protected; no original data is transmitted over the air or the original data or messages transmitted over the air are minimized;

[0338] Forward compatibility: The semantic-based perception system in the present invention can be forward compatible, i.e. can support any new perception mechanism.

[0339] In some aspects of the present invention, a computer program comprising instructions is provided. The instructions, when executed by a processor, can cause the processor to implement the method of the present invention.

[0340] In some aspects of the present invention, a non-transitory computer readable medium storing instructions is provided. The instructions, when executed by a processor, can cause the processor to implement the method of the present invention.

[0341] In some aspects of the present invention, an apparatus / chipset system is provided, comprising means for implementing the method implemented by the perception device of the present invention.

[0342] In some aspects of the present invention, an apparatus / chipset system is provided, comprising means for implementing the method implemented by the center device of the present invention.

[0343] In some aspects of the present invention, an apparatus / chipset system is provided, comprising means for implementing the method implemented by the GPT device of the present invention.

[0344] In some aspects of the present invention, a system is provided, comprising at least two of the apparatus in the perception device of the present invention, the apparatus in the center device of the present invention and the apparatus in the GPT device of the present invention.

[0345] In some aspects of the present invention, an apparatus / chipset system is provided, comprising at least one processor that executes instructions stored in a computer readable medium to implement the method implemented by the perception device of the present invention.

[0346] In some aspects of the present invention, an apparatus / chipset system is provided, comprising at least one processor that executes instructions stored in a computer readable medium to implement the method implemented by the center device of the present invention.

[0347] In some aspects of the present invention, an apparatus / chipset system is provided, comprising at least one processor that executes instructions stored in a computer readable medium to implement the method implemented by the GPT device of the present invention.

[0348] Exemplary concepts of some terms

[0349] Message: a payload in a natural language such as English, French or Chinese;

[0350] Query message: a query statement in a natural language;

[0351] Perception message: a description of an observation or perception data in a natural language;

[0352] Semantic: a vector, matrix, scalar tensor embedding a message;

[0353] Query Semantic: a semantic embedding a query message;

[0354] Perception Semantic: a semantic embedding a perception message;

[0355] Token: a scalar vector encoded from a semantic;

[0356] Query Token: a token encoded from a query semantic;

[0357] Perception Token: a token encoded from a perception semantic;

[0358] GPT Device: a device running on one or more generative AI models, generating one or more query messages from one or more perception messages;

[0359] Central Device: a device acting as a BS, connecting multiple terminal devices through wireless access in DL and UL, and connecting to a core network through a backbone network;

[0360] Perception Device: a device acting as a terminal, connected to one or more BSs, equipped with a perception gadget to measure nearby data of interest.

[0361] It should be noted that different embodiments can be implemented separately or in combination. Although a combination of features is shown in the described embodiments, not all features need to be combined to achieve the advantages of various embodiments of the present application. In other words, a system or method designed according to one embodiment of the present application does not necessarily include all the features or all the parts shown in any one of the drawings. In addition, selected features of one example embodiment can be combined with selected features of other example embodiments.

[0362] Although the present application has been described with reference to the illustrative embodiments, the present description is not intended to be understood in a limiting sense. Various modifications and combinations of the illustrative embodiments and other embodiments of the present application will be apparent to those skilled in the art upon reference to this description. Therefore, the appended claims are intended to cover any such modifications or embodiments.

[0363] Although the present application describes methods and processes by steps performed in a certain order, one or more steps in the methods and processes can be omitted or changed as appropriate. In appropriate cases, one or more steps can be performed in an order other than that described.

[0364] It is important to note that the expression "at least one of A or B" as used herein can be interchanged with the expression "A and / or B." It refers to a list of which one or both A or B can be chosen. Similarly, "at least one of A, B, or C" as used herein can be interchanged with "A and / or B and / or C" or "A, B, and / or C." It refers to a list of which one or more of A or B or C can be chosen, or A and B, or A and C, or B and C, or all of A, B, and C. The same principle applies to longer lists of the same format.

