Search

US-20260129409-A1 - METHOD, APPARATUS, AND SYSTEM FOR SEMANTIC COMMUNICATIONS

US20260129409A1US 20260129409 A1US20260129409 A1US 20260129409A1US-20260129409-A1

Abstract

Provided are a sensing communication method, apparatus, and system. An apparatus such as a central device can broadcast or multi-cast or unicast query message(s), so that other apparatus(es) such as one or more sensing devices can obtain the query message(s) and respond with sensing result(s) in response to the obtained query message(s). The sensing result(s) may include the at least one piece of sensed data and/or the at least one second sensing semantic, where the at least one second sensing semantic and/or the at least one third sensing semantic converted from the at least one piece of sensed data are included in the at least one first sensing semantic, which is generated based on at least one piece of raw sensed data and at least one semantization model preconfigured in the sensing device through communicating with the central device.

Inventors

  • Mengyao Ma
  • Yiqun Ge
  • Jianglei Ma
  • Qifan Zhang

Assignees

  • HUAWEI TECHNOLOGIES CO., LTD.

Dates

Publication Date
20260507
Application Date
20251218

Claims (20)

  1. 1 . A method, comprising: obtaining at least one query message; generating, based on at least one piece of raw sensed data and at least one semantization model, at least one first sensing semantic respectively corresponding to the at least one piece of raw sensed data; and sending a sensing result, wherein the sensing result indicates at least one of: at least one piece of sensed data or at least one second sensing semantic, and wherein the at least one first sensing semantic comprises at least one of: the at least one second sensing semantic or at least one third sensing semantic converted from the at least one piece of sensed data.
  2. 2 . The method according to claim 1 , wherein the method further comprises: obtaining a semantization model configuration, wherein the semantization model configuration indicates the at least one semantization model.
  3. 3 . The method according to claim 2 , wherein the at least one semantization model is represented by {M 1 , M 2 , . . . M s }, s≥1, wherein s is a number of the at least one semantization model, and wherein a semantization model M i for i∈[1,s] corresponds to at least one of a task or a modality.
  4. 4 . The method according to claim 3 , wherein the semantization model configuration further indicates at least one identifier for the semantization model M i , and wherein the at least one identifier comprises a task identifier, or a modality identifier, or both the task identifier and the modality identifier.
  5. 5 . The method according to claim 3 , wherein the generating, based on the at least one piece of raw sensed data and the at least one semantization model, the at least one first sensing semantic respectively corresponding to the at least one piece of raw sensed data comprises: generating the at least one first sensing semantic {o 1 , o 2 , . . . , o s } based on the at least one piece of raw sensed data and the at least one semantization model {M 1 , M 2 , . . . M s }, wherein a first sensing semantic o i is generated based on a piece of raw sensed data to which the first sensing semantic o i corresponds and the semantization model M i , i∈[1,s].
  6. 6 . The method according to claim 4 , wherein, when the at least one identifier comprises the task identifier or the modality identifier, the semantization model configuration is represented by {(t 1 , M 1 ), (t 2 , M 2 ), . . . (t s , M s )}, or {t 1 , t 2 , . . . t s ; M 1 , M 2 , . . . M s }, wherein t i is an i-th task identifier or an i-th modality identifier of the semantization model M i , i∈[1,s].
  7. 7 . A first apparatus comprising: at least one processor coupled with a memory storing instructions that, when executed by the at least one processor, cause the first apparatus to perform operations including: obtaining at least one query message; generating, based on at least one piece of raw sensed data and at least one semantization model, at least one first sensing semantic respectively corresponding to the at least one piece of raw sensed data; and sending a sensing result, wherein the sensing result indicates at least one of: at least one piece of sensed data or at least one second sensing semantic, and wherein the at least one first sensing semantic comprises at least one of: the at least one second sensing semantic or at least one third sensing semantic converted from the at least one piece of sensed data.
  8. 8 . The first apparatus according to claim 7 , the operations further comprising: obtaining a semantization model configuration, wherein the semantization model configuration indicates the at least one semantization model.
