专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

31. 发明专利

JPH09167152A INTERACTIVE MODEL PREPARING METHOD 失效
公开(公告)号：JPH09167152A
公开(公告)日：1997-06-24
申请号：JP33010295
申请日：1995-12-19
申请人： HITACHI LTD , HITACHI COMPUTER ENG
发明人： MAKI HIDEYUKI , MAEDA AKIRA , UCHIDA AKIHISA , NAKAJIMA YASUHIRO
IPC分类号： G06F9/44 , G06F17/00 , G06F19/00 , G06N5/04 , G06Q10/04 , G06Q50/00 , G06Q50/04
摘要： PROBLEM TO BE SOLVED: To efficiently prepare a model expressing the relation between attributes by combining the automatic setting of conditions of model with the correction of conditions by a user, supporting the process of explanation parameter selection and introducing the knolwdge of the user. SOLUTION: A data storage means 101 stores the set of data composed of plural attributes, and an analytic means 102 analyzes the degree of relation between the attributes in the set of these data and finds the level of degree of relation between the attributes. Based on this analyzed result, a setting means 103 automatically sets the initial conditions of model. When the user corrects these set conditions, an estimating means 105 estimates the model on the set conditions. Then, an evaluating means 106 evaluates the estimated model, automatically sets the conditions of model according to the degree of relation between the attributes, displays these conditions for the user, simultaneously accepts the correction clue to the user and preserves the history of correction and by repeatedly performing the condition setting, estimation, evaluation and correction of model, the model is prepared.

32. 发明专利

JPH096850A DATA ANALYZING METHOD 失效
公开(公告)号：JPH096850A
公开(公告)日：1997-01-10
申请号：JP15130495
申请日：1995-06-19
申请人： HITACHI LTD
发明人： MAKI HIDEYUKI , MAEDA AKIRA , UCHIDA AKIHISA , NAKAJIMA YASUHIRO
IPC分类号： B23Q41/08 , B65G61/00 , G05B19/418 , G06Q50/00 , G06Q50/04 , G06F17/60
摘要： PURPOSE: To detect/elapse and observe variation in characteristics to be ana lyzed the elapse time by analyzing the characteristics of objective data and obtaining values showing the characteristics of the data, and detecting the characteristic values meeting set conditions. CONSTITUTION: A data input means 103 reads in the data 102 from outside and holds them. An analyzing means 105 analyzes the objective data held by the data input means 103 to obtain the characteristic values showing the features of the data. For example, a rule generating means as the analyzing means 105 classifies the object data held by the input means 103 into plural categories and generates an IF-THEN rule explaining the features of the object data to obtain the evaluated value of the rule. A monitor means 108 detects the analysis result 106 which is continuously monitored meeting the predetermined conditions. A recording means 107 records the held analysis result 106 on a nonvolatile storage medium. Further, a display means 112 displays the analysis result 106 to a user.

33. 发明专利

JP2001022776A RULE GENERATION RESULT REPORT SYSTEM 失效
公开(公告)号：JP2001022776A
公开(公告)日：2001-01-26
申请号：JP19541699
申请日：1999-07-09
申请人： HITACHI LTD
发明人： TERANISHI YUKO , MORITA TOYOHISA , MAEDA AKIRA , MAKI HIDEYUKI
IPC分类号： G06F9/44 , G06F17/30 , G06N5/04
摘要： PROBLEM TO BE SOLVED: To periodically generate a rule while operating respective elements without performing input operation and to display the time sequential change of the rule by inputting rule generation conditions and start conditions by a user. SOLUTION: The condition definition of rule generation is previously stored in a rule generation condition storage means 07 by an input means 10 and the rule generation condition to be started, time or time interval is stored from the input means 10 to a start condition storage means 06. On the basis of data in the start condition storage means 06, a data mining starting part 05 periodically starts a data mining executing part 03, performs rule generation, stores the result in a rule storage means 04 and sends it to a rule comparing part 08. The rule comparing part 08 compares the rule newly generated by the data mining executing part 03 with the rule in the past stored in the rule storage means 04 and the time sequential change of the generated rule is detected and displayed on a display means 09. Thus, the time sequential change of the rule can be detected.

