-
公开(公告)号：US20180329993A1
公开(公告)日：2018-11-15
申请号：US15976770
申请日：2018-05-10
发明人： Pavan Kumar Reddy Bedadala , Shilpa Nagendra , Rajesh Polimera , Aakash Chakravarthy Vijayakumar , Jie Chen , Neha Mathur , Vinay K. Pamarthi , Surya Prakash Ramachandran , Prasanna Kumar Thoppe Ravindran , Hari Prasad Ravula , Supreeth Sanur , Ganesh Kumar Subramanian , Priya Sundaresan , Jugpreet Singh Talwar
CPC分类号： G06F17/30755 , G06F17/2863 , G06F17/3043 , G10L15/22 , G10L15/265
摘要： The disclosed technology can receive a voice query or text query in a natural language and translate it from natural language to a native database management language to respond to the query. For example, a human can ask his or her computer to “show large emails from December 2016”, and a data agent on computer can receive the voice request, convert audio associated with the voice to words in natural language, convert natural language into a SQL query, and convert the SQL query into a database management query. The data agent is trained with a corpus of technical documents and rules to determine the intent or keywords for answering the query. In some implementations, the disclosed technology can also include a chatbot and/or administrative assistant to enable a human to interface with a database management software using voice or text. In some implementations, the disclosed technology allows the user to automatically connect to a help desk technician to assist in completing the query.
-
公开(公告)号：US20180225339A1
公开(公告)日：2018-08-09
申请号：US15829697
申请日：2017-12-01
CPC分类号： H04L43/022 , G06F11/3006 , G06F11/3072 , G06F11/3082 , G06F11/3409 , G06F11/3476 , G06F17/2217 , G06F17/2252 , G06F17/2705 , G06F17/30023 , G06F17/30106 , G06F17/30221 , G06F17/30392 , G06F17/30424 , G06F17/30427 , G06F17/3043 , G06F17/30442 , G06F17/30477 , G06F17/30542 , G06F17/30551 , G06F17/30554 , G06F17/30569 , G06F17/30592 , G06F17/30595 , G06F17/30657 , G06F17/30669 , G06F17/30675 , G06F17/30699 , G06F17/30864 , G06F17/30867 , G06F17/30917 , G06F17/30958 , G06F17/30967 , G06F17/30979 , G06F17/30985 , G06F21/552 , G06F2216/03 , H04L12/4625 , H04L29/06 , H04L29/06047 , H04L29/08072 , H04L29/08099 , H04L43/04 , H04L43/12 , H04L43/14
摘要： A system to collect and store in a special data structure arranged for rapid searching massive amounts of data. Performance metric data is one example. The performance metric data is recorded in time-series measurements, converted into unicode, and arranged into a special data structure having one directory for every day which stores all the metric data collected that day. The performance metric data is collected by one or more probes running on machines about which data is being collected. The performance metric data is compressed prior to transmission to a server over any data path. The data structure at the server where analysis is done has a subdirectory for every resource type. Each subdirectory contains text files of performance metric data values measured for attributes in a group of attributes to which said text file is dedicated. Each attribute has its own section and the performance metric data values are recorded in time series as unicode hex numbers as a comma delimited list. Analysis of the performance metric data is done using regular expressions. For speed, cache memory is used. Performance metric data outside the start time and end time named by the user on a query screen is eliminated before the regular expression is applied.
-
3.发明授权公开(公告)号：US09996526B2
公开(公告)日：2018-06-12
申请号：US15297763
申请日：2016-10-19
CPC分类号： G06F17/278 , G06F17/275 , G06F17/2755 , G06F17/2785 , G06F17/3043 , G06N3/006 , G06N99/005
摘要： Embodiments can provide a computer implemented method, in a data processing system comprising a processor and a memory comprising instructions which are executed by the processor to cause the processor to implement a mixed-language question answering supplement system, the method comprising receiving a question in a target language; determining the question cannot be answered using a target-language only corpus; applying natural language processing to parse the question into at least one focus; for each focus, determining if one or more target language verbs share direct syntactic dependency with the focus; for each of the one or more verbs sharing direct syntactic dependency, determining if one or more target language entities share direct syntactic dependency with the verb; determining one or more Abstract Universal Verbal Types associated with each verb; for each of the one or more Abstract Universal Verbal Types, determining whether a dependency between a source language entity and a source language verb is of the same type as the dependency between the target language verb and the target language entity; if the dependency is similar, returning the source language entity as a member of a set; populating the set of returned source language entities for each focus in the target language question; identifying one or more parallel passages wherein all core arguments are matched; for each parallel passage: identifying the presence or absence of oblique nominal arguments; and measuring the precision of the oblique nominal arguments in the parallel passages against those present in the target language question; and returning an answer to the target question in the target language based on a scoring of the parallel passages based on the accuracy of their respective oblique nominal arguments.
-
公开(公告)号：US09996340B2
公开(公告)日：2018-06-12
申请号：US15243049
申请日：2016-08-22
发明人： Peter J. Relson , Ulrich Thiemann
CPC分类号： G06F8/70 , G06F9/445 , G06F9/44521 , G06F9/44557 , G06F9/46 , G06F17/30339 , G06F17/30424 , G06F17/3043
摘要： A computer program product for identifying user managed software modules includes program instructions for: receiving a request for a directed load of a software module into memory, wherein the request includes an address; storing the software module at the address in the received request; adding a name and an address range of the stored software module to a data structure identifying software modules that have been loaded into memory via directed loads; receiving a query that includes an input module name or an input address range; and responsive to determining that the input module name or input address range of the received query is not stored in one or more data structures identifying one or more software modules that have been loaded into memory without directed loads, searching the data structure identifying software modules that have been loaded into memory via directed loads for the respective query.
