JP3211236B2 - Automatic knowledge corrector for approximate inference - Google Patents

Description

Description: BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention, in approximate inference, feeds back information on the correctness of an inference result, and automatically corrects expert knowledge in a knowledge base based on the information. The present invention relates to an automatic knowledge correction device.

2. Description of the Related Art Approximate inference is known in which an inference result is modified or changed according to the information amount of an event used to derive the inference result (for example, Zhang Hongmin “AN EXPERT SY”).
STEM WITH THINKING IN IMAGES ", Preprints of Second
IFSA Congress, Tokyo, July 20-25, 1987, p. 765).

This approximate inference method calculates the amount of information for each event (that is, the information discrimination ability of an event) using a membership function given to each event for each event, and calculates the inference result (that is, the possibility that the conclusion holds). Is modified or changed (the product of the probability and the amount of information) by the amount of information of the event used to draw the conclusion, thereby improving the discrimination ability of the inference result.

However, in such a conventional approximation inference apparatus, since the information on the correctness of the inference result is not fed back, it is difficult to know whether the inference result is really correct or not. There is a problem that if the user does not know, there is an error in the knowledge, it is not clear how to correct the knowledge, and the knowledge base must be corrected manually.

SUMMARY OF THE INVENTION Object of the Invention The present invention provides an apparatus capable of automatically correcting expert knowledge used for approximate inference.

An automatic knowledge correcting device for approximate inference according to the present invention is an approximate inference device that calculates the possibility of knowledge by applying input data to the knowledge of a specialist. Knowledge storage means for storing expert knowledge indicating the relationship between the range of indicated event values and the conclusion, validity information input means for inputting information on the correctness of the conclusion, and conclusions for which the information on the correctness has been input are as follows: History storage means for accumulatively storing input event value data; event value data stored in the history storage means for a predetermined conclusion;
The inconsistency calculation means for calculating the degree of inconsistency with the range of event values in the expert knowledge stored in the knowledge storage means for the same conclusion as the predetermined conclusion is calculated by the inconsistency calculation means. If the degree of inconsistency is equal to or greater than a predetermined value, the range of event values in the expert's knowledge stored in the knowledge storage means is compared with the event value data stored in the history storage means. It is characterized in that it comprises a knowledge correcting means for correcting by a range consisting of a maximum value and a minimum value.

According to the present invention, information on the correctness of the conclusion with respect to the inference result is input by a human (or automatically), and the input event value data is stored as a history of the conclusion on which the correctness information is input. The degree of discrepancy between the historical event value data for the same conclusion and the range of event values in the expert's knowledge is calculated. If the degree of discrepancy is equal to or greater than a predetermined value, the degree of discrepancy in the expert's knowledge about that conclusion is calculated. The range of event values is corrected using the maximum and minimum values of the historical event value data.

Thus, according to the present invention, the expert's knowledge representing the relationship between the range of event values indicated by the maximum value and the minimum value and the conclusion is corrected based on the information on the correctness of the conclusion. A more accurate inference result can be obtained.

1. Description of Embodiment (1) Overall Configuration of Approximate Inference Apparatus and Automatic Knowledge Correction Apparatus FIG. 1 shows an example of the overall configuration of an approximate inference apparatus and automatic knowledge correction apparatus. The approximate inference device includes a knowledge storage device 11, a knowledge synthesis device 12, a synthesized knowledge storage device 13, an event value input device 14, a fitness calculation device 15, a dynamic information amount calculation device 16,
It comprises a possibility calculation device 17, possibility display device 18, static information amount calculation device 19, clarity calculation device 20, clarity storage device 21, clarity addition device 22, and clarity display device 23.

The automatic knowledge correction device includes a validity information input device 31, a history storage device 32, an inconsistency calculation device 33, a knowledge correction device 34, a knowledge resynthesis device 35, and a clarity recalculation execution device 36.

Hereinafter, these devices will be described in detail by taking a failure diagnosis as an example.

(2) Knowledge storage device The knowledge storage device 11 stores the knowledge input by an expert or the like in a format indicating the relationship between an event (a situation when a failure occurs, a measured value, etc.) and a conclusion (a type of failure, etc.). It is a device for storing. This device can store the knowledge of several experts.

The two experts ex1 and ex stored in the knowledge storage device 11
An example of knowledge of 2 is shown below in the form of rules.

Expert ex1: if 20 ≦ f1 ≦ 60, 0 ≦ f2 ≦ 40, then c1… (1) if 40 ≦ f1 ≦ 80, 60 ≦ f2 ≦ 100, then c2… (2) Expert ex2: if 30 ≦ f1 ≦ 50,10 ≦ f2 ≦ 30, then c1 ... (3) if 50 ≦ f1 ≦ 70,70 ≦ f2 ≦ 90, then c2 ... (4) f1 and f2 are events.
It may be called. c1 and c2 are conclusions, and these may be called conclusions 1 and 2, respectively.

