111 results about "Digital text" patented technology

A method and electronic device are provided for processing data. Analog text included in a document is detected. A first area of the analog text that converts to digital text and a second area of the analog text that does not convert to the digital text are determined. The digital text is displayed in the first area that converts to the digital text, and an image of at least a portion of the analog text is displayed in the second area that does not convert to digital text.

A system and method capable of reading machine-readable labels from physical objects, reading coordinate labels of geographical locations, reading timestamp labels from an internal clock, accepting digital text string labels as input obtained directly from a keyboard type input device, or indirectly using a speech-to-text engine transforming any other label type information encoding into digital data by some transduction means, and treating these different labels uniformly as object identifiers for performing various indexing operations such as content authoring, playback, annotation and feedback. The system further allows for the aggregating of object identifiers and their associated content into a single addressable unit called a tour. The system can function in an authoring and a playback mode. The authoring mode permits new audio / text / graphics / video messages to be recorded and bound to an object identifier. The playback mode triggers playback of the recorded messages when the object identifier accessed. In the authoring mode, the system supports content authoring that can be done coincident with object identifier creation thereby enabling authored content to be unambiguously bound to the object identifier. In the playback mode, the system can be programmed to accept / solicit annotations / feedback from a user which may also be recorded and unambiguously bound to the object identifier.

In an embodiment, speech is recorded and converted to digital text based on a shared vocabulary dictionary. During the session, voice recognition errors, that is, speech that could not be automatically identified (if any exists), are identified by the system and associated with digital text. When text for the voice recognition error is identified (e.g., by an editor), the shared vocabulary dictionary is updated (so that that particular voice recognition error will not occur again), thereby improving the performance of the system for all users that use the shared vocabulary dictionary. The identification of voice recognitions errors and the updated of the vocabulary dictionary are performed on an ongoing basis, so that the performance of the system for all users continually improves.

The disclosed system and method apply stores of factual information to correct errors in digital text, for example, generated from OCR, speech and / or handwriting recognition devices, and other automatic recognition devices. A text produced by OCR, speech recognition, handwriting recognition, and others may be processed to extract discussed facts. Databases of facts are searched based on information in the text. After comparing facts asserted in the text with the factual data from the databases, suggested corrections of the text are produced.

An optical text scanning device compatible with a small handheld computer such as a personal digital assistant (PDA). The scanning device allows for a clear view of the text that is scanned simultaneous to the scanning process so that the operator can continuously align the device to the text. The scanned images of the text are converted in real-time to standard byte or word characters for subsequent display on the computer's viewing screen. The operator can quickly verify the accuracy of the conversion by comparing the displayed character with the actual character of text on the surface that is being scanned. Scanned text characters are stored in standard digital text files for ease of manipulation.

In one aspect, a computerized method for operating computerized neural networks for modelling CSR-customer relationships includes the step of receiving a user query. The user query comprises a set of digital text from a customer as input into an online CSR system. The method includes the step of filtering out unnecessary content of the user query. The method includes the step of splitting filtered user query in a sentence wise manner. The method includes the step of feeding the tokenized user query into a contextualized word representation model. The method includes the step of generating a set of context-aware feature vectors from the contextualized word representation model. With the set of context-aware feature vectors, the method implements a decision-making function to generate an identified customer query. The method includes the step of receiving an agent response, wherein the agent response is a response to the user query, and wherein the agent response comprises a set of digital text from an agent. With an LSTM network, the method generates a user query tensor vector. With the LSTM network, generating an agent query tensor vector. The method includes the step of concatenating the user query tensor vector and the agent query tensor vector to produce a single tensor, wherein the single tensor is processable by a neural network.

A method of presenting text found on a substantially planar object. The method comprises positioning the substantially planar object for imaging; capturing an image from the substantially planar object; converting the image to a digital text; associating a media type with the text found on the substantially planar object; organizing the digital text according to the media type; and converting the digital text to an output format.

The invention discloses a similar Chinese herbal medicine search method based on a probability topic model. The method includes the following steps: transforming Chinese herbal medicine information in 'China Great Pharmacopoeia' and 'Chinese Materia Medica' into digital text through an optical character recognition tool; extracting information such as efficacy, property and flavor and channel tropism of Chinese herbal medicines by using a regular expression, and building a Chinese herbal medicine information base; generating corresponding vector spaces according to efficacy, property and flavor and channel tropism attributes of the Chinese herbal medicines respectively, and regulating the vector spaces of the efficacy according to the probability topic model; and at last, calculating similarity of the efficacy, property and flavor and channel tropism attributes between the Chinese herbal medicines according to cosine coefficients, and generating a Chinese herbal medicine similarity database. A user inputs the name of a Chinese herbal medicine, and a system displays the Chinese herbal medicine and similar Chinese herbal medicines visually in the form of a relational graph through searching in the corresponding Chinese herbal medicine pair similarity information database. By means of the similar Chinese herbal medicine search method based on the probability topic model, relevant Chinese herbal medicines can be searched according to attribute similarity, and the method is of great significance for Chinese herbal medicine study and Chinese herbal medicine informatization.

A system and method of call-routing and caller-screening that employs voice recognition to automatically recognize a caller's voice and then screen a caller, if appropriate; all without forcing the caller to identity himself / herself, which may be perceived as rude or offensive by some callers. Instead, a synthesized voice automatically asks the caller to identify who the caller wishes to speak with. Caller's response to this query is used to identify the callee as well as to optionally identify the caller. Thus, the screening of the caller takes place in a manner that the caller perceives as a more natural way of telephone communication. Caller's speech is used to generate digital voice samples therefrom and the caller's voice samples are directly compared with other voice samples stored in a database without converting the voice samples into digital text files. Present methodology is particularly useful when it is desired to limit one or more caller's direct access to the called party as well as to identify a caller before the called party wishes to proceed with the call. The digital call assistant system of the present invention may be implemented, for example, in a telephone company central office, in a PBX in an organization or as part of a wireless network. Subscription-based automatic caller-screening service may also be provided by a telephone service provider using the call assistant system of the present invention.

Method for web based language learning that empowers self-directed learners by introducing measurement within an integrated system of context-based non-didactic learning. In another embodiment learning system of the present invention is designed to help people learn from audio and digital text. The learning system of the present invention is effective in any learning situation where language is the main medium of instruction because the learning system of the present invention requires material to be presented in audio and digital text format. The combination of listening, reading and word and phrase review increases retention and confidence. By systematically learning new words and phrases in context, not only are language skills improved, but the ability to understand new concepts is enhanced. Reinforcement from multiple sources speeds up and enhances the learning process. The student has the instant ability to test himself on all key points. This is a kind of electronic note-taking system, which can tie all notes together and present them for quick review. Once the student understands the concepts he can listen to the lectures again or to recorded text material to reinforce comprehension.

Systems and methods are disclosed for identifying digital fonts. In particular, in one or more embodiments, the disclosed systems and methods detect a digital font, font characteristics, and a text structure with regard to digital text in an electronic document. Moreover, in one or more embodiments, the disclosed systems and methods utilize the detected font characteristics and text structure to search for complementary digital fonts. In particular, one or more embodiments include systems and methods that generate a search query based on determined font characteristics and / or text structures and utilize the search query to automatically identify, recommend, and provide complementary digital fonts for utilization in the electronic document.