-
公开(公告)号：US20240202581A1
公开(公告)日：2024-06-20
申请号：US18085257
申请日：2022-12-20
IPC分类号： G06N20/00
CPC分类号： G06N20/00
摘要： Methods, systems, and computer program products for configuring artificial intelligence-based virtual assistants using response modes are provided herein. A computer-implemented method includes configuring multiple response modes in connection with at least one artificial intelligence-based virtual assistant, each response mode corresponding to a respective set of operational settings for the at least one artificial intelligence-based virtual assistant; implementing, for the at least one artificial intelligence-based virtual assistant, one of the multiple response modes based at least in part on at least one user request submitted to the at least one artificial intelligence-based virtual assistant and one or more items of data associated with the at least one artificial intelligence-based virtual assistant; and configuring at least one workflow to be carried out by the at least one artificial intelligence-based virtual assistant in response to the at least one user request and in accordance with the implemented response mode.
-
公开(公告)号：US11443117B2
公开(公告)日：2022-09-13
申请号：US16688843
申请日：2019-11-19
发明人： Yang Yu , Ming Tan , Shasha Lin , Saloni Potdar
IPC分类号： G06F40/30 , G06F40/109 , G06F40/284
摘要： A system includes a memory having instructions therein and at least one processor configured to execute the instructions to: receive a natural language question; determine, from a chat log comprising a plurality of chat session logs, a set of chat session logs most relevant to the natural language question; determine a respective plurality of non-overlapping text spans most relevant to the natural language question within each of a respective plurality of conceptual pseudo-documents; determine a conceptual pseudo-document most relevant to the natural language question; extract a question-answer pair most relevant to the natural language question from the most relevant pseudo-document; and convey the most relevant question-answer pair to a user. Each one of the conceptual pseudo-documents corresponds to a respective one of the most relevant chat session logs.
-
公开(公告)号：US20210287667A1
公开(公告)日：2021-09-16
申请号：US16816600
申请日：2020-03-12
发明人： Ming Tan , Haoyu Wang , Saloni Potdar , Yang Yu , Navneet N. Rao , Haode Qi
IPC分类号： G10L15/183 , G06F16/9032 , G10L15/06
摘要： A mechanism is provided for implementing an intent segmentation mechanism that segments intent boundaries for multi-intent utterances in a conversational agent. For each term of a set of terms in the utterance from a real-time chat session, a set of adversarial utterances is generated for the utterance. An influence of changing each term is determined so as to identify a term importance value. Utilizing the term importance value, one or more of a change in ranking of the intent of the utterance or a change in confidence with regard to the intent of the utterance is identified. An entropy-based segmentation of the utterance into a plurality of candidate partitions is performed. An associated intent and entropy value are then assigned. Based on a segment with minimum entropy, a call associated with the real-time chat session is directed to an operation associated with an intent of the segment with minimum entropy.
-
公开(公告)号：US20210256211A1
公开(公告)日：2021-08-19
申请号：US16789804
申请日：2020-02-13
发明人： Haode Qi , Ming Tan , Yang Yu , Navneet N. Rao , Ladislav Kunc , Saloni Potdar
摘要： A mechanism is provided to implement an abnormal entity detection mechanism that facilitates detecting abnormal entities in real-time response systems through weak supervision. For each first intent from an entity labeled workspace that matches a second intent in labeled chat logs, when the entity score associated with each first entity or second entity is above a predefined significance level the first entity or the second entity is recorded. For each first intent from the entity labeled workspace that matches the second intent in the labeled chat logs: responsive to the first entity being recorded and the second entity failing to be recorded, that first entity is removed from the training data as being mistakenly included; or, responsive to the second entity being recorded and the first entity failing to be recorded, that second entity is added as a potential business case to the training data.
-
公开(公告)号：US11093707B2
公开(公告)日：2021-08-17
申请号：US16247620
申请日：2019-01-15
发明人： Ming Tan , Ruijian Wang , Inkit Padhi , Saloni Potdar
IPC分类号： G06F40/279 , G06F40/205 , G06K9/62 , G06F16/35 , G06N3/08
摘要： An intelligent computer platform to introduce adversarial training to natural language processing (NLP). An initial training set is modified with synthetic training data to create an adversarial training set. The modification includes use of natural language understanding (NLU) to parse the initial training set into components and identify component categories. One or more paraphrase terms are identified with respect to the components and component categories, and function as replacement terms. The synthetic training data is effectively a merging of the initial training set with the replacement terms. As input is presented, a classifier leverages the adversarial training set to identify the intent of the input and to output a classification label to generate accurate and reflective response data.
