知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

308 records (took 0.033 seconds)

    SYSTEMS AND METHODS FOR RULE-BASED MACHINE LEARNING MODEL PROMOTION
    11.
    发明公开
    SYSTEMS AND METHODS FOR RULE-BASED MACHINE LEARNING MODEL PROMOTION 审中-公开

    公开(公告)号：US20230281482A1

    公开(公告)日：2023-09-07

    申请号：US17653596

    申请日：2022-03-04

    Applicant: JPMORGAN CHASE BANK, N.A.

    Inventor： Eyal LANTZMAN

    IPC: G06N5/02

    CPC classification number: G06N5/027

    Abstract: Systems and methods for rule-based machine learning model promotion are disclosed. In accordance with aspects, a method may include providing a rules engine that defines a software object model, and an evaluation framework. A model metadata file having a format that is based on the software object model can be generated. The model metadata file can store metadata associated with the model. A model rule file having a format based on the software object model and that defines rule criteria for evaluating the metadata can be generated. The rules engine can instantiate a software object based on the software object model and parse the model rule file to determine rule criteria and parse the model metadata file to determine a parameter value associated with the rule criteria. The rules engine can evaluate the parameter value against a rule and provide a promotion decision for the model.

    Rule testing framework for executable rules of a service provider system
    12.
    发明授权
    Rule testing framework for executable rules of a service provider system 有权

    公开(公告)号：US11748247B2

    公开(公告)日：2023-09-05

    申请号：US17533039

    申请日：2021-11-22

    Applicant: PAYPAL, INC.

    Inventor： Raveendra Babu Chikkala ,  Ramaguru Ramasubbu

    IPC: G06F9/44 ,  G06F11/36 ,  G06N5/02 ,  G06Q20/10

    CPC classification number: G06F11/3692 ,  G06F11/3684 ,  G06N5/027 ,  G06Q20/10

    Abstract: There are provided systems and methods for a rule testing framework for executable rules of a service provider system. During processing rule implementation and/or testing for rules currently implemented in production systems, different values for the variables and attributes of the rule may be required to be tested to ensure proper rule functioning. In order to test the rule, the expression of the rule is determined, and each variable is considered in turn. The expression is evaluated so that the selected variable becomes the output of the expression. Thus, the values of the other variables may then be determined so that the selected variable is the output of the expression. The rule may then be tested for positive and negative values of the selected variable so that the rules functioning for the selected variable is tested.

    High performance machine learning inference framework for edge devices
    13.
    发明授权
    High performance machine learning inference framework for edge devices 有权

    公开(公告)号：US11704577B1

    公开(公告)日：2023-07-18

    申请号：US17716945

    申请日：2022-04-08

    Applicant: Amazon Technologies, Inc.

    Inventor： Gang Chen ,  Long Gao ,  Eduardo Manuel Calleja

    IPC: G06N5/02 ,  G06N20/00 ,  G06F16/11

    CPC classification number: G06N5/027 ,  G06F16/116 ,  G06N20/00

    Abstract: Techniques for high-performance machine learning (ML) inference in heterogenous edge devices are described. A ML model trained using a variety of different frameworks is translated into a common format that is runnable by inferences engines of edge devices. The translated model is optimized in hardware-agnostic and/or hardware-specific ways to improve inference performance, and the optimized model is sent to the edge devices. The inference engine for any edge device can be accessed by a customer application using a same defined API, regardless of the hardware characteristics of the edge device or the original format of the ML model.

    RISK ASSESSMENT APPARATUS, RISK ASSESSMENT METHOD, AND PROGRAM
    14.
    发明公开
    RISK ASSESSMENT APPARATUS, RISK ASSESSMENT METHOD, AND PROGRAM 审中-公开

    公开(公告)号：US20230177362A1

    公开(公告)日：2023-06-08

    申请号：US17911715

    申请日：2020-03-30

    Applicant: NEC Corporation

    Inventor： Yoshihiro OKADA

    IPC: G06N5/02

    CPC classification number: G06N5/027

    Abstract: There is provided a risk assessment apparatus having a model acquisition part that acquires at least one explainable predictive model; a risk determination part that determines risk in the at least one model on the basis of the at least one model and ethical risk factor information, which is information that is an ethical risk factor; a model selection part that selects a model on the basis of the result of risk determination; and a model output part that outputs the selected model.