34. 发明专利

JPH11328255A TIME SEQUENTIAL DATA FLUCTUATION MONITORING DEVICE AND STORAGE MEDIUM STORING PROGRAM RELATING TO THE DEVICE 失效
公开(公告)号：JPH11328255A
公开(公告)日：1999-11-30
申请号：JP13149098
申请日：1998-05-14
申请人： HITACHI LTD
发明人： MAKI HIDEYUKI , MORITA TOYOHISA , MAEDA AKIRA , AKIMORI HIROYUKI , OGAWA MIHOKO
IPC分类号： G06Q50/04 , G06Q50/00 , G06F17/60
摘要： PROBLEM TO BE SOLVED: To automatically monitor the large amount of time sequential data of many kinds by comparing an object time sequence for which object values are arranged corresponding to the generation time and a derivative time sequence generated based on it and judging the change of the object time sequence. SOLUTION: A data base 102 holds the object value (the measured value of a working dimension for instance) and an attribute value (the time of performing working for instance) accompanying the object value as a set. By a selection means 103, the set 110 of attribute sets is generated. The object values are summed up by a sum-up means 104 and the set 111 of the summed-up attribute sets is generated for the respective sets 110 of the attribute sets. A derivative time sequence generation means 105 performs a prescribed arithmetic operation to the object time sequence for which the summed-up attribute sets are arranged in the order of the generation time and generates the derivative time sequence 112. By a change judgement means 106, the object time sequence and the derivative time sequence are compared and the change is judged. A reporting means 107 reports the result of change judgement to a user 109.

35. 发明专利

JPH1055367A DATA UTILIZATION SYSTEM 失效
公开(公告)号：JPH1055367A
公开(公告)日：1998-02-24
申请号：JP21082896
申请日：1996-08-09
申请人： HITACHI LTD
发明人： ASHIDA HITOSHI , MAKI HIDEYUKI , AYUKAWA ERIKA , MAEDA AKIRA , ITO YUKIYASU
IPC分类号： G06F17/30
摘要： PROBLEM TO BE SOLVED: To automatically extract a statistic table showing a characteristic distribution from statistic tables of given data and further retrieve necessary data from the statistic table after confirming the distribution of data with the extracted statistic table. SOLUTION: This system extracts a partial record from data as a set of records consisting of >=2 item values including >=1 numerical item value, and consists of a statistic table list generating device 102 which generates a statistic table of partial data where >=1 item value is limited among the data, calculates feature quantities of respective statistic tables according to differences of an expected value of the statistic table from the distribution table, and generates a list of statistic tables according to the feature quantities, and a record list generating device 105 which generates a list of records included in all or >=1 specified cell from the data from an arbitrary specified statistic table.

36. 发明专利

JPH09305616A DATA ANALYSIS METHOD 失效
公开(公告)号：JPH09305616A
公开(公告)日：1997-11-28
申请号：JP11600696
申请日：1996-05-10
申请人： HITACHI LTD
发明人： MAKI HIDEYUKI , MAEDA AKIRA , UCHIDA AKIHISA , NAKAJIMA YASUHIRO
IPC分类号： G06F3/14 , G06F3/048 , G06F17/30
摘要： PROBLEM TO BE SOLVED: To improve the efficiency of analysis work by variously analyzing data in a data base by calling another data processing window to process the related data corresponding to the instruction of a user and generating another related data processing window. SOLUTION: A data processing means 203 inputs/outputs data with one or plural data bases 201 through a data inquiry processing means 202 and performs data display and data analytic processing while using these data. There is a data processing managing means 204 between terminal equipment and the data processing means 203, the display of processing result of the data processing means 203 and the management of transmission of the operation performed by a user 207 are executed, and the relation with the data processing means 203 is managed. The user 207 operates the window on the screen and operates the data processing means 203. When starting use, the data processing means 203 is activated and the correspondent window is displayed on the screen.

