WO2024253874A9 - Systèmes et procédés pour la traduction en temps réel de mesures de capteur aquatique en causes probables par l'intermédiaire d'une combinaison d'interrogations de cause à effet et d'une similarité sémantique basée sur un modèle de langage - Google Patents

Systèmes et procédés pour la traduction en temps réel de mesures de capteur aquatique en causes probables par l'intermédiaire d'une combinaison d'interrogations de cause à effet et d'une similarité sémantique basée sur un modèle de langage

Info

Publication number
WO2024253874A9
WO2024253874A9 PCT/US2024/030978 US2024030978W WO2024253874A9 WO 2024253874 A9 WO2024253874 A9 WO 2024253874A9 US 2024030978 W US2024030978 W US 2024030978W WO 2024253874 A9 WO2024253874 A9 WO 2024253874A9
Authority
WO
WIPO (PCT)
Prior art keywords
aquatic
queries
data
aquatic environment
anomalies
Prior art date
Legal status (The legal status 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 status listed.)
Ceased
Application number
PCT/US2024/030978
Other languages
English (en)
Other versions
WO2024253874A1 (fr
Inventor
Prayrona CHOUDHURY
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Individual
Original Assignee
Individual
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 Individual filed Critical Individual
Publication of WO2024253874A1 publication Critical patent/WO2024253874A1/fr
Publication of WO2024253874A9 publication Critical patent/WO2024253874A9/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/18—Water
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/903—Querying
    • G06F16/9032—Query formulation
    • G06F16/90332—Natural language query formulation or dialogue systems
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/951—Indexing; Web crawling techniques
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
    • B63B—SHIPS OR OTHER WATERBORNE VESSELS; EQUIPMENT FOR SHIPPING 
    • B63B35/00—Vessels or similar floating structures specially adapted for specific purposes and not otherwise provided for
    • B63B2035/006—Unmanned surface vessels, e.g. remotely controlled
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions

