Nothing Special   »   [go: up one dir, main page]

WO2024145925A1 - Mécanisme de surveillance de performances de modèle pour positionnement ia/ml - Google Patents

Mécanisme de surveillance de performances de modèle pour positionnement ia/ml Download PDF

Info

Publication number
WO2024145925A1
WO2024145925A1 PCT/CN2023/071056 CN2023071056W WO2024145925A1 WO 2024145925 A1 WO2024145925 A1 WO 2024145925A1 CN 2023071056 W CN2023071056 W CN 2023071056W WO 2024145925 A1 WO2024145925 A1 WO 2024145925A1
Authority
WO
WIPO (PCT)
Prior art keywords
model
pru
positioning
assistance data
location
Prior art date
Application number
PCT/CN2023/071056
Other languages
English (en)
Inventor
Mingwei Jie
Ye Huang
Pengli YANG
Chiao-Yao CHUANG
Xuancheng Zhu
Original Assignee
Mediatek Singapore Pte. Ltd.
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Mediatek Singapore Pte. Ltd. filed Critical Mediatek Singapore Pte. Ltd.
Priority to PCT/CN2023/071056 priority Critical patent/WO2024145925A1/fr
Publication of WO2024145925A1 publication Critical patent/WO2024145925A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
    • G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
    • G01S5/0205—Details
    • G01S5/0236—Assistance data, e.g. base station almanac
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management

Definitions

  • This present disclosure relates generally to wireless communications, and more specifically, to techniques of positioning a user equipment (UE) with Artificial Intelligence (AI) /Machine Learning (ML) .
  • UE user equipment
  • AI Artificial Intelligence
  • ML Machine Learning
  • the one or more aspects comprise the features hereinafter fully described and particularly pointed out in the claims.
  • the following description and the annexed figures set forth in detail certain illustrative features of the one or more aspects. These features are indicative, however, of but a few of the various ways in which the principles of various aspects may be employed, and this description is intended to include all such aspects and their equivalents.
  • Figure 1 illustrates indoor factory deployment scenario.
  • Figure 1 shows an example of indoor factory deployment scenario.
  • UEs are random distributed in the factory.
  • PRUs are deployed in known location for AI/ML assistance data. There are also some clutters in the factory.
  • the high-level flow of this invention is shown in figure 2.
  • the first step is network notify the PRU to monitor performance of one model. Network will send the model to PRU. If the model is not trained, network will send assistance data to PRU in the second step. PRU will train the model with received assistance data.
  • the third step is PRU measure model input and inference model to get model output.
  • the 4th step is PRU calculate the model loss. The last step is PRU reports the loss to network.
  • Network don’t train model M1 or trained M1 with assistance data from PRU1, network will send un-trained model M1 and assistance data D2/D3/...to PRU1. These assistance data should not include assistance data D1 from PRU1.
  • PRU1 train M1 based on received assistance data.

Landscapes

  • Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

La présente divulgation concerne un mécanisme pour surveiller les performances d'un modèle de positionnement IA/ML. La surveillance de modèle est un procédé important pour améliorer la capacité de généralisation d'IA/ML. Dans la présente invention, nous présentons un procédé pour surveiller un modèle avec PRU. Avec la PRU d'emplacement connu, une perte de modèle d'IA/ML peut être obtenue. La PRU peut fournir des données d'assistance pour un entraînement de modèle IA/ML. Les données d'assistance comprennent des données d'entrée de modèle et une étiquette de sortie de modèle. Le réseau peut envoyer un modèle à surveiller à la PRU. Ce modèle peut être entraîné ou non. Si le modèle n'est pas entraîné, le réseau envoie des données d'assistance à la PRU et la PRU entraîne le modèle. Ensuite, cette PRU infère le modèle pour obtenir un emplacement estimé et calcule la différence entre un emplacement connu et un emplacement estimé.
PCT/CN2023/071056 2023-01-06 2023-01-06 Mécanisme de surveillance de performances de modèle pour positionnement ia/ml WO2024145925A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2023/071056 WO2024145925A1 (fr) 2023-01-06 2023-01-06 Mécanisme de surveillance de performances de modèle pour positionnement ia/ml

