Abstract: A computerized vehicle route optimization system is provided, including a processor configured to receive a graph of service location nodes and edges representing a travel cost metric between the service location nodes. The processor is further configured to, for each vehicle, determine a vehicle capacity, and instantiate a route data structure storing an ordered list of service location nodes, ordered by travel order. The processor is further configured to cluster the graph into node clusters such that a total of the service weighting values of all service location nodes in each node cluster is under the vehicle capacity. The processor is further configured to populate the ordered list of each route data structure with the service location nodes in a respective cluster, and optimize, via a hybrid reinforcement learning-annealing module, the ordered list of each route data structure to minimize a total travel cost metric of the plurality of vehicles.

Abstract: A computer system is provided, including a processor and associated memory storing instructions that when executed cause the processor to implement a plurality of artificial intelligence (AI) models. Each AI model is configured to receive, as input, time series data and to output a model-specific time series forecast including a respective predicted value for each of a plurality of future time steps. The processor is further configured to implement a model selection neural network configured to select a predicted most accurate AI model from among the plurality of AI models for each of the plurality of future time steps. The processor is further configured to implement a blended output generator configured to output a model-blended time series forecast including the respective predicted value computed by the predicted most accurate AI model selected for each of the plurality of future time steps.

Abstract: A method and apparatus for facilitating a turn-based interaction between a virtual agent and a customer of an enterprise are disclosed. The method includes receiving a conversational input provided by the customer during a turn-based interaction between the customer and the agent. One or more conversational inputs exchanged between the customer and the agent prior to the customer's conversational input are identified by positioning a virtual bounding box of fixed width over textual representation of the turn-based interaction. The conversational input and the one or more conversational inputs configure a set of conversational inputs. At least one context vector representation is generated based on an encoding of the set of conversational inputs. Each word of a virtual agent reply is predicted based on the at least one context vector representation. The virtual agent reply is provided to the customer in response to the conversational input of the customer.

Abstract: A method and apparatus for facilitating persona-based agent interactions with online visitors is disclosed. A plurality of persona related attributes is extracted from a textual transcript of each interaction between an agent of an enterprise and an online visitor. A feature vector data representation is generated based on the plurality of persona related attributes extracted from each interaction to configure a plurality of feature vector data representations. The plurality of feature vector data representations is classified based on a plurality of persona-based clusters, which enables classification of the plurality of online visitors into the plurality of persona-based clusters. A learning model is trained for each persona-based cluster using utterances of online visitors classified into a respective persona-based cluster. The learning model is trained to mimic a visitor persona representative of the respective persona-based cluster.

Abstract: A method and apparatus for selecting treatment for visitors to online enterprise channels are disclosed. The method includes receiving information related to a visitor and a current activity of the visitor on an online enterprise channel. The information is transformed to generate transformed data and a plurality of features is extracted from the transformed data. Using the plurality of features, it is determined whether a treatment when rendered to the visitor is capable of increasing a likelihood of the visitor performing a desired action during a current visit to the online enterprise channel. The treatment is selected and rendered if it is determined that the treatment is capable of increasing the likelihood of the visitor performing the desired action. No treatment is rendered if it is determined that no treatment from among the plurality of treatments is capable of increasing the likelihood of the visitor performing the desired action.

Abstract: A computer-implemented method and an apparatus for facilitating training of conversational agents are disclosed. The method includes automatically extracting a workflow associated with each conversation from among a plurality of conversations between agents and customers of an enterprise. The workflow is extracted, at least in part, by encoding one or more utterances associated with the respective conversation and mapping the encoded one or more utterances to predefined workflow stages. A clustering of the plurality of conversations is performed based on a similarity among respective extracted workflows. The clustering of the plurality of conversations configures a plurality of workflow groups. At least one conversational agent is trained in customer engagement using a set of conversations associated with at least one workflow group from among the plurality of workflow groups.

Abstract: A computer-implemented method and apparatus for predicting customer intentions defines a plurality of categories for classifying customer interaction data. The plurality of categories includes at least one action category for classifying information related to customer actions on interaction channels. Data signals corresponding to a customer interaction on one or more interaction channels is received. The data signals include information related to at least one customer action. A sequence of values is generated for each customer action for classifying information related to the each customer action. A value is generated corresponding to each action category to configure the sequence of values. The sequence of values is associated with a fixed length equal to a number of action categories in the at least one action category. The fixed length of the sequence of values facilitates use of one or more intention classifiers to predict an intention of the customer.

Abstract: A computer-implemented method and an apparatus dynamically select content for online visitors. The method includes receiving information related to activity of an online visitor on an enterprise interaction channel and identifying channel data related to the activity. A plurality of content pieces capable of being provided to the online visitor during the ongoing journey is identified. A correlation score is computed for each content piece using the channel data to generate a plurality of correlation scores. The plurality of content pieces are rank-ordered by sorting the plurality of correlation scores. A display of at least one content piece is effected during the ongoing journey of the online visitor on the enterprise interaction channel based on the rank-ordering of the plurality of content pieces.

Abstract: A method and apparatus for facilitating persona-based agent interactions with online visitors is disclosed. A plurality of persona related attributes is extracted from a textual transcript of each interaction between an agent of an enterprise and an online visitor. A feature vector data representation is generated based on the plurality of persona related attributes extracted from each interaction to configure a plurality of feature vector data representations. The plurality of feature vector data representations is classified based on a plurality of persona-based clusters, which enables classification of the plurality of online visitors into the plurality of persona-based clusters. A learning model is trained for each persona-based cluster using utterances of online visitors classified into a respective persona-based cluster. The learning model is trained to mimic a visitor persona representative of the respective persona-based cluster.

