公开(公告)号：US20190245971A1

公开(公告)日：2019-08-08

申请号：US16386467

申请日：2019-04-17

申请人： CallMiner, Inc.

发明人： Michael C. Dwyer ,  Erik A. Strand ,  Scott R. Wolf ,  Frank Salinas ,  Jeffrey A. Gallino ,  Scott A. Kendrick ,  Shaoyu Xue

IPC分类号： H04M3/51 ,  G06F17/27 ,  G10L15/18 ,  G10L25/72 ,  G10L15/02 ,  H04M3/42 ,  G10L15/30 ,  G06F21/62 ,  G10L15/26

CPC分类号： H04M3/5175 ,  G06F17/2765 ,  G06F17/2785 ,  G06F21/6254 ,  G10L15/02 ,  G10L15/1815 ,  G10L15/26 ,  G10L15/30 ,  G10L25/72 ,  G10L2015/088 ,  H04M3/42221 ,  H04M3/5191 ,  H04M2203/301 ,  H04M2203/303 ,  H04M2203/401 ,  H04M2203/551 ,  H04M2203/6009

摘要： A system and method of categorizing communications involves evaluating one or more portions of a communication. Systems include a language module structured to analyze the one or more portions of the communication for at least one of a language characteristic or a non-word symbol within a text of the communication, an acoustic analysis module structured to analyze the one or more portions of the communication for an acoustic characteristic, and a determination module structured to determine at least one category label to associate with the one or more portions of the communication using at least one of the language characteristic or the non-word symbol, and the acoustic characteristic.

公开(公告)号：US20190243900A1

公开(公告)日：2019-08-08

申请号：US16387365

申请日：2019-04-17

申请人： Tencent Technology (Shenzhen) Company Limited

发明人： Jun GAN ,  Ke SU ,  Mengliang RAO

IPC分类号： G06F17/27 ,  G06F16/9032

CPC分类号： G06F17/2785 ,  G06F16/00 ,  G06F16/90332 ,  G06F17/27 ,  G06F17/2765

摘要： The present disclosure discloses an automatic question-answer (QA) processing method and an automatic QA system. The method includes: obtaining, after receiving a target question text, a target keyword corresponding to the target question text; determining a candidate question text that matches the target keyword; calculating a semantic similarity value between each candidate question text and the target question text; and determining, based on the semantic similarity value, an answer corresponding to the target question text. In the present disclosure, a semantic similarity between a target question text and each question text is considered, to determine an answer to the target question text, improving accuracy of automatic QA processing.

公开(公告)号：US20190236347A1

公开(公告)日：2019-08-01

申请号：US16379145

申请日：2019-04-09

申请人： Vatbox, Ltd.

发明人： Noam GUZMAN ,  Isaac SAFT

IPC分类号： G06K9/00 ,  G06F17/27 ,  G06F16/9032 ,  G06F16/908 ,  G06Q40/00

CPC分类号： G06K9/00442 ,  G06F16/90332 ,  G06F16/908 ,  G06F17/21 ,  G06F17/2705 ,  G06F17/2765 ,  G06Q40/123

摘要： A system and method for identifying missing required data elements in an electronic document. The method includes analyzing the electronic document to identify at least one data element; determining, based on the identified at least one data element and at least one electronic document requirement, whether there is at least one required data element missing from the electronic document; generating a query based on the identified at least one data element upon determining that there is at least one required data element missing from the electronic document; querying a database using the generated query; and modifying, based on a response to the query, the electronic document to include the at least one missing required data element.

公开(公告)号：US20190236217A1

公开(公告)日：2019-08-01

申请号：US15885430

申请日：2018-01-31

申请人： salesforce.com, inc.

发明人： Vlad EROSHIN ,  Dylan Thom ,  Ryoji Osawa ,  Dai Duong Doan

IPC分类号： G06F17/30 ,  G06F17/27

CPC分类号： G06F16/90328 ,  G06F16/243 ,  G06F17/2705 ,  G06F17/2765

摘要： Embodiments are described for enabling a user to query a database using natural language and receive results without requiring the user to manipulate or know details of the database contents. The user is guided in the creation of the natural language query by suggested predetermined queries from a template. Natural language is parsed using the template. The approach allows a user's query words to be completed automatically from the template as the user inputs the words. The approach further allows the next suggested parts of the query to be automatically typed from the template ahead of the user's cursor. Other features provide feedback to the user for invalid or irrelevant queries that cannot be parsed, including suggesting complete predetermined queries from the template. The approach helps the user focus the query on exactly what the user seeks to learn from the database without complex, process-intensive parsing.

公开(公告)号：US20190236121A1

公开(公告)日：2019-08-01

申请号：US15882673

申请日：2018-01-29

申请人： salesforce.com, inc.

发明人： Alicia Ong ,  Anjali Ashok

IPC分类号： G06F17/22 ,  G06F17/27 ,  G06F8/38 ,  G06F17/24

CPC分类号： G06F17/2247 ,  G06F8/38 ,  G06F17/24 ,  G06F17/2765

摘要： A method for efficiently generating a detail panel has been developed. First, a detail panel that contains a list of multiple items is accessed by a user. An initial component is created by populating initial items with data in a text language format. Subsequent items are also populated with data in a text language format to create a subsequent component. The text language of the initial component is compared to the text language of the subsequent components. If the initial component is similar enough to exceed a predetermined compatibility threshold, the initial component is used as a substitute for the subsequent components.

