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. 发明授权

US11288581B2 Subsymbolic encoding with preserved semantic relationships 有权
公开(公告)号：US11288581B2
公开(公告)日：2022-03-29
申请号：US15855109
申请日：2017-12-27
申请人： SAP SE
发明人： Jana Lang , Matthias Kaiser
IPC分类号： G06N5/02 , G06F16/901
摘要： Disclosed herein are system, method, and computer program product embodiments for encoding symbolic data into a subsymbolic format while preserving the semantic arrangement of the symbolic data. In an embodiment, to encode the symbolic data, a subsymbolic encoder system may convert a symbolic graph into a tuple representation having tuple elements corresponding to the nodes of the symbolic graph. The subsymbolic encoder system may retrieve a dictionary identification for each tuple element and calculate a subsymbolic value for each tuple element using an exponential component. The subsymbolic encoder system may standardize the length of the subsymbolic values and/or add a weighted relationship indicator to the subsymbolic values. The subsymbolic encoder system may transmit the subsymbolic values to a subsymbolic intelligence system.

2. 发明授权

US08954360B2 Semantic request normalizer 有权
标题翻译：语义请求规范化器
公开(公告)号：US08954360B2
公开(公告)日：2015-02-10
申请号：US13653086
申请日：2012-10-16
申请人： SAP SE , intelligent views GmbH
发明人： Robert Heidasch , Stefan Scheidl , Michael Neumann , Matthias Kaiser , Christian Lahmer , Stephan Brand , Nico Licht , Klaus Reichenberger , Steffen Moldaner
IPC分类号： G06F15/18
CPC分类号： G06F17/30731 , G06F17/2785
摘要： A cascading learning system as a normalized semantic search is described. The cascading learning system has a request analyzer, a request dispatcher and classifier, a search module, a terminology manager, and a cluster manager. The request analyzer receives a request for search terms from a client application. The request analyzer has a normalization manager, a semantic parser, and a context builder. The normalization manager normalizes the search terms and generates a normalized semantic request based on a context. The request dispatcher and classifier classifies and dispatches the normalized semantic request to a corresponding domain-specific module that generates a prediction with a trained probability of an expected output. The terminology manager receives the normalized semantic request from the request dispatcher and classifier, and manages terminology stored in a contextual network.
摘要翻译：描述了作为归一化语义搜索的级联学习系统。级联学习系统具有请求分析器，请求分派器和分类器，搜索模块，术语管理器和集群管理器。请求分析器从客户端应用程序接收到搜索条件的请求。请求分析器具有归一化管理器，语义解析器和上下文构建器。归一化管理器对搜索项进行归一化，并基于上下文生成规范化语义请求。请求分派器和分类器将归一化的语义请求分类并分派到生成具有预期输出的训练概率的预测的相应的域特定模块。术语管理器从请求分派器和分类器接收归一化语义请求，并管理存储在上下文网络中的术语。

3. 发明申请

US20220253730A1 CASE-BASED REASONING AS A CLOUD SERVICE 有权
公开(公告)号：US20220253730A1
公开(公告)日：2022-08-11
申请号：US17723889
申请日：2022-04-19
申请人： SAP SE
发明人： Matthias Kaiser , Vladimir Shapiro , Luisa Andre , Roman Rommel , Max-Samuel Lang , Jochen Steinbach , Kai Richter , Thomas Ryborz
IPC分类号： G06N5/04 , G06N20/00
摘要： The disclosure generally describes methods, software, and systems for providing solution descriptions. A problem description of a problem is received, from a client, at a cloud-based reasoning service. A solution description for a solution to the problem is received. Case metadata for a case defining the problem and solution are generated by the cloud-based reasoning service. The case metadata, including the problem description and solution description, are stored by the cloud-based reasoning service in a cases repository associating solutions with problems. A new problem is received at the cloud-based reasoning service. An automated analysis of the new problem is performed, and a comparison is made of the new problem with existing solutions in the cases repository to identify solutions matching the new problem. A new solution description is provided that is based on a match between the new problem description and the problem description and using the problem solution.

4. 发明授权

US11334805B2 Case-based reasoning as a cloud service 有权
公开(公告)号：US11334805B2
公开(公告)日：2022-05-17
申请号：US16161245
申请日：2018-10-16
申请人： SAP SE
发明人： Matthias Kaiser , Vladimir Shapiro , Luisa Andre , Roman Rommel , Max-Samuel Lang , Jochen Steinbach , Kai Richter , Thomas Ryborz
IPC分类号： G06N5/04 , G06N99/00 , G06N20/00
摘要： The disclosure generally describes methods, software, and systems for providing solution descriptions. A problem description of a problem is received, from a client, at a cloud-based reasoning service. A solution description for a solution to the problem is received. Case metadata for a case defining the problem and solution are generated by the cloud-based reasoning service. The case metadata, including the problem description and solution description, are stored by the cloud-based reasoning service in a cases repository associating solutions with problems. A new problem is received at the cloud-based reasoning service. An automated analysis of the new problem is performed, and a comparison is made of the new problem with existing solutions in the cases repository to identify solutions matching the new problem. A new solution description is provided that is based on a match between the new problem description and the problem description and using the problem solution.

5. 发明申请

US20190392325A1 TRAIN A DIGITAL ASSISTANT WITH EXPERT KNOWLEDGE 审中-公开
公开(公告)号：US20190392325A1
公开(公告)日：2019-12-26
申请号：US16013109
申请日：2018-06-20
申请人： SAP SE
发明人： Stephan Lange , Matthias Kaiser
IPC分类号： G06N5/02 , G06F17/27
摘要： Disclosed herein are system, method, and computer program product embodiments for training a digital assistant with expert knowledge. An organization or individual utilizing a suite of software applications with a harmonized user experience may employ a digital assistant within the user experience to assist users when problems arise. The digital assistant may field questions and requests in informal and unstructured speech and text, analyze this natural language, and determine an appropriate response. The digital assistant may utilize existing suitable knowledge bases and leverage subject-matter experts. The digital assistant may learn from the expert's response to the user in order to apply the knowledge to a similar question or request in the future.

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