Abstract: Methods and systems for gathering information from a user include identifying an origin topic and a target topic. A path from the origin topic to the target topic is determined. The path includes a set of bridging topics, where each bridging topic in the path is within a threshold distance in a semantic space from a previous topic and a subsequent topic. An interactive conversation is conducted with the user, introducing each topic in the path until the target topic has been reached. At least one predetermined piece of information relating to a user response to the target topic is recorded.

Abstract: A computer-implemented method for learning a policy for selection of an associative topic, which can be used in a dialog system, is described. The method includes obtaining a policy base that indicates a topic transition from a source topic to a destination topic and a short-term reward for the topic transition, by analyzing data from a corpus. The short-term reward may be defined as probability of associating a positive response. The method also includes calculating an expected long-term reward for the topic transition using the short-term reward for the topic transition with taking into account a discounted reward for a subsequent topic transition. The method further includes generating a policy using the policy base and the expected long-term reward for the topic transition. The policy indicates selection of the destination topic for the source topic as an associative topic for a current topic.

Abstract: A computer-implemented method for learning a policy for selection of an associative topic, which can be used in a dialog system, is described. The method includes obtaining a policy base that indicates a topic transition from a source topic to a destination topic and a short-term reward for the topic transition, by analyzing data from a corpus. The short-term reward may be defined as probability of associating a positive response. The method also includes calculating an expected long-term reward for the topic transition using the short-term reward for the topic transition with taking into account a discounted reward for a subsequent topic transition. The method further includes generating a policy using the policy base and the expected long-term reward for the topic transition. The policy indicates selection of the destination topic for the source topic as an associative topic for a current topic.

Abstract: A method for implementing artificial intelligence agents to perform machine learning tasks using predictive analytics to leverage ensemble policies for maximizing long-term returns includes obtaining a set of inputs including a set of ensemble policies and a meta-policy parameter, selecting an action for execution within the system environment using a meta-policy function determined based in part on the set of ensemble policies and the meta-policy function parameter, causing the artificial intelligence agent to execute the selected action within the system environment, and updating the meta-policy function parameter based on the execution of the selected action.

Abstract: A method for selecting an action, includes reading, into a memory, a Partially Observed Markov Decision Process (POMDP) model, the POMDP model having top-k action IDs for each belief state, the top-k action IDs maximizing expected long-term cumulative rewards in each time-step, and k being an integer of two or more, in the execution-time process of the POMDP model, detecting a situation where an action identified by the best action ID among the top-k action IDs for a current belief state is unable to be selected due to a constraint, and selecting and executing an action identified by the second best action ID among the top-k action IDs for the current belief state in response to a detection of the situation. The top-k action IDs may be top-k alpha vectors, each of the top-k alpha vectors having an associated action, or identifiers of top-k actions associated with alpha vectors.

Abstract: A method is provided for rule creation that includes receiving (i) a MDP model with a set of states, a set of actions, and a set of transition probabilities, (ii) a policy that corresponds to rules for a rule engine, and (iii) a set of candidate states that can be added to the set of states. The method includes transforming the MDP model to include a reward function using an inverse reinforcement learning process on the MDP model and on the policy. The method includes finding a state from the candidate states, and generating a refined MDP model with the reward function by updating the transition probabilities related to the state. The method includes obtaining an optimal policy for the refined MDP model with the reward function, based on the reward policy, the state, and the updated probabilities. The method includes updating the rule engine based on the optimal policy.

Abstract: A computer-implemented method is presented for building a topic model to discover topics in a collection of documents generated by a plurality of users. The method includes extracting conversations from the collection of documents, dividing the extracted conversations into a plurality of segments, generating a topic distribution for each of the plurality of segments based on the extracted conversations and a first pre-defined prior probability distribution, and generating continuous value constructs for each of the topic distributions based on an external corpus and a second pre-defined prior probability distribution, wherein similarity is defined between the continuous value constructs.