公开(公告)号：US20190213663A1

公开(公告)日：2019-07-11

申请号：US16237400

申请日：2018-12-31

申请人： Walmart Apollo, LLC

发明人： Victor Chowdhury

IPC分类号： G06Q30/06 ,  G06F16/2455 ,  G06F17/27 ,  G06F16/242 ,  G06F16/248

CPC分类号： G06Q30/0635 ,  G06F16/2425 ,  G06F16/24553 ,  G06F16/248 ,  G06F17/272 ,  G06F17/2765 ,  G06Q30/0641

摘要： Examples provide a system for real-time virtual cart optimization. A selected target is received for a cart match operation directed at a current cart associated with a host provider via an online selection. One or more items associated with the virtual cart are identified. A targeted query for the selected target is generated using the one or more identified items. The query results are parsed to identify at least two tags, which are used to determine item origination data and item value data. The identified tags are used to calculate per-item differentials, which are used to generate an updated cart.

公开(公告)号：US20190213246A1

公开(公告)日：2019-07-11

申请号：US16357909

申请日：2019-03-19

申请人： Tribune Broadcasting Company, LLC

发明人： Hank J. HUNDEMER

IPC分类号： G06F17/27 ,  G06F16/783

CPC分类号： G06F17/273 ,  G06F16/739 ,  G06F16/745 ,  G06F16/7844 ,  G06F17/211 ,  G06F17/24 ,  G06F17/2765 ,  G06F17/289

摘要： In one aspect, an example method involves: a computing device selecting a media program; the computing device accessing first data representing closed-captioning text that corresponds to the media program; accessing second data representing a program schedule of the selected media-program, wherein the program schedule comprises first text; the computing device selecting second text from among the first text; the computing device using the selected second-text to (i) identify a candidate misspelled-term within the closed-captioning text, and (ii) identify a candidate replacement-term for the candidate misspelled-term; and the computing device outputting, via a user interface, a prompt requesting a command to modify the closed-captioning text by replacing the identified candidate misspelled-term with the identified candidate replacement-term.

公开(公告)号：US20190205460A1

公开(公告)日：2019-07-04

申请号：US15862022

申请日：2018-01-04

申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION

发明人： Palliyathu Vishal George ,  Michael J. Iantosca ,  John Kurian ,  Balaji Sankar

IPC分类号： G06F17/30 ,  G06F17/21 ,  G06F17/27

CPC分类号： G06F16/313 ,  G06F16/93 ,  G06F17/21 ,  G06F17/2229 ,  G06F17/2241 ,  G06F17/2247 ,  G06F17/2755 ,  G06F17/2765 ,  G06T11/60

摘要： Aspects migrate an unstructured document to a specific document type definition Darwin Information Typing architecture wherein processors are configured to calculate a verb to noun ratio of an unstructured document by dividing a of plurality verbs of the unstructured document by a plurality of nouns of the unstructured document, assign a first weight to the unstructured document based on the calculated verb to noun ratio, and migrate the unstructured document to a specific document type definition Darwin Information Typing Architecture based on the first weight.

公开(公告)号：US20190205320A1

公开(公告)日：2019-07-04

申请号：US16212856

申请日：2018-12-07

申请人： KONICA MINOLTA, INC.

发明人： Kouichi TOMITA

IPC分类号： G06F16/31 ,  G06F17/27 ,  G06F16/93

CPC分类号： G06F16/313 ,  G06F16/93 ,  G06F17/2765

摘要： A sentence scoring apparatus includes a hardware processor that: extracts a sentence from a document having a hierarchical structure; derives a first weight value corresponding to a title of a hierarchical layer above a hierarchical layer to which the sentence extracted by the hardware processor belongs; extracts a keyword included in the sentence; derives a second weight value of the sentence on the basis of the extracted keyword; and determines a weight value of the sentence on the basis of the first weight value and the second weight value.

公开(公告)号：US20190180746A1

公开(公告)日：2019-06-13

申请号：US16206503

申请日：2018-11-30

申请人： Accenture Global Solutions Limited

发明人： Gaurav DIWAN ,  Tracy Ann GOGUEN

IPC分类号： G10L15/22 ,  G06F16/9032 ,  G06F16/25 ,  H04L29/08 ,  G06N20/00 ,  G06F17/27 ,  G10L15/18

CPC分类号： G06F16/252 ,  G06F3/167 ,  G06F16/90332 ,  G06F17/2765 ,  G06F17/2785 ,  G06N20/00 ,  G10L15/18 ,  G10L15/22 ,  G10L17/00 ,  G10L2015/223 ,  H04L67/306

摘要： A device receives, from a virtual assistant device, a first user input associated with a first account of a user, and causes a natural language processing analysis to be performed on the first user input to identify first information, the first account, and a first operation to be performed in association with first information in the first account. The device identifies a first data management platform, associated with the first account, that is configured to maintain the first information in a first data structure associated with the first data management platform, and determines that the first data management platform is a first type of data management platform based on the first data structure. The device causes the first operation to be performed using a RPA, that uses a user interface of the first data management platform, based on the first data management platform being the first type of data management platform.