Abstract: An information processing device, comprising: a processor; and a memory storing a program causing the processor to: (A) acquire first input/output request data for accessing a write destination file; (B) specify data to be written into the write destination file on a basis of the first acquired input/output request data; (C) determine that the specified data is abnormal data, if all of conditions about the specified data are satisfied, wherein the conditions about the specified data are conditions for determining abnormal data; and (D) execute predetermined processing related to access to the write destination file, if it is determined that the specified data is abnormal data, wherein (C) further includes: calculating a first degree of randomness of the specified data; determining that a first condition of the conditions about the specified data is satisfied; and determining that a second condition of the conditions about the specified data is satisfied.

Abstract: In order to provide dialogue management means that allows prompt identification of portions of interest in a dialogue record even in a case where various subjects are discussed, provided is a dialogue management apparatus (210) including a dialogue interface section (212) that provides a dialogue interface for holding a digital dialogue between a plurality of speakers and acquires a dialogue record of the digital dialogue, a subject management section (214) that receives an input of subject designation information for designating a subject in the digital dialogue, while the digital dialogue is being held, and a dialogue editing section (216) that generates an edited dialogue record that is organized by subject, by editing the dialogue record in reference to the subject designation information.

Abstract: An overhead wire recognition device and method are capable of overhead wire recognition based on plural images taken by an imaging device such as a digital camera. The overhead wire recognition device includes an input unit to which multi-viewpoint images taken by a camera from different viewpoints and camera positions/attitudes are inputted, an overhead wire candidate extraction unit which selects, from the multi-viewpoint input images inputted to the input unit, an overhead wire region including an overhead wire and extracts, from the overhead wire region, a line segment as a candidate of the overhead wire, and an overhead wire model estimation unit which projects the candidate line segment in an imaginary 3D space, determines, based on the candidate line segment, the camera positions/attitudes, and the multi-viewpoint images, a plane where the overhead wire is present in the 3D space, and estimates a 3D model of the overhead wire.

Abstract: A computer system accurately selects learning data for improving a prediction accuracy of a predictor, and is connected to a database that stores a plurality of pieces of learning data and information for managing a plurality of predictors generated under different learning conditions. A target predictor is selected, an influence degree representing strength of an influence of the learning data on a prediction accuracy of the target predictor for test data is calculated for each of a plurality of pieces of test data, an influence score of the learning data is calculated for the plurality of predictors based on a plurality of influence degrees of the learning data associated with the predictors, and the learning data to be used is selected from the plurality of pieces of learning data on the basis of a plurality of the influence scores of each of the plurality of pieces of learning data.

Abstract: An electronic device (communication device) including a reflecting member having a reflecting surface that causes electro-magnetic waves emanating from a predetermined part of the electronic device in a predetermined radiating direction to be reflected in a direction other than the radiating direction.

Abstract: An connection apparatus receives a purchase desire notification including a public key from another connection apparatus via a blockchain network and transmits an encrypted content key acquired by encrypting a content key using the public key to the other connection apparatus via the blockchain network. The other connection apparatus transmits the purchase desire notification to the one connection apparatus and transmits transmission source information representing a transfer destination of the content to the blockchain network. In addition, the other connection apparatus decrypts the encrypted content key from the one connection apparatus using the stored secret key. In a case in which the encrypted content key is received, the blockchain network changes an owner represented in owner management information to the transfer destination.

Abstract: It is provided a federated learning system for aggregating gradient information representing a result of training an AI model in an edge device, the federated learning system comprising the edge device and a server apparatus, the training module in the edge device being configured to generate an edge switch share in which the encrypted aggregated gradient is encrypted, and to transmit the generated edge switch share to the server apparatus, the encryption/decryption module in the server apparatus being configured to generate an encrypted aggregated gradient for decryption by adding edge switch shares received from the plurality of the edge device, generate an aggregated gradient by decrypting the generated encrypted aggregated gradient for decryption, and to transmit the generated aggregated gradient to the edge device, the training module in the edge device being configured to train the AI model by using the aggregated gradient received from the server apparatus.

Abstract: The purpose of the present invention is to provide a data collection system capable of appropriately setting a range for collecting image data used as training data of a learning device that recognizes an image. A data collection system according to the present invention receives requirement variables that represent the requirement of image data necessary for a learning device to be sufficiently trained and requirement definition data that designates the requirement value, further receives priority data that designates the priority of the requirement variables, presents the requirement variables and the requirement values in the order of the priorities, and presents a requirement value response rate that represents the ratio of the requirement variables for which the requirement value is specified.

Abstract: An object of the invention is to appropriately diagnose ethicality of a prediction result of an AI model. An ethicality diagnosis device stores sensitive feature data, which is data that associates a value of a sensitive feature, which is a feature required to take a certain consideration in handling from a perspective of the ethicality with a value of a selected feature, which is one or more features selected from a feature constituting the AI model, a sensitive feature coefficient, and a per-feature importance level, and obtains, based on the sensitive feature coefficient and the per-feature importance level, a non-ethical degree, which is a value indicating a degree of ethicality of the prediction result output by the AI model.

Abstract: A network communication acquisition unit acquires network communication from an application. A communication discrimination filter determines whether the network communication is communication to a data store, and determines whether the network communication is communication for uploading a file to the data store when the network communication is communication to the data store. When the network communication is communication for uploading a file to the data store, a suspicious file upload detection filter evaluates whether the file is encrypted and determines whether the network communication is unauthorized access based on a result of the evaluation.

Abstract: In order to provide dialogue management means that allows prompt identification of portions of interest in a dialogue record even in a case where various subjects are discussed, provided is a dialogue management apparatus (210) including a dialogue interface section (212) that provides a dialogue interface for holding a digital dialogue between a plurality of speakers and acquires a dialogue record of the digital dialogue, a subject management section (214) that receives an input of subject designation information for designating a subject in the digital dialogue, while the digital dialogue is being held, and a dialogue editing section (216) that generates an edited dialogue record that is organized by subject, by editing the dialogue record in reference to the subject designation information.