Definitions

  • the present invention relates to data collection and analysis in aquatic environments. More particularly, the present invention provides a system and device for acquiring location-based data on water quality, contaminants, and flora presence and providing data analysis and assessment of potential causes of water quality issues and anomalies shared across network devices in real time.
  • the present invention thus provides an innovative Aquatic Data Analysis and Reporting System, referred to throughout as AquaTranslate, and comprises a state-of-the-art rover designed to collect comprehensive aquatic data.
  • the rover is capable of measuring essential parameters such as temperature, pH, and total dissolved solids (TDS). These data points serve as crucial indicators of water quality.
  • TDS total dissolved solids
  • One innovative aspect lies in its AI-based software, which undertakes the intricate task of analyzing the collected data. Leveraging sophisticated algorithms, the software generates comprehensive reports that elucidate the significance of the data points gathered. The system also employs machine learning techniques to identify and highlight potential issues within the water, such as the presence of algae or waste.
  • AquaTranslate empowers researchers, environmentalists, and industries to proactively address water quality concerns. Rapid and accurate identification of problems allows for timely interventions, reducing the negative impact on aquatic ecosystems and the industries dependent on them.
  • AquaTranslate thus presents a novel system that addresses the urgent need for efficient aquatic data analysis.
  • this invention has the potential to contribute to environmental sustainability, safeguarding aquatic biomes and supporting industries vital to our global food supply.
  • Preferable embodiments of the present invention thus comprise a rover and specialized software designed to analyze and process data collected from aquatic environments.
  • the rover is responsible for gathering various types of aquatic data, including but not limited to temperature, pH, and TDS (total dissolved solids) data.
  • the present invention employs advanced algorithms to translate the collected data into comprehensive reports. Additionally, the system generates a list of potential issues or concerns related to the quality of the water being analyzed.
  • the software component of the AquaTranslate System utilizes a combination of C++ programming language, specifically tailored for iOS and sensor measurements, as well as Python programming language for AquaTranslate's natural language processing capabilities and querying Google search.
  • Preferable embodiments of the AquaTranslate system include a software system for real-time analysis of anomalous water quality that uses Cause- driven searches utilizing a search engine to identify potential causes of water quality anomalies.
  • a breadth-first search is used to generate many automated queries to a search engine (such as Google) that produce a list of search results.
  • the system then summarizes search results using language model-generated vector-based comparisons that group items with high semantic similarity, referred to as vector embedding methods, to generate possible causes for anomalous water quality.
  • the present invention also preferably includes a hardware system enabling the real-time operation of the software system, which includes a low-cost, stable aquatic vehicle (also referred to as “rover” in text), preferably using a pontoon- boat structure with onboard electrical and computing units.
  • the electrical units preferably include brushed motors that are used to propel “in-air” propellers that drive the rover.
  • the rover of the present invention is preferably equipped with at least two motors, and a user from land can preferably control the speed and direction of the vehicle using a radio controller that controls the operation of each of the motors.
  • the rover also preferably includes one or more sensor units.
  • the sensor units preferably consist of sensors to collect data on water temperature, pH, and total dissolved solids in addition to a microcontroller that collects GPS data.
  • Each sensor unit preferably is attached to a separate iOS microcontroller that executes a C++ module for collecting the sensor measurements.
  • a Raspberry Pi computer is also preferably mounted on-board the rover to communicate with the iOS microcontrollers and execute a Python software that translates sensor into natural language based description of potential causes.
  • the Raspberry Pi system is preferably remotely controllable (using a messaging software framework) such that a user from land can send a control message to the on-board software in the waterborne rover to execute the AquaTranslate software system.
  • the AquaTranslate system operating in the aquatic environment such as river
  • the AquaTranslate system Upon generation of probable causes creating the environmental factors detected by the sensor measurements, the AquaTranslate system operating in the aquatic environment (such as river) notifies the user standing on land (such as riverbank) via a text message over bluetooth or cellular interface.
  • the system’s analysis and messaging preferably include an assessment of the most likely cause(s) of the environmental factors and, in some preferable embodiments, remedial actions that can be taken immediately or over the long term to resolve the water quality issues or anomalies.
  • the one or more computing units utilized by the AquaTranslate system such as iOS microcontrollers and Raspberry Pi, are specifically selected and designed to have minimal volume and weight, enabling attachment to an autonomous or human-guided rover operating in aquatic environments. Such design increases the floating stability of the rover and minimizes the rover’s on-board power requirements extending the operating range of the rover and the data collection and analysis system as a whole.
  • the present invention is not limited to the embodiments and arrangements described above.
  • FIG.1 depicts a rover and sample data analysis and schematic of the AquaTranslate system according to preferable embodiments of the present invention.
  • FIG.2 depicts various design options for a rover according to the preferable embodiments of the present depicted in Fig.1.
  • FIG.3 depicts features of a rover according to the preferable embodiments of the present invention depicted in Figs.1-2.
  • FIG.4 depicts features of a rover according to the preferable embodiments of the present invention depicted in Figs.1-3.
  • FIG.5 depicts a schematic of a circuit diagram for the features of the rover according to the preferable embodiments of the present invention depicted in Figs.1-4.
  • FIG.6 depicts a data flow schematic for the transmission and processing of acquired data according to the preferable embodiments of the present invention depicted in Figs.1-5.
  • FIG.7 depicts computing unit features utilized with the AquaTranslate system according to the preferable embodiments of the present invention depicted in Figs.1-6.
  • FIG.8 depicts a schematic diagram of the process of converting acquired data to output report according to the preferable embodiments of the present invention depicted in Figs.1-7.
  • FIG.9 depicts a schematic illustration of the AquaTranslate system’s use of querying through a search engine according to the preferable embodiments of the present invention depicted in Figs.1-8.
  • FIG.10 depicts a schematic illustration of the AquaTranslate system’s use of querying through a search engine according to the preferable embodiments of the present invention depicted in Figs.1-9.
  • FIG.11 depicts a schematic illustration of the AquaTranslate system’s extraction of applicable terms identified through repeated search engine queries according to the preferable embodiments of the present invention depicted in Figs.1- 10.
  • FIG.12 depicts a schematic illustration of the AquaTranslate system’s extraction of common factors using the of semantic similarity obtained by querying language models according to the preferable embodiments of the present invention depicted in Figs.1-11.
  • FIG.13 depicts a schematic illustration of the AquaTranslate system’s extraction of common factors using the principle of semantic similarity obtained by querying language models according to the preferable embodiments of the present invention depicted in Figs.1-12.
  • FIG.14 depicts a exemplary report produced by the AquaTranslate system based upon data acquired and processed from one or more aquatic biomes according to the preferable embodiments of the present invention depicted in Figs.1- 13.
  • FIG.15 depicts an overhead view of an area selected for exemplary assessment by the AquaTranslate system according to the preferable embodiments of the present invention depicted in Figs.1-14.
  • FIG.16 depicts an exemplary data collection and analysis as provided by the AquaTranslate system according to the preferable embodiments of the present invention depicted in Figs.1-15.
  • the Pi receives the numerical TDS (total solids) and pH data approximately 20 seconds after the rover is in the water.
  • This data is provided to the AquaTranslate software system.
  • the software system categorizes the numerical data into a set of strings. Next, a starter search is made using the string previously categorized. String variables such as “high pH” are replaced in a certain format that all the automated searches follow.
  • the format that all AquaTranslate search engine queries follow is “What causes” + the problem such as “high pH” + “in” + the location, such as “rivers”. This all adds up creating the search engine query “What causes high pH in rivers”.
  • AquaTranslate uses a web-search API, such as Google, Bing, Yahoo, or the like, to submit the search engine query, parse the HTML response and save the answer.
  • a web-search API such as Google, Bing, Yahoo, or the like
  • a designed algorithm is then preferably used to take the previous query result and identify the main “branching variables" from the results.
  • the results from the query “what causes high pH in rivers” is “In general, chemicals, minerals, pollutants, soil or bedrock composition, and any other contaminants that interact with a water supply will create an imbalance in the water's natural pH of 7.”
  • Preferable embodiments of the AquaTranslate code use Spacy, a natural language processing library, which uses machine learning to extract the nouns such as “chemicals”, “minerals”, “pollutants”, “soil”, and “bedrock composition.” The algorithm will then input these variables into their own search such as “what causes chemicals in rivers”.
  • the same variables are preferably stored in a list for possible problems.
  • Preferable embodiments of the algorithm will iterate a maximum of five times but will stop when either the results are quite similar or the search engine does not provide a useful answer.
  • AquaTranslate will create and provide a report compiling the sequence of searches for their results, with a list containing terms that are possible aquatic problems. This process is preferably repeated twice to provide a list of possible problem terms for both TDS and pH.
  • Preferable embodiments of the AquaTranslate system and invention finish the process by cross-analyzing both lists to identify similar terms in both lists. This task is preferably performed using OpenAI’s davinci language model.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Chemical & Material Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Medicinal Chemistry (AREA)
  • Medical Informatics (AREA)
  • Food Science & Technology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

