Hitachi, Ltd.

Tadashi Tenma

Kichizo Akashi

Tetsuo Kusuzaki

Akira Maeda

Koichi Homma

Akira Kagami

Norihisa Komoda

Isao Tsushima

Hitoshi Ashida

Yoji Taniguchi

Hiroaki Oyama

Mitsuo Sudo

Miyuki Maeda

Tatsumi Nishimoto

Hideo Watase

Yozo Konishi

Shouji Igeta

Takayuki Ishii

Hideki Nakata

Shooji Shinoda

The present invention is intended to automatically select least required input items for a non-linear model and improve an efficiency of building up the non-linear model. For building up, for example, a neural network as the non-linear model, a group-by rule 105 and dividing point information 106 of the data are automatically generated by a group-by rule induction device 104 by selecting a dividing method option 101 and a group selection information 103 if data for learning 101 is given. An initial neural network model generating device 107 automatically generates an initial neural network model 108 from the group-by rule 105. The initial neural network model is learned in a neural network model learning device 111 and outputted as a post-learning neural network model 112. Data for learning with group information 110 which is the data for learning is generated in a data classification device 109 by using data for learning 102, group-by rule 105 and dividing point information 106. Input-output variables can be automatically selected from the data for learning according to selection of the group and a neural network model of respective groups can be built up.

Non-linear model automatic generating method

A merchandising system for conducting a control of article display positions that are generally changed by the customers includes a method of obtaining article display positions based on the present display state. In this system, when selecting coordinate items to be suitably combined with an article, the display positions thereof can be easily determined, which advantageously helps the customer to search the store or floor for the desired items.

Visual merchandizing (VMD) control method and system

A merchandise analysis system for predicting the sale of a registered item, including: a sales data table having sales data of a plurality of items; an input terminal for registering an item and for setting an analysis term; a retrieval unit connected to the table and the input terminal to search the sales data table for the sales data corresponding to the registered item and the analysis term; a function table having various functions fitted to respective data of sale versus price; a dispersion measure table for storing errors obtained with respect to the respective data of sale versus price retrieved on the basis of the respective functions; an analysis device connected to the dispersion measure table so as to determine one function giving the minimum one of the errors and the values of parameters therefor; and a display connected to the dispersion measure table so as to display the sales data of the registered item corresponding to the analysis term in a graph expressing the determined one function into which the determined parameters are substituted, the display being arranged to display the predicted sale corresponding to the registered price inputted through the input terminal in accordance with the display of the sales data.

Merchandise analysis system with sales data table and various functions

In a data management system necessary for management such as a profit management of a shop, it is required to collect and to analyze a great amount of various kinds of data items. In such a data management system, in addition to a data base storing therein all data, there are disposed a data base associated with each data utilization purpose and a data base for the data analysis so as to conduct data-base-oriented processing, which enables an analysis result suitable for a purpose to be easily attained and which simplifies the system configuration.

System and method for computing profits for individual entities of an

A goods layout planning method for making a layout for a quantity of goods arranged on gondolas in a store by using a terminal device including a display and a processor. Rules regarding goods layouts are stored in a knowledge base. The effort to make layout plans for goods can be simplified and the efficiency thereof improved by using sales data for each of the goods, attributes of goods, attributes of gondolas, and the rules with respect to the goods layouts.

Method of managing layout of goods

An automatic freight stacking system for loading previously determined freight articles of various configurations (shapes, size, material, etc.) to be shipped, using a loading scheduler for determining a loading schedule on the basis of the existing various configurations of the freight articles, marshalling equipment for receiving the freight articles in a given order and delivering them in a predetermined order which is determined by the scheduler, a feeding conveyor for carrying the delivered freight articles and transporting means to the places of the respective loading means allocated by the loading scheduler, and the loading means for loading the carried freight articles on the transporting means in accordance with the scheduled operation sequence. In the case where the configurations of certain freight articles to be shipped are unknown before the arrival thereof, a reader is provided to read the dimensions of the freight articles upon arrival thereof and then the operator monitors through a display terminal the state of the articles and the state of the articles loaded on the transporting means and indicates the freight article to be loaded as well as the position to be loaded to the loading means.

Automatic freight stacking system

Growing community of inventors

Sagamihara, Japan

Tadashi Tenma