Method of controlling a classifier system

Claim 2

An adaptive computing system comprising, in combination, a message memory for storing a plurality of messages, each message being represented by a sequence of binary digits; a classifier memory for storing a plurality of classifiers, each such classifier consisting of a condition part identifying a subset of messages in said message memory which are to be translated into result messages, an action part which specifies the functional relationship between the messages in said subset and said result messages, and a strength value; processing means for producing the result messages specified by each of said classifiers, said processing means further including bid generating means for producing a bid value for each given one of said classifiers which produces at least one of said result messages, said bid value being related to the strength value of said given classifier and being further related to the strength values of those classifiers which produced the messages in the subset specified by the condition part of said given classifier, and selection means responsive to said bid value for placing the result messages specified by only chosen ones of said classifiers in said message memory for further processing.

Claim 3

An adaptive computing system as set forth in claim 1 wherein said bid value produced by said bid generating means is further directly related to the specificity with which the condition part of said given classifier specifies said subset.

Claim 4

An adaptive computing system as set forth in claim 1 wherein said bid value is directly proportional to the strength value of said given classifier.

Claim 5

An adaptive computing system as set forth in claim 1 wherein said bid value is directly related to the sum of bid values previously generated for those classifiers which produced the messages specified by the condition part of said given classifier.

Claim 6

An adaptive computing system as set forth in claims 1, 2, 3, or 4 further including means for periodically reducing the strength values of at least selected ones of the classifiers in said classifier memory.

Claim 7

An adaptive computing system as set forth in claim 5 wherein said selected classifiers comprise all of the classifiers in said classifier memory.

Claim 8

An adaptive computing system as set forth in claim 5 wherein said selected classifiers comprise those classifiers for which a bid value is produced.

Claim 9

An adaptive computing system as set forth in claim 5 wherein said selected classifiers comprise said chosen classifiers.

Claim 10

In an adaptive computing system of the class comprising, in combination, storage means for storing a plurality of messages and a plurality of classifiers, each of said classifiers comprising: a condition part which specifies the attributes of selected ones of said messages, an action part which specifies the functional relationship between the information content of said selected messages and at least one output message, and a strength value for indicating the past performance of said classifier during the course of operation of said adaptive computing system, and processing means for comparing the condition part of each of said classifiers in said storage means with each of said messages in said storage means to identify said selected messages, said processing means further including: means for generating a bid-value whenever the condition part of a given classifier is satisfied, said bid value being related to the strength value of said given classifier, means for placing those output messages generated by successful classifiers which produce relatively larger bid-values in said storage means for further processing, and means for increasing the strength value associated with said successful classifiers, the improvement comprising processing means for varying said bid value in response to the combined strength values of those classifiers which generated said selected messages.

Claim 11

In an adaptive computing system of the class comprising, in combination, storage means for storing a plurality of messages and a plurality of classifiers, each of said classifiers comprising: a condition part which specifies the attributes of selected ones of said messages, an action part which specifies the functional relationship between the information content of said selected messages and at least one output message, and a strength value for indicating the past performance of said classifier during the course of operation of said adaptive computing system, and processing means for comparing the condition part of each of said classifiers in said storage means with each of said messages in said storage means to identify said selected messages, said processing means further including: means for generating a bid-value whenever the condition part of a given classifier is satisfied, said bid value being related to the strength value of said given classifier, means for placing those output messages generated by successful classifiers which produce relatively larger bid-values in said storage means for further processing, and means for increasing the strength value associated with said successful classifiers, the improvement comprising processing means for varying said bid value in response to the combined strength values of those classifiers which generated said selected messages.

Claim 12

An adaptive computing system as set forth in claim 9 wherein each generated bid value is proportional to the strength of said given classifier.

Claim 13

An adaptive computing system as set forth in claim 9 wherein said bid value is directly related to the sum of the bid values associated with said selected messages.

Claim 14

An adaptive computing system as set forth in claims 9, 10 or 11 wherein said means for increasing the strength value associated with said successful classifiers increases the strength value of only those successful classifiers which produce messages which subsequently satisfy the condition part of a further successful classifier.

