Abstract: An inference apparatus includes: an inference module configured to infer a modification plan for modification target data by inputting, for each of agents, a state of the each of the agents to a policy model of the each of the agents which is related to the modification target data, and by acquiring an action of the each of the agents, and store, as experience data, the state and the action of each of the agents as well as a reward earned by taking the action; an evaluation module configured to calculate an evaluation value for each of the agents, the evaluation value being a probability at which the action is selected under the state; and a modification module configured to modify the experience data based on the evaluation value of each of the agents calculated by the evaluation module.

Abstract: A coordinating apparatus selects discrete systems that simulate behavior of an actual environment and outputs an indicator value related to the actual environment, shares internal states related to the actual environments obtained on a basis of the behavior simulated by the discrete systems selected in the selection process, generates a shared internal state, decides such an action that a post-coordination integrated indicator value obtained by integrating a post-coordination indicator value from the discrete systems when the discrete systems are coordinated is optimized, the action being should be taken and being able to be taken by the discrete systems on a basis of the shared internal state in a case where the discrete systems are coordinated, determines whether or not the discrete systems should be coordinated on a basis of the post-coordination indicator values, and the indicator value from each of the discrete systems, and outputs a determination result.

Abstract: An object of the present invention is to reduce an error between an actual machine and a simulation by removing the influence of overlearning of an adjustment by a mathematically-described function, and to optimize automatic operation control of the machine. An automatic operation control system for controlling an automatic operation of a machine sets a first model showing a relation between a control signal string input to the machine on the basis of a mathematically-described function and data output from the machine controlled in accordance with the control signal string. In a learning process including learning the automatic operation control of the machine, the system executes learning using the first model until a first condition is satisfied.

Abstract: Provided is a reward function generation method for calculating a reward in reinforcement learning, the method being executed by a computer, and the method includes accepting input of an instruction to generate a reward function including a plurality of setting data that is information regarding a key performance indicator, generating one partial reward function for one of the setting data, generating a linear combination of a plurality of the partial reward functions as the reward function, and outputting information regarding the reward function generated to the computer that executes the reinforcement learning, by the computer.

Abstract: A data analysis apparatus generates M (M is an integer of 3 or greater) groups each including data regarding a plurality of units from data where first KPIs and K (K is an integer of 2 or greater) explanatory variables are given by 1:1, generates a second KPI indicating the state of the group based on the values of a plurality of first KPIs included in the group, and selects a feature for the first KPIs based on a correlation analysis between the second KPI of each group and the feature of each group calculated based on the explanatory variables.

Abstract: An object of the present invention is to reduce an error between an actual machine and a simulation by removing the influence of overlearning of an adjustment by a mathematically-described function, and to optimize automatic operation control of the machine. An automatic operation control system for controlling an automatic operation of a machine sets a first model showing a relation between a control signal string input to the machine on the basis of a mathematically-described function and data output from the machine controlled in accordance with the control signal string. In a learning process including learning the automatic operation control of the machine, the system executes learning using the first model until a first condition is satisfied.

Abstract: Provided is a reward function generation method for calculating a reward in reinforcement learning, the method being executed by a computer, and the method includes accepting input of an instruction to generate a reward function including a plurality of setting data that is information regarding a key performance indicator, generating one partial reward function for one of the setting data, generating a linear combination of a plurality of the partial reward functions as the reward function, and outputting information regarding the reward function generated to the computer that executes the reinforcement learning, by the computer.

Abstract: A data analysis apparatus generates M (M is an integer of 3 or greater) groups each including data regarding a plurality of units from data where first KPIs and K (K is an integer of 2 or greater) explanatory variables are given by 1:1, generates a second KPI indicating the state of the group based on the values of a plurality of first KPIs included in the group, and selects a feature for the first KPIs based on a correlation analysis between the second KPI of each group and the feature of each group calculated based on the explanatory variables.

Abstract: An optimal path search system, which optimizes a travel path of a moving object, comprising: a path information database; and a path search unit that searches for an optimal path that exhibits a minimum travel cost borne by the moving object, from among travel paths of the moving object, wherein: the path search unit is configured to: determine destination points on the path network; search for at least one nearest node to each of destination points, search for a second travel path along which the moving object travels by passing through the at least one nearest node and all of the at least one destination point, determine the second travel path for which a travel cost is minimum; and search for the travel paths followed by using each of a plurality of moving means, respectively, in a case where the moving object travels along the optimal path.

Abstract: Provided is a route generation device capable of generating an appropriate route. A route generation system of one embodiment of the present invention includes: analysis sections that analyze aerial image data to identify the land state of an area included in an aerial image; a storage section that stores traffic cost information associating a traffic-cost coefficient indicating traffic difficulty with the land state; a route searching section that calculates traffic costs of a plurality of routes from a start point to an end point by referring to the analysis results of the analysis sections and the traffic cost information and that determines a route candidate to be used from the start point to the end point based on the calculation results.

