-
公开(公告)号：US20230342653A1
公开(公告)日：2023-10-26
申请号：US17660036
申请日：2022-04-21
摘要： Technology for: (i) receiving a domain-dependent artificial intelligence planning problem including definitions for a plurality of operators; (ii) creating an initial version of a label set, which defines an initial version of an action space, with the label set including a plurality of labels, and with each label of the plurality of labels respectively corresponding to the operators of the plurality of operators; (iii) performing, automatically and by machine logic, a label reduction on the initial version of the label set to obtain a reduced version of the label set that defines a reduced action space; and (iv) recasting the artificial planning problem as a first Markov decision process using the reduced version of label set.
-
公开(公告)号：US11755923B2
公开(公告)日：2023-09-12
申请号：US16205212
申请日：2018-11-29
IPC分类号： G06N5/02 , G06F11/34 , G06F21/56 , G06F11/30 , G06Q10/00 , G06N5/045 , G06N20/00 , G06N5/04 , G06N3/042 , G06N5/043
CPC分类号： G06N5/02 , G06F11/3024 , G06F11/3409 , G06F21/56 , G06N3/042 , G06N5/04 , G06N5/043 , G06N5/045 , G06N20/00 , G06Q10/00 , G06F2221/033
摘要： Performance of a computer running a plan recognition application is improved by obtaining, with a user interface implemented on the computer, a specification of a plan recognition problem, including a plurality of candidate observations; formulating at least one planning problem, with the computer, based on the specification; solving the at least one planning problem, with the computer, to determine at least one plan. The at least one plan is post-processed, with the computer, to determine at least one of the candidate observations which should be selected to solve the plan recognition problem; and the plan recognition problem is solved, with the computer, using the at least one of the candidate observations which should be selected to solve the plan recognition problem. Less CPU time is typically required for the solution as compared to techniques without guidance for selecting the observations.
-
公开(公告)号：US20230177368A1
公开(公告)日：2023-06-08
申请号：US17546022
申请日：2021-12-08
发明人： Junkyu Lee , Michael Katz , Shirin Sohrabi Araghi , Don Joven Ravoy Agravante , Miao Liu , Tamir Klinger , Murray Scott Campbell
CPC分类号： G06N7/005 , G06K9/6262
摘要： A computer-implemented method of integrating an Artificial Intelligence (AI) planner and a reinforcement learning (RL) agent through AI planning annotation in RL (PaRL) includes identifying an RL problem. A description received of a Markov decision process (MDP) having a plurality of states in an RL environment is used to generate an RL task to solve the RL problem. An AI planning model described in a planning language is received, and mapping state spaces from the MDP states in the RL environment to AI planning states of the AI planning model is performed. The RL task is generated with an AI planning task from the mapping to generate a PaRL task.
-
公开(公告)号：US20180218475A1
公开(公告)日：2018-08-02
申请号：US15842252
申请日：2017-12-14
CPC分类号： G06T1/20 , G06F15/18 , G06F17/30277 , G06N5/02 , G06N5/022
摘要： Techniques for translating graphical representations of domain knowledge are provided. In one example, a computer-implemented method comprises receiving, by a device operatively coupled to a processor, a graphical representation of domain knowledge. The graphical representation comprises information indicative of a central concept and at least one chain of events associated with the central concept. The computer-implemented method further comprises translating, by the device, the graphical representation into an artificial intelligence planning problem. The artificial intelligence planning problem is expressed in an artificial intelligence description language. The translating comprises parsing the graphical representation into groupings of terms. A first grouping of terms of the grouping of terms comprises an event from the at least one chain of events and a second grouping of terms of the grouping of terms comprises the information indicative of the central concept. The computer-implemented method also comprises validating, by the device, the artificial intelligence planning problem.
-
公开(公告)号：US20180218270A1
公开(公告)日：2018-08-02
申请号：US15420433
申请日：2017-01-31
发明人： Lydia Manikonda , Anton Viktorovich Riabov , Shirin Sohrabi Araghi , Biplav Srivastava , Kartik Talamadupula , Deepak Srinivas Turaga
摘要： Techniques for autonomously generating a domain model and/or an action model based on unstructured data are provided. In one example, a computer implemented method can comprise extracting, by a system operatively coupled to a processor, a plurality of actions from a non-numerical language. The plurality of actions can achieve a goal. The computer-implemented method can also comprise generating, by the system, a domain model based on the plurality of actions. Further, the computer-implemented method can comprise generating, by the system, an action model based on the domain model. In various embodiments, the action model can comprise an action transition for accomplishing the goal.
