Abstract: A device, system and method is provided for monitoring a user's interactions with Internet-based programs or documents. Content may be extracted from Internet server traffic according to predefined rules. Extracted content may be associated with a user's Internet interaction. The user's Internet interaction may be stored and indexed. The user's Internet interaction may be analyzed to generate a recommendation provided to a contact center agent while the contact center agent is communicating with said user for guiding the user's interaction, for example, in real-time. Traffic other than Internet server traffic may also be used.

Abstract: The subject matter discloses a method, comprising obtaining a current retention time of storage associated with a digital recorder; obtaining current bitrates of channels used to transmit video captured by edge devices communicating with the digital recorder. The method then determines change in compression rates to be allocated to at least a portion of the channels according to the current retention time and the current bitrates and transmits the change in compression rates to be allocated to the channels to edge devices communicating with the digital recorder. The method can be implemented in a system in which several digital recorders use the same storage.

Abstract: The subject matter discloses a method for expansion of search queries on large vocabulary continuous speech recognition transcripts comprising: obtaining a textual transcript of audio interaction generated by the large vocabulary continuous speech recognition; generating a topic model from the textual transcripts; said topic model comprises a plurality of topics wherein each topic of the plurality of topics comprises a list of keywords; obtaining a search term; associating a topic from the topic model with the search term; and generating a list of candidate term expansion words by selecting keywords from the list of keywords of the associated topic; said candidate term expansion words are of high probability to be substitution errors of the search term that are generated by the large vocabulary continuous speech recognition.

Abstract: A system and method for classifying a webpage may include generating, by an analysis server, a first representation of a webpage. A system and method may include generating, by a unit installed in a user web browser, a second representation of the webpage and the method may comprise producing a classification of the webpage by relating the first representation to the second representation.

Abstract: Some embodiments of the present invention refer to an apparatus and method for managing video storages. The method may include periodically receiving parameters indicative of a level of performance of video storage units and detecting up-down states of the video storage units upon receipt of an instruction to record video data. The method may further include detecting writing rates and reading rates of video data associated with the storage units and selecting one of the video storage units to record the video data, based on the parameters received, the detected up-down states, the detected writing rates and the detected reading rates.

Abstract: A computerized method for sales optimization including receiving at a computer server a digital representation of a portion of an interaction between a customer and an organization representative, the portion of an interaction comprises a speech signal of the customer and a speech signal of the organization representative; analyzing the speech signal of the organization representative; analyzing the speech signal of the customer; determining a distance vector between the speech signal of the organization representative and the speech signal of the customer; and predicting a sale success probability score for the captured speech signal portion.

Abstract: System and method for recording communication sessions in a peer-to-peer communication networks. A conference call may be established between an external end-device, a target agent end-device of a call center and a recorder over a peer-to-peer communication network. After the conference call is established, the recorder may receive media transferred between the external end-device and the target agent end-device and record that media.

Abstract: Some aspects of the invention may include a computer-implemented method for enrolling voice prints generated from audio streams, in a database. The method may include receiving an audio stream of a communication session and creating a preliminary association between the audio stream and an identity of a customer that has engaged in the communication session based on identification information. The method may further include determining a confidence level of the preliminary association based on authentication information related to the customer and if the confidence level is higher than a threshold, sending a request to compare the audio stream to a database of voice prints of known fraudsters. If the audio stream does not match any known fraudsters, sending a request to generate from the audio stream a current voice print associated with the customer and enrolling the voice print in a customer voice print database.

Abstract: A system and method for detecting an object of interest. A system and method may generate a first signature for an object of interest based on an image of the object of interest. A system and method may generate a second signature for a candidate object based on an image of the candidate object. A system and method may calculate a similarity score by relating the first signature to the second signature and may determine the image of the candidate object is an image of the object of interest based on the similarity score.

Abstract: Systems and methods for identifying an appearance of an object in a video stream, include receiving, in real-time, an indication of an area of interest, from a user, within a frame of a video stream. The area of interest may include an image of an object. Automatically analyzing the characteristics of the area of interest, finding a frame in which the object first appears in time in the video stream and displaying to the user the video stream starting from the frame in which the object first appears.

