公开(公告)号：US11900334B2

公开(公告)日：2024-02-13

申请号：US17385273

申请日：2021-07-26

申请人： eBay Inc.

发明人： Jeremy Leigh Cattone

IPC分类号： G06Q10/20 ,  G06Q10/087

CPC分类号： G06Q10/20 ,  G06Q10/087

摘要： An electronic garage shelf is described. The system includes an electronic garage shelf which may be a metaphor for a shelf in a garage that is used to store parts for a vehicle. Merely for example, the electronic garage shelf may store a token part that signifies a part or smart component such as an oil filter, carburetor, spark plug, on a garage shelf in the user's garage. Further, the metaphor for a shelf in the garage may be expanded to include a virtual part that represents a part or smart component the user wants to acquire. Accordingly, the system may include garage shelf information comprised of virtual part information and token part information where the virtual part information may store virtual parts signifying parts that are desirable for acquisition and the token part information may store token parts signifying parts that are in the possession of the user.

公开(公告)号：US11886809B1

公开(公告)日：2024-01-30

申请号：US17977730

申请日：2022-10-31

申请人： Adobe Inc.

发明人： Nipun Jindal ,  Anand Khanna ,  Oliver Brdiczka

IPC分类号： G06F17/00 ,  G06F40/186 ,  G06N3/08 ,  G06F3/0484 ,  G06F40/109 ,  G06F40/30

CPC分类号： G06F40/186 ,  G06F3/0484 ,  G06F40/109 ,  G06F40/30 ,  G06N3/08

摘要： In implementations of systems for identifying templates based on fonts, a computing device implements an identification system to receive input data describing a selection of a font included in a collection of fonts. The identification system generates an embedding that represents the font in a latent space using a machine learning model trained on training data to generate embeddings for digital templates in the latent space based on intent phrases associated with the digital templates and embeddings for fonts in the latent space based on intent phrases associated with the fonts. A digital template included in a collection of digital templates is identified based on the embedding that represents the font and an embedding that represents the digital template in the latent space. The identification system generates an indication of the digital template for display in a user interface.

公开(公告)号：US11886681B2

公开(公告)日：2024-01-30

申请号：US18124456

申请日：2023-03-21

申请人： eBay Inc.

发明人： David A. Ramadge ,  Justin Van Winkle ,  Corinne Elizabeth Sherman

IPC分类号： G06F3/0481 ,  G06F3/04847 ,  G06F3/04817 ,  G06F9/445 ,  G06F9/451 ,  G06F21/36

CPC分类号： G06F3/0481 ,  G06F3/04817 ,  G06F3/04847 ,  G06F9/4451 ,  G06F9/451 ,  G06F21/36

摘要： A system and method for standardizing user interface elements are presented. A first application is identified having a higher use metric than a second application, the first application including one or more user interface elements that have one or more respective parameters. The second application has one or more user interface elements that are similar to the user interface elements of the first application and has one or more respective parameters that are different than the respective parameters of the user interface elements of the first application. A determination of similarity is made between the user interface elements applications based upon at least one predetermined criterion. Based on the determination, one or more parameters of the user interface elements of the second application are modified to match one or more parameters of the first application.

公开(公告)号：US11886367B2

公开(公告)日：2024-01-30

申请号：US17545930

申请日：2021-12-08

申请人： ATI Technologies ULC

发明人： Michael E. McLean ,  Philip Ng

IPC分类号： G06F13/372 ,  G06F13/364 ,  G06F9/48 ,  G06F13/40 ,  G06F13/366

CPC分类号： G06F13/372 ,  G06F9/4812 ,  G06F13/364 ,  G06F13/366 ,  G06F13/4059

摘要： An arbitration system receives requests to access a destination during an arbitration window that spans multiple processor clock cycles. During each clock cycle, the destination is monitored to determine whether the destination is suffering from backpressure by receiving more requests than the destination is able to accommodate during the clock cycle. In response to detecting backpressure, a masking index value assigned to a requesting source is incremented, which limits an amount of requests from the source that will be granted destination access during a subsequent arbitration window. Alternatively, in response to detecting an absence of backpressure during an arbitration window, the masking index value is decremented, which increases the amount of requests from the source that will be granted destination access during a subsequent arbitration window. This arbitration process continues for successive arbitration windows, oscillating between incrementing and decrementing the masking index value during the successive arbitration windows.

公开(公告)号：US11886285B2

公开(公告)日：2024-01-30

申请号：US17843198

申请日：2022-06-17

申请人： eBay Inc.

发明人： Maxwell Henry Poole ,  Satish Sambasivan ,  Vivek Siva Kaushik

IPC分类号： G06F11/07

CPC分类号： G06F11/0793 ,  G06F11/0706

摘要： Technologies are disclosed herein for cross-correlating metrics for anomaly root cause detection. Primary and secondary metrics associated with an anomaly are cross-correlated by first using the derivative of an interpolant of data points of the primary metric to identify a time window for analysis. Impact scores for the secondary metrics can be then be generated by computing the standard deviation of a derivative of data points of the secondary metrics during the identified time window. The impact scores can be utilized to collect data relating to the secondary metrics most likely to have caused the anomaly. Remedial action can then be taken based upon the collected data in order to address the root cause of the anomaly.

公开(公告)号：US11869021B2

公开(公告)日：2024-01-09

申请号：US17503702

申请日：2021-10-18

申请人： Adobe Inc.