-
公开(公告)号：US09785755B2
公开(公告)日：2017-10-10
申请号：US14283867
申请日：2014-05-21
摘要： In at least one embodiment, a method and a system include receiving a trace into a hypotheses generator from a source a trace, translating the trace and a state transition model into a planning problem using the hypotheses generator, producing a set of plans for the trace using at least one planner, translating each plan into hypothesis using the hypotheses generator and/or the planner, and returning the hypotheses from the hypotheses generator. In a further embodiment, the trace includes at least one of a future observation and a past observation. In at least one embodiment, the system includes at least one planner that develops a set of plans, a hypothesis generator, a database, at least one analytic, and at least one sensor where the hypotheses generator and/or the at least one planner converts each plan into a respective hypothesis.
-
公开(公告)号：US09697467B2
公开(公告)日：2017-07-04
申请号：US14283945
申请日：2014-05-21
CPC分类号： G06N5/04 , G06F7/523 , G06F17/30312
摘要： In at least one embodiment, a method and a system for determining a set of plans that best match a set of preferences. The method may include receiving into a goal specification interface at least one goal to be accomplished by the set of plans; receiving into a preference engine a pattern that includes preferences; generating a planning problem by using the preference engine; generating a set of plans by at least one planner; and providing the set of plans for selection of one plan to deploy. In a further embodiment, the preferences may be an occurrence or non-occurrence of at least one component, an occurrence of one component over another component, an ordering between at least two components, an existence or non-existence of at least one tag in a final stream, an existence of one tag over another tag in the final stream.
-
公开(公告)号：US11922129B2
公开(公告)日：2024-03-05
申请号：US17354171
申请日：2021-06-22
发明人： Manik Bhandari , Oktie Hassanzadeh , Mark David Feblowitz , Kavitha Srinivas , Shirin Sohrabi Araghi
摘要： A computer-implemented method is provided that includes accessing candidate text and a candidate pair including first and second phrases, substituting the first and second phrases into cause-effect patterns to generate variant sentences. An artificial intelligence model is leveraged to determine respective probabilities that the variant sentences are inferred from the candidate text, calculate a statistical measure of the respective probabilities, and assess the calculated statistical measure to ascertain whether the first and second phrases possess a causal relationship or non-causal relationship to one another. A knowledge base including one or more pairs of cause-effect phrase pairs is populated with the first and second phrases possessing the causal relationship. A computer system and a computer program product are also provided.
-
公开(公告)号：US11107182B2
公开(公告)日：2021-08-31
申请号：US16717146
申请日：2019-12-17
IPC分类号： G06T1/20 , G06N5/02 , G06N20/00 , G06F16/532
摘要： Techniques for translating graphical representations of domain knowledge are provided. In one example, a computer-implemented method comprises receiving, by a device operatively coupled to a processor, a graphical representation of domain knowledge. The graphical representation comprises information indicative of a central concept and at least one chain of events associated with the central concept. The computer-implemented method further comprises translating, by the device, the graphical representation into an artificial intelligence planning problem. The artificial intelligence planning problem is expressed in an artificial intelligence description language. The translating comprises parsing the graphical representation into groupings of terms. A first grouping of terms of the grouping of terms comprises an event from the at least one chain of events and a second grouping of terms of the grouping of terms comprises the information indicative of the central concept. The computer-implemented method also comprises validating, by the device, the artificial intelligence planning problem.
-
公开(公告)号：US11030561B2
公开(公告)日：2021-06-08
申请号：US15842281
申请日：2017-12-14
发明人： Yuan-Chi Chang , Mark D. Feblowitz , Nagui Halim , Stuart S. Horn , Edward J. Pring , Anton V. Riabov , Edward W. Shay , Shirin Sohrabi Araghi , Deepak S. Turaga , Octavian Udrea , Fang Yuan , Peter Zimmer
IPC分类号： G06Q10/06 , G06N5/02 , G06F16/951
摘要： Techniques for scenario planning are provided. In one example, a computer-implemented method can comprise analyzing, by a device operatively coupled to a processor, content using a topic model. The content can be associated with a defined source and is related to one or more current events. The computer-implemented method can also comprise determining, by the device, one or more portions of the analyzed content that are relevant to one or more key risk drivers using a risk driver model. The computer-implemented method can also comprise aggregating, by the device, the determined one or more portions into one or more emerging storylines based on values of one or more attributes of the topic model.
-
-
-
-
-
-
-
-
-
搜索结果
52 条记录 (耗时 0.033 秒)