L'invention concerne un système pour l'analyse en temps réel et sur site de problèmes de qualité de l'eau utilisant des algorithmes avancés, un apprentissage automatique et une évaluation basée sur l'intelligence artificielle, IA, le système employant un robot de l'état de la technique équipé de capteurs avancés pour détecter des problèmes et des anomalies dans un biome aquatique et fournir des données collectées à des unités informatiques, également déployées localement sur le robot, qui servent ensuite à évaluer les données collectées en employant des algorithmes avancés pour générer des interrogations de moteur de recherche, identifier et extraire des termes pertinents à partir de résultats de recherche, évaluer des causes probables de problèmes et d'anomalies détectés, et fournir des rapports en temps réel sur site et une analyse des conclusions.
PCT/US2024/030978 2023-06-07 2024-05-24 Systèmes et procédés pour la traduction en temps réel de mesures de capteur aquatique en causes probables par l'intermédiaire d'une combinaison d'interrogations de cause à effet et d'une similarité sémantique basée sur un modèle de langage Ceased WO2024253874A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US202363506779P 2023-06-07 2023-06-07
US63/506,779 2023-06-07

Publications (2)

Publication Number Publication Date
WO2024253874A1 WO2024253874A1 (fr) 2024-12-12
WO2024253874A9 true WO2024253874A9 (fr) 2025-10-16