[0365] Although the present application is described in terms of methods, one of ordinary skill in the art will understand that the present application also relates to various components for performing at least some of the aspects and features of the described methods, whether through hardware components, software, or any combination of the two. Accordingly, the technical solutions of the present application can be embodied in the form of a software product. The appropriate software product can be stored in a pre-recorded storage device or other similar non-volatile or non-transitory computer-readable medium, including DVDs, CD-ROMs, U disks, removable hard disks, or other storage media. The software product includes instructions tangibly stored thereon, which enable a processing device (e.g., a personal computer, a server, or a network device) to perform the method examples disclosed herein. The machine executable instructions can be in the form of code sequences, configuration information, or other data, which, when executed, cause a machine (e.g., a processor or other processing device) to perform the steps in the methods provided by the examples of the present application.

[0366] All values and subranges within the disclosed ranges are also disclosed. In addition, although specific embodiments have been illustrated and described herein, it will be appreciated that various modifications can be made to the system, device, and process, to include more or less of such elements / components. For example, while any of the elements / components disclosed can be referred to as a singular number, the possible implementations disclosed herein can be modified to include a plurality of such elements / components. The subject matter described herein is intended to cover and encompass all suitable variations.

Claims

1. A communication method, characterized in that, include: Obtain at least one task instruction message sent in at least one region, wherein each task instruction message in the at least one task instruction message is sent in the corresponding region of the at least one region and indicates at least one task instruction, and each task instruction indicates the task type supported by the corresponding region; Based on the type of task of interest and the at least one task instruction information, select one region from the at least one region.

2. The method according to claim 1, characterized in that, Each of the at least one task indication includes a reference signal for measurement.

3. The method according to claim 1 or 2, characterized in that, Also includes: The type of task of interest is determined based on the capabilities of the first device and / or the current state of the first device.

4. The method according to any one of claims 1 to 3, characterized in that, Selecting a region from the at least one region based on the type of task of interest and the at least one task instruction information includes: The task type of interest is measured in one or more of the at least one region to obtain one or more measurement results corresponding to the one or more regions in the at least one region. The corresponding task indication information sent by the one or more regions in the at least one region indicates one or more task indications, and the one or more task indications indicate the task type of interest. Select one region from the at least one region, wherein the value of the measurement result corresponding to the selected region is higher than a threshold.

5. The method according to any one of claims 1 to 4, characterized in that, The at least one region includes a first region and a second region, and the at least one task instruction information includes a first task instruction information sent in the first region and a second task instruction information sent in the second region, wherein at least one first task instruction indicated by the first task instruction information and at least one second task instruction indicated by the second task instruction information indicate different task types.

6. The method according to any one of claims 1 to 5, characterized in that, The at least one task indication is scrambled by the identifier of the region that sends a task indication message indicating the at least one task indication.

7. The method according to any one of claims 1 to 6, characterized in that, The at least one region includes a first region and a second region, wherein the time-frequency resources indicated by one or more first tasks for a certain task type in the first region are the same as the time-frequency resources indicated by one or more second tasks for the same task type in the second region.

8. The method according to any one of claims 1 to 6, characterized in that, The at least one region includes a first region and a second region, wherein the time-frequency resources indicated by one or more first tasks for a certain task type in the first region are different from the time-frequency resources indicated by one or more second tasks for the same task type in the second region.

9. The method according to claim 7 or 8, characterized in that, The time-frequency resources indicated by the one or more first tasks for the task type in the first region include time-frequency resources of one or more first reference signals for the task type in the first region, and the time-frequency resources indicated by the one or more second tasks for the same task type in the second region include time-frequency resources of one or more second reference signals for the same task type in the second region.

10. The method according to any one of claims 1 to 9, characterized in that, The at least one task indication is represented by at least one pattern of at least one task type.

