EASE for Windows is a knowledge-based system for assessing workplace exposure to potentially hazardous new substances.AIAI and HSE staff worked together using the CommonKADS knowledge engineering methodology to model the task and capture the knowledge involved. Execution of the work was audited against TickIT criteria by Lloyds Register.
Ease guides the user by offering a menu of appropriate choices whenever it needs information. When numerical values must be provided, e.g. vapour pressure, sanity checks are carried out.
The user can always back-track and change the answer to an earlier question and a full explanation of the conclusion is always given as well as an explanation of why a particular question is being asked.
The system has been widely distributed for use by authorities throughout Europe.
I-X is a new systems integration architecture. Based on the O-Plan agent architecture, I-X provides an issue-handling workflow style of architecture, with reasoning and functional capabilities provided as plug-ins.The I-Technology programme has 5 aspects:
- Systems Integration - A broad vision of an open architecture for intelligent systems creation for synthesis tasks (such as planning, design and configuration) based on the handling of "issues" and the management or maintenance of the constraints describing the product of the process.
- Representation - a core notion of the representation of a synthesis process and the product(s) of such processes as a set of nodes making up the process or product, along with constraints on the relationship between those nodes, a set of outstanding issues, and annotations related to these - <I-N-C-A> - Issues, Nodes, (Critical and Auxiliary) Constraints and Annotations. Engagement with various standards setting groups is a part of this work.
- Reasoning - the provision of reusable reasoning and constraint or model management capabilities.
- User Interfaces - to understand user roles in performing collaborative activities and to provide generic modules which present the state of the processes they are engaged in, their relationships to others and the status of the artifacts/products they are working with.
- Applications - work in various application sectors which will seek to create generic approaches (I-Tools) for the various types of Task in which users may engage.
AIAI's members are active in a number of standards activities related to ontologies, web content, process models, plans, workflow and web services standards.
Examples are:
Our research and commercial experience in Workflow Management Systems (WfMS) include the following:
- National Institute for Standards and Technology Process Specification Language (NIST PSL)
- Process Interchange Format (PIF)
- US Defense Advanced Research projects Agency Shared Planning and Activity Language (DARPA SPAR)
- Ontoweb European Union Research Programme - Web Contents Standards
- Semantic Web Services Language
- Workflow Management Coalition (WfMC) Workflow Process Definition Language (Interface 1)
Our research and commercial experience in Workflow Management Systems (WfMS) include the following:
- Visual business process modelling languages
- Methodologies for creating business and process models
- Virtual organisation communication and collaboration
- Adaptive Workflow applications
- E-Business applications
- Agent based systems collaboration.
Optimum-AIV: Planning and Scheduling of Spacecraft Assembly, Integration and TestOptimum-AIV is now being operationally applied to the strategic planning of the production of ARIANE IV equipment bays. This activity frequently requires the plans to be updated due to non-availability of equipment, and test failures.
A consortium consisting of Computer Resources International A/S, Matra Marconi Space, Progespace and AIAI was responsible for the development of the European Space Agency (ESA) knowledge based system for the planning and scheduling of activities for spacecraft assembly, integration and verification (AIV).
The system supports the entire AIV life cycle, i.e. not only scheduling of the activities but also monitoring of plan execution and the plan repair phases. State of the art knowledge based techniques have been applied in the planning/scheduling process: preconditions and effects on the spacecraft configuration of individual activities can be stated and used for verification of the plan logic. The system allows scheduling of activities to be performed either manually or automatically using resource levelling.
Formation - a system to lay out all British Telecom Yellow Pages directories and to create a new business area for Pindar Set Ltd for responsive marketing support and catalogue layout systems. Winner of an award for innovative applications of AI in 1998, Formation is a knowledge-based document layout system, originally designed for large classified directories and catalogues.Pindar Set Ltd., the UK company that originates the British Telecom Yellow Pages, have developed an international business strategy to market generic, customisable, knowledge-based layout software and services to publishers of classified directories and catalogues. Pindar's clients, such as BTYP, increasingly demand faster and more flexible responses to requests for change in the layout of their pages, in order to improve their correctness, useability, and aesthetics. Pindar also wishes to attract new clients from around the world to its directory and catalogue services. Formation is allowing Pindar to implement this strategy, providing the company with a system offering much greater flexibility and higher throughput than the many other batch layout systems in regular use around the world."
The applications of O-Plan fit midway between the large scale manufacturing scheduling
problems found in some industries (where there are often few inter-operation
constraints) and the complex puzzles dealt with by very flexible logic
based tools. However, problems of this type represent an important class
of industrial relevance.
O-Plan is relevant to the following types of problems:
- project management for product introduction, systems engineering, construction
- assembly, integration and verification
- process flow and workflow planning
- planning and control of supply and distribution logistics.
- mission sequencing and control of space probes such as Voyager and ERS-1.
- crisis response
- Space Platform Construction
- Satellite Planning and Control
- Construction and House Building
- Software Development
- Unix administrator's script writing
- Logistics
- Non-Combatant Evacuation Operations
- Crisis Response
- Air Campaign Planning Workflow
- Other Demonstrations
Subcontracted by British Aerospace, AIAI were involved in part of a larger project for EUMETSAT, the European agency responsible for meteorological satellites. Our role was helping in the specification and prototyping of the scheduling component. After an initial feasibility study it was decided to prototype the system using PECOS, an object-oriented constraint programming tool. This approach allowed rapid development while retaining the flexibility to make changes as the problem specification evolved.
