Estimation accuracies of a conversation satisfaction and a speech satisfaction are improved. A learning data storage unit (10) stores learning data including a conversation voice containing a conversation including a plurality of speeches, a correct answer value of a conversation satisfaction for the conversation, and a correct answer value of a speech satisfaction for each speech included in the conversation. A model learning unit (13) learns a satisfaction estimation model using a feature quantity of each speech extracted from the conversation voice, the correct answer value of the speech satisfaction, and the correct answer value of the conversation satisfaction, the satisfaction estimation model configured by connecting a speech satisfaction estimation model part that receives a feature quantity of each speech and estimates the speech satisfaction of each speech with a conversation satisfaction estimation model part that receives at least the speech satisfaction of each speech and estimates the conversation satisfaction.

Estimation accuracies of a conversation satisfaction and a speech satisfaction are improved. A learning data storage unit (10) stores learning data including a conversation voice containing a conversation including a plurality of speeches, a correct answer value of a conversation satisfaction for the conversation, and a correct answer value of a speech satisfaction for each speech included in the conversation. A model learning unit (13) learns a satisfaction estimation model using a feature quantity of each speech extracted from the conversation voice, the correct answer value of the speech satisfaction, and the correct answer value of the conversation satisfaction, the satisfaction estimation model configured by connecting a speech satisfaction estimation model part that receives a feature quantity of each speech and estimates the speech satisfaction of each speech with a conversation satisfaction estimation model part that receives at least the speech satisfaction of each speech and estimates the conversation satisfaction.

Aspects of the subject disclosure may include, for example, a method in which a processing system collects information associated with trouble tickets each including a problem abstract and a log text. The method includes analyzing the log text to obtain a problem resolution for that ticket; defining ticket clusters according to the problem abstracts, and labeling the clusters. The processing system creates a library of the labeled clusters, each entry including a cluster label, a problem abstract for that cluster, and a resolution summary for that problem abstract, indicating a mapping of the problem abstract to the resolution summary for that cluster. The method includes training, based on the mapping, machine-learning applications for a predicted resolution summary for each cluster and for classifying a new ticket. The method includes assigning the new ticket to a cluster according to the classifying. Other embodiments are disclosed.

Aspects of the subject disclosure may include, for example, a method in which a processing system collects information associated with trouble tickets each including a problem abstract and a log text. The method includes analyzing the log text to obtain a problem resolution for that ticket; defining ticket clusters according to the problem abstracts, and labeling the clusters. The processing system creates a library of the labeled clusters, each entry including a cluster label, a problem abstract for that cluster, and a resolution summary for that problem abstract, indicating a mapping of the problem abstract to the resolution summary for that cluster. The method includes training, based on the mapping, machine-learning applications for a predicted resolution summary for each cluster and for classifying a new ticket. The method includes assigning the new ticket to a cluster according to the classifying. Other embodiments are disclosed.

In an approach, a processor trains a model, via a reinforcement learning process, to produce a first action function for relating states of a natural language based response environment to actions applicable to the natural language based response environment. A processor retrains the model, via the reinforcement learning process, to produce a second action function, including iterations of: applying the first action function to a current state representation of the natural language based response environment to obtain a ground-truth action representation, emphasizing a word of the current state representation based on relevancy to the ground-truth action representation to obtain a modified state representation, applying a model to the modified state representation to obtain an untrained action representation, and submitting the untrained action representation to a natural language based response environment to obtain a subsequent state representation, where the subsequent state representation becomes the current state representation for a subsequent iteration.

In an approach, a processor trains a model, via a reinforcement learning process, to produce a first action function for relating states of a natural language based response environment to actions applicable to the natural language based response environment. A processor retrains the model, via the reinforcement learning process, to produce a second action function, including iterations of: applying the first action function to a current state representation of the natural language based response environment to obtain a ground-truth action representation, emphasizing a word of the current state representation based on relevancy to the ground-truth action representation to obtain a modified state representation, applying a model to the modified state representation to obtain an untrained action representation, and submitting the untrained action representation to a natural language based response environment to obtain a subsequent state representation, where the subsequent state representation becomes the current state representation for a subsequent iteration.

A task agnostic framework for neural model transfer from a first language to a second language, that can minimize computational and monetary costs by accurately forming predictions in a model of the second language by relying on only a labeled data set in the first language, a parallel data set between both languages, a labeled loss function, and an unlabeled loss function. The models may be trained jointly or in a two-stage process.

A system and method for intelligently routing calls between customers and agents. The system and method use knowledge graphs to generate route recommendations for a route selection system. The system uses dynamically selected objective functions to generate the route recommendations. The objective functions may be selected according to the intent of the call. The system and method can also be used to reroute ongoing calls when the intent of the call changes.

A computer-implemented method of mapping attribute names of a source data model to a destination data model includes obtaining multiple source attribute names from the source data model, and obtaining multiple destination attribute names from the destination data model. The destination data model includes multiple attributes that correspond to attributes in the source data model having different attribute names. The method includes processing the obtained source attribute names and the obtained destination attribute names to standardize the attribute names according to specified character formatting, supplying the standardized attribute names to a machine learning network model to predict a mapping of each source attribute name to a corresponding one of the destination attribute names, and outputting, according to mapping results of the machine learning network model, an attribute mapping table indicating the predicted destination attribute name corresponding to each source attribute name.

Using a classical data model executing on a classical processor, a set of classical features is scored. A classical feature comprises a first attribute of a resource, and a score of the classical feature comprises an evaluation of a utility of the classical feature in predicting a result involving the resource. Using a quantum data model executing on a quantum processor and the scored set of classical features, a set of quantum features is scored. The scored set of classical features and the scored set of quantum features are correlated, forming a combined set of scored features. Using the combined set of scored features and a first set of input data of a resource, a valuation of the resource is calculated.