11. The method according to claim 10, characterized in that, Different patterns are defined for different task types.

12. The method according to claim 11, characterized in that, The at least one task instruction is configurable.

13. The method according to claim 12, characterized in that, The different patterns are predefined in the specification and can be selected according to the current scenario.

14. The method according to claim 12, characterized in that, The different patterns are broadcast, multicast, or unicast via signaling.

15. The method according to claim 14, characterized in that, The signaling is carried in radio resource control (RRC) signaling.

16. The method according to any one of claims 1 to 15, characterized in that, Different task types correspond to different task instructions.

17. The method according to claim 16, characterized in that, Messages of a given task type are scrambled using the task identifier of that task type.

18. The method according to claim 16, characterized in that, The at least one task instruction belongs to at least one group, each of the at least one task instruction belongs to one group of the at least one group, each of the at least one group corresponds to a different task type, and includes one or more task instructions indicating the different task types.

19. The method according to any one of claims 1 to 18, characterized in that, Each of the at least one regions is a cell, or each of the at least one regions is a paging area.

20. The method according to claim 3, characterized in that, The first device is a sensing device.

21. A communication method, characterized in that, include: At least one task instruction message is sent in at least one region, each of the at least one task instruction messages being sent in the corresponding region of the at least one region and indicating at least one task instruction, each task instruction indicating the task type supported by the corresponding region.

22. The method according to claim 21, characterized in that, Each of the at least one task indication includes a reference signal for measurement.

23. The method according to claim 21 or 22, characterized in that, The at least one region includes a first region and a second region, and the at least one task instruction information includes a first task instruction information sent in the first region and a second task instruction information sent in the second region, wherein at least one first task instruction indicated by the first task instruction information and at least one second task instruction indicated by the second task instruction information indicate different task types.

24. The method according to any one of claims 21 to 23, characterized in that, The at least one task indication is scrambled by the identifier of the region that sends a task indication message indicating the at least one task indication.

25. The method according to any one of claims 21 to 24, characterized in that, The at least one region includes a first region and a second region, wherein the time-frequency resources indicated by one or more first tasks for a certain task type in the first region are the same as the time-frequency resources indicated by one or more second tasks for the same task type in the second region.

26. The method according to any one of claims 21 to 24, characterized in that, The at least one region includes a first region and a second region, wherein the time-frequency resources indicated by one or more first tasks for a certain task type in the first region are different from the time-frequency resources indicated by one or more second tasks for the same task type in the second region.

27. The method according to claim 25 or 26, characterized in that, The time-frequency resources indicated by the one or more first tasks for the task type in the first region include time-frequency resources of one or more first reference signals for the task type in the first region, and the time-frequency resources indicated by the one or more second tasks for the same task type in the second region include time-frequency resources of one or more second reference signals for the same task type in the second region.

28. The method according to any one of claims 21 to 27, characterized in that, The at least one task indication is represented by at least one pattern of at least one task type.

29. The method according to claim 28, characterized in that, Different patterns are defined for different task types.

30. The method according to claim 29, characterized in that, The at least one task instruction is configurable.

31. The method according to claim 30, characterized in that, The different patterns are predefined in the specification and can be selected according to the current scenario.

32. The method according to claim 30, characterized in that, The different patterns are broadcast, multicast, or unicast via signaling.

33. The method according to claim 32, characterized in that, The signaling is carried in radio resource control (RRC) signaling.

34. The method according to any one of claims 21 to 33, characterized in that, Different task types correspond to different task instructions.

35. The method according to claim 34, characterized in that, Messages of a given task type are scrambled using the task identifier of that task type.

36. The method according to claim 34, characterized in that, The at least one task instruction belongs to at least one group, each of the at least one task instruction belongs to one group of the at least one group, each of the at least one group corresponds to a different task type, and includes one or more task instructions indicating the different task types.

37. The method according to any one of claims 21 to 36, characterized in that, Each of the at least one regions is a cell, or each of the at least one regions is a paging area.