Family

ID=93796381

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2024/030978 Ceased WO2024253874A1 (fr) 2023-06-07 2024-05-24 Systèmes et procédés pour la traduction en temps réel de mesures de capteur aquatique en causes probables par l'intermédiaire d'une combinaison d'interrogations de cause à effet et d'une similarité sémantique basée sur un modèle de langage

Country Status (1)

Country Link
WO (1) WO2024253874A1 (fr)

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180217029A1 (en) * 2015-07-27 2018-08-02 Woods Hole Oceangraphic Institution Aquatic Sampler and Collection Apparatus
WO2019129068A1 (fr) * 2017-12-27 2019-07-04 北京臻迪科技股份有限公司 Robot aquatique multifonctionnel et son système
EP3770586B1 (fr) * 2019-07-26 2021-11-10 Currenta GmbH & Co. OHG Procédé et dispositif de surveillance de la qualité et de détermination d'une contamination d'un espace
CN211925820U (zh) * 2019-11-25 2020-11-13 广州环峰能源科技股份有限公司 一种生物质气锅炉的监测与诊断系统
CN115905450B (zh) * 2023-01-04 2023-05-09 深圳联和智慧科技有限公司 一种基于无人机监控的水质异常溯源方法及系统

Also Published As

Publication number Publication date
WO2024253874A1 (fr) 2024-12-12

Similar Documents

Publication Publication Date Title
Bhardwaj et al. Smart IoT and machine learning-based framework for water quality assessment and device component monitoring
Rahu et al. Toward design of internet of things and machine learning-enabled frameworks for analysis and prediction of water quality
Ambelu et al. Comparison of modelling techniques to predict macroinvertebrate community composition in rivers of Ethiopia
Wu et al. Water eutrophication evaluation based on semi-supervised classification: A case study in Three Gorges Reservoir
Woo et al. Understanding the long-term emergence of autonomous vehicles technologies
Patro et al. Fish Detection in Underwater Environments Using Deep Learning: KSK Patro et al.
Thackeray et al. Quantitative analysis of the importance of wind‐induced circulation for the spatial structuring of planktonic populations
Khemiri et al. The use of otolith shape to determine stock structure of Engraulis encrasicolus along the Tunisian coast
Walia et al. Optimized custom dataset for efficient detection of underwater trash
Di Ciaccio The supporting role of Artificial Intelligence and Machine/Deep Learning in monitoring the marine environment: a bibliometric analysis
Busari et al. A review of machine learning models for harmful algal bloom monitoring in freshwater systems
Edeh et al. A novel deep learning model for predicting marine pollution for sustainable ocean management
Xia et al. Interspecific variations in fish occupancy and abundance are driven by niche characteristics in a monsoon climate river basin
Castro‐Gutiérrez et al. Using artificial neural networks and citizen science data to assess jellyfish presence along coastal areas
WO2024253874A9 (fr) Systèmes et procédés pour la traduction en temps réel de mesures de capteur aquatique en causes probables par l'intermédiaire d'une combinaison d'interrogations de cause à effet et d'une similarité sémantique basée sur un modèle de langage
Senthil Kumar et al. Eamlm: Enhanced automated machine learning model for IoT based water quality analysis with real-time dataset
Alvard et al. Identifying patch types using movement data from artisanal fishers from the commonwealth of dominica
Huang et al. Fault diagnosis in autonomous underwater vehicle propulsion system: a systematic review
CN116450856B (zh) 气象海洋非结构化文本知识构建方法、装置及电子设备
Dadheech et al. Revolutionizing Ocean Cleanup: AI and Robotics Tackle Pollution Challenges
Ermolaeva et al. Influence of the ionic composition of water on the structure of the zooplankton of the lakes of the Tazheran Steppe (Western Baikalia)
Ahamed et al. Marine Resources: Identification, Restoring, and Monitoring of Fisheries Food Resources Using Deep Learning and Image Processing
Tate et al. Using model-free reinforcement learning combined with underwater mass spectrometer and material archiving coupled to lab analysis for autonomous chemical source verifications
Kavitha et al. Artificial intelligence methods in marine biotechnology
Baltzi et al. Naiad: novel agentic intelligent autonomous system for inland water monitoring

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: 24819789

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE