Robert W. Blanning

A Formal Approach to Workflow Analysis

Agile manufacturing, fast-response micromarketing, and the rise of the virtual organization have led managers to focus on cross-functional business processes that link various divisions and organizations. These processes may be realized as one or more workflows, each of which is an instantiation of a process under certain conditions. Because an ability to adapt processes to workflow conditions is essential for organizational responsiveness, identifying and analyzing significant workflows is an important activity for managers, organization designers, and information systems specialists. A variety of software systems have been developed to aid in the structuring and implementation of workflow systems, but they are mostly visualization tools with few analytical capabilities. For example, they do not allow their users to easily determine which information elements are needed to compute other information elements, whether certain tasks depend on other tasks, and how resource availability affects information and tasks. Analyses of this type can be performed by inspection, but this gives rise to the possibility of error, especially in large systems. In this paper, we show how a mathematical construct called a metagraph can be used to represent workflows, so that such questions can be addressed through formal operations, leading to more effective design of organizational processes.

SoftCord: an intelligent agent for coordination in software development projects

Over the years, software development has become more complex. and the problems of unreliability, high maintenance costs, and time overruns have greatly increased. A major contributor to this state of crisis in software development is the problem of coordinating activities. Based on a case study of a large software development project, we develop SoftCord, an intelligent agent that helps improve coordination in these projects. SoftCord is an autonomous program that incrementally records problem solving knowledge in a knowledge base (the MS-ATMS), and informs designers of inter-task conficts when these are detected. Other features of SoftCord include the ability to respond to queries from individual designers, and the abtlity to set up and support negotiation sessions between designers when conflict resolution is necessary. 0 I997 Published by Elsevier Science B.V.Abstract Over the years, software development has become more complex, and the problems of unreliability, high maintenance costs, and time overruns have greatly increased. A major contributor to this state of crisis in software development is the problem of coordinating activities. Based on a case study of a large software development project, we develop SoftCord, an intelligent agent that helps improve coordination in these projects. SoftCord is an autonomous program that incrementally records problem solving knowledge in a knowledge base (the MS-ATMS), and informs designers of inter-task conflicts when these are detected. Other features of SoftCord include the ability to respond to queries from individual designers, and the ability to set up and support negotiation sessions between designers when conflict resolution is necessary.

A relational framework for join implementation in model management systems

Two important issues in the design of relational model banks are the degree to which they should be aggregated or disaggregated and the methods by which disaggregated model banks might be integrated in response to user queries. Three topics relevant to this issue are addressed in this paper. The first is whether a universal model and its projections may possess the lossy join property. We will show that they do not. The second is the development of a relational algebra for the specification of join implementation in model banks, and the third is the realization of such an algebra in a language similar to Query-by-Example.

Model management systems: an overview

Abstract During the past fifteen years, model management has grown from a few suggestions that data management be enlarged to include decision models to an established but still growing field of study. We examine three central topics in model management. The first is model base structure and its correspondence to network and relational data base structures. The second is model base processing and the application of artificial intelligence to model interfacing, integration, construction, and interpretation. The third is the organizational environment of model management systems and the contribution of model management systems to organizational intelligence.

Synthesis and Decomposition of Processes in Organizations

Organizations today face increasing pressures to integrate their processes across disparate divisions and functional units, in order to remove inefficiencies as well as to enhance manageability. Process integration involves two major types of changes to process structure: (1) synthesizing processes from separate but interdependent subprocesses, and (2) decomposing aggregate processes into distinct subprocesses that are more manageable. We present an approach to facilitate this type of synthesis and decomposition through formal analysis of process structure using a mathematical structure called a metagraph.

Management applications of expert systems

Abstract The development of expert systems for such professionals as doctors diagnosing and treating infectious diseases and geologists exploring for mineral deposits has led to suggestions that expert systems be developed for managers in public and private organizations who make manufacturing, marketing, financial, personnel, and other decisions. This paper describes briefly some of the systems of this type that have already been developed, with an emphasis on the logic expressions used in them, examines other fruitful areas for system development, and identifies software requirements for the implementation of such systems.

Model Integration Using Metagraphs

The availability of a large and diverse collection of stored modules such as data relations and decision models is a desirable feature in a decision support system DSS. However, it is usually infeasible to design a DSS in which every problem instance can be solved using a single module. Instead, it may be necessary to combine several stored modules into an integrated model that is sufficient to solve the given problem. We show that modules such as data files and decision models in a DSS can be usefully represented by a metagraph, a graph-theoretic construct that captures relationships between pairs of sets of elements. In addition to the visualization benefits that graphical representation offers, we show that many useful questions faced by the designers and users of DSS can be addressed by exploiting analytical properties of metagraphs. In particular, we show that the process of model integration can be significantly facilitated by exploiting certain connectivity properties in metagraphs.

A relational theory of model management

The field of DSS, which began as an investigation into the need for tools to help managers to solve ill-structured problems [Carlson, 1977; Keen and Morton, 1978; Keen and Wagner, 1979; Alter, 1980], has grown to encompass a variety of approaches and concerns, including artificial intelligence, model management, information economics, and individual and group behavior [Blanning, 1983b; Bonczek, Holsapple and Whinston, 1981]. This is also reflected in the content of several recent collections of papers on DSS [Fick and Sprague, 1980; Ginzberg, Reitman, and Stohr, 1982; Bennett, 1983; House, 1983; Sol, 1983], and in attempts to develop a framework for DSS that includes stored data, data analysis procedures, and decision models [Blanning, 1982c, 1982d, 1979].

Issues in the design of relational model management systems

One component of the literature on model management in decision support systems (DSSs) suggests that the relational framework for data management be extended to the management of decision models. This paper examines three important design issues in relational model management: the organization of relational model banks, relational completeness of model query languages, and system implementation.

Conversing with management information systems in a natural language

A key objective of information systems is to provide effective communication between their users and the information they contain. This was the idea behind the development of a decision calculus for increasing communication between models and managers [30], and behind management decision systems that use interactive graphics to enhance the interface between models and managers [38]. It is also part of the rationale for such interactive decision-making environments as operations rooms [6], decision rooms [21], and planning laboratories [45], which assist groups of senior executives with problem identification and decision making; and or for decision support systems (DSS), which help managers to solve unstructured or semistructured problems by providing convenient access to various information sources, including information retrieved from files or provided by decision models [3, 15, 26, 27]. The interrelationship among data, models, and the user interface is spelled out in the work of Sprague [39] and Sprague and Carlson [40]. They identify three major functions of a DSS: data management, model management, and dialogue management. The dialogue between a DSS and its users may take many forms-menus or structured query languages, for instance. We are concerned here with a flexible interface: natural language query processors that allow a user to instruct or query a DSS using a large subset of the users natural language.