GENESYS TELECOMMUNICATIONS LABORATORIES, INC.

A method facilitating a customer exercising post-purchase rights associated with a purchase made by the customer of a product. The method includes: receiving first documentation related to the purchase of the product; extracting purchase data from the first documentation, where the extracted purchase data describes the purchase including a vendor identify, purchase date, and product type; conducting search using terms derived from the extracted purchase data to connect to a vendor web site; conducting a search of the vendor web site using terms derived from the extracted purchase data to locate a first vendor policy of the vendor that defines a first post-purchase right of the customer; determining a milestone date associated with the first post-purchase right of the customer; and sending a notification to the customer appraising the customer of the milestone date and the material change.

A method for authoring a conversational bot including: receiving conversation data; receiving seed intent data that comprises seed intents having a seed intent label and sample intent-bearing utterances; using an intent mining algorithm to mine the conversation data to determine new utterances to associate with the seed intent; augmenting the seed intent data to include the mined new utterances associated with the seed intents; and uploading the augmented seed intent data into the conversation bot. The intent mining algorithm may include: identifying intent-bearing utterances; identifying candidate intents; for each of the seed intents, identifying seed intent alternatives from the sample intent-bearing utterances; associating the intent-bearing utterances from the conversation data with the seed intents via determining a degree of semantic similarity between the candidate intents of the intent-bearing utterances and the seed intent alternatives.

A system and method for multimedia contact center interactions via an audiovisual asynchronous messaging channel is provided. In an embodiment, an organization might operate a website comprising information and for providing an entry point of communication with a contact center. A communications channel may be integrated directly with the organization's website, which includes an editable audiovisual interface. A user may interact with the editable interface through a variety of means, including sketching on a webpage and recording to create a video form of audiovisual asynchronous query over the web page. The interaction is analyzed and routed to an agent for handling. The agent may then be connected to the user through the asynchronous channel.

An end-user device operable in a retail store records a voice conversation held in the retail store. The recording is transmitted to a server for comparing it to recordings of other conversations from a plurality of other retail stores. The server makes a recommendation based on the comparing. Embodiments of the invention are also directed to an analytics system that collects real-time metrics data for various virtual or physical retail stores associated with a plurality of contact centers. The system performs real-time analytics of the collected metrics data for identifying a product or service. The processor modifies, based on the real-time analytics, a prior service or product to be offered by a particular retail store, with the identified service or product. The processor pushes the modified service or product for display on the end-user device use in the particular retail store.

A system and method are presented for the addition of content to contact center interactions. An interaction is routed to an agent in the contact center environment. The interaction is routed through one or more providers of embedded client applications. Providers may be a first party, a DSL provider, or a programmatic provider. The provider triggers a user interface which displays one or more specified embedded client applications to the agent and when the agent selects one of the applications, it is asynchronously loaded through an inline frame.

A system and method are presented relating to emotion-based action recommendations. The present invention may include a recommender engine that analyzes several pieces of information and using artificial intelligence derived models, provides a course of action for a contact center agent and the probability and estimations behind the recommendation as a justification. System inputs include cost of the item or service being troubleshooted, estimated costs for different resolutions, cost of each escalation level of the interaction, history of previous interactions, agent costs, history of the current interaction, acoustic events and sentiment or primary detected emotions of the customer's transcript. The recommended course of action, rationale, and authorization can be provided as output. The system may record whether the agent followed the recommendation to improve further recommendations.

A system and method are presented for model derivation for entity prediction. An LSTM with 100 memory cells is used in the system architecture. Sentences are truncated and provided with feature information to a named-entity recognition model. A forward and a backward pass of the LSTM are performed, and each pass is concatenated. The concatenated bi-directional LSTM encodings are obtained for the various features for each word. A fully connected set of neurons shared across all encoded words is obtained and the final encoded outputs with dimensions equal to the number of entities is determined.

A system and method are presented for the correction of packet loss in audio in automatic speech recognition (ASR) systems. Packet loss correction, as presented herein, occurs at the recognition stage without modifying any of the acoustic models generated during training. The behavior of the ASR engine in the absence of packet loss is thus not altered. To accomplish this, the actual input signal may be rectified, the recognition scores may be normalized to account for signal errors, and a best-estimate method using information from previous frames and acoustic models may be used to replace the noisy signal.

A system including a mobile application on a user's mobile device for connecting to a plurality of contact centers and providing personalized context to the user. The system includes: the mobile application; a connection from the mobile application to a central API service, wherein the central API service provides authentication tokens to the mobile application for facilitating interaction therebetween; a plurality of vendors which the user has associated with their profile and have been integrated with the central API service, wherein the vendors are operably connected with the central API service for information sharing; and a plurality of media channels connecting the plurality of vendors with the central API service, allowing the user to: view personalized context from past interactions between the user and the plurality of contact centers through the mobile application; and connect with the contact centers.

A first text corpus comprising punctuated and capitalized text is received. The words in the first text corpus are then annotated with a set of labels indicating a punctuation and a capitalization of each word. At an initial training stage, a machine learning model is trained on a first training set using the annotated words from the first text corpus and the labels. A second text corpus is received representing conversational speech. The words in the second text corpus are then annotated with the set of labels. In a re-training stage, the machine learning model is re-trained on a second training set comprising the annotated words from the second text corpus, and the labels. At an inference stage, the trained machine learning model is applied to a target set of words representing conversational speech to predict a punctuation and capitalization of each word in the target set.