会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 2. 发明专利
    • DEVICE FOR SUPPORTING PROGRAM UTILIZATION
    • JPH023824A
    • 1990-01-09
    • JP15178288
    • 1988-06-20
    • MITSUBISHI HEAVY IND LTD
    • YOSHIKAWA TETSUTOTANAKA MICHIOTANABE YUTAKA
    • G06F9/45G06F9/06G06F9/44
    • PURPOSE:To easily and accurately adjust a program and processing contents by changing the processing contents so that the program can be used and deciding the appropriate program when the program is judged to be appropriate or not by means of the inputted processing contents and when the program is beyond a use range. CONSTITUTION:An analysis content adjustment device 6 previously loads a rule on adjustment contents based on a deviation from a program function and constraint from a knowledge memory 5, judges whether or not there is a term which requires change among designation analysis contents. When analysis contents concerned is not changed, the objective analysis contents are dealt with by the designated program. When there is the term which requires change, 'No' is written in a program use feasibility memory 8 and the contents are simultaneously written in a change content memory 7 and an analysis content change device 9 fetches the contents of the memory 7, whereby the contents of an analysis content storage memory 10 are rewritten. After rewriting, control is again given to the analysis adjustment content decision device 6 and a similar processing is repeated. Thus, the processing by the program can be executed within the function range of the program and adjustment is attained without overlook.
    • 3. 发明专利
    • DIAGNOSING DEVICE FOR ABNORMALITY OF PLANT
    • JPS63189906A
    • 1988-08-05
    • JP2294187
    • 1987-02-03
    • MITSUBISHI HEAVY IND LTD
    • MORIMOTO HARUKIOKETANI TOSHIHARUYOSHIKAWA TETSUTOGOTO TETSUYA
    • G01D1/18G01D21/00G05B23/02G21C17/00
    • PURPOSE:To omit the determination of a searching range and a searching order by ruling that apparatuses are sccessively evaluated in the reverse direction from an apparatus to be the anbormality in case of determining influenced by the cause of the abnormal event. CONSTITUTION:An apparatus characteristics evaluating part 36 inputs abnormal cause identifying data 35 from an abnormal cause searching order determining part 34 and extracts a plant 30 observation value corresponding to the input signal from a data storing part 32. The part 36 finds out the estmation value of an output signal by using the observation value and the characteristics of the normal apparatus, and when the difference between the estimated value of the output signal and the observation value exceeds a certain limit value, the apparatus is the cause of the abnormal event is decided. The evaluated result is returned to the determining part 34 through the NO line of an apparatus abnormality searching completion deciding part 37 and apparatus data for outputting the input name of the evaluated apparatus are extracted from the abnormal cause identifying data 35 and sent to the evaluating part 36. The evaluation is successively repeated executed, and when the search is completed, the output signal name of the abnormal apparatus is sent to an abnormality affecting range searching order deciding part 39.
    • 4. 发明专利
    • AI TOOL
    • JPH0346030A
    • 1991-02-27
    • JP18044789
    • 1989-07-14
    • MITSUBISHI HEAVY IND LTD
    • YOSHIKAWA TETSUTO
    • G06F9/44G06N5/04
    • PURPOSE:To efficiently construct an AI system by making processes for solving a problem into a module as task, combining them and forming a scenario for solving problem. CONSTITUTION:This tool consists of a task library for diagnosis 4 which is necessary for describing a task for diagnosis, a task library for schedule 5 which is required for describing a task for schedule, and an engine development system 1 describing a shell for the problem by using these libraries. Then, the knowledge expression method of the private shell is defined as the natural extension of the knowledge expression of a general tool, and the inference engine of the private shell is assumued to be the set of knowledge operation primitives (task) inherent to the problem area. The tasks are made into the libraries and several libraries are selected from among the libraries so as to generate the scenario for solving the problem. Thus, the development efficiency of the AI system improves.
    • 6. 发明专利
    • KNOWLEDGE BASE DEVELOPING DEVICE
    • JPH01224844A
    • 1989-09-07
    • JP5091088
    • 1988-03-04
    • MITSUBISHI HEAVY IND LTD
    • MIYAMOTO SHINICHIMURATA RYOICHIYOSHIKAWA TETSUTO
    • G06F9/44G06Q10/04
    • PURPOSE:To raise inferring efficiency in an expert system by providing a means to store hierarchical knowledge and a storage to store the hierarchical judging reference of the stored knowledge. CONSTITUTION:The title device consists of a storage 11 to store general hierarchical knowledge, a storage 12 to store the hierarchical knowledge peculiar to a problem area, a knowledge base developing controller 13,an input/output device 14 for questions and answers and a storing device 15 to store a judging reference in hierarchization. That is, a knowledge base developing device 10 is a device to sort, to abstract and to hierarchize the unprocessed knowledge given by a system engineer A through a control system with the knowledge developing controller 13 with noticing the property and to store it to a knowledge base 23, and on hierarchizing the sorted data by the dependency, the general hierarchical knowledge stored in the storing device 11 and the hierarchical knowledge peculiar to the problem area stored in the storing device 12 are used. Thus, the efficiency inferring can be executed.