发明人： Kourosh Modarresi ,  Jamie Mark Diner ,  Elizabeth T. Chin ,  Aran Nayebi

IPC分类号： G06Q30/0201 ,  G06N20/00 ,  G06N20/20 ,  G06N5/01 ,  G06Q30/0251 ,  G06Q30/0202 ,  G06Q30/02

CPC分类号： G06Q30/0201 ,  G06N5/01 ,  G06N20/00 ,  G06N20/20 ,  G06Q30/02 ,  G06Q30/0202 ,  G06Q30/0269

摘要： Segment valuation techniques usable in a digital medium environment are described. To do so, a segment valuation system first identifies the attributes that are significant in achievement of a desired metric (e.g., conversion) and then values segments based on those significant attributes. Attributes are selected from the trained model based on significance of those attributes towards achieving the desired metric. A valuation of a segment may then be calculated based on the valuations of these attributes. For example, inclusion of the selected attributes within a segment, and the valuations of those selected attributes, is then used by the segment valuation system to generate data describing a value of the segment towards achieving the metric.

公开(公告)号：US11868889B2

公开(公告)日：2024-01-09

申请号：US17588516

申请日：2022-01-31

申请人： Adobe Inc.

发明人： Zhe Lin ,  Xiaohui Shen ,  Mingyang Ling ,  Jianming Zhang ,  Jason Wen Yong Kuen

IPC分类号： G06N3/08 ,  G06N3/04 ,  G06V20/20 ,  G06V20/64 ,  G06V10/82 ,  G06V20/10 ,  G06F18/214 ,  G06V10/764 ,  G06V10/44

CPC分类号： G06N3/08 ,  G06F18/214 ,  G06N3/04 ,  G06V10/454 ,  G06V10/764 ,  G06V10/82 ,  G06V20/10 ,  G06V20/20 ,  G06V20/64

摘要： In implementations of object detection in images, object detectors are trained using heterogeneous training datasets. A first training dataset is used to train an image tagging network to determine an attention map of an input image for a target concept. A second training dataset is used to train a conditional detection network that accepts as conditional inputs the attention map and a word embedding of the target concept. Despite the conditional detection network being trained with a training dataset having a small number of seen classes (e.g., classes in a training dataset), it generalizes to novel, unseen classes by concept conditioning, since the target concept propagates through the conditional detection network via the conditional inputs, thus influencing classification and region proposal. Hence, classes of objects that can be detected are expanded, without the need to scale training databases to include additional classes.

公开(公告)号：US11861763B2

公开(公告)日：2024-01-02

申请号：US17235067

申请日：2021-04-20

申请人： Adobe Inc.

发明人： Jose Ignacio Echevarria Vallespi

IPC分类号： G06T11/00

CPC分类号： G06T11/001

摘要： A contrast ratio color picker system is described that generates, based on a selected color, a contrast ratio color picker that presents a filtered palette of colors satisfying a contrast ratio threshold, relative to the selected color. To do so, the contrast ratio color picker system computes a relative luminance value for the selected color and identifies a contrast ratio threshold for the digital content. The contrast ratio color picker system then selects a palette from a target color space and generates a filtered palette by masking pixels displaying colors of the target color space palette that fail to satisfy the contrast ratio threshold. The filtered palette is then output as part of the contrast ratio color picker, which enables application of colors selected from the filtered palette to digital content.

公开(公告)号：US11860972B2

公开(公告)日：2024-01-02

申请号：US17211310

申请日：2021-03-24

申请人： Adobe Inc.

发明人： Abbas Kazerouni ,  Mohammad Ghavamzadeh

IPC分类号： G06F17/18 ,  G06Q30/0241 ,  G06Q30/0242 ,  G06F111/10

CPC分类号： G06F17/18 ,  G06Q30/0241 ,  G06Q30/0242 ,  G06F2111/10

摘要： Sequential hypothesis testing in a digital medium environment is described using continuous data. To begin, a model is received that defines at least one data distribution. Testing data is also received that describes an effect of user interactions with the plurality of options of digital content on achieving an action using continuous non-binary data. Values of parameters of the model are then estimated for each option of the plurality of options based on the testing data. In one example. A variance estimate is then generated based on the estimated values of the parameters of the model for each option of the plurality of options. From this, a determination is made as to a decision boundary based on the variance estimate and an estimate for a mean value of each option of the plurality of options based on the testing data.

公开(公告)号：US11853107B2

公开(公告)日：2023-12-26

申请号：US17006812

申请日：2020-08-29

申请人： MachEye, Inc.

发明人： Ramesh Panuganty ,  Chandrasekhar Varada ,  Gopikrishna Putti

IPC分类号： G06F16/24 ,  G06F16/2453 ,  G06F16/2452 ,  G06F9/50 ,  G06F16/242 ,  G06F9/445 ,  G06F16/248

CPC分类号： G06F16/24549 ,  G06F9/4451 ,  G06F9/505 ,  G06F16/244 ,  G06F16/248 ,  G06F16/24522

摘要： Techniques are described for dynamic phase generation and load reduction for a query. A query, for instance, is based on user input of a query in a natural language (NL) form, e.g., an NL query. Generally, an NL query may include multiple terms and/or phrases that make up a complex query, such as a sentence in a human-readable language. Accordingly, to enable a query result to be generated, the NL query is parsed into multiple logical sections and query contexts are determined for the logical sections. A set of search phases is generated based on the logical sections and the query contexts. The search phases can then be executed in a specific execution order to generate a query result for the NL query.