“Blackboard system”的意思、由来-开放百科全书

A blackboard system is an artificial intelligence approach based on the blackboard architectural model,^[1]^[2]^[3]^[4] where a common knowledge base, the "blackboard", is iteratively updated by a diverse group of specialist knowledge sources, starting with a problem specification and ending with a solution. Each knowledge source updates the blackboard with a partial solution when its internal constraints match the blackboard state. In this way, the specialists work together to solve the problem. The blackboard model was originally designed as a way to handle complex, ill-defined problems, where the solution is the sum of its parts.

Metaphor

The following scenario provides a simple metaphor that gives some insight into how a blackboard functions:

Components

Learnable Task Modeling Language

A blackboard system is the central space in a multi-agent system. It's used for describing the world as a communication platform for agents. To realize a blackboard in a computer program, a machine readable notation is needed in which facts can be stored. One attempt in doing so is a SQL database, another option is the Learnable Task Modeling Language (LTML). The syntax of the LTML planning language is similar to PDDL, but adds extra features like control structures and OWL-S models.^[5]^[6] LTML was developed in the year 2007^[7] as part of a much larger project called POIROT (Plan Order Induction by Reasoning from One Trial)^[8], which is a Learning from demonstrations framework for process mining. In POIROT, Plan traces and hypotheses are stored in the LTML syntax for creating semantic web services.^[9]

Here is a small example: A human user is executing a workflow in a computergame. He presses some buttons and interacts with the game engine. While he is doing so, a plan trace is created. That means, the user's actions are stored in a logfile. The logfile gets transformed into a machine readable notation which is enriched by semantic attributes. The result is a textfile in the LTML syntax which is put on the blackboard. Agents (software programs in the blackboard system) are able to parse the LTML syntax.

Implementations

Famous examples of early academic blackboard systems are the Hearsay II speech recognition system and Douglas Hofstadter's Copycat and Numbo projects.

More recent examples include deployed real-world applications, such as the PLAN component of the Mission Control System for RADARSAT-1,^[10] an Earth observation satellite developed by Canada to monitor environmental changes and Earth's natural resources.

GTXImage CAD software by [https://web.archive.org/web/20110830054943/http://www.gtx.com/ GTX Corporation] was developed in the early 1990s using a set of rulebases and neural networks as specialists operating on a blackboard system.

Adobe Acrobat Capture (now discontinued) used a Blackboard system to decompose and recognize image pages to understand the objects, text, and fonts on the page. This function is currently built into the retail version of Adobe Acrobat as "OCR Text Recognition". Details of a similar OCR blackboard for Farsi text are in the public domain.^[11]

Blackboard systems are used routinely in many military C4ISTAR systems for detecting and tracking objects.

Criticism

Blackboard systems were popular before the AI Winter and, along with most symbolic AI models, fell out of fashion during that period. Along with other models it was realised that initial successes on toy problems did not scale well to real problems on the available computers of the time. Most problems using blackboards are inherently NP-hard, so resist tractable solution by any algorithm in the large size limit. During the same period, statistical pattern recognition became dominant, most notably via simple Hidden Markov Models outperforming symbolic approaches such as Hearsay-II in the domain of speech recognition.

Recent developments

Blackboard-like systems have been constructed within modern Bayesian machine learning settings, using agents to add and remove Bayesian network nodes. In these 'Bayesian Blackboard' systems, the heuristics can acquire more rigorous probabilistic meanings as proposal and acceptances in Metropolis Hastings sampling though the space of possible structures.^[12]^[13]^[14] Conversely, using these mappings, existing Metropolis-Hastings samplers over structural spaces may now thus be viewed as forms of blackboard systems even when not named as such by the authors. Such samplers are commonly found in musical transcription algorithms for example.^[15]

Blackboard systems have also been used to build large-scale intelligent systems for the annotation of media content, automating parts of traditional social science research. In this domain, the problem of integrating various AI algorithms into a single intelligent system arises spontaneously, with blackboards providing a way for a collection of distributed, modular natural language processing algorithms to each annotate the data in a central space, without needing to coordinate their behavior.^[16]