    • 7. 发明专利
    • INTERACTIVE RULE BASE EDITING DEVICE
    • JPH01220038A
    • 1989-09-01
    • JP4677088
    • 1988-02-29
    • MITSUBISHI HEAVY IND LTD
    • YOSHIKAWA TETSUTOYOSHIDA KOJI
    • G06F9/44
    • PURPOSE:To smoothly prepare a knowledge base having good quality without errors or omissions by giving an environment to edit each rule while looking at the whole rule base and thus, only proceeding with a simple editing work. CONSTITUTION:A first stage consists of an event defining stage input/output device 1 to talk with a user, an event name to store an event and an attribute inputted from the user, and an event attribute storage device 2. A second state consists of an inter-event relation defining stage input/output device 3. A third stage consists of a rule belonging group defining stage input/output device 4, a rule set name and a belonging rule name storage device 5. A fourth stage consists of a group attribute, an inter-group relation defining stage input/output device 6 and interrule-set relation defining device 7. The respective pieces of input information inputted by the first-fourth stages are integrated and the rule base is generated. Thus, by only proceeding with the simple editing work, the knowledge having good quality without the errors or omission can be smoothly prepared.
    • 8. 发明专利
    • ABNORMALITY DIAGNOSTIC SYSTEM
    • JPH03125921A
    • 1991-05-29
    • JP26285889
    • 1989-10-11
    • MITSUBISHI HEAVY IND LTD
    • YOSHIKAWA TETSUTO
    • G01D21/00
    • PURPOSE:To reduce the number of items for investigation and change a time required for a diagnosis in accordance with a situation by providing means for diagnosing the cause of an abnormality from information including a hypothesis and means for automatically modifying a hypothesis in accordance with the progress of a diagnosis. CONSTITUTION:A diagnostic apparatus is composed of a diagnostic knowledge base 1, a diagnostic inference engine 2, a hypothesis candidate investigated item registering mechanism 3 for registering an item possible to be made a hypothesis from the investigated items in advances, an investigated hypothesis selecting mechanism 4 for taking out some of the registered hypotheses and generating the combinations of the hypotheses and an investigated hypothesis verifying mechanism 5 for verifying whether the generated combination of hypotheses is prohibited. This system enables an operator to execute a right diagnosis by building up a suitable hypothesis or appropriately presuming in the system for an uninvestigated item. For the investigated items, when the result of a diagnosis using a hypothesis is self-contradictory, the system rejects the hypothesis and adopts another one or sometimes requires a real investigation.
    • 9. 发明专利
    • AI TOOL
    • JPH03125225A
    • 1991-05-28
    • JP26285789
    • 1989-10-11
    • MITSUBISHI HEAVY IND LTD
    • YOSHIKAWA TETSUTO
    • G06F9/44G06N5/04
    • PURPOSE:To simply develop a knowledge base by providing a means which constructs an inference module from each knowledge and an inferring method, a means which constructs an inference algorithm from the inference module, and a means which carries out interactively and with trial and error those two mentioned means. CONSTITUTION:A building block BB production system 1 which constructs the BB is provided together with a BB inspection system 2 which inspects the BB, a BB data base 3 which registers the BB, a bulder 4 which combines interactively the BBs and also inspects the result of combination of BBs, and a total control system 5. A BB serves as a least unit for execution of the infer ence and describes an inference method and the address of a knowledge base used for the inference. Then a list of events are shown on a screen and a user selects these events. Thus it is possible to interactively decide an inference method and to simply develop a knowledge base.
    • 10. 发明专利
    • COMPUTER-AIDED LEARNING DEVICE
    • JPH03125176A
    • 1991-05-28
    • JP26285989
    • 1989-10-11
    • MITSUBISHI HEAVY IND LTD
    • YOSHIKAWA TETSUTO
    • G09B5/00
    • PURPOSE:To enable relearning in a short time and to rearrange personal knowledge by providing a space where learning contents are taken down on a display screen, a means which edits the memo, a means which controls the memo, and a means which stores the contents of the memo. CONSTITUTION:The private memo space 1 is arranged on the same bit map display with the screen of the learning device on a multi-window basis and consists of memo pads which can freely be edited. A private memo control mechanism 2 has two functions. One function controls the name, generation date, version, generation learning stage, and link of a generated memo pad by a memo pad control table 4 and retrieves and displays a corresponding memo pad when a user specifies the memo-pad name. Consequently, a learner acquires taught contents as his or her knowledge and the learning effect can be improved and a memo can be left and confirmation after the lecture is facilitated.