专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明专利

AU2021104408A4 Method for automating Smart Green House using IoT 未知
公开(公告)号：AU2021104408A4
公开(公告)日：2022-05-19
申请号：AU2021104408
申请日：2021-07-21
申请人： DAS SUNANDA , G MURUGESAN , H PANEM CHARANARUR , M DARSANA , MEHBODNIYA ABOLFAZL , N PRIYA , PALLATHADKA HARIKUMAR , SHINDE SAGAR UTTAM , UMAR SYED , VENAIK ANITA
发明人： MEHBODNIYA ABOLFAZL , G MURUGESAN , VENAIK ANITA , SHINDE SAGAR UTTAM , UMAR SYED , PALLATHADKA HARIKUMAR , N PRIYA , DAS SUNANDA , M DARSANA , H PANEM CHARANARUR
IPC分类号： H04Q9/02 , G06Q50/02 , G16Y10/05 , G16Y20/10 , H04W4/38
摘要： Method for automating Smart Green House using IoT The optimization of land area and people in the agricultural sector is a difficult undertaking that all farmers must do. It is due to a lack of information and communication in the agricultural industry that the costs and time required to establish a farming operation with all of the essential natural resources are not correctly calculated. The majority of farmers continue to use traditional agricultural methods to cultivate their crops, with only a small number of them adopting cutting-edge techniques in recent years. The Internet of Things (IoT) is the framework that is utilised to give automated control over agricultural land and monitoring through the use of sensors on plants. Perhaps sensors are used to collect data from the entire plant, which is then transferred to a centralised controller for analysis, allowing farmers to make more informed decisions. In the event of short-term plant culture, the effects on plant growth are not noticeable for a considerable period of time. In order to address this issue, the Smart Green House concept has been established in the agricultural area in order to promote plant development within a specified time period. By utilising an Internet of Things-enabled framework that is controlled by a Smart Green House Intelligence Decision Support System (SGHIDSS), it is feasible to improve the overall quality of the system. The system is comprised of a number of sensors that are strategically placed throughout a greenhouse and that automatically make decisions about actions such as water supply and nutrition level. In an automated environment, all of the sensors and control systems are in full operation, allowing the greenhouse technique to be successful for small farms. For small-scale farmers and people, this invention gives a framework or model that they can utilise to quickly and easily deploy the smart greenhouse in their own areas. Additionally, it supplies less workforce and a smaller number of natural resources for the development of agricultural production and production. Ventilation -1 Unit Temperature LightIntensity Uni. & Humidity j sensor GSM Alarm sensor Smoke/Gas Cooling Fan Soil~tumsensor |Buzzer Sensor ExhaustFan Ultra sonic Arduino Micro o ContingSoftware Sensor Controller Water Pump pH sensor LCSdisplay Motor LDR sensor system PIR sensor Light bulbs Cloud Mobile App Storage Figure 1: Automated Smart Green House Architecture

2. 发明专利

AU2020103586A4 LNUM- Human Immune Detection System: Human Immune Level Detection and Notification System Using Mobile Phone 未知
公开(公告)号：AU2020103586A4
公开(公告)日：2021-02-04
申请号：AU2020103586
申请日：2020-11-20
申请人： BODE PRASAD , CHORDIYA S B , DANIEL RAVURI , GOGINENI HIMABINDU , JALUMURI ANITHA , KIRAN PASAM PRUDHVI , KUMAR SARKAR BIPLAB , RAO M VENKATA , SAINATH N , UMAR SYED
发明人： UMAR SYED , DANIEL RAVURI , BODE PRASAD , JALUMURI ANITHA , GOGINENI HIMABINDU , KIRAN PASAM PRUDHVI , SAINATH N , CHORDIYA S B , RAO M VENKATA , KUMAR SARKAR BIPLAB
IPC分类号： A61K39/12 , A61K39/08 , A61K39/42 , A61P31/04 , A61P31/14 , A61P37/04
摘要： Our invention "LNUM- Human Immune Detection System" is a method of modulating an immune response and detection in a subject by using a binding protein (e.g., an antibody or an antigen-binding portion of an antibody) to mask or alter an epitope on an antigen that is administered to the subject. The LNUM- human immune detection system is also methods are useful for inducing an immune response (e.g., production of an antibody) in the subject to a non-immunodominant epitope on the antigen and the invention also encompasses an antigen- binding protein complex comprising at least one binding protein bound to at least one immunodominant epitope on an antigen. The LNUM- human immune detection system is an infectious organism antigen may be a viral antigen (e.g, a filovirus antigen) or a bacterial antigen (e.g., a Clostridium difficile antigen) and some embodiments the filovirus antigen is a Marburg virus antigen or an Ebola virus antigen. For example: the filovirus antigen may be a filovirus glycoprotein and in certain embodiments, the filovirus glycoprotein comprises the GP2 subunit or the GP1 subunit of the Marburg virus glycoprotein. The LNUM- human immune detection system is the Clostridium difficile antigen is C. difficile toxin A or C. difficile toxin B. In some aspects the antigen can be a polypeptide corresponding to a domain or subdomain of the target antigen. Tonsil Right Cenvical lymph nodes lympaticThymus gland Axillery lymph nodes Thoracieduct Spleen Inguinal lymph nodes Popilteat lymph nodes FIG.1: Nature Human Immune Status