38. The method according to any one of claims 21 to 37, characterized in that, The at least one task instruction message is sent by the central device.

39. A first device, characterized in that, include: The acquisition module is used to acquire at least one task indication information sent in at least one region, wherein each task indication information in the at least one task indication information is sent in a corresponding region of the at least one region and indicates at least one task indication, and each task indication indicates the task type supported by the corresponding region; The selection module is used to select a region from the at least one region based on the type of task of interest and the at least one task instruction information.

40. The first apparatus according to claim 39, characterized in that, Each of the at least one task indication includes a reference signal for measurement.

41. The first apparatus according to claim 39 or 40, characterized in that, Also includes: A determining module is configured to determine the type of task of interest based on the capabilities of the first device and / or the current state of the first device.

42. The first device according to any one of claims 39 to 41, characterized in that, The selection module is used for: The task type of interest is measured in one or more of the at least one region to obtain one or more measurement results corresponding to the one or more regions in the at least one region. The corresponding task indication information sent by the one or more regions in the at least one region indicates one or more task indications, and the one or more task indications indicate the task type of interest. Select one region from the at least one region, wherein the value of the measurement result corresponding to the selected region is higher than a threshold.

43. The first device according to any one of claims 39 to 42, characterized in that, The at least one region includes a first region and a second region, and the at least one task instruction information includes a first task instruction information sent in the first region and a second task instruction information sent in the second region, wherein at least one first task instruction indicated by the first task instruction information and at least one second task instruction indicated by the second task instruction information indicate different task types.

44. The first device according to any one of claims 39 to 43, characterized in that, The at least one task indication is scrambled by the identifier of the region that sends a task indication message indicating the at least one task indication.

45. The first device according to any one of claims 39 to 44, characterized in that, The at least one region includes a first region and a second region, wherein the time-frequency resources indicated by one or more first tasks for a certain task type in the first region are the same as the time-frequency resources indicated by one or more second tasks for the same task type in the second region.

46. ​​The first device according to any one of claims 39 to 44, characterized in that, The at least one region includes a first region and a second region, wherein the time-frequency resources indicated by one or more first tasks for a certain task type in the first region are different from the time-frequency resources indicated by one or more second tasks for the same task type in the second region.

47. The first apparatus according to claim 45 or 46, characterized in that, The time-frequency resources indicated by the one or more first tasks for the task type in the first region include time-frequency resources of one or more first reference signals for the task type in the first region, and the time-frequency resources indicated by the one or more second tasks for the same task type in the second region include time-frequency resources of one or more second reference signals for the same task type in the second region.

48. The first device according to any one of claims 39 to 47, characterized in that, The at least one task indication is represented by at least one pattern of at least one task type.

49. The first apparatus according to claim 48, characterized in that, Different patterns are defined for different task types.

50. The first apparatus according to claim 49, characterized in that, The at least one task instruction is configurable.

51. The first apparatus according to claim 50, characterized in that, The different patterns are predefined in the specification and can be selected according to the current scenario.

52. The first apparatus according to claim 50, characterized in that, The different patterns are broadcast, multicast, or unicast via signaling.

53. The first apparatus according to claim 52, characterized in that, The signaling is carried in radio resource control (RRC) signaling.

54. The first device according to any one of claims 39 to 53, characterized in that, Different task types correspond to different task instructions.

55. The first apparatus according to claim 54, characterized in that, Messages of a given task type are scrambled using the task identifier of that task type.

56. The first apparatus according to claim 54, characterized in that, The at least one task instruction belongs to at least one group, each of the at least one task instruction belongs to one group of the at least one group, each of the at least one group corresponds to a different task type, and includes one or more task instructions indicating the different task types.

57. The first device according to any one of claims 39 to 56, characterized in that, Each of the at least one regions is a cell, or each of the at least one regions is a paging area.