-
公开(公告)号：US09916348B1
公开(公告)日：2018-03-13
申请号：US14824538
申请日：2015-08-12
申请人： Google Inc.
CPC分类号： G06F17/3043 , G06F17/30424 , G06F17/3053 , G06F17/30864
摘要： In one aspect, a method includes receiving a query determined to be a question query that seeks an answer response and data identifying resources determined to be responsive to the query; identifying structured content set in a top-ranked subset of the resources, each structured content set being content arranged according to related attributes in one of the resources; for each identified structured content set, determining whether the query matches the structured content set based on terms of the query matching related attributes of the structured content set; selecting one of the structured content sets for which the query is determined to match; generating, from the selected structured content set, a structured fact set from the related attributes that matched the terms of the query; and providing the structured fact set with search results that identify the resources determined to be responsive to the query.
-
公开(公告)号：US09886958B2
公开(公告)日：2018-02-06
申请号：US14966257
申请日：2015-12-11
CPC分类号： G10L17/22 , G06F17/2785 , G06F17/3043 , G10L17/04 , G10L17/26
摘要： A universal model-based approach for item disambiguation and selection is provided. An utterance may be received by a computing device in response to a list of items for selection. In aspects, the list of items may be displayed on a display screen. The universal disambiguation model may then be applied to the utterance. The universal disambiguation model may be utilized to determine whether the utterance is directed to at least one of the list of items and identify an item from the list corresponding to the utterance, based on identified language and/or domain independent referential features. The computing device may then perform an action which may include selecting the identified item associated with utterance.
-
公开(公告)号：US09886479B2
公开(公告)日：2018-02-06
申请号：US14445182
申请日：2014-07-29
CPC分类号： G06F17/3043 , G06F17/30675 , G06F17/30684 , G06F17/30861 , G06F17/30864 , H04L67/02
摘要： A method and system for managing credibility of a set of search results for a search query is disclosed. The method can include determining, by a natural language processing technique configured to analyze a portion of the set of search results and a portion of the search query, a credibility factor configured to indicate similarity to a subject matter of the search query. The method can also include establishing a relevance relationship between the credibility factor and source information of a first search result of the set of search results, wherein the source information is based on the credibility factor. The method may also include computing a credibility score for the first search result of the set of search results based on the relevance relationship between the credibility factor and the source information of the set of search results.
-
公开(公告)号：US20170344611A1
公开(公告)日：2017-11-30
申请号：US15678338
申请日：2017-08-16
CPC分类号： G06F17/30528 , G06F17/3043 , G06F17/3053 , G06F17/30554 , G06F17/30864 , G06F17/3087 , G06Q50/22
摘要： A question relating to an individual is received and context from the question is extracted. Subject matter criteria can be identified from the context of the question. A database containing history data that includes recorded positional data for physical objects relative to the location of the individual at the time of recording can be accessed and relevant physical objects from the history data can be identified based upon the subject matter criteria. A set of answers can be generated for the question from a corpus of data and ranked based upon the identified physical objects and physical distance between the individual and the relevant physical objects.
-
公开(公告)号：US20170293725A1
公开(公告)日：2017-10-12
申请号：US15455591
申请日：2017-03-10
发明人： Wen Liu , Ashutosh Modi , Bogdan Georgescu , Francisco Pereira
CPC分类号： G16H50/20 , G06F17/271 , G06F17/2785 , G06F17/279 , G06F17/3043 , G06F17/30654 , G06F19/00 , G06F19/321 , G06N3/0445 , G06N3/08
摘要： A computer-implemented method for predicting answers to questions concerning medical image analytics reports includes splitting a medical image analytics report into a plurality of sentences and generating a plurality of sentence embedding vectors by applying a natural language processing framework to the plurality of sentences. A question related to subject matter included in the medical image analytics report is received and a question embedding vector is generated by applying the natural language processing framework to the question. A subset of the sentence embedding vectors most similar to the question embedding vector is identified by applying a similarity matching process to the sentence embedding vectors and the question embedding vector. A trained recurrent neural network (RNN) is used to determine a predicted answer to the question based on the subset of the sentence embedding vectors.
-
公开(公告)号：US20170228372A1
公开(公告)日：2017-08-10
申请号：US15018338
申请日：2016-02-08
申请人： Taiger Spain SL
发明人： Carlos Ruiz Moreno , Sinuhé Arroyo
IPC分类号： G06F17/30
CPC分类号： G06F17/3043 , G06F17/30654
摘要： A system and method for information retrieval are presented. A client computer receives a natural language query comprising an array of tokens. A query processing server analyzes the natural language query (interpreted as a question) to identify a plurality of terms and a relationship between one or more pairs of the terms according to a knowledge model defining interrelationships between a plurality of entities. A set of assertions is constructed using the relationship between the pair of terms, and a query is executed against a knowledge base of frequently asked questions, corresponding answers, documents and/or data using the set of assertions to generate a set of results. The knowledge base identifies a plurality of items, each of the plurality of items is associated with at least one annotation identifying at least one of the entities in the knowledge model. The set of results are transmitted to the client computer.
-
-
-
-
-
-
-
-
-
搜索结果
532 条记录 (耗时 0.027 秒)