Abstract: A method is provided for rule creation that includes receiving (i) a MDP model with a set of states, a set of actions, and a set of transition probabilities, (ii) a policy that corresponds to rules for a rule engine, and (iii) a set of candidate states that can be added to the set of states. The method includes transforming the MDP model to include a reward function using an inverse reinforcement learning process on the MDP model and on the policy. The method includes finding a state from the candidate states, and generating a refined MDP model with the reward function by updating the transition probabilities related to the state. The method includes obtaining an optimal policy for the refined MDP model with the reward function, based on the reward policy, the state, and the updated probabilities. The method includes updating the rule engine based on the optimal policy.

Abstract: A computer-implemented method is presented for building a topic model to discover topics in a collection of documents generated by a plurality of users. The method includes extracting conversations from the collection of documents, dividing the extracted conversations into a plurality of segments, generating a topic distribution for each of the plurality of segments based on the extracted conversations and a first pre-defined prior probability distribution, and generating continuous value constructs for each of the topic distributions based on an external corpus and a second pre-defined prior probability distribution, wherein similarity is defined between the continuous value constructs.

Abstract: A method for implementing artificial intelligence agents to perform machine learning tasks using predictive analytics to leverage ensemble policies for maximizing long-term returns includes obtaining a set of inputs including a set of ensemble policies and a meta-policy parameter, selecting an action for execution within the system environment using a meta-policy function determined based in part on the set of ensemble policies and the meta-policy function parameter, causing the artificial intelligence agent to execute the selected action within the system environment, and updating the meta-policy function parameter based on the execution of the selected action.

Abstract: Methods and systems for gathering information from a user include identifying an origin topic and a target topic. A path from the origin topic to the target topic is determined. The path includes a set of bridging topics, where each bridging topic in the path is within a threshold distance in a semantic space from a previous topic and a subsequent topic. An interactive conversation is conducted with the user, introducing each topic in the path until the target topic has been reached. At least one predetermined piece of information relating to a user response to the target topic is recorded.

Abstract: A method of recommending Mashups, including identifying, using a processor, pre-existing Mashups implementing application program interfaces (APIs), where each implemented API has one or more attached Tag(s) including API characteristics; extracting the characteristics from the Tags attached to the API(s) implemented in the Mashup, form a set including all of the characteristics from the APIs implemented in Mashup; identifying one or more API(s) not implemented in the Mashups; extracting the characteristics from the Tags attached to the API(s) not implemented in the Mashup to form another set; identifying API characteristics that are an element of one set, but not an element of the other set, forming a third set of these characteristics; modeling a relationship between API(s) using the sets; calculating the probability of one or more API(s) not implemented in a Mashup being used for new Mashup; and presenting the API(s) to a user for new Mashups.

Abstract: A method is provided for rule creation that includes receiving (i) a MDP model with a set of states, a set of actions, and a set of transition probabilities, (ii) a policy that corresponds to rules for a rule engine, and (iii) a set of candidate states that can be added to the set of states. The method includes transforming the MDP model to include a reward function using an inverse reinforcement learning process on the MDP model and on the policy. The method includes finding a state from the candidate states, and generating a refined MDP model with the reward function by updating the transition probabilities related to the state. The method includes obtaining an optimal policy for the refined MDP model with the reward function, based on the reward policy, the state, and the updated probabilities. The method includes updating the rule engine based on the optimal policy.

Abstract: A method is provided for rule creation that includes receiving (i) a MDP model with a set of states, a set of actions, and a set of transition probabilities, (ii) a policy that corresponds to rules for a rule engine, and (iii) a set of candidate states that can be added to the set of states. The method includes transforming the MDP model to include a reward function using an inverse reinforcement learning process on the MDP model and on the policy. The method includes finding a state from the candidate states, and generating a refined MDP model with the reward function by updating the transition probabilities related to the state. The method includes obtaining an optimal policy for the refined MDP model with the reward function, based on the reward policy, the state, and the updated probabilities. The method includes updating the rule engine based on the optimal policy.