Abstract: A method and apparatus for selecting treatment for visitors to online enterprise channels are disclosed. The method includes receiving information related to a visitor and a current activity of the visitor on an online enterprise channel. The information is transformed to generate transformed data and a plurality of features is extracted from the transformed data. Using the plurality of features, it is determined whether a treatment when rendered to the visitor is capable of increasing a likelihood of the visitor performing a desired action during a current visit to the online enterprise channel. The treatment is selected and rendered if it is determined that the treatment is capable of increasing the likelihood of the visitor performing the desired action. No treatment is rendered if it is determined that no treatment from among the plurality of treatments is capable of increasing the likelihood of the visitor performing the desired action.

Abstract: A method and apparatus for facilitating a turn-based interaction between a virtual agent and a customer of an enterprise are disclosed. The method includes receiving a conversational input provided by the customer during a turn-based interaction between the customer and the agent. One or more conversational inputs exchanged between the customer and the agent prior to the customer's conversational input are identified by positioning a virtual bounding box of fixed width over textual representation of the turn-based interaction. The conversational input and the one or more conversational inputs configure a set of conversational inputs. At least one context vector representation is generated based on an encoding of the set of conversational inputs. Each word of a virtual agent reply is predicted based on the at least one context vector representation. The virtual agent reply is provided to the customer in response to the conversational input of the customer.

Abstract: A computer-implemented method and an apparatus for improving experiences of an online visitor visiting a website detects a website access event. A visitor profile is generated by defining a plurality of attributes related to visitor activities on the website. A data field is allocated to each attribute to configure the visitor profile including a plurality of data fields. Each data field is capable of accommodating a respective fixed number of entries determined based on a temporal threshold value computed to determine a number of entries required for storing of information related to past activities that are relevant to current activity of the online visitor on the website. The visitor profile is dynamically updated based on the current activity. At least one intention of the online visitor is predicted based on a state of the visitor profile selected at a chosen time instant during the current activity of the online visitor.

Abstract: A computer-implemented method and an apparatus for facilitating training of conversational agents are disclosed. The method includes automatically extracting a workflow associated with each conversation from among a plurality of conversations between agents and customers of an enterprise. The workflow is extracted, at least in part, by encoding one or more utterances associated with the respective conversation and mapping the encoded one or more utterances to predefined workflow stages. A clustering of the plurality of conversations is performed based on a similarity among respective extracted workflows. The clustering of the plurality of conversations configures a plurality of workflow groups. At least one conversational agent is trained in customer engagement using a set of conversations associated with at least one workflow group from among the plurality of workflow groups.

Abstract: A computer-implemented method and an apparatus dynamically select content for online visitors. The method includes receiving information related to activity of an online visitor on an enterprise interaction channel and identifying channel data related to the activity. A plurality of content pieces capable of being provided to the online visitor during the ongoing journey is identified. A correlation score is computed for each content piece using the channel data to generate a plurality of correlation scores. The plurality of content pieces are rank-ordered by sorting the plurality of correlation scores. A display of at least one content piece is effected during the ongoing journey of the online visitor on the enterprise interaction channel based on the rank-ordering of the plurality of content pieces.

Abstract: A computer-implemented method and an apparatus for improving experiences of an online visitor visiting a website detects a website access event. A visitor profile is generated by defining a plurality of attributes related to visitor activities on the website. A data field is allocated to each attribute to configure the visitor profile including a plurality of data fields. Each data field is capable of accommodating a respective fixed number of entries determined based on a temporal threshold value computed to determine a number of entries required for storing of information related to past activities that are relevant to current activity of the online visitor on the website. The visitor profile is dynamically updated based on the current activity. At least one intention of the online visitor is predicted based on a state of the visitor profile selected at a chosen time instant during the current activity of the online visitor.

Abstract: A computer-implemented method and apparatus for predicting customer intentions defines a plurality of categories for classifying customer interaction data. The plurality of categories includes at least one action category for classifying information related to customer actions on interaction channels. Data signals corresponding to a customer interaction on one or more interaction channels is received. The data signals include information related to at least one customer action. A sequence of values is generated for each customer action for classifying information related to the each customer action. A value is generated corresponding to each action category to configure the sequence of values. The sequence of values is associated with a fixed length equal to a number of action categories in the at least one action category. The fixed length of the sequence of values facilitates use of one or more intention classifiers to predict an intention of the customer.

Abstract: A method for predicting potential injury assessment for at least one occupant of a vehicle involved in a crash event and for broadcasting assessment of the occupant to a medical response unit. An occupant seated in each seat of a vehicle is detected. Occupant data is obtained relating to physical characteristics of each occupant seated in the vehicle. A crash event involving the vehicle is detected. Vehicle dynamic data and safety restraint data during the crash event is recorded. The potential injury assessment of each occupant is predicted by an injury assessment processing module based on the vehicle dynamic data and safety restraint data obtained during the crash event and the occupant data of each occupant in the vehicle. The corresponding injury assessment of each occupant of the vehicle is broadcast to a medical response unit.

Abstract: A method for predicting potential injury assessment for at least one occupant of a vehicle involved in a crash event and for broadcasting assessment of the occupant to a medical response unit. An occupant seated in each seat of a vehicle is detected. Occupant data is obtained relating to physical characteristics of each occupant seated in the vehicle. A crash event involving the vehicle is detected. Vehicle dynamic data and safety restraint data during the crash event is recorded. The potential injury assessment of each occupant is predicted by an injury assessment processing module based on the vehicle dynamic data and safety restraint data obtained during the crash event and the occupant data of each occupant in the vehicle. The corresponding injury assessment of each occupant of the vehicle is broadcast to a medical response unit.