专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO2022177711A1 LOCALIZING RELEVANT OBJECTS IN MULTI-OBJECT IMAGES 审中-公开
公开(公告)号：WO2022177711A1
公开(公告)日：2022-08-25
申请号：PCT/US2022/013815
申请日：2022-01-26
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： BARKAN, Oren , HERTZ, Amir , ARMSTRONG, Omri , KOENIGSTEIN, Noam
IPC分类号： G06V10/82 , G06V10/25 , G06V20/70 , G06F16/58 , G06Q30/06 , G06F16/53
摘要： Solutions for localizing relevant objects in multi-object images include receiving a multi-object image; detecting a plurality of detected objects within the multi-object image; generating a primary heatmap for the multi-object image, the primary heatmap having at least one region of interest; determining a relevant detected object corresponding to a region of interest in the primary heatmap; determining an irrelevant detected object not corresponding to a region of interest in the primary heatmap; and indicating the relevant detected object as an output result but not indicating the irrelevant detected object as an output result. Some examples identify a plurality of objects that are visually similar to the relevant object and displaying the visually similar objects to a user, for example as recommendations of alternative catalog items on an e-commerce website. Some examples are able to identify a plurality of relevant objects and display multiple sets of visually similar objects.

2. 发明申请

WO2015153240A1 DIRECTED RECOMMENDATIONS 审中-公开
标题翻译：指导性建议
公开(公告)号：WO2015153240A1
公开(公告)日：2015-10-08
申请号：PCT/US2015/022602
申请日：2015-03-26
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： NICE, Nir , KOENIGSTEIN, Noam , PAQUET, Ulrich , FINKELSTEIN, Yehuda
IPC分类号： G06Q30/06
CPC分类号： G06Q30/0631 , G06Q30/02
摘要： Example apparatus and methods perform matrix factorization (MF) on a usage matrix to create a latent space that describes similarities between items in the usage matrix. The usage matrix relates source items that a user already has to target items that a user might acquire. A cell in the usage matrix may store a value that describes the likelihood (e.g., probability) that an acquisition of item x will lead to an acquisition of item y. The value stored in cell (x,y) is not transitive with the value stored in cell (y,x). Values that are missing in the usage matrix may be computed using vectors in the latent space. Once the usage matrix is updated, a directed recommendation may be produced from data in the usage matrix. Initial values in the usage matrix may be produced from data associated with actual acquisitions.
摘要翻译：示例性设备和方法在使用矩阵上执行矩阵分解（MF）以创建描述使用矩阵中的项之间的相似性的潜在空间。使用矩阵涉及用户已经必须定位用户可能获取的项目的源项目。使用矩阵中的单元可以存储描述项目x的获取将导致项目y的获取的可能性（例如，概率）的值。存储在单元格（x，y）中的值不与存储在单元格（y，x）中的值进行传递。使用矩阵中缺少的值可以使用潜在空间中的向量来计算。一旦使用矩阵被更新，可以从使用矩阵中的数据产生定向推荐。使用矩阵中的初始值可以由与实际采集相关联的数据生成。

3. 发明申请

WO2022066248A1 DIAGNOSTIC TOOL FOR DEEP LEARNING SIMILARITY MODELS 审中-公开
公开(公告)号：WO2022066248A1
公开(公告)日：2022-03-31
申请号：PCT/US2021/036074
申请日：2021-06-07
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： BARKAN, Oren , ARMSTRONG, Omri , KATZ, Ori , KOENIGSTEIN, Noam
IPC分类号： G06K9/46 , G06K9/62
摘要： A diagnostic tool for deep learning similarity models and image classifiers provides valuable insight into neural network decision-making. A disclosed solution generates a saliency map by: receiving a baseline image and a test image; determining, with a convolutional neural network (CNN), a first similarity between the baseline image and the test image; based on at least determining the first similarity, determining, for the test image, a first activation map for at least one CNN layer; based on at least determining the first similarity, determining, for the test image, a first gradient map for the at least one CNN layer; and generating a first saliency map as an element-wise function of the first activation map and the first gradient map. Some examples further determine a region of interest (ROI) in the first saliency map, cropping the test image to an area corresponding to the ROI, and determine a refined similarity score.

4. 发明申请

WO2021118737A1 SENTENCE SIMILARITY SCORING USING NEURAL NETWORK DISTILLATION 审中-公开
公开(公告)号：WO2021118737A1
公开(公告)日：2021-06-17
申请号：PCT/US2020/059907
申请日：2020-11-11
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： BARKAN, Oren , RAZIN, Noam , KOENIGSTEIN, Noam
IPC分类号： G06F40/30 , G06N3/02
摘要： The disclosure herein describes a system and method for attentive sentence similarity scoring. A distilled sentence embedding (DSE) language model is trained by decoupling a transformer language model using knowledge distillation. The trained DSE language model calculates sentence embeddings for a plurality of candidate sentences for sentence similarity comparisons. An embedding component associated with the trained DSE language model generates a plurality of candidate sentence representations representing each candidate sentence in the plurality of candidate sentences which are stored for use in analyzing input sentences associated with queries or searches. A representation is created for the selected sentence. This selected sentence representation is used with the plurality of candidate sentence representations to create a similarity score for each candidate sentence-selected sentence pair. A retrieval component identifies a set of similar sentences from the plurality of candidate sentences responsive to the input query based on the set of similarity scores.

