Method, System, and Computer Program Product for Dynamically Assigning an Inference Request to a CPU or GPU

    公开(公告)号:US20210232399A1

    公开(公告)日:2021-07-29

    申请号:US16750100

    申请日:2020-01-23

    摘要: A method for dynamically assigning an inference request is disclosed. A method for dynamically assigning an inference request may include determining at least one model to process an inference request on a plurality of computing platforms, the plurality of computing platforms including at least one Central Processing Unit (CPU) and at least one Graphics Processing Unit (GPU), obtaining, with at least one processor, profile information of the at least one model, the profile information including measured characteristics of the at least one model, dynamically determining a selected computing platform from between the at least one CPU and the at least one GPU for responding to the inference request based on an optimized objective associated with a status of the computing platform and the profile information, and routing, with at least one processor, the inference request to the selected computing platform. A system and computer program product are also disclosed.

    Method, System, and Computer Program Product for Simulating Fraud Detection Rules

    公开(公告)号:US20210103927A1

    公开(公告)日:2021-04-08

    申请号:US16592374

    申请日:2019-10-03

    IPC分类号: G06Q20/40

    摘要: Methods, systems, and computer program products are provided for simulating fraud detection rules. The method includes: receiving user input including at least one proposed fraud detection rule in at least one input field of a user interface; simulating the at least one proposed fraud detection rule by: querying historical transaction data based on the at least one proposed fraud detection rule; and generating a simulation result for the at least one proposed fraud detection rule based on the queried historical transaction data; and displaying the simulation result on the user interface. The simulation result is displayed on the user interface asynchronously and in near real-time relative to receiving the user input.