利索-全球专利检索

  1. Login
  2. Sign Up

Search Results

4076 records (took 0.039 seconds)

    Inferring brand similarities using graph neural networks and selection prediction
    85.
    发明授权
    Inferring brand similarities using graph neural networks and selection prediction 有权

    公开(公告)号：US11966405B1

    公开(公告)日：2024-04-23

    申请号：US18064591

    申请日：2022-12-12

    Applicant: Amazon Technologies, Inc.

    Inventor： Chaoran Wei ,  Shaunak Mishra ,  Anirban Sengupta ,  Ravendar Lal

    IPC: G06F16/2457 ,  G06N3/045

    CPC classification number: G06F16/24578 ,  G06N3/045

    Abstract: Disclosed are various embodiments for inferring brand similarities using graph neural networks and selection prediction. In one embodiment, a brand-to-brand graph is generated indicating similarities between a set of brands according to at least one of: click-through data or conversion data. Using a first graph neural network (GNN) tower, the brand-to-brand graph is analyzed to determine brand similarities among a first brand identified from a search query and a first set of other brands. Using a second GNN tower, the brand-to-brand graph is analyzed to determine brand similarities among a second brand and a second set of other brands. A level of similarity between the first brand and the second brand is determined based at least in part on an output of the first GNN tower and an output of the second GNN tower.

    Storage medium, pattern search device, and pattern search method
    87.
    发明授权
    Storage medium, pattern search device, and pattern search method 有权

    公开(公告)号：US11960491B2

    公开(公告)日：2024-04-16

    申请号：US17676926

    申请日：2022-02-22

    Applicant: FUJITSU LIMITED

    Inventor： Hiroaki Iwashita

    IPC: G06F16/2457 ,  G06F16/22 ,  G06F16/248 ,  G06F16/28 ,  G06N7/01

    CPC classification number: G06F16/24578 ,  G06F16/2246 ,  G06F16/248 ,  G06F16/285 ,  G06N7/01

    Abstract: A non-transitory computer-readable storage medium storing a pattern search program that causes a computer to execute a process, the process includes designating priority ranks of each of attributes included in a plurality of attribute patterns that indicate one or more attributes, based on an inclusion relationship between occurrence sets of a plurality of samples with respect to each of the attributes included in the plurality of attribute patterns; and determining whether each of the plurality of attribute patterns is an emerging pattern according to a search order based on the priority ranks, when a frequency of occurrence of the plurality of samples in a first attribute pattern is less than the frequency of occurrence of the plurality of samples in a second attribute pattern that has all the attributes except one of the attributes with lowest one of the priority ranks among the attributes included in the first attribute pattern.

    METHODS, APPARATUSES AND COMPUTER PROGRAM PRODUCTS FOR OUTPUTTING IMPROVED AUTOSUGGESTIONS IN A GROUP-BASED COMMUNICATION PLATFORM
    88.
    发明公开
    METHODS, APPARATUSES AND COMPUTER PROGRAM PRODUCTS FOR OUTPUTTING IMPROVED AUTOSUGGESTIONS IN A GROUP-BASED COMMUNICATION PLATFORM 审中-公开

    公开(公告)号：US20240119060A1

    公开(公告)日：2024-04-11

    申请号：US18543205

    申请日：2023-12-18

    Applicant: Salesforce, Inc.

    Inventor： Andrew S. Morrison ,  Aaron J. Maurer

    IPC: G06F16/2457 ,  G06F16/25

    CPC classification number: G06F16/24578 ,  G06F16/252

    Abstract: An apparatus is provided for outputting suggested query items by a group-based communication platform. The apparatus may include at least one memory and at least one processor configured to detect group-based communication platform query data stored in a memory of the apparatus. The processor is also configured to rank suggested query items based on the group-based communication platform query data. The processor is further configured to detect non-keystroke engagement of a search input interface of the group-based communication platform. The processor is further configured to determine a first subset of the suggested query items based on the ranking of the suggested query items and automatically launch a query suggestion interface including a first subset of the suggested query items in response to detecting the non-keystroke engagement of the search input interface. Corresponding methods and computer program products are also provided.

    System and Methods for Monitoring and Quantifying Influential Effect of Social Media Accounts
    90.
    发明公开
    System and Methods for Monitoring and Quantifying Influential Effect of Social Media Accounts 审中-公开

    公开(公告)号：US20240111776A1

    公开(公告)日：2024-04-04

    申请号：US17959154

    申请日：2022-10-03

    Applicant: StratInt Research

    Inventor： Lusine Kodagolian

    IPC: G06F16/2457 ,  G06Q50/00

    CPC classification number: G06F16/24578 ,  G06Q50/01

    Abstract: An influence quantification system and associated methods are disclosed for monitoring and quantifying a real-time influential effect of an at least one social media account hosted on an at least one social media platform. In at least one embodiment, a computing device is configured for receiving and processing data related to the at least one social media account. An influencer record is associated with each of the at least one social media account, with each influencer record containing at least one of a unique record identifier, a post count containing a numerical value corresponding to a quantity of discrete content posts made by the associated social media account, a follower count containing a numerical value corresponding to a quantity of followers of the associated social media account, a numerical engagement rate, and an influencer score containing a numerical value corresponding to the relative effectiveness of the associated social media account.

Patent Agency Ranking