    FRAMEWORK TO ASSESS TECHNICAL FEASIBILITY OF DESIGNS FOR ADDITIVE MANUFACTURING
    15.
    发明申请
    FRAMEWORK TO ASSESS TECHNICAL FEASIBILITY OF DESIGNS FOR ADDITIVE MANUFACTURING 审中-公开

    公开(公告)号：US20190220754A1

    公开(公告)日：2019-07-18

    申请号：US16172681

    申请日：2018-10-26

    Applicant: Tata Consultancy Services Limited

    Inventor： Sukhdev BALAJI ,  Goutham PATHURI ,  Ankur KRISHNA ,  Pramod Ramdas ZAGADE ,  Arockiam DANIEL

    IPC: G06N5/02 ,  G06N5/04 ,  G06F17/50 ,  B33Y50/00

    CPC classification number: G06N5/027 ,  B33Y50/00 ,  G06F17/50 ,  G06N5/04

    Abstract: A framework for assessing technical feasibility of additive manufacturing of an engineering design. This framework needs to be based on preliminary identification of key parameters that influence the decision making process. The parameters may also be customized for a particular application. Each of these parameters can be assigned weightage either relative or arrived at by paired comparison using a pre-determined minimum point method. Each of the attributes are then assigned scores which are then multiplied by the weightages assigned. The summation of all such scores on a weighted average basis indicates the potential for 3D printing of that part or assembly. It offers to select the right part to leverage the benefit of additive manufacturing. It narrows down on the ideal manufacturing process for the qualified parts and proposes to reduce subjectivity by using paired comparison of attributes. It also provides a faster assessment of technical aspects of the design.

    AUTONOMOUS LEARNING PLATFORM FOR NOVEL FEATURE DISCOVERY
    18.
    发明申请
    AUTONOMOUS LEARNING PLATFORM FOR NOVEL FEATURE DISCOVERY 审中-公开

    公开(公告)号：US20180330258A1

    公开(公告)日：2018-11-15

    申请号：US15590988

    申请日：2017-05-09

    Applicant: Theodore D. Harris ,  Craig O'Connell ,  Yue Li ,  Tatiana Korolevskaya

    Inventor： Theodore D. Harris ,  Craig O'Connell ,  Yue Li ,  Tatiana Korolevskaya

    IPC: G06N7/00 ,  G06N5/02 ,  G06N5/00

    CPC classification number: G06N7/005 ,  G06N5/003 ,  G06N5/022 ,  G06N5/027

    Abstract: Embodiments are directed to a method of performing autonomous learning for updating input features used for an artificial intelligence model, the method comprising receiving updated data of an information space that includes a graph of nodes having a defined topology, the updated data including historical data of requests to the artificial intelligence model and output results associated with the requests, wherein different categories of input data corresponds to different input nodes of the graph. The method may further comprise updating edge connections between the nodes of the graph by performing path optimizations that each use a set of agents to explore the information space over cycles to reduce a cost function, each connection including a strength value, wherein during each path optimization, path information is shared between the rest of agents at each cycle for determining a next position value for each of the set of agents in the graph.

    Knowledge representation on action graph database
    20.
    发明授权
    Knowledge representation on action graph database 有权

    公开(公告)号：US10019538B2

    公开(公告)日：2018-07-10

    申请号：US14869137

    申请日：2015-09-29

    Applicant: TATA CONSULTANCY SERVICES LIMITED

    Inventor： Rajesh Kartha ,  Supriya V ,  Viju Chacko ,  Shampa Sarkar

    IPC: G06F17/00 ,  G06F17/30 ,  G06N5/02 ,  G06F17/27

    CPC classification number: G06F16/9024 ,  G06F16/367 ,  G06F17/2785 ,  G06N5/027

    Abstract: Knowledge representation in multi-layered database includes systems and methods for storing and retrieving data in the multi-layered database. In the multi-layered database, an action graph database includes participant-entity nodes corresponding to real world entities and action nodes corresponding to action capabilities of the real world entities. Each of the participant-entity nodes and the action nodes is associated with properties, relationships, and relationship properties. Underlying the action graph layer is a standard graph layer that stores nodes, node properties associated with the nodes, edges, and edge properties associated with the edges, wherein the nodes correspond to the participant-entity nodes and the action nodes. Further, underlying the standard graph layer is a backend database layer that stores corresponding data and metadata.

Patent Agency Ranking