  9. 9 . The first apparatus according to claim 8 , wherein the at least one semantization model is represented by {M 1 , M 2 , . . . M s }, s≥1, wherein s is a number of the at least one semantization model, and wherein a semantization model M i for i∈[1,s] corresponds to at least one of a task or a modality.
  10. 10 . The first apparatus according to claim 9 , wherein the semantization model configuration further indicates at least one identifier for the semantization model M i , and wherein the at least one identifier comprises a task identifier, or a modality identifier, or both the task identifier and the modality identifier.
  11. 11 . The first apparatus according to claim 9 , wherein the generating, based on the at least one piece of raw sensed data and the at least one semantization model, the at least one first sensing semantic respectively corresponding to the at least one piece of raw sensed data comprises: generating the at least one first sensing semantic {o 1 , o 2 , . . . , o s } based on the at least one piece of raw sensed data and the at least one semantization model {M 1 , M 2 , . . . M s }, wherein a first sensing semantic o i is generated based on a piece of raw sensed data to which the first sensing semantic o i corresponds and the semantization model M i , i∈[1,s].
  12. 12 . The first apparatus according to claim 10 , wherein when the at least one identifier comprises the task identifier or the modality identifier, the semantization model configuration is represented by {(t 1 , M 1 ), (t 2 , M 2 ), . . . (t s , M s )}, or {t 1 , t 2 , . . . t s ; M 1 , M 2 , . . . M s }, wherein t i is an i-th task identifier or an i-th modality identifier of the semantization model M i , i∈[1,s].
  13. 13 . The first apparatus according to claim 10 , wherein when the at least one identifier is represented by {(t 1 , t′ 1 , M 1 ), (t 2 , t′ 2 , M 2 ), . . . (t s , t′ s , M s )}, or {t 1 , t 2 , . . . t s ; t′ 1 , t′ 2 , . . . t′ s ; M 1 , M 2 , . . . M s }, wherein t i is an i-th task identifier of model M i , and t′ i is an i-th modality identifier of the semantization model M i , i∈[1,s].
  14. 14 . A second apparatus, comprising: at least one processor coupled with a memory storing instructions that, when executed by the at least one processor, cause the second apparatus to perform operations including: sending at least one query message; and obtaining one or more sensing results, wherein each sensing result of the one or more sensing results indicates at least one of: at least one piece of sensed data or at least one second sensing semantic, wherein at least one first sensing semantic respectively corresponds to at least one piece of raw sensed data and is generated based on the at least one piece of raw sensed data and at least one semantization model, and wherein the at least one first sensing semantic comprises at least one of: the at least one second sensing semantic or at least one third sensing semantic converted from the at least one piece of sensed data.
  15. 15 . The second apparatus according to claim 14 , the operations further comprising: sending a semantization model configuration, wherein the semantization model configuration indicates the at least one semantization model.
  16. 16 . The second apparatus according to claim 15 , wherein the at least one semantization model is represented by {M 1 , M 2 , . . . M s }, s≥1, wherein s is a number of the at least one semantization model, and wherein a semantization model M i for i∈[1, s] corresponds to at least one of a task or a modality.
  17. 17 . The second apparatus according to claim 16 , wherein the semantization model configuration further indicates at least one identifier for the semantization model M i , and wherein the at least one identifier comprises a task identifier, or a modality identifier, or both the task identifier and the modality identifier.
  18. 18 . The second apparatus according to claim 17 , wherein when the at least one identifier comprises the task identifier or the modality identifier, the semantization model configuration is represented by {(t 1 , M 1 ), (t 2 , M 2 ), . . . (t s , M s )}, or {t 1 , t 2 , . . . t s ; M 1 , M 2 , . . . M s }, wherein t i is an i-th task identifier or an i-th modality identifier of the semantization model M i , i∈[1, s].
  19. 19 . The second apparatus according to claim 17 , wherein when the at least one identifier is represented by {(t 1 , t′ 1 , M 1 ), (t 2 , t′ 2 , M 2 ), . . . (t s , t′ s , M s )}, or {t 1 , t 2 , . . . t s ; t′ 1 , t′ 2 , . . . t′ s ; M 1 , M 2 , . . . M s }, wherein t i is an i-th task identifier of model M i , and t′ i is an i-th modality identifier of the semantization model M i , i∈[1, s].
