Abstract: Techniques for automatically switching between chatbot skills in the same domain. In one particular aspect, a method is provided that includes receiving an utterance from a user within a chatbot session, where a current skill context is a first skill and a current group context is a first group, inputting the utterance into a candidate skills model for the first group, obtaining, using the candidate skills model, a ranking of skills within the first group, determining, based on the ranking of skills, a second skill is a highest ranked skill, changing the current skill context of the chatbot session to the second skill, inputting the utterance into a candidate flows model for the second skill, obtaining, using the candidate flows model, a ranking of intents within the second skill that match the utterance, and determining, based on the ranking of intents, an intent that is a highest ranked intent.

Abstract: A distribution network may efficiently communicate items/item details in a private manner, with different access rights tailored to various tenants residing within a same or different customer landscape. A first input comprising a flat file with items/item details, is received. A second input comprising permissions entries for per-user, per-item direct access rights (e.g., view, read, write, delete) is also received. The first and second inputs are recursively processed to find nearest ancestors having the direct access rights, with a hash maintained including the nearest ancestors. An effective permitted structure (e.g., tree comprising root and leaf nodes) is generated by recursively adding descendant items having inherited access rights, to the nearest ancestors. Ultimately, descendant item(s) are privately distributed to a user with an access right according to the effective permitted structure. Embodiments may be particularly suited to the private distribution of analytics content (e.g.

Abstract: A distribution network may efficiently communicate items/item details in a private manner, with different access rights tailored to various tenants residing within a same or different customer landscape. A first input comprising a flat file with items/item details, is received. A second input comprising permissions entries for per-user, per-item direct access rights (e.g., view, read, write, delete) is also received. The first and second inputs are recursively processed to find nearest ancestors having the direct access rights, with a hash maintained including the nearest ancestors. An effective permitted structure (e.g., tree comprising root and leaf nodes) is generated by recursively adding descendant items having inherited access rights, to the nearest ancestors. Ultimately, descendant item(s) are privately distributed to a user with an access right according to the effective permitted structure. Embodiments may be particularly suited to the private distribution of analytics content (e.g.

Abstract: A distribution network communicates content to tenant groups in a secure manner. An engine of the distribution network receives content created utilizing an application having different customers and partners. The engine also receives: a first identifier indicating a customer of the application with which a tenant is associated, and a second identifier indicating a partner of the application with which the tenant is associated. The engine references a stored database table to correlate the first identifier and the second identifier. Based upon the first identifier and the second identifier, the engine evaluates whether the tenant is to be provided access to the content. The engine may provide the tenant with the content according to an access right determined from the first identifier and the second identifier. Certain embodiments may find particular use disseminating content to new tenants of a customer, based upon prior distribution to other tenants of that customer.

Abstract: The present disclosure relates to chatbot systems, and more particularly, to batching techniques for handling unbalanced training data when training a model such that bias is removed from the trained machine learning model when performing inference. In an embodiment, a plurality of raw utterances is obtained. A bias eliminating distribution is determined and a subset of the plurality of raw utterances is batched according to the bias-reducing distribution. The resulting unbiased training data may be input into a prediction model for training the prediction model. The trained prediction model may be obtained and utilized to predict unbiased results from new inputs received by the trained prediction model.

Abstract: The present disclosure relates to techniques for identifying out-of-domain utterances.

Abstract: Techniques are disclosed for tuning hyperparameters of a model. Datasets are obtained for training the model and metrics are selected for evaluating performance of the model. Each metric is assigned a weight specifying an importance to the performance of the model. A function is created that measures performance based on the weighted metrics. Hyperparameters are tuned to optimize the model performance. Tuning the hyperparameters includes: (i) training the model that is configured based on a current values for the hyperparameters; (ii) evaluating a performance of the model using the function; (iii) determining whether the model is optimized for the metrics; (iv) in response to the model not being optimized, searching for a new values for the hyperparameters, reconfiguring the model with the new values, and repeating steps (i)-(iii) using the reconfigured model; and (v) in response to the model being optimized for the metrics, providing a trained model.

