99 results about "Frequently asked questions" patented technology

A voice-enabled help desk service is disclosed. The service comprises an automatic speech recognition module for recognizing speech from a user, a spoken language understanding module for understanding the output from the automatic speech recognition module, a dialog management module for generating a response to speech from the user, a natural voices text-to-speech synthesis module for synthesizing speech to generate the response to the user, and a frequently asked questions module. The frequently asked questions module handles frequently asked questions from the user by changing voices and providing predetermined prompts to answer the frequently asked question.

A voice-enabled help desk service is disclosed. The service comprises an automatic speech recognition module for recognizing speech from a user, a spoken language understanding module for understanding the output from the automatic speech recognition module, a dialog management module for generating a response to speech from the user, a natural voices text-to-speech synthesis module for synthesizing speech to generate the response to the user, and a frequently asked questions module. The frequently asked questions module handles frequently asked questions from the user by changing voices and providing predetermined prompts to answer the frequently asked question.

The embodiment of the invention discloses an automatic question-answering system. According to the automatic question-answering system, a user interaction unit receives a question input by a user, a question analysis unit extracts keywords from the question input by the user and expands the keywords, then an information retrieval unit searches a frequently asked question bank for answers to the question according to the expanded keywords and returns the answers to related documents, and finally, according to answer extraction rules corresponding to the question type, an answer extraction unit extracts an answer according with the rules from the related documents returned by the information retrieval unit, and sends the extracted answer to the user interaction unit to be fed back to the user. Compared with an automatic question-answering system in the prior art, the automatic question-answering system can automatically expand the keywords and divide the types of the input questions, different types of questions correspond to different types, further answer search is carried out in the types, and the accuracy and diversity of answers are improved.

The invention provides an implement method of an FAQ Chinese question answering system in the tourism field. The implement method comprises the steps of FAQ collection and organization, construction of a tourism field knowledge base, user query, question analysis, answer extraction and the like, thereby realizing the FAQ Chinese question answering system in the tourism field. The implement method constructs the tourism field knowledge base-field knowledge network with the help of the idea of ontology, utilizes the KDML language to define and describe the terms and the relations of the tourism field and realizes the integration of the tourism field knowledge network and a general knowledge base-knowledge network. The invention proposes a calculation method of similarity of tourism questions on the basis, the method realizes the calculation of the similarity of the questions with the help of the characteristics of the questions of the tourism field and the combination of morphological relations, the syntactic dependency relations and the field concept semantic relations in the questions, and the method further searches the related question from a candidate question set and extracts the answer of the question based on the similarity calculation. The test result of a Yunnan tourism FAQ question answering system proves that the method is feasible and has better effect.

The invention provides a question and answer method based on a knowledge graph, and an agricultural encyclopedia question and answer system. A natural language question raised by a user can be automatically analyzed; a topological structure based on a syntax tree is formed; retrieval and comparison are carried out through the topological structure and a question template in a grammar library; according to a mapping relation between the topological structure and a predicate nominatum, and a mapping relation between a synonym set and a relation or an attribute in the knowledge graph, a question-mapped predicate is obtained; in combination with an entity identified in the question, a final structured knowledge graph query statement is generated; retrieval is carried out in the knowledge graphaccording to the query statement; and a final result is returned. When the relevant topological structure cannot be retrieved in a question template library, the question answering is carried out bycalling common question-answer pairs of an FAQ question library. The question and answer system can give accurate answer retrieval for the question posed by the user, so that the satisfaction degree of the user to the agricultural encyclopedia question retrieval is improved.

A communications tool that combines a software application and various communication systems that parallel natural styles of knowledge sharing and problem solving. It merges with normal patterns of relationship to create a seamless and transparent extension of community. By using computer, Internet, telephone, e-mail, and other communications technologies, the present invention brings these communities of practice to a new level of immediacy and relevance—one not encumbered by time or place. The invention is issue-centered versus document-centered, incorporates a leader-controlled structure, which is distributive and transparent, and enables stratification of items to allow multiple and simultaneous uses of the invention (e.g. dynamic FAQ, electronic whiteboard, expert center, committee review tool, etc.). Leaders control through inherited parameters. The present invention more effectively captures and leverages “tacit” knowledge (that which exists in the minds of participants and has not been written down), by connecting communities and adapting to their forms of interrelationships.