Claim 15

An adaptive computing system as set forth in claim 12 wherein said strength value is increased by an amount directly related to the bid value produced by said further successful classifier.

Claim 16

An adaptive computing system as set forth in claim 12 including means for maintaining a system treasury value which is increased in direct relation to each decrease in an individual classifier's strength value and which is decreased in direct relation to any increase in an individual classifier's strength value.

Claim 17

In an adaptive computing system of the class comprising, in combination, storage means for storing a plurality of messages and a plurality of classifiers, each of said classifiers comprising: a condition part which specifies the attributes of selected ones of said messages, an action part which specifies the functional relationship between the information content of said selected messages and at least one output message, and a strength value for indicating the past performance of said classifier during the course of operation of said adaptive computing system, and processing means for comparing the condition part of each of said classifiers in said storage means with each of said messages in said storage means to identify said selected messages, said processing means further including: means for placing those output messages generated by successful classifiers having larger strength values in said storage means for further processing, and means for increasing the strength value associated with said successful classifiers, the improvement comprising processing means for periodically reducing the strength value associated with all of said classifiers in said storage means whereby the strength of those classifiers which fail to produce messages with acceptable strength values is eventually diminished relative to others of said classifiers.

Claim 18

In an adaptive computing system of the class comprising, in combination, storage means for storing a plurality of messages and a plurality of classifiers, each of said classifiers comprising: a condition part which specifies the attributes of selected ones of said messages, an action part which specifies the functional relationship between the information content of said selected messages and at least one output message, and a strength value for indicating the past performance of said classifier during the course of operation of said adaptive computing system, and processing means for comparing the condition part of each of said classifiers in said storage means with each of said messages in said storage means to identify said selected messages, said processing means further including: means for placing those output messages generated by successful classifiers having larger strength values in said storage means for further processing, and means for increasing the strength value associated with said successful classifiers, the improvement comprising processing means for periodically reducing the strength value associated with all of said classifiers in said storage means whereby the strength of those classifiers which fail to produce messages with acceptable strength values is eventually diminished relative to others of said classifiers.

Claim 19

An adaptive computing system as set forth in claim 15 further including means for reducing the strengths of all those classifiers whose conditions are satisfied.

Claim 20

In an adaptive computing system of the class comprising, in combination, storage means for storing a plurality of messages and a plurality of classifiers, each of said classifiers comprising: a condition part which specifies the attributes of selected ones of said messages, an action part which specifies the functional relationship between the information content of said selected messages and at least one output message, and a strength value for indicating the past performance of said classifier during the course of operation of said adaptive computing system, and processing means for comparing the condition part of each of said classifiers in said storage means with each of said messages in said storage means to identify said selected messages, said processing means further including: means for placing those output messages generated by successful classifiers having larger strength values in said storage means for further processing, and means for increasing the strength value associated with said successful classifiers; and an input interface for generating input messages for use in said system derived from a source external to said system; the improvement wherein said input interface further includes means for generating an intensity value associated with each of said input messages which is functionally equivalent to a bid value proportional to said strength value associated with classifier-produced messages whereby messages produced by said input means are treated as if they had been generated by a classifier making a comparable bid.

Claim 21

In an adaptive computing system of the class comprising, in combination, storage means for storing a plurality of messages and a plurality of classifiers, each of said classifiers comprising: a condition part which specifies the attributes of selected ones of said messages, an action part which specifies the functional relationship between the information content of said selected messages and at least one output message, and a strength value for indicating the past performance of said classifier during the course of operation of said adaptive computing system, and processing means for comparing the condition part of each of said classifiers in said storage means with each of said messages in said storage means to identify said selected messages, said processing means further including: means for placing those output messages generated by successful classifiers having larger strength values in said storage means for further processing, and means for increasing the strength value associated with said successful classifiers; and an input interface for generating input messages for use in said system derived from a source external to said system; the improvement wherein said input interface further includes means for generating an intensity value associated with each of said input messages which is functionally equivalent to a bid value proportional to said strength value associated with classifier-produced messages whereby messages produced by said input means are treated as if they had been generated by a classifier making a comparable bid.