Abstract: Provided is a route generation device capable of generating an appropriate route. A route generation system of one embodiment of the present invention includes: analysis sections that analyze aerial image data to identify the land state of an area included in an aerial image; a storage section that stores traffic cost information associating a traffic-cost coefficient indicating traffic difficulty with the land state; a route searching section that calculates traffic costs of a plurality of routes from a start point to an end point by referring to the analysis results of the analysis sections and the traffic cost information and that determines a route candidate to be used from the start point to the end point based on the calculation results.

Abstract: An optimal path search system, which optimizes a travel path of a moving object, comprising: a path information database; and a path search unit that searches for an optimal path that exhibits a minimum travel cost borne by the moving object, from among travel paths of the moving object, wherein: the path search unit is configured to: determine destination points on the path network; search for at least one nearest node to each of destination points, search for a second travel path along which the moving object travels by passing through the at least one nearest node and all of the at least one destination point, determine the second travel path for which a travel cost is minimum; and search for the travel paths followed by using each of a plurality of moving means, respectively, in a case where the moving object travels along the optimal path.

Abstract: In an information providing service that utilizes a car navigation system or the like, ensuring safety while viewing content is a matter of great concern. A vehicle-mounted onboard content providing apparatus for providing content to a user of the vehicle, comprising a current location acquisition unit for acquiring information about the current location, an instruction input unit whereby information about the destination and instructions for selecting the content to be delivered are inputted, a control unit for editing the content retrieved based on the instructions, and an output unit for outputting the edited content, wherein the control unit determines, on the basis of attribute information assigned to the route included in the results of retrieving the route from the current location to the destination, sections in which content is outputted or not outputted on the route, and edits the content on the basis of the result of this determination.

Abstract: Collecting the sound while rotating at least one or more microphone around a rotational axis, the filter processing is carried out in accordance with the positional information of the microphone at each point.

Abstract: Arrangements, including a method of speech command management that changes a content of active speech commands and inactive speech commands, based on each application status in a terminal. When plural applications are active and when a user is interacting with one of the active applications, the provided speech command management makes the content of recognizable speech commands to be limited to local commands of an interacting application, and also global commands of other background applications. Also, the provided management arrangement makes the content of recognizable global speech commands based on each application status. This management arrangement reduces the number of recognizable speech commands, and thus prevents misrecognitions inducted by using many speech commands.

Abstract: Provided are a voice recognition system for making a response based on an input of a voice uttered by a user including: an audio input unit for converting the uttered voice into voice data; a voice recognizing unit for recognizing a combination of terms constituting the voice data and calculating reliability of recognition of each of the terms; a response generating unit for generating a voice response; and an audio output unit for presenting the user with information using the voice response. The response generating unit: generates synthesis audio for a term whose calculated reliability satisfies a predetermined condition; extracts from the voice data a part corresponding to a term whose calculated reliability does not satisfy the predetermined condition; and generates the voice response based on at least one of the synthesis audio, the extracted voice data and a combination of the synthesis audio and the extracted voice data.

Abstract: A HMI (Human Machine Interface) development support apparatus that has at least a CPU, memory devices, a display unit and an input device and supports development of a display screen regarding a HMI of an information processing system includes a layout editing means that creates a layout of the display screen regarding the HMI of the information processing system in such a manner that the layout editing means lays out at least either a graphic component having graphic data or an image component having image data based on operational information input from the input device; an image editing means that creates an image for either the graphical component or the image component based on the operational information input from the input device; and data storage means that stores layout data of the layout created by the layout editing means, component data of components included in the layout and image data of the components.

Abstract: An image design support tool for designing a display image of an information terminal, which includes: storage means for storing a plurality of display images and an image group to which the display images belong; first setting means for setting a first display rule on each image group for displaying an interruption screen on an interruption event occurring; second setting means for setting a second display rule on each display image for the interruption screen on an interruption event occurring as an exception of the first display rule; and guidance means for generating and outputting guidance information on an image group to which the display image, to which the second display rule is applied, is transferred by using a difference between the first display rule and the second display rule.

Abstract: The present invention is characterized in that the car navigation system for, at the time of desiring map information, traffic information, and other required information in a car, inquiring an information distribution service provider for distribution the information is composed of a moving terminal device which can be operated by inputting and outputting voice, a communication device, an audio interactive server which can input and output voice and data, is connected to an external device and the Internet on the basis of audio interactions by the voice recognition process and voice synthesis process, and executes information transfer, and one or a plurality of information distribution service providers connected to the Internet for distributing information such as map information and traffic information.

Abstract: Collecting the sound while rotating at least one or more microphone around a rotational axis, the filter processing is carried out in accordance with the positional information of the microphone at each point.