The disclosed database-based Chinese natural language question-answering method comprises mainly analyzing Web structure to extract internet FAQ and question-answering from opening community to build database. Unlike to prior art, this invention can accept natural language query and return the answer directly without user screening, and overcomes defects in a certain extent.

A method and mechanism for a web based knowledge management tool. A knowledge management tool enables one to interact with a knowledge base and enable distributed collaboration between parties. Users may create and customize portlets to interact with the knowledge base in a variety of formats, such as, e.g., a survey and a FAQ. The information describing the appearance and operation of the portlets is stored within a database coupled to a portal database server, which is a component that provides content pertaining to a portal web site to one or more web browsers 101. Graphical based reports based upon user activity may be dynamically generated and subsequently displayed through portlets as well.

A method of selecting a set of questions to display comprises receiving a request from a user to access a frequently asked questions (FAQ) page. Account data for the user is retrieved. A set of questions is selected to display to the user based on the account data.

An Internet based computer application that consists of a back-end user interface for use by the client (“client”), and a front-end interface website for use by the end-user of the client (“user”, “end-user”), comprising customisable frequently asked questions (FAQs), help pages, discussion forums, downloadable documents, user created web pages, multiple word and phrase searching, query bot natural language parser, news and event ticker, and a customisable calendar. The front end is accessed by the end-user via a unique website address, and allows them access to the aforementioned features. The back end is accessed by the client using a unique username and password, and allows the client to modify all aforementioned features, an image library, account information, and other website features. All user-accessible features provide information to the user and provide feedback to the client, allowing them to adapt their website to the specific needs of their end-users.

A lightweight document matcher employs minimal processing and storage. The lightweight document matcher matches new documents to those stored in a database. The matcher lists, in order, those stored documents that are most similar to the new document. The new documents are typically problem statements or queries, and the stored documents are potential solutions such as FAQs (Frequently Asked Questions). Given a set of documents, titles, and possibly keywords, an automatic back-end process constructs a global dictionary of unique keywords and local dictionaries of relevant words for each document. The application front-end uses this information to score the relevance of stored documents to new documents. The scoring algorithm uses the count of matched words as a base score, and then assigns bonuses to words that have high predictive value. It optionally assigns an extra bonus for a match of words in special sections, e.g., titles. The method uses minimal data structures and lightweight scoring algorithms to compute efficiently even in restricted environments, such as mobile or small desktop computers.

The present invention relates to systems and methods for communicating with various people from remote locations, and more particularly to assisting customers through online commercial transactions utilizing a mix of live and pre-recorded video presentations and interactions. Various embodiments of the invention comprise: a) a customer connected to a network by a customer interface; b) an operator connected to a network by an operator interface; c) at least one display window in the customer interface, wherein said display window displays an object selected from a list consisting of: a live video feed of operator and a pre-recorded video clip of an operator; d) at least one interaction between said customer and said operator, wherein the interaction may be selected from a list consisting of: live text chat, live video conference, pre-recorded video messages, third party intervention, and changing the appearance of the customer interface; e) a recording device for recording customer behaviors and customer interactions with operator; f) data storage for retention of said customer behaviors and said customer interactions with operator; and g) recall device for playing at least one prerecorded video clip selected by an operator for said customer, wherein said clip is selected from a list consisting of: a prerecorded video clip of an answer to a frequently asked question, a greeting previously recorded by the operator, an answer previously recorded by said operator and an answer previously recorded by a third party.

A method and system of detecting and reporting failures in a computer, in particular a personal computer is disclosed. Event codes related to failure events are given unique alpha numeric designations, allowing universal recognition of failures related to diagnostic programs that are ran. The unique event codes are stored in an error log when a particular failure is found through the operation of a diagnostic program. The error log is parsed as to determined values and can be minimized further by eliminating redundant occurrences of the event codes. Event codes can be related to frequently asked question (FAQ) files, the FAQ files can then be presented to a user. In certain cases, the presented FAQ files can be minimized further by a template that masks out irrelevant FAQ files. The FAQ file that are considered relevant can be predetermined per the requirements of the user.