37. 发明专利

JPH0934719A DATA ANALYZER 失效
公开(公告)号：JPH0934719A
公开(公告)日：1997-02-07
申请号：JP18529895
申请日：1995-07-21
申请人： HITACHI LTD
发明人： SATO YOSHINORI , MAEDA AKIRA , MAKI HIDEYUKI , OMORI KATSUMI
IPC分类号： G06F9/44 , G05B23/02 , G06F17/30 , G06F19/00 , G06N5/02 , G06N5/04
摘要： PROBLEM TO BE SOLVED: To analyze symbolized time sequential data for the unit of a case and to extract the causal relation contained in the data as a rule expressing data structure. SOLUTION: The time sequential data are preserved as the records of symbols and time by a symbolized data managing device 100 and the description unit of analysis is decided by a case preparing device 509 and a class sorting device 510. A model extracting device 511 extrcats the data structure contained in the class and outputs it as a rule. Besides, the analyzed result is outputted by an analyzed result output device 505 as the timewise relation between the case and the rule or the degree of similarity between the cases.

38. 发明专利

JPH06231105A NEURAL NETWORK 失效
公开(公告)号：JPH06231105A
公开(公告)日：1994-08-19
申请号：JP1726693
申请日：1993-02-04
申请人： HITACHI LTD
发明人： MAKI HIDEYUKI
IPC分类号： G06F15/18 , G06G7/60 , G06N99/00
摘要： PURPOSE:To form a neural network having redundancy in the number of calculation units and the number of inter-unit connections and capable of preventing the generation of troubles such as over-fitting. CONSTITUTION:Units 101, 102 are used for all or a part of computing units constituting a neural network. The unit has two states, a sensitive state and a non-sensitive state, and these states are switched by a certain probability. In the sensitive state, the output value of each unit is determined in accordance with its input value. In the non-sensitive state, the output value of the unit is determined independently of its input value.

39. 发明专利

JPH06149771A METHOD AND DEVICE FOR CONSTITUTING NEURAL NETWORK FOR ASSOCIATIVE STORAGE 失效
公开(公告)号：JPH06149771A
公开(公告)日：1994-05-31
申请号：JP30513192
申请日：1992-11-16
申请人： HITACHI LTD
发明人： MAKI HIDEYUKI , MATSUBA IKUO
IPC分类号： G06F15/18 , G06G7/60 , G06N99/00
摘要： PURPOSE:To easily perform the learning of a recurrent type network for associative storage which includes a hidden unit. CONSTITUTION:Neural networks corresponding to storage items one to one are prepared. The networks learn the relation between the corresponding storage items and other storage items. Those networks are feedforward type neural networks and an error inverse propagating method which is widely used by the feedforward type networks is employed for learning. The input of a feedforward type neural network after learning and the output of another feedforward type neural network are coupled through a feedback loop 103 to form one recurrent type network.

40. 发明专利

JPS5478016A SCREEN AMPLITUDE DETECTOR 失效
公开(公告)号：JPS5478016A
公开(公告)日：1979-06-21
申请号：JP14495477
申请日：1977-12-05
申请人： HITACHI LTD
发明人： SUDOU TATSUO , OGAWA JIYUNICHI , KOMABA MAKOTO , MAKI HIDEYUKI
IPC分类号： H04N3/22
摘要： PURPOSE:To automatize quantitative measurement at a production time and improve precision by using a black-and-white TV camera to pick up the acreen of a receiver and deciding whether horizontal and vertical raster lack is present or not. CONSTITUTION:Rated voltage power source 5 for projecting white raster throughout the available picture area by white signal 9 inputted to adjusted Tv receiver 8 and low voltage power source 6 for projecting white raster in the area smaller than the available picture area are supplied while being switched to generate raster lack between both white rasters, and this raster lack quantity is picked up by black-and-white Tv camera 11. Then, the time of the raster lack part in the picked up output waveform is measured in 15, and the measurement result is decided whether it is zero or not to detect the screen amplitude in 16. Then, screen amplitude adjustment mechanism 18 of receiver 8 is driven by the signal of the detection result to control so that the signal of the detection result may be zero.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式