International Business Machines Corporation

Tetsunosuke Fujisaki

Makoto Kobayashi

Charles C Tappert

Joonki Kim

William David Modlin

Thomas E Chefalas

Wlodek Wlodzimierz Zadrozny

Jianchang Mao

Yoav Medan

Hiroyasu Takahashi

Krishna Sundaram Nathan

Shuang Chen

Savitha Srinivasan

Nandakishore Kambhatla

Yiming Ye

Tong-Haing Fin

Yoichi Yoshida

Dragomir Radkov Radev

Catherine Gody Wolf

Kottappuram Mohamedali Mohiuddin

Masahide Shinozaki

George J Leibman

Mitsuru Ohshima

Kottappuram Mohammedali Mohiuddin

Joyce Yue Chai

Kenneth Steven Wenstrup

Sunil Subramanyam Govindappa

Homayoon Sadr Beigi

This patent describes a novel system, method, and program product that are used in interactive natural language dialog. One or more presentation managers operating on a computer system present information from the computer system to one or more users over network interface(s) and accept queries from the users using one or more known input/output modalities (e.g. Speech, typed in text, pointing devices, etc.). A natural language parser parses one or more natural language phrases received over one or more of the network interfaces by one or more of the presentation managers into one or more logical forms (parsed user input), each logical form having a grammatical and structural organization. A dialog manager module maintains and directs interactive sessions between each of the users and the computer system. The dialog manager receives logical forms from one or more of the presentation managers and sends these to a taxonomical mapping process which matches the items of interest to the user against the content organization in the content database to match business categories and sends modified logical forms back to the dialog manager.

System, method and program product for interactive natural dialog

Improved reliability and reduced delays and packet losses of Internet media transmissions over packet switching networks such as Internet and Intranet is achieved by replicating a sent message/information packet(s) from one or more source computers connected to the network into two or more replicas of one or more of the packets of the sent message. Each of the replicas is then directed through a different route through the network to one or more destination computers. In one embodiment, each of the routes is determined so that the routes have the least number of routers and access points in common. Since the replicas are redundant, losses and delays of some of the replicas is not fatal to assemble the packet sequence at the destination(s). Thus, the destination computer can assemble the sent message/information packet from received replicas in a more complete and faster manner. Redundant replicas that are received can be ignored and/or discarded at the destination computer.

Quality of service improvement of internet real-time media transmission by transmitting redundant voice/media frames

The web sharing manager of a receiving sharing client receives duplicated events (e.g. browser requests) and messages from the web sharing manager of a source sharing client that causes the browser of the receiving sharing client to execute the duplicate event/message so that the browsers of the source and receiving sharing client computer system(s) process the same events/messages. Because events/messages, that include control and information locations (addresses), are shared between the source and receiving and sharing client(s), the same web page is simultaneously displayed and controlled, i.e. shared, on all of the sharing client(s).

Internet web page sharing

A server system that is connected to one or more networks, e.g., the Internet, corporate or government intranets, extranets, etc. The server has one or more application files or configuration sets that the server serves to from one or more kiosks on the network. The configuration sets are application specific. (An application is a use for which the kiosks are configured or reconfigured.) One or more of the files in the configuration sets include one or more embedded (control) programs that are used to control the local APIs of one or more of the devices on the kiosk. In this way, the devices are controlled to configure the kiosk to perform the application.

Server for reconfiguring control of a subset of devices on one or more kiosks

The hybrid handwriting recognition method includes the steps of (a), in response to a handwriting input from a user, providing dynamic, time ordered stroke information; (b) determining a first list comprised of at least one probable character that the dynamic, time ordered stroke information is intended to represent; (c) converting the dynamic, time ordered stroke information to static stroke information; (d) determining a second list comprised of at least one probable character that the static stroke information represents; and (e) merging the first list and the second list to provide a third, unified list comprised of at least one element representing a most probable character that the dynamic, time ordered stroke information is intended to represent. The step of converting includes the steps of generating a static, bit-mapped representation of the dynamic stroke information, and generating one or more first stroke features based on contour directions of the bit-mapped stroke information. The first stroke features are applied as inputs to a plurality of neural network recognizers.

Hybrid on-line handwriting recognition and optical character recognition

A system and method for performing an incremental search using a character string returned by a recognizer on a confusion matrix encoded dictionary to predict a word in a handwriting input field of an application program. In the system and method, handwritten characters are input into a data entry field of an application program. The handwritten characters are recognized and assigned a cluster code. The string of characters is characterized by the cluster codes of the individual characters. The cluster codes of the string are compared with strings of cluster codes representing words in a dictionary. All or some of the matching words are displayed to the user, from which a selection can be made.