A typical problem that the EUMETSAT scheduler has to deal with consists of some 1300 activities over a 14 day period. Activities to be scheduled include regular fixed activities (e.g. image taking every 30 minutes), maintenance activities, and station keeping manoeuvres consisting of series of linked activities which maintain the satellite in its correct position. An important part of the problem was in recognising overconstrained problems (i.e. where it is not possible to meet all the constraints) and dealing with them appropriately.
British Aerospace are now in the process of porting to a C++ version of the tool, in order to integrate the scheduling component with the larger system.
A typical problem that the EUMETSAT scheduler has to deal with consists of some 1300 activities over a 14 day period. Activities to be scheduled include regular fixed activities (e.g. image taking every 30 minutes), maintenance activities, and station keeping manoeuvres consisting of series of linked activities which maintain the satellite in its correct position. An important part of the problem was in recognising overconstrained problems (i.e. where it is not possible to meet all the constraints) and dealing with them appropriately.
British Aerospace are now in the process of porting to a C++ version of the tool, in order to integrate the scheduling component with the larger system.
Expert Provisioner, a knowledge-based provisioning system prototype, was designed to support RAF Range Managers in the procurement of consumable supplies. The system consists of a graphical user interface to display the procurement item requisition information and a consultation style interface to a knowledge based system.
The RAF wished to have a better understanding of their purchasing commitments as well as a improving the consistency and quality of purchase decisions. By linking into existing procurement information and providing a knowledge based decision aid, Expert Provisioner allows the RAF to know exactly what has been bought, what it cost and why it is needed, thereby reducing the uncertainty of procurement budgets near financial year-ends and wastage caused by over-ordering. Not only this, but it allowed the RAF to take advantage of price breaks for large orders and maintained consistency throughout order processing.
Expert Provisioner was successfully evaluated by end users and a full production system was developed in collaboration with AIAI.
The RAF wished to have a better understanding of their purchasing commitments as well as a improving the consistency and quality of purchase decisions. By linking into existing procurement information and providing a knowledge based decision aid, Expert Provisioner allows the RAF to know exactly what has been bought, what it cost and why it is needed, thereby reducing the uncertainty of procurement budgets near financial year-ends and wastage caused by over-ordering. Not only this, but it allowed the RAF to take advantage of price breaks for large orders and maintained consistency throughout order processing.
Expert Provisioner was successfully evaluated by end users and a full production system was developed in collaboration with AIAI.
Fraud Detection using the CBR Shell
At the request of one of the UK's most successful fraud detection system software providers, AIAI undertook an investigation into methods of applying new AI technologies to increase the accuracy of the already highly advanced systems presently in use. While the firm's software presently reduces the number of necessary fraud investigations by several orders of magnitude, our investigation showed that utilising adaptive algorithms and fuzzy logic results in significant diagnostic improvement on the most difficult sub-section of cases.
The goal of the work was to reduce the number of applications referred for costly manual investigation after the existing detection systems had been utilised. It was decided to use Case-Based Reasoning (CBR) for this end, a technique based on the intuition that new problems are often similar to previously encountered problems, and therefore, that past solutions may be of use in the current situation.
The developed CBR system was able to prioritise the referred applications from the most to the least suspicious, aiding the decision process of the fraud investigator.
At the request of one of the UK's most successful fraud detection system software providers, AIAI undertook an investigation into methods of applying new AI technologies to increase the accuracy of the already highly advanced systems presently in use. While the firm's software presently reduces the number of necessary fraud investigations by several orders of magnitude, our investigation showed that utilising adaptive algorithms and fuzzy logic results in significant diagnostic improvement on the most difficult sub-section of cases.
The goal of the work was to reduce the number of applications referred for costly manual investigation after the existing detection systems had been utilised. It was decided to use Case-Based Reasoning (CBR) for this end, a technique based on the intuition that new problems are often similar to previously encountered problems, and therefore, that past solutions may be of use in the current situation.
The developed CBR system was able to prioritise the referred applications from the most to the least suspicious, aiding the decision process of the fraud investigator.
GhostWriter is a demonstration of how plan-based modelling and natural language generation can be used to greatly assist human technical authors in the production of aircraft maintenance manuals.GhostWriter was a research project between British Aerospace Defence and Dassault Aviation, with assistance from AIAI and the Department of AI. Its primary objective was to design, develop and demonstrate a prototype authoring environment so as to illustrate the kinds of proactive support that are required by and that would benefit authors in the production of technical documents.
The volume of technical publications produced by and on behalf of each of the two aerospace companies is very large. From a business perspective, the motivation behind the GhostWriter project was to seek ways in which the production of technical publications could be made more efficient and reliable.
GhostWriter had to demonstrate an approach that would pay for itself in terms of the longer lifecycle of a publication, therefore the project concentrated particularly on the technology that would enable documents to be generated in English and French, and on knowledge-based techniques that would enable the author to receive advice about possible errors and omissions during the construction of a publication."
