Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo1 Sistemi per la Gestione Aziendale. AA. 2008-09 Ingegneria Gestionale (LS) Facoltà di Ingegneria.

Presentazione sul tema: "Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo1 Sistemi per la Gestione Aziendale. AA. 2008-09 Ingegneria Gestionale (LS) Facoltà di Ingegneria."— Transcript della presentazione:

1 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo1 Sistemi per la Gestione Aziendale. AA. 2008-09 Ingegneria Gestionale (LS) Facoltà di Ingegneria di Napoli SGA0809 UD09 Tecniche di acquisizione delle conoscenze

2 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo2 Reference Book and website http://turing.une.edu.au/~comp292/Lectures/HEADER_KM_2004_LEC_NOTES/

3 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo3 Interviewing as a Tacit Knowledge Capture Tool Advantages of using interviewing as a tacit knowledge capture tool: –It is a flexible tool. –It is excellent for evaluating the validity of information. –It is very effective in case of eliciting information regarding complex matters. –Often people enjoy being interviewed.

4 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo4 Interviews (1) Interviews can range from the highly unstructured type to highly structured type. –The unstructured types are difficult to conduct, and they are used in the case when the knowledge developer really needs to explore an issue. –The structured types are found to be goal-oriented, and they are used in the case when the knowledge developer needs specific information. –Structured questions can be of the following types: Multiple-choice questions. Dichotomous questions. Ranking scale questions. –In semistructured types, the knowledge developer asks predefined questions, but he/she allows the expert some freedom in expressing his/her answer.

5 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo5 Interviews (2) Guidelines for successful interviewing: –Setting the stage and establishing rapport. –Phrasing questions. –Listening closely/avoiding arguments. –Evaluating the session outcomes

6 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo6 Interviews (3) Reliability of the information gathered from experts: –Some uncontrolled sources of error that can reduce the information's reliability: –Expert's perceptual slant. –The failure in expert's part to exactly remember what has happened. –Fear of unknown in the part of expert. –Problems with communication. –Role bias.

7 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo7 Interviews (4) Errors in part of the knowledge developer: validity problems are often caused by the interviewer effect (something about the knowledge developer colours the response of the expert). Some of the effects can be as follows: –Gender effect –Age effect –Race effect

8 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo8 Interviews (5) Problems encountered during interviewing Response bias. Inconsistency. Problem with communication. Hostile attitude. Standardizing the questions. Setting the length of the interview.

9 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo9 Interviews (6) Process of ending the interview: –The end of the session should be carefully planned. –One procedure calls for the knowledge developer to halt the questioning a few minutes before the scheduled ending time, and to summarize the key points of the session. –This allows the expert to comment a schedule a future session. –Many verbal/nonverbal cues can be used for ending the interview.

10 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo10 Interviews (7) Many issues may arise during the interview, and to be prepared for the most important ones, the knowledge developer can consider the following questions: –How would it be possible to elicit knowledge from the experts who can not say what they mean or can not mean what they say. –How to set up the problem domain. –How to deal with uncertain reasoning processes. –How to deal with the situation of difficult relationships with expert(s). –How to deal with the situation when the expert does not like the knowledge developer for some reason.

11 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo11 Interviews (8) Rapid Prototyping in interviews: –Rapid prototyping is an approach to building KM systems, in which knowledge is added with each knowledge capture session. –This is an iterative approach which allows the expert to verify the rules as they are built during the session. –This approach can open up communication through its demonstration of the KM system. –Due to the process of instant feedback and modification, it reduces the risk of failure.

12 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo12 Interviews (9) Rapid Prototyping in interviews: –It allows the knowledge developer to learn each time a change is incorporated in the prototype. –This approach is highly interactive. –The prototype can create user expectations which in turn can become obstacles to further development effort.

13 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo13 Example (1) University of Dortmund / Hong Kong Baptist University –Professor Dr. Detlef Müller-Böling Professor Dr. Heinz Klandt Department of Economic and Social Sciences Faculty of Methods of Empirical Economic and Social Research Universität Dortmund Universität Dortmund –Associate Professor Wai-Sum Siu Department of Marketing Hong Kong Baptist University Department of Marketing Hong Kong Baptist University Inquiry of participants of the lecture "Introduction into methods of empirical economic and social research"

14 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo14 Internet Questionnaire Sampler

15 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo15 Internet Questionnaire Sampler

16 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo16 Internet Questionnaire Sampler

17 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo17 Example (2)

18 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo18 Example (3)

19 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo19 Example (4)

20 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo20 Example (5)

21 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo21 Example (5)

22 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo22 SAMPLING

23 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo23 Campionamento (Sampling) Definizione –Il Sampling è il processo di selezione di un numero di items o individuo per uno studio, in modo tale che gli item scelti siano rappresentativi dell’insieme più ampio a cui appartengono –Lo scopo del sampling è ottenere informazioni sulla popolazione La popolazione –Una popolazione ha almeno una caratteristica che la differenzia da altri gruppi –Distinzione tra Popolazione Target e Popolazione Accessibile Metodi di selezione del campione –Random Sampling: ogni individuo ha la stessa probabilità di essere scelto –Stratified Random Sampling: la popolazione è divisa in gruppi, quindi RS –Cluster Sampling: i gruppi, e non gli individui sono selezionati a caso –Systematic Sampling: individui selezionati da una lista a intervalli regolari

24 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo24 Campionamento (Sampling) Fasi del Random Sampling –1. Definisci la popolazione –2. Determini la dimensione del campione –3. Lista tutti i membri della popolazione –4. Assegna un numero ad ognuno –5. Seleziona un numero da una tabella di numeri casuali –6. Scegli l’individuo –7. Ripeti step 5 e 6 Esempio –1. I 5000 dipendenti di INN Inc. –2. Campione = 10% –3. Lista dei dipendenti –4. Un numero da 0 a 4999 –5. Seleziona il numero 3634 –6. Scegli l’individuo –7. Ripeti step 5 e 6

25 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo25 Campionamento (Sampling) Fasi del Sampling –1. Definisci la popolazione N –2. Determini la dimensione del campione C –3. Lista gli individui –4. Seleziona un punto qualsiasi della lista –5. Estrai individui dalla lista con passo N/C Esempio: –1. I 5000 dipendenti di INN Inc. –2. Campione = 500 –3. Lista dei 5000 –4. Seleziona un punto di partenza –5. Estrazione con passo = 10

26 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo26 Campionamento (Sampling) Fasi del Stratified Random Sampling –1. Definisci la popolazione –2. Determini la dimensione del campione –3. Identifica la variabile rappresentativa e i gruppi –4. Classifica la popolazione in gruppi –5. Seleziona casualmente un individuo da ogni sottogruppo Esempio: verificare due politiche diverse di assistenza infanzia da parte di INN Inc –1. I 300 genitori di INN Inc. –2. Campione = 45 genitori per metodo –3. Tre gruppi: genitori singoli, due in carriera, due con uno in carriera –4. Gruppo 1 = 175, gruppo 2 = 75, gruppo 3 = 50 –5. Seleziona causalmente 30 individui per ogni gruppo, e assegna casualmente 15 genitori per metodo

27 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo27 Campionamento (Sampling) Fasi del Cluster Sampling –1. Definisci la popolazione –2. Determini la dimensione del campione –3. Identifica un clustering logico –4. Definisci tutti i cluster della popolazione –5. Definisci o stima la dimensiona media dei cluster –6. Seleziona il richiesto numero di cluster –7. Seleziona i cluster –Includi tutti i membri dei cluster scelti Esempio: –1. I 5000 dipendenti di INN Inc. –2. Campione = 500 –3. I cluster = gli enti aziendali –4. Enti = 50 –5. Dim(ente) = 100 –6. Num(cluster) = 5 –7. Scelta casuale dei cluster –8. Inclusione di tutti i membri