-
公开(公告)号：US11074414B2
公开(公告)日：2021-07-27
申请号：US16454773
申请日：2019-06-27
IPC分类号： G06F40/289 , G06F3/0482 , G06K9/62 , G06F40/166
摘要： A test controller submits testing phrases to a text classifier and receives, from the text classifier, classification labels each comprising one or more respective heatmap values each associated with a separate word. The test controller aligns each of the classification labels corresponding with a respective testing phrase. The test controller identifies one or more anomalies of a selection of one or more classification labels that are different from an expected classification label for the respective testing phrase. The test controller outputs a graphical representation in a user interface of the selection of one or more classification labels and one or more respective testing phrases with visual indicators based on one or more respective heatmap values.
-
公开(公告)号：US20210224415A1
公开(公告)日：2021-07-22
申请号：US16749163
申请日：2020-01-22
发明人： Haode Qi , Saloni Potdar , Ming Tan , Navneet R. Rao
IPC分类号： G06F21/62 , G06K9/34 , G06F40/186 , G06K9/48 , G06F40/279
摘要： A mechanism is provided to implement a personally identifiable information (PII) detection mechanism that facilitates privacy protection utilizing template embedding learned from text sequences. Input text is processed using natural language processing to identify one or more pieces of personally identifiable information. A character analysis is performed of each character of each piece of personally identifiable information of the one or more pieces of personally identifiable information to identify a character type of character in the piece of personally identifiable information. For each piece of personally identifiable information and based on the associated identified character type, the identified character type is mapped to an associated template character in a set of template characters in a template character data structure. Utilizing the character-to-template mappings for the one or more pieces of personally identifiable information, an output text is generated that projects the template characters by direct character-level mapping.
-
公开(公告)号：US20200226212A1
公开(公告)日：2020-07-16
申请号：US16247620
申请日：2019-01-15
发明人： Ming Tan , Ruijian Wang , Inkit Padhi , Saloni Potdar
摘要： An intelligent computer platform to introduce adversarial training to natural language processing (NLP). An initial training set is modified with synthetic training data to create an adversarial training set. The modification includes use of natural language understanding (NLU) to parse the initial training set into components and identify component categories. One or more paraphrase terms are identified with respect to the components and component categories, and function as replacement terms. The synthetic training data is effectively a merging of the initial training set with the replacement terms. As input is presented, a classifier leverages the adversarial training set to identify the intent of the input and to output a classification label to generate accurate and reflective response data.
-
公开(公告)号：US20240193377A1
公开(公告)日：2024-06-13
申请号：US18063788
申请日：2022-12-09
发明人： LIN PAN , Haode Qi , Ladislav Kunc , Saloni Potdar
IPC分类号： G06F40/58
CPC分类号： G06F40/58
摘要： A method, computer system, and a computer program product for training a machine learning model are provided. A machine learning model may be split into a lower portion and an upper portion. The lower portion includes at least one layer. The upper portion includes at least one layer. The lower portion may be pre-trained via a generator task and via alternating between inputting of monolingual text data and multilingual text data. The upper portion may be pre-trained via a discriminator task. The pre-trained lower portion may be joined to the pre-trained upper portion to form a trained multilingual machine learning model.
-
公开(公告)号：US20240070401A1
公开(公告)日：2024-02-29
申请号：US17897887
申请日：2022-08-29
发明人： Cheng Qian , Haode Qi , Saloni Potdar , Ladislav Kunc
摘要： Methods, systems, and computer program products for detecting out-of-domain text data in dialog systems using artificial intelligence techniques are provided herein. A computer-implemented method includes updating artificial intelligence techniques related to out-of-domain text data detection, the updating based on encoding training data and generating regularized representations of at least a portion of the encoded training data by combining the at least a portion of the encoded training data and at least one intent centroid associated with the updated artificial intelligence techniques; encoding input text data; computing out-of-domain scores, in connection with the at least one dialog system, for at least a portion of the encoded input text data by processing the at least a portion of encoded input data using at least a portion of the one or more updated artificial intelligence techniques; and performing one or more automated actions based on the computed out-of-domain scores.
-
-
-
-
-
-
-
-
-
搜索结果
53 条记录 (耗时 0.021 秒)