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2023/071056 WO2024145925A1 (fr) 2023-01-06 2023-01-06 Mécanisme de surveillance de performances de modèle pour positionnement ia/ml

Publications (1)

Publication Number Publication Date
WO2024145925A1 true WO2024145925A1 (fr) 2024-07-11

Family

ID=91803542

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/071056 WO2024145925A1 (fr) 2023-01-06 2023-01-06 Mécanisme de surveillance de performances de modèle pour positionnement ia/ml

Country Status (1)

Country Link
WO (1) WO2024145925A1 (fr)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022155244A2 (fr) * 2021-01-12 2022-07-21 Idac Holdings, Inc. Procédés et appareil de positionnement basé sur l'apprentissage dans des systèmes de communication sans fil
US20220317230A1 (en) * 2021-04-01 2022-10-06 Qualcomm Incorporated Positioning reference signal (prs) processing window for low latency positioning measurement reporting

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022155244A2 (fr) * 2021-01-12 2022-07-21 Idac Holdings, Inc. Procédés et appareil de positionnement basé sur l'apprentissage dans des systèmes de communication sans fil
US20220317230A1 (en) * 2021-04-01 2022-10-06 Qualcomm Incorporated Positioning reference signal (prs) processing window for low latency positioning measurement reporting

Similar Documents

Publication Publication Date Title
US8818288B2 (en) Statistical inversion method and system for device-free localization in RF sensor networks
EP2222053B1 (fr) Système et procédé de prédiction de réunions futures d'utilisateurs sans fil
US8340022B2 (en) Wireless location determination system and method
US9664770B2 (en) Method and system for simultaneous receiver calibration and object localisation for multilateration
CN105738922B (zh) 导航卫星星座系统的服务可靠性分析方法及系统
US20180047174A1 (en) Target monitoring system and target monitoring method
US20180283861A1 (en) Altitude measurement system and altitude measurement method
WO2003001236A3 (fr) Procedes et dispositifs pour estimations de position precises en cas de deterioration marquee de la precision
CN110557191B (zh) 一种低轨卫星移动通信系统中的终端定位方法及装置
CN109506647B (zh) 一种基于神经网络的ins和磁力计组合定位方法
US20190317221A1 (en) Systems and methods for satellite-based navigation
Nguyen et al. Applying time series analysis and neighbourhood voting in a decentralised approach for fault detection and classification in WSNs
CN110673168B (zh) 异步多用户联合欺骗信号检测方法及装置
JP2008014938A (ja) 衛星ナビゲーション受信機の性能を高めるシステム及び方法
US20160291121A1 (en) Backtracking indoor trajectories using mobile sensors
WO2024145925A1 (fr) Mécanisme de surveillance de performances de modèle pour positionnement ia/ml
Sheppard et al. Bayesian diagnosis and prognosis using instrument uncertainty
CN115702590A (zh) 位置估计
WO2024148576A1 (fr) Mécanisme de surveillance de scénario pour positionnement ia/ml
WO2024197735A1 (fr) Mécanisme de surveillance de performances de modèle pour positionnement ia/ml
US20240097811A1 (en) Method for identifying and diagnosing failures in pairwise time synchronization and frequency calibration in a mesh network
KR20190111587A (ko) 딥 러닝 기반 사용자 단말 위치 추정 장치 및 방법
US12015966B2 (en) Method and apparatus for sensor selection for localization and tracking
WO2024164116A1 (fr) Mécanisme d'unités de référence de positionnement auxiliaire pour le positionnement intelligence artificielle/apprentissage machine (ia/am)
Im et al. Deep LSTM-based multimode pedestrian dead reckoning system for indoor localization

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23914082

Country of ref document: EP

Kind code of ref document: A1