See also

References

1. ^{{Cite journal|last1=Erman|first1=L. D.|last2=Hayes-Roth|first2=F.|last3=Lesser|first3=V. R.|last4=Reddy|first4=D. R.|year=1980|title=The Hearsay-II Speech-Understanding System: Integrating Knowledge to Resolve Uncertainty|journal=ACM Computing Surveys|volume=12|issue=2|pages=213|doi=10.1145/356810.356816|pmc=|pmid=}}
2. ^{{cite journal |last1 = Corkill |first1 = Daniel D. |title = Blackboard Systems |journal = AI Expert |volume = 6 |issue = 9 |date=September 1991 |pages = 40–47 |url = http://bbtech.com/papers/ai-expert.pdf }}
3. ^* {{cite techreport |first = H. Yenny |last = Nii |title = Blackboard Systems |number = STAN-CS-86-1123 |institution = Department of Computer Science, Stanford University |year = 1986 |url = http://i.stanford.edu/pub/cstr/reports/cs/tr/86/1123/CS-TR-86-1123.pdf |accessdate = 2013-04-12 }}
4. ^{{Cite journal|last1=Hayes-Roth|first1=B.|year=1985|title=A blackboard architecture for control|journal=Artificial Intelligence|volume=26|issue=3|pages=251–321|doi=10.1016/0004-3702(85)90063-3|pmc=|pmid=}}
5. ^{{cite conference |title=Shopper: A System for Executing and Simulating Expressive Plans |author=Goldman, Robert P and Maraist, John |conference=ICAPS |pages=230–233 |year=2010}}
6. ^{{cite techreport |title=Agent-Based Computing in Distributed Adversarial Planning |author=Pechoucek, Michal |year=2010 |institution=Czech Technical Univ Prague}}
7. ^{{cite conference |title=An architecture and language for the integrated learning of demonstrations |author=Burstein, Mark and Brinn, Marshall and Cox, Mike and Hussain, Talib and Laddaga, Robert and McDermott, Drew and McDonald, David and Tomlinson, Ray |conference=AAAI Workshop Acquiring Planning Knowledge via Demonstration |pages=6–11 |year=2007}}
8. ^{{cite conference |title=Designing experiments to test planning knowledge about plan-step order constraints |author=Morrison, Clayton T and Cohen, Paul R |conference=ICAPS workshop on Intelligent Planning and Learning |year=2007}}
9. ^{{cite conference |title=Learning from Observing: Vision and POIROT-Using Metareasoning for Self Adaptation |author=Burstein, Mark and Bobrow, Robert and Ferguson, William and Laddaga, Robert and Robertson, Paul |conference=Self-Adaptive and Self-Organizing Systems Workshop (SASOW), 2010 Fourth IEEE International Conference on |pages=300–307 |year=2010}}
10. ^Corkill, Daniel D. "Countdown to success: Dynamic objects, GBB, and RADARSAT-1." Communications of the ACM 40.5 (1997): 48-58.
11. ^Khosravi, H., & Kabir, E. (2009). A blackboard approach towards integrated Farsi OCR system. International Journal of Document Analysis and Recognition (IJDAR), 12(1), 21-32.
12. ^{{cite journal |vauthors=Fox C, Evans M, Pearson M, Prescott T |title=Towards hierarchical blackboard mapping on a whiskered robot |journal=Robotics and Autonomous Systems |volume=60 |issue=11 |pages=1356–66 |year=2011 |url=http://eprints.uwe.ac.uk/18368/1/fox_ras_RAS_corrected.pdf |doi=10.1016/j.robot.2012.03.005}}
13. ^Sutton C. A Bayesian Blackboard for Information Fusion, Proc. Int. Conf. Information Fusion, 2004
14. ^{{cite conference |first1 = Norman |last1 = Carver |title = A Revisionist View of Blackboard Systems |booktitle = Proceedings of the 1997 Midwest Artificial Intelligence and Cognitive Science Society Conference |date=May 1997 |url = http://www.cs.siu.edu/~carver/ps-files/maics97.ps.gz}}
15. ^Godsill, Simon, and Manuel Davy. "Bayesian harmonic models for musical pitch estimation and analysis." Acoustics, Speech, and Signal Processing (ICASSP), 2002 IEEE International Conference on. Vol. 2. IEEE, 2002.
16. ^{{Cite arxiv|last=Flaounas|first=Ilias|last2=Lansdall-Welfare|first2=Thomas|last3=Antonakaki|first3=Panagiota|last4=Cristianini|first4=Nello|date=2014-02-25|title=The Anatomy of a Modular System for Media Content Analysis|eprint=1402.6208|class=cs.MA}}