Also, a and b expressed as a ≦ f1 ≦ b are called a minimum value and a maximum value, respectively.

The above rules are expressed in the form of a table for each expert as follows.

(3) Knowledge Synthesizing Device The knowledge synthesizing device 12 is a device that synthesizes knowledge of a plurality of specialists stored in the knowledge storage device 11 and combines them into one knowledge.

Although there are various methods for synthesizing knowledge, here, the average value and standard deviation of multiple experts are calculated for the maximum value and the minimum value of each event involved in each conclusion.

The knowledge synthesizing process will be described below by taking as an example the knowledge that leads to the conclusion c1 from the event f1 of the two experts described above.

From the above rules (Equations (1) and (3)), event 1
Extracting the rule for obtaining the conclusion 1 (c1) from (f1) is expressed as follows.

Expert ex1: if 20 ≦ f1 ≦ 60 then c1 (5) Expert ex2: if 30 ≦ f1 ≦ 50 then c1 (6) The average value m _{min of the} minimum value and the average value m _{max of the} maximum value are calculated. You.

Standard deviation σ _{min of} minimum value and standard deviation σ of maximum value
_max is calculated.

When such a synthesis operation of expert knowledge is performed for all of the minimum and maximum values of each event involved in each conclusion with respect to the above-described rules (Equations (1) to (4)) , The following table is obtained.

In general, in approximate inference, a membership function is given to an event. Here, as an example, a method of obtaining a membership function by a Gaussian distribution using the expert's knowledge synthesized as described above will be described.

Using the average value of the minimum value m _min , the average value of the maximum value m _max , the standard deviation σ _{min of} the minimum value, and the standard deviation σ _max of the maximum value, the membership function is expressed by the following equation.

Where x is the value of the input data to the event Φ (x) is the degree to which the input data x matches the event (fitness) Gauss (x) is the value of the Gaussian distribution at the input x.

FIG. 2 shows an example of a Gaussian distribution. In this Gaussian distribution, only the left half is used to create the membership function. Position of x in Φ (x) = 0.5 is determined by m _min or m _max, the slope is determined by the sigma _min or sigma _max.

As an example, a membership function for obtaining the conclusion c1 from the event f1 is created as shown in FIGS. 3a to 3c using the values calculated from the equations (7) to (10). In this case, equation (11) becomes as follows.

FIG. 3a shows the first term on the right side of equation (11) or (12), FIG. 3b shows the second term on the right side of equation (11) or (12), and FIG. It represents the result of subtracting the second term from the first term, that is, the membership function represented by equation (11) or (12).

4a and 4b show examples of membership functions for obtaining the conclusions c1 and c2 for each of the events f1 and f2 created based on the combined knowledge shown in Table 3.

(4) Post-synthesis knowledge storage device The post-synthesis knowledge storage device 13 stores the average value and the standard deviation calculated by the knowledge synthesis device 12 in a format as shown in Table 3. Since it is not necessary to synthesize knowledge every time inference is performed, the result calculated in advance in this way is stored. Then, by reading and using the value in the storage device 13 each time inference is performed, it is possible to speed up the inference processing.

(5) Event Value Input Device The event value input device 14 is a device that reads input data input for each event from a failure diagnosis target device, a keyboard, a communication interface device, a memory, a file, and the like. The input data is provided to the fitness calculating device 15 and information on whether or not data of each event has been input is provided to the clarity adding device 22.

(6) Fitness calculating device The fitness calculating device 15 calculates the fitness of the data input from the event value input device 14 with respect to each membership function (or conclusion). Specifically, the fitness is
It is obtained as Φ (x) by substituting the input data as the variable x on the right side of the equation (11). Of course, such an arithmetic expression need not always be used.

(7) Dynamic information amount operation device and static information amount operation device The event value (input data) of event f1 is x1, and the event value of event f2 is x2. These data are input from the event value input device 14.

Each fit as shown in FIG. 5a and FIG. 5b m _11, m _12, m
_21, defines the m ₂₂ as follows.

m ₁₁ : Fitness of input data x1 for conclusion c1 m ₁₂ : Fitness of input data x1 for conclusion c2 m ₂₁ : Fitness of input data x2 for conclusion c1 m ₂₂ : Fitness of input data x2 for conclusion c2 The fitness is calculated by the fitness calculation device 15 when the input data x1 and x2 are given.

 Now consider the concept of fuzzy entropy.

Fuzzy entropy Ef1 given input x1
Is defined as follows.

This fuzzy entropy is a kind of index of information discriminating ability, and when input data x1 is given, the value is small enough to clearly identify the conclusion, and large so that the conclusion can be identified only ambiguously. In other words, input data x1
Will fit m ₁₁ CONCLUSION c1 between the smaller value is larger the difference between the fit m ₁₂ CONCLUSION c2 of the input data x1,
The smaller the difference, the larger the value.