3. 发明授权

US08473292B2 System and method for generating user models from transcribed dialogs 有权
标题翻译：从转录对话框生成用户模型的系统和方法
公开(公告)号：US08473292B2
公开(公告)日：2013-06-25
申请号：US12552832
申请日：2009-09-02
申请人： Jason Williams , Umar Syed
发明人： Jason Williams , Umar Syed
IPC分类号： G10L15/26
CPC分类号： G10L15/265 , G10L15/07 , G10L2015/0631
摘要： Disclosed herein are systems, computer-implemented methods, and computer-readable storage media for generating personalized user models. The method includes receiving automatic speech recognition (ASR) output of speech interactions with a user, receiving an ASR transcription error model characterizing how ASR transcription errors are made, generating guesses of a true transcription and a user model via an expectation maximization (EM) algorithm based on the error model and the respective ASR output where the guesses will converge to a personalized user model which maximizes the likelihood of the ASR output. The ASR output can be unlabeled. The method can include casting speech interactions as a dynamic Bayesian network with four variables: (s), (u), (r), (m), and encoding relationships between (s), (u), (r), (m) as conditional probability tables. At each dialog turn (r) and (m) are known and (s) and (u) are hidden.
摘要翻译：这里公开了用于生成个性化用户模型的系统，计算机实现的方法和计算机可读存储介质。该方法包括接收与用户的语音交互的自动语音识别（ASR）输出，接收表征如何进行ASR转录错误的ASR转录错误模型，通过期望最大化（EM）算法产生真实转录的猜测和用户模型基于错误模型和相应的ASR输出，其中猜测将会聚合到使ASR输出的可能性最大化的个性化用户模型。 ASR输出可以是未标记的。该方法可以包括将语音交互作为具有四个变量的动态贝叶斯网络：（s），（u），（r），（m）以及（s），（u），（r），）作为条件概率表。在每个对话中，转（r）和（m）是已知的，（s）和（u）被隐藏。

4. 发明申请

US20110054893A1 SYSTEM AND METHOD FOR GENERATING USER MODELS FROM TRANSCRIBED DIALOGS 有权
标题翻译：用于生成用户模型的系统和方法
公开(公告)号：US20110054893A1
公开(公告)日：2011-03-03
申请号：US12552832
申请日：2009-09-02
申请人： Jason Williams , Umar Syed
发明人： Jason Williams , Umar Syed
IPC分类号： G10L15/26
CPC分类号： G10L15/265 , G10L15/07 , G10L2015/0631
摘要： Disclosed herein are systems, computer-implemented methods, and computer-readable storage media for generating personalized user models. The method includes receiving automatic speech recognition (ASR) output of speech interactions with a user, receiving an ASR transcription error model characterizing how ASR transcription errors are made, generating guesses of a true transcription and a user model via an expectation maximization (EM) algorithm based on the error model and the respective ASR output where the guesses will converge to a personalized user model which maximizes the likelihood of the ASR output. The ASR output can be unlabeled. The method can include casting speech interactions as a dynamic Bayesian network with four variables: (s), (u), (r), (m), and encoding relationships between (s), (u), (r), (m) as conditional probability tables. At each dialog turn (r) and (m) are known and (s) and (u) are hidden.
摘要翻译：这里公开了用于生成个性化用户模型的系统，计算机实现的方法和计算机可读存储介质。该方法包括接收与用户的语音交互的自动语音识别（ASR）输出，接收表征如何进行ASR转录错误的ASR转录错误模型，通过期望最大化（EM）算法产生真实转录的猜测和用户模型基于错误模型和相应的ASR输出，其中猜测将会聚合到使ASR输出的可能性最大化的个性化用户模型。 ASR输出可以是未标记的。该方法可以包括将语音交互作为动态贝叶斯网络，具有四个变量：（s），（u），（r），（m）以及（s），（u），（r），）作为条件概率表。在每个对话中，转（r）和（m）是已知的，（s）和（u）被隐藏。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式