-
公开(公告)号:US10832554B1
公开(公告)日:2020-11-10
申请号:US16682751
申请日:2019-11-13
摘要: Aspects of the disclosure provide for a system. In some examples, the system comprises a first sensor associated with first and second attributes and a second sensor associated with the second attribute and a third attribute. The system further comprises a processor communicatively coupled to the first and second sensors. The processor is configured to identify a number of activations of the first sensor within a time window, identify a number of activations of the second sensor within the time window, and construct a sensor vector identifying a number of first attribute activations based on the first number of activations of the first sensor, a number of second attribute activations based on the number of activations of the first sensor and the number of activations of the second sensor, and a number of third attribute activations based on the number of activations of the second sensor.
-
公开(公告)号:US11507862B2
公开(公告)日:2022-11-22
申请号:US16846375
申请日:2020-04-12
摘要: A computer-implemented method, a computer program product, and a computer system for determining skill adjacencies using a machine learning model. A computer calculates first similarity scores between first skill vectors obtained from one or more training datasets and second similarity scores between the first skill vectors and skill category vectors pre-calculated from job requisitions, using both a reference corpus word embedding model and a target corpus word embedding model. The computer generates features extracted from the first similarity scores and the second similarity scores. Based on the features, the computer trains a machine learning model for classifying combinations of skills as adjacent and non-adjacent. The machine learning model is used to determine skill adjacencies between skills extracted from the job requisitions and skills extracted from resumes.
-
公开(公告)号:US20220311611A1
公开(公告)日:2022-09-29
申请号:US17215102
申请日:2021-03-29
摘要: A node in a blockchain network may initiate a non-fungible token identity, establish a profile for the non-fungible token identity, receive reputation data related to the non-fungible token identity, determine, based on the reputation data, a reputation score, append the non-fungible token identity with the reputation score as a non-fungible token metadata tag, and upload the non-fungible token identity and the metadata tag to an ID repository.
-
公开(公告)号:US11222143B2
公开(公告)日:2022-01-11
申请号:US16215845
申请日:2018-12-11
发明人: Scott Gerard , Donna K. Byron
摘要: Provided are embodiments for a method, system, and computer program product for operating a certified information verification service. Some embodiments include receiving an article including one or more claims, and extracting the one or more claims from the article. The one or more claims are analyzed by the one or more information verification services, and a report for the article is generated based on the analysis.
-
公开(公告)号:US20210319334A1
公开(公告)日:2021-10-14
申请号:US16846375
申请日:2020-04-12
摘要: A computer-implemented method, a computer program product, and a computer system for determining skill adjacencies using a machine learning model. A computer calculates first similarity scores between first skill vectors obtained from one or more training datasets and second similarity scores between the first skill vectors and skill category vectors pre-calculated from job requisitions, using both a reference corpus word embedding model and a target corpus word embedding model. The computer generates features extracted from the first similarity scores and the second similarity scores. Based on the features, the computer trains a machine learning model for classifying combinations of skills as adjacent and non-adjacent. The machine learning model is used to determine skill adjacencies between skills extracted from the job requisitions and skills extracted from resumes.
-
公开(公告)号:US20210350078A1
公开(公告)日:2021-11-11
申请号:US16868575
申请日:2020-05-07
发明人: Smitashree Choudhury , Stephen Mitchell , Scott Gerard , Abhay Choudhary , Paul Charles James Dunning , Jacek Adam Piskorski , Wing Yin Leung , David Glenn George
IPC分类号: G06F40/284 , G06F40/30 , G06N20/00 , G06Q10/10
摘要: A method, computer system, and a computer program product for semantic matching is provided. The present invention may include pre-processing and normalizing a job title. The present invention may include deconstructing the job title based on at least one semantic element. The present invention may include training a machine learning model. The present invention may include creating a contextual word representation of the job title using the at least one semantic element of the job title. The present invention may include computing a similarity score for each of the at least one semantic element of the job title. The present invention may lastly include applying a weight to the computed similarity score before making a final match assessment.
-
公开(公告)号:US20190387057A1
公开(公告)日:2019-12-19
申请号:US16008721
申请日:2018-06-14
摘要: A system is provided for inferring sensor topology in a structure. The system includes a receiver, a server communicatively coupled to the receiver and a sensor topology engine communicatively coupled to the receiver and the server. The receiver is configured to receive identification information that sensors have been and deployed throughout the structure to sense a presence of an operator and to receive sensor readings from the sensors and couple the sensor readings to the sensor topology engine. The sensor topology engine is further configured analyze the identification information and the sensor readings to infer zones of the multiple spaces in which the presence of the operator is sensed by at least one of the sensors, borders of each of the zones, and dead zones adjacent to one or more of the zones in which the presence of the operator is not sensed and build a topological graph.
-
公开(公告)号:US11507769B2
公开(公告)日:2022-11-22
申请号:US16217288
申请日:2018-12-12
发明人: Susann Marie Keohane , Scott Gerard , Aliza Heching , Samuel Scott Adams , Mohammad Arif Ul Alam
摘要: A method and system to interpret sensor transmission patterns to analyze anomalies in a smart environment include obtaining a map of the smart environment, the map including an indication of obstructions and openings. The method includes determining an initial location of each sensor of a plurality of sensors in the smart environment. Each sensor emits a transmission after each detection. The method also includes identifying an initial transmission pattern associated with each sensor, and identifying a change in the initial transmission pattern of a sensor among the plurality of sensors. The change is interpreted to determine whether the change in the initial transmission pattern of the sensor among the plurality of sensors is due to movement or obstruction of the sensor. Action is taken based on a determination that the sensor among the plurality of sensors is obstructed or removed.
-
公开(公告)号:US20200184109A1
公开(公告)日:2020-06-11
申请号:US16215845
申请日:2018-12-11
发明人: Scott Gerard , Donna K. Byron
摘要: Provided are embodiments for a method, system, and computer program product for operating a certified information verification service. Some embodiments include receiving an article including one or more claims, and extracting the one or more claims from the article. The one or more claims are analyzed by the one or more information verification services, and a report for the article is generated based on the analysis.
-
-
-
-
-
-
-
-