-
公开(公告)号：US20220253607A1
公开(公告)日：2022-08-11
申请号：US17169711
申请日：2021-02-08
Applicant: International Business Machines Corporation
Inventor： Eric Aubineau , Hugues Citeau
IPC: G06F40/35 , G06N5/04 , H04L12/58 , G06F40/169 , G06F40/279
Abstract: A method, apparatus and computer program product for creating and operating a conversational system are described. A user annotated Web API specification is received which includes a set of user annotations The user annotated Web API specification is analyzed to produce an action catalog. The action catalog includes a set of sentences, each sentence describing a respective Web API call. The user annotated Web API specification is also analyzed to produce a rule set, each rule in the rule set has a rule condition which corresponds to an input in the user annotated Web API specification. The action catalog and the rule set are provided to the conversational system. The conversational system uses a question answering (QA) system as a natural language understanding (NLU) component. When the conversational system receives a user input during a dialog between a user and the conversational system, the user input is interpreted by the question answering (QA) system to identify an action from an action catalog. The identified action is set as a goal for a goal-based reasoning engine. A response is issued to the user based on the identified action and results from the goal-based reasoning engine.
-
Patent Agency Ranking
公开(公告)号：US20130144829A1
公开(公告)日：2013-06-06
申请号：US13688462
申请日：2012-11-29
Applicant: International Business Machines Corporation
Inventor： Thomas Baudel , Hugues Citeau , Marcos Didonet Del Fabro
IPC: G06N5/02
CPC classification number: G06N5/02
Abstract: An aspect of the invention includes transforming a source model to a target model. A source model is received and a transformation specification that includes a set of rules is accessed. Each rule includes a pattern description and a production component. The pattern description includes a pattern in the source model and the production component includes an algorithm for generating an output in the target model from the pattern. For each expression in the source model, the expression is decomposed into sub-expressions, matching rules in the transformation specification for the expression and the sub-expressions are detected, one of the matching rules having the most specific pattern description is selected, and the production component of the selected rule is executed to generate the output in the target model. The target model is created from the generated output.
Abstract translation: 本发明的一个方面包括将源模型转换为目标模型。 接收源模型，并访问包含一组规则的变换规范。 每个规则包括模式描述和生产组件。 模式描述包括源模型中的模式，并且生产组件包括用于从模式生成目标模型中的输出的算法。 对于源模型中的每个表达式，表达式被分解为子表达式，表达式的转换规范中的匹配规则被检测，并且检测到子表达式，选择具有最特定模式描述的匹配规则之一，并且 执行所选规则的生产组件以在目标模型中生成输出。 目标模型是从生成的输出创建的。
-
公开(公告)号：US11741313B2
公开(公告)日：2023-08-29
申请号：US17169711
申请日：2021-02-08
Applicant: International Business Machines Corporation
Inventor： Eric Aubineau , Hugues Citeau
IPC: G06F40/35 , G06N5/04 , G06F40/279 , G06F40/169 , H04L51/02
CPC classification number: G06F40/35 , G06F40/169 , G06F40/279 , G06N5/04 , H04L51/02
Abstract: A method, apparatus and computer program product for creating and operating a conversational system are described. A user annotated Web API specification is received which includes a set of user annotations The user annotated Web API specification is analyzed to produce an action catalog. The action catalog includes a set of sentences, each sentence describing a respective Web API call. The user annotated Web API specification is also analyzed to produce a rule set, each rule in the rule set has a rule condition which corresponds to an input in the user annotated Web API specification. The action catalog and the rule set are provided to the conversational system. The conversational system uses a question answering (QA) system as a natural language understanding (NLU) component. When the conversational system receives a user input during a dialog between a user and the conversational system, the user input is interpreted by the question answering (QA) system to identify an action from an action catalog. The identified action is set as a goal for a goal-based reasoning engine. A response is issued to the user based on the identified action and results from the goal-based reasoning engine.
-
公开(公告)号：US20230252242A1
公开(公告)日：2023-08-10
申请号：US18137616
申请日：2023-04-21
Applicant: International Business Machines Corporation
Inventor： Eric Aubineau , Hugues Citeau
IPC: G06F40/35 , G06N5/04 , G06F40/279 , G06F40/169 , H04L51/02
CPC classification number: G06F40/35 , G06N5/04 , G06F40/279 , G06F40/169 , H04L51/02
Abstract: A method, apparatus and computer program product for creating and operating a conversational system are described. A user annotated API specification is received which includes a set of user annotations. The user annotated API specification is analyzed to produce an action catalog. The user annotated API specification is also analyzed to produce a rule set, each rule in the rule set has a rule condition which corresponds to an input in the user annotated API specification. The action catalog and the rule set are provided to the conversational system. The conversational system uses a question answering (QA) system as a natural language understanding (NLU) component. When the conversational system receives a user input during a dialog between a user and the conversational system, the user input is interpreted by the question answering (QA) system to identify an action from an action catalog. The identified action is set as a goal for a goal-based reasoning engine. A response is issued to the user based on the identified action and results from the goal-based reasoning engine.
-
公开(公告)号：US09798975B2
公开(公告)日：2017-10-24
申请号：US14146219
申请日：2014-01-02
Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor： Hugues Citeau , Adil El Ghali
Abstract: A production rules engine comprises: a class loader for loading a production rule ontology into a rule engine; a class loader for loading production rules into the rule engine, wherein a production rule comprises a rule and an action defined in the production rule ontology; instance creation logic for creating instances of production rules; a reasoner for executing the production rules and for locating an instance of a production rule having an inconsistency between an action to change the ontology and the existing ontology and for executing the production rules after inconsistencies have been fixed; a constraint engine for locating a solution to an inconsistent ontology; and a fixer for updating the inconsistent ontology with the located solution.
-
公开(公告)号：US08972327B2
公开(公告)日：2015-03-03
申请号：US13688462
申请日：2012-11-29
Applicant: International Business Machines Corporation
Inventor： Thomas Baudel , Hugues Citeau , Marcos Didonet Del Fabro
CPC classification number: G06N5/02
Abstract: An aspect of the invention includes transforming a source model to a target model. A source model is received and a transformation specification that includes a set of rules is accessed. Each rule includes a pattern description and a production component. The pattern description includes a pattern in the source model and the production component includes an algorithm for generating an output in the target model from the pattern. For each expression in the source model, the expression is decomposed into sub-expressions, matching rules in the transformation specification for the expression and the sub-expressions are detected, one of the matching rules having the most specific pattern description is selected, and the production component of the selected rule is executed to generate the output in the target model. The target model is created from the generated output.
Abstract translation: 本发明的一个方面包括将源模型转换为目标模型。 接收源模型，并访问包含一组规则的变换规范。 每个规则包括模式描述和生产组件。 模式描述包括源模型中的模式，并且生产组件包括用于从模式生成目标模型中的输出的算法。 对于源模型中的每个表达式，将表达式分解为子表达式，在表达式的转换规范中匹配规则，并检测子表达式，选择具有最特定模式描述的匹配规则之一， 执行所选规则的生产组件以在目标模型中生成输出。 目标模型是从生成的输出创建的。
-
-
-
-
-
Search Results
6
records
(took 0.015 seconds)
