AI ENABLED SENSOR DATA ACQUISITION
    23.
    发明申请

    公开(公告)号:US20210375492A1

    公开(公告)日:2021-12-02

    申请号:US16886428

    申请日:2020-05-28

    申请人: Hitachi, Ltd.

    摘要: Example implementations described herein can dynamically adapt to changing nature of sensor data traffic and through artificial intelligence (AI, strike a good tradeoff between reducing volume of sensed data, and retain enough data fidelity so that subsequent analytics applications perform well. The example implementations eliminate heuristic methods of setting sensing parameters (such as DAQ sampling rate, resolution etc.) and replaces them with an automated, AI driven edge solution core that can be readily ported on any Internet of Things (IoT) edge gateway that is connected to the DAQ.

    SYSTEM AND METHOD FOR MONITORING VIA SMART DEVICES

    公开(公告)号:US20210241927A1

    公开(公告)日:2021-08-05

    申请号:US17166553

    申请日:2021-02-03

    摘要: A system and method for determining abnormal conditions based on signals received from smart devices. The method includes receiving, via a controller and transmitted via one or more devices, one or more first signals indicative of one or more first statuses of the one or more devices. The method includes determining, via the controller and based on the one or more first statuses, a base model. The method includes receiving, via the controller and transmitted via the one or more devices, one or more second signals indicative of one or more second statuses of the one or more devices. The method includes comparing, via the controller, the one or more statuses to the base model and determining, via the controller and based on the comparison, an occurrence of an abnormal condition.

    REAL-TIME DYNAMIC MONITORING OF SENTIMENT TRENDS AND MITIGATION OF THE SAME IN A LIVE SETTING

    公开(公告)号:US20210224828A1

    公开(公告)日:2021-07-22

    申请号:US16745673

    申请日:2020-01-17

    摘要: A method for identifying and mitigating a negative sentiment trend derived from sentiment analysis is provided. The analysis is based on aggregating a plurality of biometric information artifacts obtained from consumers in a consumer center. The method includes harvesting the artifacts from the plurality of consumers, identifying a biometric information trend. The biometric trend includes a verbal communications trend recorded from among the plurality of consumers. The verbal communications are captured using microphone(s). The method may also include periodically updating the harvesting to update the biometric information trend. The method may also include determining, over the pre-determined amount of time, that the biometric information trend is a negative biometric information trend. In response to the determining the method may trigger, based at least in part on a slope of the negative biometric information trend, a mitigating response to the negative biometric information trend.

    Method for physical system anomaly detection

    公开(公告)号:US20210182693A1

    公开(公告)日:2021-06-17

    申请号:US16716993

    申请日:2019-12-17

    申请人: Tignis, Inc.

    摘要: A method for detecting anomalies in a physical system generates from a set of physics rules and a process graph representing the system a set of candidate physics models that assign physics rules to portions of the process graph representing sensors. Candidate physics models are rejected if an error between the models and sensor data exceed a predetermined error tolerance. Supervised learning is used to train a machine learning model to predict an error between the physics models and the sensor data. The predicted error and predicted sensor measurements from the physics models are then used to detect anomalies using unsupervised learning on a distribution of error between the predicted sensor measurements and the sensor data.

    METHODS, DEVICES, AND COMPUTER PROGRAM PRODUCTS FOR MODEL ADAPTATION

    公开(公告)号:US20210166083A1

    公开(公告)日:2021-06-03

    申请号:US16805065

    申请日:2020-02-28

    IPC分类号: G06K9/62 G06N20/10 G16Y40/20

    摘要: Embodiments of the present disclosure provide methods, devices, and computer program products for model adaptation. The method for model adaptation comprises: receiving, at a first computing device, a data set to be analyzed from a data collector and determining abnormality of the data set to be analyzed using a machine learning model deployed at the first computing device. The method further comprises transmitting, based on the determined abnormality of the data set, at least a portion of data in the data set to a second computing device, for update of the machine learning model, the second computing device having a higher computing capability than the first computing device. The method further comprises obtaining redeployment of the updated machine learning model from the second computing device.

    AUTOMATED SYSTEMS AND METHODS FOR FACILITY MANAGEMENT

    公开(公告)号:US20210065256A1

    公开(公告)日:2021-03-04

    申请号:US17002584

    申请日:2020-08-25

    申请人: Lexis B. SHONTZ

    发明人: Lexis B. SHONTZ

    摘要: Systems and methods for automated management of facility operations and information are described. A portal is provided which stores significant information about the facility, such as regulatory, safety, operational and product information. Users may access the portal by scanning a scannable placard, which may use a QR code. Portal information may be customized based on user type or identity. Useful displays are generated which overlay live, or near-live, sensor readings onto maps, blueprints or images of the facility. Facility operators can use the systems and methods to automate repurchase of materials for the facility. Regulators, consumers, first responders, and others can use the portal to obtain, at a glance, all key information about the facility. Safety is substantially enhanced by the ability to collate all important safety information in one location, and to overlay such information with live readings from the facility.

    Electronic device for providing activity information about user and method of operating the same

    公开(公告)号:US11636178B2

    公开(公告)日:2023-04-25

    申请号:US17084793

    申请日:2020-10-30

    发明人: Kwansu Park

    摘要: According to certain embodiments, an electronic device comprises a communication module; a plurality of sensors and configured to obtain sensing data; at least one processor operatively connected to the plurality of sensors and the communication module; and a memory operatively connected to the at least one processor, wherein the memory stores instructions that, when executed, cause the at least one processor to perform a plurality of operations comprising: transmitting the sensing data to a server through the communication module; receiving, from the server, information on a similarity between the sensing data and a first cluster among a plurality of clusters clustering data related to user activities, through the communication module, wherein the similarity is identified based on a center similarity score between the sensing data and the first cluster, a score that is a function of a variance of the first cluster, a score that is a function a distance between the first cluster and other clusters, and an intersection score between the first cluster and a second cluster adjacent to the first cluster; and executing a function corresponding to the sensing data based on the similarity.