28 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo28 Campionamento (Sampling) La dimensione minima del campione –ricerca descrittiva. 10% della popolazione. Per piccole popolazioni 20% o più. –ricerca correlativa: 30 individui NB: anche campioni molto grandi possono creare problemi se non sono ben selezionati Sampling Bias –Sampling error sono dovuti a fattori casuali fuori del controllo del ricercatore –Sampling Bias sono responsabilità del ricercatore Nonprobability sampling Convenience sampling Judgment sampling (uso del giudizio di esperti per il campione) Quota sampling (nelle interviste)

29 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo29 Selezione degli strumenti di misura (1) Le scale –Nominale, Ordinale, Intervalli, a Rapporti Test standardizzati (ST) –si definisce Test Standardizzato un qualsiasi elenco di domande che dia origine ad un punteggio numerico utilizzabile per identificare, classificare e valutare l’oggetto del test. Caratteristiche dei ST: –oggettività (indipendenza dal ricercatore) –validità (grado con cui il test misura ciò che vogliamo misurare) Content validity (item validity and sample validity) Construct validity (per i tratti non osservabili, es: intelligenza) Concurrent validity (accordo con altri test simili) Predictive validity (accordo tra test e altre misure)

30 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo30 Selezione degli strumenti di misura (2) Caratteristiche dei ST (continua): –affidabilità (grado con cui il test misura stabilmente che vogliamo misurare): di solito espresso da un numero. Diverse sono le procedure per verificare l’affidabilità del test: Test-Retest Reliability (coerenza nel tempo) –due test successivi, correlazione Equivalent-Form Reliability (coerenza per formati diversi dello stesso test) –due formati diversi, correlazione Split-Half Reliability (coerenza interna) –dividi le risposte in due insiemi, calcola i punteggi, trova il Pearson r, applica la formula di correzione Spearman-Brown r(sb) = 2r(split-half)/ (1+ r(split-half). Se r =.88, r(sb) =.94

31 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo31 Giuseppe Zollo - DIS, Facoltà di Ingegneria, Università di Napoli Federico II - Piazzale Tecchio 80, 80125 Napoli (I) - email: giuzollo@unina.it MetRicEmp Met Quant Selezione degli strumenti di misura (3) Pag. Caratteristiche dei ST (continua): –affidabilità (continua) Rationale Equivalence Reliability (coerenza interna) –uso delle formule Kuder-Richardson KR21 –r(KR21) = (K (SD^2) - M(K-M))/((SD^2)(K-1), dove K è il numero di items, SD è la deviazione standard, M è la media dei punteggi. Con un test di 25 items (K), e con una media M = 15 e SD = 5, si ha r(KR21) =.79 Reliability coefficients –va valutato il reliability coefficient per il desiderato livello di significatività; va calcolato il coefficiente per ogni parte del test Errore Standard di Misura SE(m) –SE(m) = SD* SR(1-r). Es: con SD = 5 e r(sb) =.84 avremo SE(m) = 2.0. Se il punteggio è 23 ciò significa un intervallo 21-25. Interjudge and Intrajudge Reliability (quando vi sono giudizi)

32 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo32 Selezione degli strumenti di misura (4) Tipi di test –Inventories SI/NO/non so –Attitudes Scales Scala di Likert –SA, A, U, D,SD = (5,4,3,2,1) o (1,2,3,4,5) Semantic-Differential scale –scale bipolari crescenti, decrescenti, simmetriche; pari o dispari; normalmente a 5, 7, 8 elementi –Halo effect; generosity effect Forced choice scale –questionario con risposte chiuse Interest Inventories –like/dislike Scoring Procedures –Problemi di affidabilità con questionari propri. Sono necessari test preliminari

33 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo33 Altre tecniche per catturare la conoscenza

34 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo34 Knowledge Capturing Techniques On-Site Observation (Action Protocol) Brainstorming Electronic Brainstorming Protocol Analysis (Think-Aloud Method) Consensus Decision Making Repertory Grid Nominal Group Technique (NGT) Delphi Method Concept Mapping Blackboarding

35 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo35 On-Site Observation (Action Protocol) It is a process which involves observing, recording, and interpreting the expert's problemsolving process while it takes place. The knowledge developer does more listening than talking; avoids giving advice and usually does not pass his/her own judgment on what is being observed, even if it seems incorrect; and most of all, does not argue with the expert while the expert is performing the task. Compared to the process of interviewing, on-site observation brings the knowledge developer closer to the actual steps, techniques, and procedures used by the expert. One disadvantage is that sometimes some experts do not like the idea of being observed. The reaction of other people (in the observation setting) can also be a problem causing distraction. Another disadvantage is the accuracy/completeness of the captured knowledge.