  20. 20 . The second apparatus according to claim 15 , the operations further comprising: compressing one or more semantization models of the at least one semantization model in the semantization model configuration.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS This application is a continuation of International Application No. PCT/CN2023/128877, filed on Oct. 31, 2023, which claims priority to U.S. Provisional Patent Application No. 63/509,393, filed on Jun. 21, 2023, applications of which are hereby incorporated by reference in its entirety. TECHNICAL FIELD The present disclosure relates generally to the field of sensing communication technologies and, in particular, to a sensing communication method, apparatus, and system. BACKGROUND A sensing function will be integrated into the 6th generation (6G) system. A large number of the sensing user equipments (UEs) or sensing devices will be densely deployed in cities, factories, farms and so on. In addition to mobile phones, sensing devices will become an important type of UEs or devices that claim an arrival of IoT time. Like internet searching engines, 6G will come up with the counterpart, an internet of thing (IoT) searching engine, in a true physical world. In fact, billions of IoT-based applications such as driverless cars, automation factories, smart cities, and autonomous farms, will heavily depend on an efficient and real-time searching engine in our physical world. Recently, artificial intelligence (AI) has conquered various intellectual and cognitive domains. Some AI is exploring the cutting edge of our intellectual knowledge in chemistry, gaming, mathematics, gene engineering. Some other AI is providing a human-level Q&A platform in the digital world; the domain that AI has not conquered is real-time physical world. Physical-world AI, in which AI technologies are to penetrate into all the aspects of our society and life, may be built on omnipresent IoT connections thanks to 6G. More challenging than internet searching engine, real-world searching engine would have to search the physical world in real time over a large scale of physical areas and to deal with a multitude of types of data and information (some may be novel and some may not have been invented yet). Furthermore, green technology, low-energy and low-emission, are also raised as key feature of 6G. A sensing device may be battery powered and/or completely powered by solar and wind. It would be costly and impracticable to ask all the sensing devices in a large scale to feedback what they are sensing at the same time. On one hand, the frequent sensing and transmission consumes a sensing device much energy and reduce their battery life time; on other hand, such a high density of the IoT deployment may block the uplink channels, especially the uplink (UL) bandwidth is more expensive than the downlink (DL) one. This background information is provided to reveal information believed by the applicant to be of possible relevance to the present disclosure. No admission is necessarily intended, nor should it be construed, that any of the preceding information constitutes prior art against the present disclosure. SUMMARY In a first aspect, the present disclosure provides a sensing communication method, where the method includes: obtaining at least one query message;generating, based on at least one piece of raw sensed data and at least one semantization model, at least one first sensing semantic respectively corresponding to the at least one piece of raw sensed data, where the at least one semantization model is preconfigured in a first apparatus through communicating with a second apparatus; andsending a sensing result, where the sensing result includes at least one piece of sensed data and/or at least one second sensing semantic, and where the at least one first sensing semantic includes the at least one second sensing semantic and/or at least one third sensing semantic converted from the at least one piece of sensed data. Because the at least one first sensing semantic may be generated based on the at least one piece of raw sensed data and the at least one semantization model preconfigured in the first apparatus through communicating with the second apparatus, query may be conducted more flexibly and reasonably based on the at least one semantization model. In a possible implementation of the first aspect, before the obtaining at least one query message, the method further includes: obtaining a semantization model configuration, where the semantization model configuration indicates the at least one semantization model. Because the semantization model configuration may be obtained in advance, the semantization model indicated in the semantization model configuration can be used to convert the sensed data to a sensing semantic (and/or convert the query message to a query semantic if necessary), thereby realizing the configuration of the semantization model, and thus facilitating the generation of the sensing semantic and further improving the flexibility of query. In a possible implementation of the first aspect, the at least one semantization model is represented by {M1, M2, . . . Ms}, s≥1, where the s is the number