Confusion matrix mediated word prediction

A multi-stage multi-network character recognition system decomposes the estimation of a posteriori probabilities into coarse-to-fine stages. Classification is then based on the estimated a posteriori probabilities. This classification process is especially suitable for the tasks that involve a large number of categories. The multi-network system is implemented in two stages: a soft pre-classifier and a bank of multiple specialized networks. The pre-classifier performs coarse evaluation of the input character, developing different probabilities that the input character falls into different predefined character groups. The bank of specialized networks, each corresponding to a single group of characters, performs fine evaluation of the input character, where each develops different probabilities that the input character represents each character in that specialized network's respective predefined character group. A network selector is employed to increase the system's efficiency by selectively invoking certain specialized networks selected, using a combination of prior external information and outputs of the pre-classifier. Relative to known single network or one-stage multiple network recognition systems, the invention provides improved recognition, accuracy, confidence measure, speed, and flexibility.

Concurrent two-stage multi-network optical character recognition system

A dictionary based post-processing technique for an on-line handwriting recognition system is described. An input word has all punctuation removed, and the word is checked against a word processing dictionary. If any word matches against the dictionary, it is verified as a valid word. If it does not verify, a stroke match function and a spell-aid dictionary are used to construct a list of possible words. In some cases, the list is appended with possible words based on changing the first character of the originally recognized word. A character-match score, a substitution score and a word length are assigned to the items on the list. A word hypothesis is constructed from the list with each such word being assigned a score. The word with the best score is chosen as the output word for the processor.

Post-processing error correction scheme using a dictionary for on-line

Methods and apparatus are disclosed for recognizing handwritten words in response to an input signal from a handwriting transducer. The method includes the steps of: (a) partitioning the input signal into N frames; and (b) processing words from a vocabulary model to determine, for each processed word, a probability that the word represents a written word that is conveyed by the input signal. The determined probability is a function of N letter-frame alignment probabilities and also a probability based on a grouping of the N frames into L groups, where L is a number of letters in the word. A further step (c) identifies a word having a highest determined probability as being a most-likely word that is conveyed by the input signal. The determined probability is also a function of (a) a probability based on a frequency of occurrence of words and portions of words within a selected language model; and (b) when processing a frame other than the Nth frame, a number of frames that remain to be processed. In one embodiment of the invention all words in the vocabulary model are searched in parallel, thereby significantly reducing the recognition time. The use of a beam search technique is illustrated to perform the parallel search. Also, this invention teaches the use of hashing to increase the speed of the beam search technique.

On-line connected handwritten word recognition by a probabilistic method

A handwriting recognition system in which a user, on-line can reduce similarity between different prototypes. The user interactively can delete a prototype or add a new prototype, while at the same time is not allowed to delete a prototype when it is the only prototype for a given character.

On-line handwriting recognition using a prototype confusability dialog

For use in a handwriting recognition system a method, and apparatus for accomplishing same, that includes the steps of (a) inputting a plurality of strokes each of which is a constituent stroke of a symbol or symbols to be recognized by the system; (b) forming from the inputted strokes a first set (CHR) comprised of one or more symbols; and (c) averaging at least one characteristic of similarly formed symbols that are members of the first set to form a second set (AVG) comprised of prototype symbols to which, during the use of the system, assemblages of input strokes are compared. The method further includes the steps of (d) identifying a symbol or symbols of the second set that corresponds to only a single symbol of the first set; and (e) deleting the identified symbol or symbols from the second set. The method further includes the steps of (f) decomposing into constituent strokes the prototype symbols of the second set; and (g) forming a third set (STK) comprised of the constituent strokes of the second set to which, during the use of the system, input strokes are compared.

Robust prototype establishment in an on-line handwriting recognition

Method and apparatus for identifying a valid symbol or a string of valid symbols from a sequence of handwritten strokes. A method includes the steps of (a) generating in response to one or more handritten strokes a plurality of stroke labels each having an associated score; (b) processing the plurality of stroke labels in accordance with a beam search-like technique to identify those stroke labels indicative of a valid symbol or portion of a valid symbol; and (c) associating together identified stroke labels to determine an identity of a valid symbol or a string of valid symbols therefrom. An aspect of the invention is that each of the constraint validation filters is switchably coupled into a serial filter chain. The switches function to either couple a filter input to a stroke label or decouple the input and provide a path around the filter block. An application writer has available a plurality of constraint filters. The application writer specifies which one or ones of the constraint filters are to be applied for a specific sequence of strokes.

Growing community of inventors

Armonk, NY, United States of America

Tetsunosuke Fujisaki