36 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo36 ESEMPIO di Action Protocol Il problema: analisi della funzione di supporto software di media impresa Patrimonio di competenze aziendali Variabilità della richiesta di assistenza ?

37 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo37 La grammatica dell’azione organizzativa La grammatica definisce un insieme di possibilità. Il concetto di grammatica può essere applicato per ordinare un qualsiasi insieme di eventi (linguistici e non) Attività Mosse Sequenze di mosse Routine che consente le sequenze Frasi Parole Sequenze di parole Grammatica che consente le sequenze

38 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo38 L’analisi sul campo 25 specialisti rispondono a circa 100 chiamate la settimana codifica delle mosse da un database semplificato training degli osservatori 3 mesi di osservazione diretta stesura di field notes dall’analisi sul campo emergono 20 sequenze diverse di mosse Costruzione della grammatica per tentativi Test della grammatica

39 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo39 Move O = Open the call W = Work on the call C = Close the call I = Declare the problem inactive D = Defer the problem: can’t solve it T = Tentative fix completed R = Resolve the problem but leave the call open F = fix given to the customer E = explain reason for closing US = transfer responsability to user PS = transfer responsability to product support DV = transfer responsability to development TR = transfer call to another functionalit area

40 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo40 Sequence 1)OWWUSPSWWWC 2)OWWCE 3)OWWWWWWWW CE 4)OWC 5)OWCE 6)OW WWC 7)OWWTRC ………. 20) OWUSWWC

41 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo41 Rules Call -> opening, search for solution, closing Opening -> O Search for solution -> any order (work, tranfer, user, developer) Closing -> tentative fix, done, comment Closing -> done, comment Tentative fix -> (F or R or T) Done -> (C or I or D) Comment -> (E or blank) Work -> (W, W, …) User -> US, PS User ->(US, work, PS) Developer -> DV, PS Developer -> DV, work, PS

42 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo42 Brainstorming (1) It is an unstructured approach towards generating ideas about creative solution of a problem which involves multiple experts in a session. In this case, questions can be raised for clarification, but no evaluations are done at the spot. Similarities (that emerge through opinions) are usually grouped together logically and evaluated by asking some questions like: –What benefits are to be gained if a particular idea is followed. –What specific problems that idea can possibly solve. –What new problems can arise through this.

43 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo43 Brainstorming (2) The general procedure for conducting a brainstorming session: Introducing the session. Presenting the problem to the experts. Prompting the experts to generate ideas. Looking for signs of possible convergence. If the experts are unable to agree on a specific solution, they knowledge developer may call for a vote/consensus.

44 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo44 Brainstorming (3)

45 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo45 Electronic Brainstorming (1) It is a computer-aided approach for dealing with multiple experts. It usually begins with a pre-session plan which identifies objectives and structures the agenda, which is then presented to the experts for approval. During the session, each expert sits on a PC and get themselves engaged in a predefined approach towards resolving an issue, and then generates ideas. This allows experts to present their opinions through their PC's without having to wait for their turn. Usually the comments/suggestions are displayed electronically on a large screen without identifying the source.

46 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo46 Electronic Brainstorming (2) This approach protects the introvert experts and prevents tagging comments to individuals. The benefit includes improved communication, effective discussion regarding sensitive issues, and closes the meeting with concise recommendations for necessary action (refer to Figure for the sequence of steps). This eventually leads to convergence of ideas and helps to set final specifications. The result is usually the joint ownership of the solution.