5. 发明申请

WO2016040211A1 MODIFIED MATRIX FACTORIZATION OF CONTENT-BASED MODEL FOR RECOMMENDATION SYSTEM 审中-公开
标题翻译：基于内容的建模系统模型的修改矩阵拟合
公开(公告)号：WO2016040211A1
公开(公告)日：2016-03-17
申请号：PCT/US2015/048757
申请日：2015-09-07
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： NICE, Nir , KOENIGSTEIN, Noam , KEREN, Shahar , KROSKIN, Ayelet , PAQUET, Ulrich
IPC分类号： G06Q30/02 , G06Q30/06
CPC分类号： G06Q30/0631 , G06F17/30867 , G06Q30/02
摘要： A recommendation system is implemented using modified matrix factorization on top of a content-based matrix to provide both user-to-item and item-to-item content-based recommendations while exposing the full depth of transitive relationships among recommendations. Content information such as features and characteristics may be represented in a usage matrix in which features are treated as users would be in traditional matrix factorization. Matrix factorization is applied to the "features-as-users" matrix to build a content-based model in which features and items are embedded in a low dimension latent space. User history is employed for system training by locating user vectors within the latent space. Recommendations that are near to the vector can be provided to the users along with explanations (e.g., a recommendation is given because of an item's proximity to a particular feature).
摘要翻译：在基于内容的矩阵之上使用修改矩阵分解来实现推荐系统，以提供用户对项目和项目到项目基于内容的建议，同时暴露推荐之间的传递关系的全部深度。诸如特征和特征的内容信息可以在使用矩阵中表示，其中特征被视为用户将处于传统矩阵分解中。矩阵分解被应用于“特征为用户”矩阵，以构建基于内容的模型，其中特征和项目嵌入在低维潜力空间中。通过将用户向量定位在潜在空间内，用户历史被用于系统训练。靠近向量的建议可以与说明一起提供给用户（例如，由于项目与特定特征的接近而给出推荐）。

6. 发明申请

WO2015148422A1 RECOMMENDATION SYSTEM WITH DUAL COLLABORATIVE FILTER USAGE MATRIX 审中-公开
标题翻译：具有双协同滤波器使用矩阵的建议系统
公开(公告)号：WO2015148422A1
公开(公告)日：2015-10-01
申请号：PCT/US2015/022104
申请日：2015-03-24
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： NICE, Nir , KOENIGSTEIN, Noam , PAQUET, Ulrich , KEREN, Shahar
IPC分类号： G06Q30/02 , G06Q30/06
CPC分类号： G06F17/30699 , G06Q30/02 , G06Q30/0631
摘要： Example apparatus and methods perform matrix factorization (MF) on a usage matrix to create a latent space that describes similarities between users and items and between items and items in the usage matrix. The usage matrix relates users to items according to a collaborative filtering approach. A cell in the usage matrix may store a value that describes whether a user has acquired an item and the strength with which the user likes an item that has been acquired. The latent item space may reflect true relationships between items represented in the usage matrix and those relationships may be proportional to the strength in the usage matrix. The strength of the relationship may be encoded using continuous data that measures, for example, the amount of time a video game has been played, the amount of time content has been viewed, or other continuous or cumulative engagement measurements.
摘要翻译：示例性装置和方法在使用矩阵上执行矩阵分解（MF）以创建描述用户和项目之间以及使用矩阵中的项目和项目之间的相似性的潜在空间。使用矩阵根据协作过滤方法将用户与项目相关联。使用矩阵中的单元可以存储描述用户是否已经获取项目的值和用户喜欢已经获取的项目的强度。潜在项目空间可以反映在使用矩阵中表示的项目之间的真实关系，并且这些关系可以与使用矩阵中的强度成比例。关系的强度可以使用测量例如视频游戏已经播放的时间量，已经观看的时间量或其他连续或累积的接合测量的连续数据进行编码。