58. The first apparatus according to claim 41, characterized in that, The first device is a sensing device.

59. A second device, characterized in that, include: A sending module is configured to send at least one task indication message in at least one region, wherein each task indication message is sent in a corresponding region of the at least one region and indicates at least one task indication, and each task indication indicates a task type supported by the corresponding region.

60. The second apparatus according to claim 59, characterized in that, Each of the at least one task indication includes a reference signal for measurement.

61. The second apparatus according to claim 59 or 60, characterized in that, The at least one region includes a first region and a second region, and the at least one task instruction information includes a first task instruction information sent in the first region and a second task instruction information sent in the second region, wherein at least one first task instruction indicated by the first task instruction information and at least one second task instruction indicated by the second task instruction information indicate different task types.

62. The second device according to any one of claims 59 to 61, characterized in that, The at least one task indication is scrambled by the identifier of the region that sends a task indication message indicating the at least one task indication.

63. The second device according to any one of claims 59 to 62, characterized in that, The at least one region includes a first region and a second region, wherein the time-frequency resources indicated by one or more first tasks for a certain task type in the first region are the same as the time-frequency resources indicated by one or more second tasks for the same task type in the second region.

64. The second device according to any one of claims 59 to 62, characterized in that, The at least one region includes a first region and a second region, wherein the time-frequency resources indicated by one or more first tasks for a certain task type in the first region are different from the time-frequency resources indicated by one or more second tasks for the same task type in the second region.

65. The second apparatus according to claim 63 or 64, characterized in that, The time-frequency resources indicated by the one or more first tasks for the task type in the first region include time-frequency resources of one or more first reference signals for the task type in the first region, and the time-frequency resources indicated by the one or more second tasks for the same task type in the second region include time-frequency resources of one or more second reference signals for the same task type in the second region.

66. The second device according to any one of claims 59 to 65, characterized in that, The at least one task indication is represented by at least one pattern of at least one task type.

67. The second apparatus according to claim 66, characterized in that, Different patterns are defined for different task types.

68. The second apparatus according to claim 67, characterized in that, The at least one task instruction is configurable.

69. The second apparatus according to claim 68, characterized in that, The different patterns are predefined in the specification and can be selected according to the current scenario.

70. The second apparatus according to claim 68, characterized in that, The different patterns are broadcast, multicast, or unicast via signaling.

71. The second apparatus according to claim 70, characterized in that, The signaling is carried in radio resource control (RRC) signaling.

72. The second device according to any one of claims 59 to 71, characterized in that, Different task types correspond to different task instructions.

73. The second apparatus according to claim 72, characterized in that, Messages of a given task type are scrambled using the task identifier of that task type.

74. The second apparatus according to claim 72, characterized in that, The at least one task instruction belongs to at least one group, each of the at least one task instruction belongs to one group of the at least one group, each of the at least one group corresponds to a different task type, and includes one or more task instructions indicating the different task types.

75. The second device according to any one of claims 59 to 74, characterized in that, Each of the at least one regions is a cell, or each of the at least one regions is a paging area.

76. The second device according to any one of claims 59 to 75, characterized in that, The at least one task instruction message is sent by the central device.

77. A third device, characterized in that, include: A processing circuit for performing the method according to any one of claims 1 to 20.

78. A fourth device, characterized in that, include: A processing circuit for performing the method according to any one of claims 21 to 38.

79. A wireless communication system, characterized in that, include: At least one first device according to any one of claims 39 to 58 or at least one third device according to claim 77; At least one second device according to any one of claims 59 to 76 or at least one fourth device according to claim 78.

80. A wireless communication system, characterized in that, include: A first processing circuit is configured to perform the method according to any one of claims 1 to 20; A second processing circuit is configured to perform the method according to any one of claims 21 to 38.

81. A computer-readable medium, characterized in that, The computer executes instructions, which, when executed by a processor, cause the processor to perform the method according to any one of claims 1 to 38.

82. A computer program product, characterized in that, Includes computer execution instructions, which, when executed by a processor, cause the processor to perform the method according to any one of claims 1 to 38.

Images