47 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo47 Electronic Brainstorming (3) Expert Ideas Expert Priorites Expert Convergence Expert Specification Decision by Consensus

48 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo48 Protocol Analysis (Think-Aloud Method) In this case, protocols (scenarios) are collected by asking experts to solve the specific problem and verbalize their decision process by stating directly what they think. Knowledge developers do not interrupt in the interim. The elicited information is structured later when the knowledge developer analyzes the protocol. Here the term scenario refers to a detailed and somehow complex sequence of events or more precisely, an episode. A scenario can involve individuals and objects. A scenario provides a concrete vision of how some specific human activity can be supported by information technology.

49 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo49 Consensus Decision Making Consensus decision making usually follows brainstorming. It is effective if and only if each expert has been provided with equal and adequate opportunity to present their views. In order to arrive at a consensus, the knowledge developer conducting the exercise tries to rally the experts towards one or two alternatives. The knowledge developer follows a procedure designed to ensure fairness and standardization. This method is democratic in nature. This method can be sometimes tedious and can take hours.

50 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo50 Repertory Grid This is a tool used for knowledge capture. The domain expert classifies and categorizes a problem domain using his/her own model. The grid is used for capturing and evaluating the expert's model. Two experts (in the same problem domain) may produce distinct sets of personal and subjective results. The grid is a scale (or a bipolar construct) on which elements can be placed within gradations. The knowledge developer usually elicits the constructs and then asks the domain expert to provide a set of examples called elements. Each element is rated according to the constructs which have been provided.

51 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo51 Nominal Group Technique (NGT) This provides an interface between consensus and brainstorming. Here the panel of experts becomes a Nominal Group whose meetings are structured in order to effectively pool individual judgment. Ideawriting is a structured group approach used for developing ideas as well as exploring their meaning and the net result is usually a written report. NGT is an ideawriting technique.

52 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo52 Delphi Method It is a survey of experts where a series of questionnaires are used to pool the experts' responses for solving a specific problem. Each experts' contributions are shared with the rest of the experts by using the results from each questionnaire to construct the next questionnaire.

53 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo53 Concept Mapping (1) It is a network of concepts consisting of nodes and links. A node represents a concept, and a link represents the relationship between concepts. Concept mapping is designed to transform new concepts/propositions into the existing cognitive structures related to knowledge capture. It is a structured conceptualization. It is an effective way for a group to function without losing their individuality.

54 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo54 Concept Mapping (2) Concept mapping can be done for several reasons: –To design complex structures. –To generate ideas. –To communicate ideas. –To diagnose misunderstanding.

55 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo55 Concept Mapping (3) Six-step procedure for using a concept map as a tool: – Preparation. –Idea generation. –Statement structuring. –Representation. –Interpretation –Utilization.

56 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo56 Concept Mapping (4) Similar to concept mapping, a semantic net is a collection of nodes linked together to form a net. A knowledge developer can graphically represent descriptive/declarative knowledge through a net. Each idea of interest is usually represented by a node linked by lines (called arcs) which shows relationships between nodes. Fundamentally it is a network of concepts and relationships

57 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo57 Blackboarding (1) In this case, the experts work together to solve a specific problem using the blackboard as their workspace. Each expert gets equal opportunity to contribute to the solution via the blackboard. It is assumed that all participants are experts, but they might have acquired their individual expertise in situations different from those of the other experts in the group. The process of blackboarding continues till the solution has been reached.

58 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo58 Blackboarding (2) Characteristics of blackboard system: Diverse approaches to problem-solving. Common language for interaction. Efficient storage of information Flexible representation of information. Iterative approach to problem-solving. Organized participation

59 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo59 Blackboarding (3) Components of blackboard system: The Knowledge Source (KS): Each KS is an independent expert observing the status of the blackboard and trying to contribute a higher level partial solution based on the knowledge it has and how well such knowledge applies to the current blackboard state. The Blackboard : It is a global memory structure, a database, or a repository that can store all partial solutions and other necessary data that are presently in various stages ofcompletion. A Control Mechanism: It coordinates the pattern and flow of the problem solution.

60 Sistemi per la Gestione Aziendale - Prof. Giuseppe Zollo60 Blackboarding (4) The inference engine and the knowledge base are part of the blackboard system. This approach is useful in case of situations involving multiple expertise, diverse knowledge representations, or situations involving uncertain knowledge representation.