Claim 22

An adaptive computing system as set forth in claim 17 including means for forming new classifiers of quasi-random content having condition parts adapted to be satisfied by said input messages.

Claim 23

In an adaptive computing system of the class comprising, in combination, storage means for storing a plurality of messages and a plurality of classifiers, each of said classifiers comprising: a condition part which specifies the attributes of selected ones of said messages, an action part which specifies the functional relationship between the information content of said selected messages and at least one output message, and a strength value indicative of the past performance of said classifier in said system; processing means for comparing the condition part of each of said classifiers in said storage means with each of said messages in said storage means to identify said selected messages, said processing means further including means for placing selected ones of the output messages generated by classifiers whose condition part is satisfied into said storage means for further processing, and means for periodically producing new classifiers which are modified versions of one or more existing classifiers in said storage means: the improvement wherein said classifiers include positional punctuation marks imbedded therein and wherein said means for producing new classifiers includes means for combining parts of existing classifiers formed by dividing said existing classifiers at positions determined by the placement of said punctuation marks.

Claim 24

In an adaptive computing system of the class comprising, in combination, storage means for storing a plurality of messages and a plurality of classifiers, each of said classifiers comprising: a condition part which specifies the attributes of selected ones of said messages, an action part which specifies the functional relationship between the information content of said selected messages and at least one output message, and a strength value indicative of the past performance of said classifier in said system; processing means for comparing the condition part of each of said classifiers in said storage means with each of said messages in said storage means to identify said selected messages, said processing means further including means for placing selected ones of the output messages generated by classifiers whose condition part is satisfied into said storage means for further processing, and means for periodically producing new classifiers which are modified versions of one or more existing classifiers in said storage means: the improvement wherein said classifiers include positional punctuation marks imbedded therein and wherein said means for producing new classifiers includes means for combining parts of existing classifiers formed by dividing said existing classifiers at positions determined by the placement of said punctuation marks.

Claim 25

In an adaptive computing system of the class comprising, in combination, storage means for storing a plurality of messages and a plurality of classifiers, each of said classifiers comprising: a condition part which specifies the attributes of selected ones of said messages, an action part which specifies the functional relationship between the information content of said selected messages and at least one output message, and a strength value indicative of the past performance of said classifier in said system; processing means for comparing the condition part of each of said classifiers in said storage means with each of said messages in said storage means to identify said selected messages, said processing means further including means for placing selected ones of the output messages generated by classifiers whose condition part is satisfied into said storage means for further processing, and means for periodically producing new classifiers having an information content derived in part from selected classifiers in said storage means; the improvement wherein said means for producing new classifiers further includes means for deriving the content of new classifiers from the information content of selected messages in said storage means.

Claim 26

In an adaptive computing system of the class comprising, in combination, storage means for storing a plurality of messages and a plurality of classifiers, each of said classifiers comprising: a condition part which specifies the attributes of selected ones of said messages, an action part which specifies the functional relationship between the information content of said selected messages and at least one output message, and a strength value indicative of the past performance of said classifier in said system; processing means for comparing the condition part of each of said classifiers in said storage means with each of said messages in said storage means to identify said selected messages, said processing means further including means for placing selected ones of the output messages generated by classifiers whose condition part is satisfied into said storage means for further processing, and means for periodically producing new classifiers having an information content derived in part from selected classifiers in said storage means; the improvement wherein said means for producing new classifiers further includes means for deriving the content of new classifiers from the information content of selected messages in said storage means.

Claim 27

An adaptive computing system as set forth in claim 20 wherein said means for deriving the content of new classifiers from the content of existing messages includes means for monitoring the number of new messages being produced from classifiers and activating the production of classifiers from messages whenever that number falls below a predetermined acceptable level.

