-
公开(公告)号:US20220414452A1
公开(公告)日:2022-12-29
申请号:US17360666
申请日:2021-06-28
发明人: Viatcheslav Gurev , James R. Kozloski , Kenney Ng , Jaimit Parikh
摘要: Techniques regarding inferring parameters of one or more mechanistic models are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a machine learning component that can identify a causal relationship in a mechanistic model via a machine learning architecture that employs a parameter space of the mechanistic model as a learned distribution sampled within a generative adversarial network.
-
公开(公告)号:US11423775B2
公开(公告)日:2022-08-23
申请号:US16515957
申请日:2019-07-18
摘要: Methods and systems for predicting congestion duration are described. A processor can detect an occurrence of an incident in an area. The processor can receive context data associated with the area from at least one data source. The processor can execute a prediction engine using the received context data to predict a clearance time indicating a predicted completion time of post-incident activities related to the incident in the area. The processor can determine a congestion duration based on the clearance time. The congestion duration can be an estimated duration of congestion in the area in response to the occurrence of the incident. The processor can compare the congestion duration with a threshold. The processor can select, based on the comparison, at least one operation to optimize an amount of congestion in the area. The processor can execute the selected operations to optimize the amount of congestion in the area.
-
公开(公告)号:US11301948B2
公开(公告)日:2022-04-12
申请号:US16371233
申请日:2019-04-01
发明人: Komminist Weldemariam , Isaac Markus Serfaty , Michael S. Gordon , James R. Kozloski , Shikhar Kwatra
摘要: An artificial neural network trained to predict the availability of an unused duration of a parking space based on input features is executed. Input features may include at least a contextual situation associated with the second entity, a behavior factor associated with a first entity that has been using the parking space, geographical location and time, events occurring within a threshold distance from the parking space. The artificial neural network may be further trained to output a transfer affinity based on the predicted availability of an unused duration, the contextual situation associated with the second entity and the behavior factor associated with the first entity. Based at least on the transfer affinity, the second entity can be selected. The unused duration can be transferred to the second entity from the first entity. The transferring can also include storing a payment and associated computation as a blockchain node in a blockchain.
-
公开(公告)号:US11295372B2
公开(公告)日:2022-04-05
申请号:US16812128
申请日:2020-03-06
摘要: A method, system, and/or computer program product controls a self-driving vehicle (SDV) based on a purchase transaction at a point of sale (POS) device. One or more processors detects a purchase transaction at a device for a product. In response to detecting the purchase transaction at the POS device, the processors(s) transmits instructions to the SDV to transport a passenger associated with the purchase transaction from a location of the POS device to a predetermined location.
-
公开(公告)号:US11249945B2
公开(公告)日:2022-02-15
申请号:US15842582
申请日:2017-12-14
IPC分类号: G06F16/14 , G06F3/0484
摘要: An embodiment of the invention includes a method of managing data items based on context, where markers are associated with the data items, where the markers indicate states of authors of the data items when the data items were created. The markers can be associated with the data items by a processor. A query for a data item can be received from a user via an interface, where the query can include one or more markers indicative of the state of an author of the data item when the data item was created. The results of the query can be displayed, where the results of the query can include data items that are associated with the marker(s).
-
公开(公告)号:US11244574B2
公开(公告)日:2022-02-08
申请号:US16812351
申请日:2020-03-08
摘要: A method, system, and/or computer program product controls operations of an aerial drone within a predetermined airspace. One or more processors detects that the aerial drone has entered a predetermined airspace, and also determines a physical size of the aerial drone. In response to detecting that the aerial drone has entered the predetermined airspace, one or more processors directs the aerial drone to alter a velocity of the aerial drone based on its physical size.
-
公开(公告)号:US11175260B2
公开(公告)日:2021-11-16
申请号:US16174615
申请日:2018-10-30
IPC分类号: G01N27/447 , G01N33/487 , B82Y15/00
摘要: A nanopore device for molecular characterization that includes a supporting substrate. The supporting substrate has at least one nanopore where the nanopore is a carbon nanotube of a first diameter. The nanodevice is configured to provide a stimulus to the carbon nanotube causing the first diameter to change to a second diameter. The nanopore device also includes a device configured to apply the stimulus to the nanopore. The nanopore device further includes an electrical circuit configured to measure an electrical property across the nanopore, where there is a change in the electrical property when a molecule traverses the nanopore.
-
公开(公告)号:US11163964B2
公开(公告)日:2021-11-02
申请号:US16375930
申请日:2019-04-05
IPC分类号: G06F40/56 , G06F16/332 , G06N5/04 , G06F3/0481 , G06F16/9536 , H04L12/58 , G10L13/08
摘要: Embodiments of the present invention are directed to a computer-implemented method for generating a configurable conversational agent. A non-limiting example of the computer-implemented method includes providing available conversational agents to a user's computing device. The user uses a graphical user interface to choose desired characteristics of a conversational agent. The conversational agent generating service receives the chosen characteristics to generate a customized conversational agent and integrate the conversational agent into the user's system.
-
公开(公告)号:US11151616B2
公开(公告)日:2021-10-19
申请号:US16510171
申请日:2019-07-12
摘要: Context associated with content may be received. An additional content may be generated for insertion into the content. The additional content can be created to be within the context associated with the content and based on a likely responsiveness of the user to the additional content, the additional content referring to an item. The additional content preserves continuity and/or semantics in the context of the content.
-
公开(公告)号:US20210304891A1
公开(公告)日:2021-09-30
申请号:US16831428
申请日:2020-03-26
摘要: Mechanisms are provided for training a hybrid machine learning (ML) computer model to simulate a biophysical system of a patient and predict patient classifications based on results of simulating the biophysical system. A mechanistic model is executed to generate a training dataset. A surrogate ML model is trained to replicate logic of the mechanistic computer model and generate patient feature outputs based on surrogate ML model input parameters. A transformation ML model is trained to transform patient feature outputs of the surrogate ML model into a distribution of patient features. A generative ML model is trained to encode samples from a uniform distribution of input patient data into mechanistic model parameter inputs that are coherent to the target distribution of patient features and are input to the surrogate ML model. Input patient data for a patient is processed through the ML models to predict a patient classification for the patient.
-
-
-
-
-
-
-
-
-