A voice-enabled help desk service is disclosed. The service comprises an automatic speech recognition module for recognizing speech from a user, a spoken language understanding module for understanding the output from the automatic speech recognition module, a dialog management module for generating a response to speech from the user, a natural voices text-to-speech synthesis module for synthesizing speech to generate the response to the user, and a frequently asked questions module. The frequently asked questions module handles frequently asked questions from the user by changing voices and providing predetermined prompts to answer frequently asked questions.

Systems and methods for integrating collaborative services with content. Collaboration services are provided to a user in the context of content such that the user may collaborate with other contacts or users within the context of the content. The collaborative services are accessed through a pane or window that initially displays a list of experts and peers as well as frequently asked questions links, availability data and configuration data. When a contact is selected, more details about the selected contact are provided to the user including a contact block that indicates how the user may collaborate with the selected contact. The contact block identifies modes of communication such as e-mail, instant messaging, video conferencing, threads, telephone, and the like. When a mode of communication is selected, the user may collaborate with the selected contact. The context of the content is often supplied to the selected contact to improve the collaboration.

An automated customer support tool. A web server receives one or more queries regarding the product from a customer. A categorizer coupled to the web server categorizes the received queries based on a type of query, to determine whether the answers to the queries can be automatically communicated to the customer. An FAQ extractor extracts one or more corresponding product FAQs from respective product FAQ data bases. A key-word extractor extracts one or more key-words from the received queries and the extracted product FAQs. The key-word extractor further transforms the extracted key words to unique numerical representations. An analyzer coupled to the key-word extractor represents the transformed key-words into respective query and product FAQ vector forms. The analyzer further applies a convolution algorithm to each of the query vector forms, with each of the product FAQ vector forms separately and obtains one or more appropriate answers to the queries. Then the analyzer automatically communicates the answers to the queries received from the customer.

Building, reusing and calibrating network of authored content, in one aspect, may comprise clustering a plurality of problem tickets into one or more clusters. The clusters may be associated to one or more FAQ nodes in a FAQ network. The associated one or more FAQ nodes may be checked to determine whether the nodes are part of a broken branch. If the one or more FAQ nodes leads to a broken branch, a user may be notified to update the branch, e.g., with an answer or resolution to the one or more FAQ nodes.

A mobile telephone is used to search the web site (or computer database) of an entity to find information such as in an FAQ. The user speaks the first few letters of a word (or the first few letters of each of a string of words) into the telephone. The spoken letters are converted into text, search words are formed and the search is sent to the web site. A match results in the answer to the question being returned to the user. Once the first letters are spelled out, the latter letters are essentially redundant, and software can figure out what the intended word is. Error correction is used if the user or speech engine makes a mistake. Confidence values are output by the speech engine when recognizing a spoken letter. The location of each letter and the number of letters spoken is taken into account when attempting a match. The search technique not only matches recognized letters, but also matches their determined location within a search word. The user is provided with a choice if there is more than one match. The user provides their preferred delivery means (voice, SMS, e-mail, facsimile, etc.) on input. Also, a Web server implements a telephone directory that may be citywide, statewide, countrywide or even global. A user speaks a few letters in order find a telephone number of a person or business.

The invention discloses a device and a method for optimizing search ranking of frequently asked question and answer pairs, which is used for optimizing the ranking of search results searched by the frequently asked question and answer pairs. The method comprises the following steps: receiving a search query of a user, and obtaining multiple frequently asked question and answer pairs to be analyzed matched with the search query according to the search query of the user; according to a question and answer knowledge base including multiple question and answer knowledge records, obtaining associated degree of each frequently asked question and answer pair to be analyzed; according to the associated degrees of the frequently asked question and answer pairs to be analyzed, optimizing the search ranking of the frequently asked question and answer pairs to be analyzed matched. The device and the method can evaluate the associated degrees of the frequently asked question and answer pairs to be analyzed as the search results and optimize the ranking of the search results, and the ranking effect is better.

The invention relates to a man-machine interaction method of a customer service system. The method enables the effect to be continuously optimized by virtue of user feedbacks, and comprises the following steps that a user raises a question and waits the customer service system to answer the question; buttons representing satisfactory and dissatisfactory feedbacks of the user are added on a question answering interface of the customer service system, and the user is invited to give feedback to whether an answer is satisfactory or not; satisfaction and dissatisfaction clicking behaviors of the user are fed back to logs of the customer service system and associated with the question of the user and the answer of a customer service staff at that time; a positive sample and a negative sample of the answer of the customer service staff are generated based on the logs; offline learning is carried out by utilizing the positive sample and the negative sample; and frequently asked question (FAQ) knowledge after the offline learning of the customer service system is updated. According to the method, the user experience is improved and the user does not feel unfriendly; sufficient positive and negative samples are provided for question and answer effects of customer service staffs; and continuously innovated fresh question-asking ways of users can be quickly adapted.