Claim 28

In an adaptive computing system of the class comprising, in combination, storage means for storing a plurality of messages and a plurality of classifiers, each of said classifiers comprising: a condition part which specifies the attributes of selected ones of said messages, an action part which specifies the functional relationship between the information content of said selected messages and at least one output message, and a strength value indicative of the past performance of said classifier in said system; processing means for comparing the condition part of each of said classifiers in said storage means with each of said messages in said storage means to identify said selected messages, said processing means further including means for placing selected ones of the output messages generated by classifiers whose condition part is satisfied into said storage means for further processing, and means for periodically producing new classifiers which are modified versions of one or more existing classifiers in said message store; the improvement wherein said means for producing new classifiers includes means for forming first and second classifiers which operate in succession, the first of said classifiers generating an output message which thereafter satisfies the condition part of the second of said classifiers whereby a message at one time which satisfies the condition part of said first classifier necessarily produces an output message from said second classifier at a later time.

Claim 29

In an adaptive computing system of the class comprising, in combination, storage means for storing a plurality of messages and a plurality of classifiers, each of said classifiers comprising: a condition part which specifies the attributes of selected ones of said messages, an action part which specifies the functional relationship between the information content of said selected messages and at least one output message, and a strength value indicative of the past performance of said classifier in said system; processing means for comparing the condition part of each of said classifiers in said storage means with each of said messages in said storage means to identify said selected messages, said processing means further including means for placing selected ones of the output messages generated by classifiers whose condition part is satisfied into said storage means for further processing, and means for periodically producing new classifiers which are modified versions of one or more existing classifiers in said message store; the improvement wherein said means for producing new classifiers includes means for forming first and second classifiers which operate in succession, the first of said classifiers generating an output message which thereafter satisfies the condition part of the second of said classifiers whereby a message at one time which satisfies the condition part of said first classifier necessarily produces an output message from said second classifier at a later time.

Claim 30

An adpative computing system as set forth in claim 22 wherein said first and second classifiers are derived from third and fourth existing classifiers which act in succession, said first classifier having a condition part derived from the condition part of said third classifier and said second classifier having an action part derived from said fourth classifier.

Claim 31

An adaptive computing system comprising, in combination, a central computing unit including means for storing a plurality of messages, a plurality of independent processing units, each of which includes means for storing a classifier, said classifier comprising a condition part which specifies the attributes of selected ones of the messages stored in central computing unit, an action part which specifies the functional relationship between the information content of said selected messages and at least one output message, and a strength value indicative of the past performance of said classifier; parallel switching means for interconnecting said independent processing units; broadcast switching means for interconnecting said central computer with each of said independent processing units; an input interface for providing data to said central computing unit in the form of messages from a source external to said system; and an output interface for providing result information derived from selected ones of said messages to utilization means for external to said computing system, wherein said central computing unit transmits said messages to said independent units via said broadcast switch, said independent units compare said messages with said classifiers, and wherein selected result messages produced by selected ones of said independent processors are returned via said broadcast switch to said central computing unit.

Claim 32

An adaptive computing system comprising, in combination, a central computing unit including means for storing a plurality of messages, a plurality of independent processing units, each of which includes means for storing a classifier, said classifier comprising a condition part which specifies the attributes of selected ones of the messages stored in central computing unit, an action part which specifies the functional relationship between the information content of said selected messages and at least one output message, and a strength value indicative of the past performance of said classifier; parallel switching means for interconnecting said independent processing units; broadcast switching means for interconnecting said central computer with each of said independent processing units; an input interface for providing data to said central computing unit in the form of messages from a source external to said system; and an output interface for providing result information derived from selected ones of said messages to utilization means for external to said computing system, wherein said central computing unit transmits said messages to said independent units via said broadcast switch, said independent units compare said messages with said classifiers, and wherein selected result messages produced by selected ones of said independent processors are returned via said broadcast switch to said central computing unit.

Claim 33

An adaptive computing system as set forth in claim 24 wherein each of said independent processors calculates a bid value proportional to said strength value whenever a message from said central unit satisfies the condition part of said classifier, wherein said central computing unit transmits to said independent processors a sequence of descending bid floor values, and wherein each of said independent processors returns to said central computer a result message only if the calculated bid value associated with that result message exceeds the current bid floor value most recently transmitted from said central unit.

Claim 34

An adaptive computing system unit as set forth in claim 24 or 25 wherein the strength value of a first classifier which generated a message subsequently employed by a second classifier is increased by an amount communicated to the independent processor handling said first classifier from the processor handling said second classifier via said parallel switching means.