7. 发明申请

WO2023075935A1 REPRESENTATION LEARNING WITH SIDE INFORMATION 审中-公开
公开(公告)号：WO2023075935A1
公开(公告)日：2023-05-04
申请号：PCT/US2022/042820
申请日：2022-09-08
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC.
发明人： BARKAN, Oren , CACIULARU, Avi , REJWAN, Idan , WEILL, Yonathan , KOENIGSTEIN, Noam , KATZ, Ori , MALKIEL, Itzik , NICE, Nir
IPC分类号： G06F16/35 , G06N20/00
摘要： A relational similarity determination engine receives as input a dataset including a set of entities and co-occurrence data that defines co-occurrence relations for pairs of the entities. The relational similarity determination engine also receives as input side information defining explicit relations between the entities. The relational similarity determination engine jointly models the co-occurrence relations and the explicit relations for the entities to compute a similarity metric for each different pair of entities within the dataset. Based on the computed similarity metrics, the relational similarity determination engine identifies a most similar replacement entity from the dataset for each of the entities within the dataset. For a select entity received as an input, the relational similarity determination engine outputs the identified most similar replacement entity.

8. 发明申请

WO2022271304A1 SELF-SUPERVISED DOCUMENT-TO-DOCUMENT SIMILARITY SYSTEM 审中-公开
公开(公告)号：WO2022271304A1
公开(公告)日：2022-12-29
申请号：PCT/US2022/029096
申请日：2022-05-13
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： MALKIEL, Itzik , GINZBURG, Dvir , KOENIGSTEIN, Noam , BARKAN, Oren , NICE, Nir
IPC分类号： G06F16/335 , G06F16/338 , G06F16/93 , G06F16/337 , G06F18/2113 , G06F18/2178 , G06V10/751 , G06V30/418
摘要： Examples provide a self-supervised language model for document-to-document similarity scoring and ranking long documents of arbitrary length in an absence of similarity labels. In a first stage of a two-staged hierarchical scoring, a sentence similarity matrix is created for each paragraph in the candidate document. A sentence similarity score is calculated based on the sentence similarity matrix. In the second stage, a paragraph similarity matrix is constructed based on aggregated sentence similarity scores associated with the first candidate document. A total similarity score for the document is calculated based on the normalize the paragraph similarity matrix for each candidate document in a collection of documents. The model is trained using a masked language model and intra-and-inter document sampling. The documents are ranked based on the similarity scores for the documents.

9. 发明申请

WO2020112580A1 DATA RETRIEVAL 审中-公开
公开(公告)号：WO2020112580A1
公开(公告)日：2020-06-04
申请号：PCT/US2019/062900
申请日：2019-11-24
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： NOWOZIN, Sebastian , ZHANG, Cheng , KOENIGSTEIN, Noam , MA, Chao , LOBATO, Jose Miguel Hernandez , GONG, Wenbo
IPC分类号： G06F16/9535 , G06Q30/02
摘要： In various examples there is a data retrieval apparatus. The apparatus has a processor configured to receive a data retrieval request associated with a user. The apparatus also has a machine learning system configured to compute an affinity matrix of users for data items. The affinity matrix has a plurality of observed ratings of data items, and a plurality of predicted ratings of data items. The processor is configured to output a ranked list of data items for the user according to contents of the affinity matrix.

10. 发明申请

WO2017209981A1 HIERARCHICAL MULTISOURCE PLAYLIST GENERATION 审中-公开
标题翻译：分层多方播放列表生成
公开(公告)号：WO2017209981A1
公开(公告)日：2017-12-07
申请号：PCT/US2017/033442
申请日：2017-05-19
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： KOENIGSTEIN, Noam , NICE, Nir , ELAZAR, Shay Ben , BEREZIN, Yehiel , BARKAN, Oren , ZACCAI, Tal , SHLEVICH, Shimon , SIMHON, Nimrod Ben , NOGUES, Paul , LAVEE, Gal
IPC分类号： G06F17/30
CPC分类号： G06F16/639 , G06F16/4387 , G06F16/68
摘要： A playlist generator that utilizes multiple data sources to rank each track within a set of candidate tracks to enable selection of candidate tracks according to the ranking. Candidate tracks are each scored according to one or more features, such as acoustic similarity and/or similar usage patterns of the candidate track or artist of the candidate track to a current or previously played track or artist. Each feature is weighted according to historical listening patterns surrounding a user-selected playlist seed artist. The weighting may also be further corrected according to historical listening patterns of the particular user. When historical usage data related to a particular seed artist is limited, more generalized historical usage data related to a higher level in a genre hierarchy may be used.
摘要翻译：播放列表生成器利用多个数据源对一组候选音轨内的每个音轨进行排名，以使得能够根据排名选择候选音轨。候选曲目每个根据一个或多个特征来评分，诸如候选曲目或艺术家对当前或先前播放的曲目或艺术家的候选曲目或艺术家的声学相似性和/或类似使用模式。根据用户选择的播放列表种子艺术家周围的历史收听模式对每个功能进行加权。加权也可以根据特定用户的历史收听模式进一步校正。当与特定种子艺术家相关的历史使用数据是有限的时，可以使用与类型层级中的较高级别相关的更一般化的历史使用数据。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式