Abstract: An unauthorized access detection device that includes a control device for executing: abnormal access request detection processing in which a plurality of pieces of input/output request data for accessing a file is acquired and it is determined whether or not an access mode to the file is abnormal on the basis of patterns of the acquired plurality of pieces of input/output request data; abnormal data detection processing in which, where it is determined that the access mode to the file is abnormal, it is determined, by specifying data to be written into the file on the basis of the acquired input/output request data and specifying a trend of the specified data, whether or not the specified data is abnormal data; and suspicious process resolution processing in which, where it is determined that the specified data is abnormal data, predetermined processing related to access to the file is executed.

Abstract: It is possible to effectively and efficiently add training data. A training data evaluation system includes an uncertainty calculation unit configured to calculate, based on a prediction value obtained from a machine learning model using evaluation data for evaluating a shortage of training data as an input and a correct answer for the evaluation data, a data shortage degree representing a training data shortage degree for each piece of the evaluation data; a target selection unit configured to extract target data, which is data to be added to the training data, based on a predetermined selection rule and the data shortage degree; and a tendency analysis planning unit configured to specify a tendency of the target data based on a predetermined analysis rule and specify a property of the training data to be added based on the tendency of the target data.

Abstract: A method of simulating codes that form a program configured to control a control target includes causing a processor to execute the following: first-setting a first process of executing a simulation of an operation of a code group excluding a specific code among the codes; second-setting a second process of executing a simulation of an operation of a specific model obtained by modeling the specific code; first-simulating, in the first process, a first simulation of a code preceding the specific code in the code group; second-simulating, in the second process, a second simulation of the specific model through use of an execution result of the first simulation by inter-process communication between the first process and the second process; and third-simulating, in the first process, a third simulation of a code succeeding the specific code through use of an execution result of the second simulation by the inter-process communication.

Abstract: A conversion apparatus includes a storage unit storing definition information in which position information and a type of the signal are associated with each other; a decoder referring to, when first reception data is input, the definition information of the first control target to determine a type of a first signal at a first position in the first reception data, and output first input data in which the determined type of the first signal and a value of the first signal in the first reception data are associated with each other; and an encoder referring to the definition information of a second control target to output second input data in which identification information of second computing units that corresponds to the type of the first signal, position information indicating a second position of the first signal, and a value of the first signal are associated with one another.

Abstract: An connection apparatus receives a purchase desire notification including a public key from another connection apparatus via a blockchain network and transmits an encrypted content key acquired by encrypting a content key using the public key to the other connection apparatus via the blockchain network. The other connection apparatus transmits the purchase desire notification to the one connection apparatus and transmits transmission source information representing a transfer destination of the content to the blockchain network. In addition, the other connection apparatus decrypts the encrypted content key from the one connection apparatus using the stored secret key. In a case in which the encrypted content key is received, the blockchain network changes an owner represented in owner management information to the transfer destination.

Abstract: Provided is a manufacture and sales strategy planning method comprising a step of determining, based on information related to a sales plan of a plurality of products and a production capacity of a production facility to produce each product, whether there is any spare capacity in the production capacity of the production facility in relation to the sales plan for each of the products, a step of applying one among a plurality of profit improvement strategies, according to an availability of the spare capacity, to each product determined in this step, and calculating an improvement effect of each product, a step of selecting, based on each calculation result obtained in this step, a specific product among the plurality of products in which the improvement effect has exceeded a set value with regard to each of the plurality of profit improvement strategies, a step of extracting, for each profit improvement strategy, an item which satisfies a restricting condition of sale or production of the specific product se

Abstract: Provided are: an amodal segmentation unit that generates a set of first amodal masks indicating a probability that a particular pixel belongs to a relevant object for each of objects, with respect to an input image in which a plurality of the objects partially overlap; an overlap segmentation unit that generates an overlap mask corresponding only to an overlap region where the plurality of objects overlap in the input image based on an aggregate mask obtained by combining the set of first amodal masks generated for each of the objects and a feature map generated based on the input image; and an amodal mask correction unit that generates and outputs a second amodal mask, which includes an annotation label indicating a category of each of the objects corresponding to a relevant pixel, for each of pixels in the input image using the overlap mask and the aggregate mask.

Abstract: It is provided a federated learning system for aggregating gradient information representing a result of training an AI model in an edge device, the federated learning system comprising the edge device and a server apparatus, the training module in the edge device being configured to generate an edge switch share in which the encrypted aggregated gradient is encrypted, and to transmit the generated edge switch share to the server apparatus, the encryption/decryption module in the server apparatus being configured to generate an encrypted aggregated gradient for decryption by adding edge switch shares received from the plurality of the edge device, generate an aggregated gradient by decrypting the generated encrypted aggregated gradient for decryption, and to transmit the generated aggregated gradient to the edge device, the training module in the edge device being configured to train the AI model by using the aggregated gradient received from the server apparatus.

Abstract: A computer system accurately selects learning data for improving a prediction accuracy of a predictor, and is connected to a database that stores a plurality of pieces of learning data and information for managing a plurality of predictors generated under different learning conditions. A target predictor is selected, an influence degree representing strength of an influence of the learning data on a prediction accuracy of the target predictor for test data is calculated for each of a plurality of pieces of test data, an influence score of the learning data is calculated for the plurality of predictors based on a plurality of influence degrees of the learning data associated with the predictors, and the learning data to be used is selected from the plurality of pieces of learning data on the basis of a plurality of the influence scores of each of the plurality of pieces of learning data.