Abstract: An extraction method for extracting a sub query to be converted to a program for processing stream data continuously inputted to a database, from a query including instructions, as sub queries, to be issued to a database management system. The extraction method includes receiving input of the query and a lower limit value of efficiency as processing time per unit memory increase amount. A calculating operation calculates a one memory increase amount and the efficiency using the memory increase amount and the processing time to be reduced. The method selects a sub query whose calculated efficiency is equal to or higher than the lower limit value and extracts the selected sub query as a conversion object on condition that the integrated memory increase amount is equal to or smaller than the maximum memory increase amount.

Abstract: A computer-implemented method for learning a policy for selection of an associative topic, which can be used in a dialog system, is described. The method includes obtaining a policy base that indicates a topic transition from a source topic to a destination topic and a short-term reward for the topic transition, by analyzing data from a corpus. The short-term reward may be defined as probability of associating a positive response. The method also includes calculating an expected long-term reward for the topic transition using the short-term reward for the topic transition with taking into account a discounted reward for a subsequent topic transition. The method further includes generating a policy using the policy base and the expected long-term reward for the topic transition. The policy indicates selection of the destination topic for the source topic as an associative topic for a current topic.

Abstract: A computer-implemented method for learning a policy for selection of an associative topic, which can be used in a dialog system, is described. The method includes obtaining a policy base that indicates a topic transition from a source topic to a destination topic and a short-term reward for the topic transition, by analyzing data from a corpus. The short-term reward may be defined as probability of associating a positive response. The method also includes calculating an expected long-term reward for the topic transition using the short-term reward for the topic transition with taking into account a discounted reward for a subsequent topic transition. The method further includes generating a policy using the policy base and the expected long-term reward for the topic transition. The policy indicates selection of the destination topic for the source topic as an associative topic for a current topic.

Abstract: A method for selecting an action, includes reading, into a memory, a Partially Observed Markov Decision Process (POMDP) model, the POMDP model having top-k action IDs for each belief state, the top-k action IDs maximizing expected long-term cumulative rewards in each time-step, and k being an integer of two or more, in the execution-time process of the POMDP model, detecting a situation where an action identified by the best action ID among the top-k action IDs for a current belief state is unable to be selected due to a constraint, and selecting and executing an action identified by the second best action ID among the top-k action IDs for the current belief state in response to a detection of the situation. The top-k action IDs may be top-k alpha vectors, each of the top-k alpha vectors having an associated action, or identifiers of top-k actions associated with alpha vectors.

Abstract: A method for selecting an action, includes reading, into a memory, a Partially Observed Markov Decision Process (POMDP) model, the POMDP model having top-k action IDs for each belief state, the top-k action IDs maximizing expected long-term cumulative rewards in each time-step, and k being an integer of two or more, in the execution-time process of the POMDP model, detecting a situation where an action identified by the best action ID among the top-k action IDs for a current belief state is unable to be selected due to a constraint, and selecting and executing an action identified by the second best action ID among the top-k action IDs for the current belief state in response to a detection of the situation. The top-k action IDs may be top-k alpha vectors, each of the top-k alpha vectors having an associated action, or identifiers of top-k actions associated with alpha vectors.

Abstract: An extraction device for extracting a sub query to be converted to a program for processing stream data continuously inputted to a database, from a query including instructions, as sub queries, to be issued to a database management system. The extraction device includes: an input unit; an operation unit for calculating the memory increase amount in a case of processing the stream data and the processing time to be reduced for each sub query, and calculating the efficiency by using them; and an extraction unit for selecting at least one sub query whose efficiency is equal to or higher than the lower limit value, integrating the memory increase amount calculated for the selected sub query, and on condition that the integrated memory increase amount is equal to or smaller than the maximum memory increase amount, extracting the selected sub query as a conversion object.