Abstract: Techniques for noise data augmentation for training chatbot systems in natural language processing. In one particular aspect, a method is provided that includes receiving a training set of utterances for training an intent classifier to identify one or more intents for one or more utterances; augmenting the training set of utterances with noise text to generate an augmented training set of utterances; and training the intent classifier using the augmented training set of utterances. The augmenting includes: obtaining the noise text from a list of words, a text corpus, a publication, a dictionary, or any combination thereof irrelevant of original text within the utterances of the training set of utterances, and incorporating the noise text within the utterances relative to the original text in the utterances of the training set of utterances at a predefined augmentation ratio to generate augmented utterances.

Abstract: Techniques for stop word data augmentation for training chatbot systems in natural language processing. In one particular aspect, a computer-implemented method includes receiving a training set of utterances for training an intent classifier to identify one or more intents for one or more utterances; augmenting the training set of utterances with stop words to generate an augmented training set of out-of-domain utterances for an unresolved intent category corresponding to an unresolved intent; and training the intent classifier using the training set of utterances and the augmented training set of out-of-domain utterances. The augmenting includes: selecting one or more utterances from the training set of utterances, and for each selected utterance, preserving existing stop words within the utterance and replacing at least one non-stop word within the utterance with a stop word or stop word phrase selected from a list of stop words to generate an out-of-domain utterance.

Abstract: In one aspect, a computerized method generating and managing a set of broadcast-application messages includes the step of providing a dashboard view that enables the creation of a broadcast-application message creation. The computerized method includes the step of receiving a user addressee instruction. The computerized method includes the step of receive a user reply instruction. The computerized method includes the step of receiving a rich-media content card with a set of broadcast-application message creation instructions. The computerized method includes the step of receiving, with the dashboard view, an aggregation of reply instructions. The computerized method includes the step of generating the broadcast application message generated using a set of tools presented by the dashboard view. The computerized method includes the step of communicating the broadcast application message to a designated addressee.

Abstract: In one aspect, a computerized method useful for implementing a language neutral virtual assistant including the step of providing a language detector. The language detector comprises one or more trained language classifiers. With language detector identifying a language of an incoming message from a user to an artificially intelligent (AI) personal assistant. The method includes the step of receiving an incoming message to the AI personal assistant. The method includes the step of normalizing the incoming message, wherein the normalizing the incoming message comprises a set of spelling corrections and a set of grammar corrections. The method includes the step of translating the incoming message to a specified language with a specified encoding process and a specified decoding process. The method includes the step of providing an AI personal assistant engine that comprise an artificial intelligence which conducts a conversation via auditory or textual methods.

Abstract: In one aspect, a computerized method useful for implementing and managing an Automated assistant translator between an Automated assistant service and a plurality of third-party messaging platforms includes the step of deploying an Automated assistant in a plurality of third-party messaging platforms. The method includes the step of, with the Automated assistant, receiving a conversational input from a human user via a first third-party messaging platform of the plurality of third-party messaging platforms. The method includes the step of parsing the conversation input. The method includes the step of determining a request for additional information in the conversation input. The method includes the step of retrieving a set of information relating to the request for additional information in the conversation input. The method includes the step of generating a natural-language output that includes the information.

Abstract: In one aspect, a computerized method generating and managing a set of broadcast-application messages includes the step of providing a dashboard view that enables the creation of a broadcast-application message creation. The computerized method includes the step of receiving a user addressee instruction. The computerized method includes the step of receive a user reply instruction. The computerized method includes the step of receiving a rich-media content card with a set of broadcast-application message creation instructions. The computerized method includes the step of receiving, with the dashboard view, an aggregation of reply instructions. The computerized method includes the step of generating the broadcast application message generated using a set of tools presented by the dashboard view. The computerized method includes the step of communicating the broadcast application message to a designated addressee.