Abstract: The subject matter discloses a method, comprising obtaining a scene from a video camera and defining at least one point of the scene; creating a first scene terrain model of the scene, said first scene terrain model comprises a typical human object size in pixels in said at least one point of the scene; creating a second scene model of the scene, said second model defines a false positive determination that said at least one point comprises a human object; wherein said second scene model is created when the scene does not contain a human object; obtaining an image of the scene, said image is captured by a video camera; determining whether the human object is detected at the at least one point of said captured image by applying said first scene terrain model and said second scene model on the least one point.

Abstract: System and method for enabling interoperability between a Flex application included in a web page and an external application. A method includes substituting the Flex application included in the web page with a container application, the container application including an external interface; loading the Flex application into the container application; generating, by the container application, a representation for at least one object in the Flex application; and facilitating a communication between the Flex application and the external application based on the representation of the object.

Abstract: A generic categorization method may include receiving interaction data on a distributed computing system operating on a plurality of computing nodes. The distributed computing system may distribute the received interaction data across the plurality of nodes. On each node, categorization rules may be applied to the interaction data via parallel processing. The results, which may include a category associated with each interaction, may be written to a distributed storage system. A user interface may allow a user to define the categorization rules and schemas of interaction data.

Abstract: A method for fault-tolerant recording of calls of a PBX, comprising concurrently receiving metadata of calls of a PBX by a plurality of computerized apparatuses, generating unique identifiers for each of the calls such the unique identifiers that are common between the plurality of the computerized apparatuses, activating a first computerized apparatus to control recordings of contents of the calls and assigning the recording with the unique identifiers respective to the calls, operating the computerized apparatuses to receive feedbacks of activities of the recordings, where the feedbacks comprise the assigned unique identifiers and in case of a failure of the first computerized apparatus, activating a second computerized apparatus to maintain the recordings that were controlled by the first computerized apparatus.

Abstract: The subject matter discloses a computerized method for real time emotion detection in audio interactions comprising: receiving at a computer server a portion of an audio interaction between a customer and an organization representative, the portion of the audio interaction comprises a speech signal; extracting feature vectors from the speech signal; obtaining a statistical model; producing adapted statistical data by adapting the statistical model according to the speech signal using the feature vectors extracted from the speech signal; obtaining an emotion classification model; and producing an emotion score based on the adapted statistical data and the emotion classification model, said emotion score represents the probability that the speaker that produced the speech signal is in an emotional state.

Abstract: A method and apparatus combining the advantages of phonetic search such as the rapid implementation and deployment and medium accuracy, comprising steps and components for receiving the audio signal captured in the call center environment, extracting a multiplicity of feature vectors from the audio signal, creating a phoneme lattice from the multiplicity of feature vectors wherein the phoneme lattice comprising one or more allophone and each allophone comprising two or more phonemes, creating a hybrid phoneme-word lattice from the phoneme lattice and extracting the word by analyzing the hybrid phoneme-Word lattice.

Abstract: A call center system optimizing rules enforced over interactions with customers, including: an infrastructure including a module for handling interactions with customers, and hardware for at least maintaining the communication with said customers; management rules comprising one or more rule parameters, enforcing interaction behavior during all interactions with customers; and an adaptive, self learning module, for: monitoring interactions with customers; upon completion of each interaction, recording a corresponding set of full interaction details, which includes rule parameters that were enforced during said interaction, and those additional interaction parameters that are specific to that interaction; and using an adaptive engine, periodically analyzing said sets of recorded full interaction details, and producing one or more modified rules having modified rule, parameters, and enforcing said modified rules over future interactions with customers.

Abstract: A system and method for recording and distributing calls are provided. A call may be associated with an information record. Parameters in the information record may be used to determine if the call is to be recorded. Parameters in the information record may be used to determine a method of providing a recording of the call. Other embodiments are described and claimed.

Abstract: A method and apparatus for automatically sectioning an interaction into sections, in order to get more insight into interactions. The method and apparatus include training, in which a model is generated upon training interactions and available tagging information, and run-time in which the model is used towards sectioning further interactions. The method and apparatus operate on context units within the interaction, wherein each context unit is characterized by a feature vector relate to textual, acoustic or other characteristics of the context unit.

Abstract: A system and method for capturing screen events, and processing these events to form data in a data format which is susceptible to analysis. Preferably, the method also comprises analyzing the data in order to extract useful information about the user of the screen and computational device which generated these screen events. More preferably, the method of the present invention is able to assess the quality of the performance of the user whose interaction with the computational device caused the screen events to be generated.