At least one social media channel includes a plurality of user messages, which are accessible via a communication network. At least some of the stored messages are retrieved from the at least one social media channel via the communication network, and a collection of frequently asked questions (FAQ) is generated or updated by analyzing the retrieved messages to form a plurality of topical issue clusters. Each topical issue cluster is associated with at least one topic parameter from among a plurality of topic parameters, each topic parameter relates to at least one of use, installation or maintenance of a product or service, and each topical issue cluster includes at least one issue identified by a community of users and at least one resolution of the issue identified by the community of users. The generated or updated FAQ is uploaded to a storage location accessible to the community of users.

One embodiment of the invention provides a question answering device and method for vehicles, belonging to the field of vehicles. The device comprises a receiving module for receiving questions brought out by users; an application scene classification module for performing application scene classification on the questions brought out by the users, wherein the application scene comprises one or many of the followings: fault type, general knowledge type, handbook type, car purchasing type and insurance type; a semantic comprehension module for semantic recognition of the questions brought out by the users according to the classified application scene to obtain feature information; an answer assuring module for determining answers corresponding to the questions brought by the users according to the feature information; and an answer outputting module for outputting the answers corresponding to the questions brought by the users. The method and device effectively solve the problem of low accuracy of FAQ-based question answering mode.

A user support system provides a user interface that integrates FAQ features and helpdesk features and a user support request handling interface that integrates user support request handing and FAQ database maintenance. The user interface screen allows a user to select one or more levels of categories of support topic, and displays a list of frequently asked questions (FAQ) based on the user-selected categories. Once the categories are selected, a message input window is displayed on the user interface screen to allow the user to send a support request to the support provider. The user support request handling interface allows a support staff to select from a database a template answer to the user's request; it also provides means for the support staff to directly edit the template answer in the database, add new questions and answers to the database, or assign a question to a category.

The invention discloses a fusion knowledge base processing method and a device and a knowledge base management system. The fusion knowledge base processing method comprises the steps of extracting a knowledge classification catalogue from a common problem FAQ library and an ontology knowledge base, wherein the ontology knowledge base comprises a knowledge ontology and a ontology relation, based on the knowledge ontology, ontology relation and the knowledge classification catalogue, mount the contents of the FAQ library into the ontology knowledge base, and generating a fusion knowledge base. The fusion knowledge base processing method solves the problem that in the prior art the performance of the FAQ system can hardly be enhanced because the retrieval question answering system, the question answering system based on the knowledge base and the community cooperative question answering system have many defects in the practical application.

A user support system and related user interface that integrates FAQ features and helpdesk features. The user interface screen includes menu windows that allow the user to select a main category and a subcategory of the support topic, and displays a list of frequently asked questions (FAQ) based on the user-selected main category and subcategory. A message input window and associated metadata windows are also displayed on the user interface screen, which allow the user to send a question to the support provider. The support provider then communicates with the user through email or other means to provide answers to the user's questions. Optionally, after the support request is resolved, the question and answer may be used to update the FAQ database, taking into consideration the category and subcategory already selected by the user.

The disclosed invention is a system and method (collectively the “system”) for the automated management of content on a network interface. The network interface can be a web site on the World Wide Web, an Internet location, an intranet location, an extranet location, or some other form of network interface (collectively “web site”). The system can automatically create applications and links to those applications without human intervention. Examples of automated applications include newsroom applications, calendar of events, employment opportunities, project portfolio, biographies, frequently asked questions, document library, category management, product catalogs, e-mail broadcasts, surveys, and newsletters. Fully normalized hierarchies of business rules and user profiles can be supported by the system to facilitate automation and configurability. Multiple content providers can manage a single web site in a simultaneous or substantially simultaneous manner. In ASP embodiments, multiple organizations can use the system to manage multiple web sites in a substantially simultaneous manner.