Similarly, the fuzzy entropy Ef2 when the input x2 is given is given by the following equation.

The possible value range of the fuzzy entropy Ef is as follows.

0 ≦ Ef ≦ log (n) n: Number of conclusions on event In this example, the number of conclusions on event 1 (f1) is 2 (c1, c2)
Therefore, the maximum value of fuzzy entropy Ef is log
(2).

Next, using this fuzzy entropy Ef1, the dynamic information amount If1 _D (x1) when the input data x1 is given is obtained. Here, the dynamic information amount If1 _D (x1), in the event of identification ability to determine a conclusion at the time of performing reasoning, the conclusions of adaptability m ₁₁ and the input data x1 CONCLUSION c1 of the input data x1 c2 It takes a larger value difference adaptability m ₁₂ is large with respect to, and made a smaller value as the difference is smaller.

Therefore, the dynamic information amount If1 _D (x1) for event f1 is
It is defined as the value obtained by subtracting the fuzzy entropy Ef1 when the input data x1 is given from the maximum fuzzy entropy.

Similarly, the dynamic information amount when the input data x2 is given for the event f2 is defined as follows.

The dynamic information amount calculation device 16 calculates the dynamic information amount for each event according to the expressions (15) and (16) using the fitness obtained by the fitness calculation device 15.

The dynamic information amount depends on the input data x1, x2 as described above. On the other hand, the amount of static information does not depend on the input data, and the maximum fuzzy entropy minus the average of the fuzzy entropy within the range of the event is calculated as the static information of the entire event. Amount. For example, the static information amount for event 1 is given by the following equation.

Similarly, the static information amount for event 2 is given by the following equation.

Here, m ₁₁ (x): conclusion c1 of input data x for event f1
M ₁₂ (x): Conclusion c2 of input data x for event f1
M ₂₁ (x): Conclusion c1 of input data x for event f2
Fit m ₂₂ for (x): Conclusions of the input data x for events f2 c2
Goodness of fit As can be seen from Equations (17) and (18), the larger the overlap between the event membership functions, the smaller the static information amount of the event, and the smaller the overlap between the event membership functions, the smaller the overlap between the event membership functions. The amount of static information of the event is large. That is,
Static information indicates the ability of the event membership function to identify conclusions.

The static information amount calculation device 19 calculates and stores the static information amount for each event from the membership function obtained by the synthesized knowledge according to the above-described equations (17) and (18). I do. Since the static information amount does not depend on the input data, it has to be calculated only once.

(8) Possibility calculating device For each conclusion, the sum of the information amounts of the events involved in the conclusion becomes 1, and the information amount of the event such that the relative intensity of the information amounts of those events does not change is calculated. . The calculated information amount is called a weight.

For example, when the above-mentioned dynamic information amount is used, each weight is as follows.

Weight of event 1 for conclusion 1: wf ₁₁ = If1 _D (x1) / [If1 _D (x1) + If2 _D (x2)] (19) Weight of event 2 for conclusion 1: wf ₁₂ If2 _D (x2) / [ If1 _D (x1) + If2 _D (x2)] (20) Weight of event 1 with respect to conclusion 2: wf ₂₁ = If1 _D (x1) / [If1 _D (x1) + If2 _D (x2)] (21) Conclusion 2 Weight of event 2 with respect to: wf ₂₂ = If2 _D (x2) / [If1 _D (x1) + If2 _D (x2)] ... (22) Next, the product of these weights and the fitness is calculated, and the result is concluded. The sum of each is calculated as the possibility of conclusion.

For example the conclusions 1 possibility _{= wf 11 × m 11 + wf} 12 × m 21 ... (23) Conclusion 2 possibilities _{= wf 21 × m 12 + wf} 22 × m 22 ... (24) in the above example.

The possibility calculating device 17 calculates the possibility for each conclusion by performing the above-described calculation.

(9) Possibility display device The possibility display device 18 displays the possibility calculated by the possibility calculation device 17 for each conclusion. This possibility may be displayed for all conclusions, or one or more conclusions with high possibility may be displayed. For example, a conclusion that the probability is equal to or higher than a predetermined threshold (for example, 50%) is displayed. Also,
The possibility may be transmitted to another device by communication, or the possibility may be stored in a memory or a file.

(10) Clarity calculation device The clarity calculation device 20 is a device that calculates the clarity of each event for each conclusion. Here, the clarity of each event for each conclusion indicates the relative discriminating ability of each event when determining a certain conclusion. Therefore, this clarity allows one to compare the discriminating power of multiple events to determine a certain conclusion, and to determine which events have a high discriminating power (has a lot of information). You. The method of calculating clarity is described below.

First, Table 4 shows the conclusions and the relationship between events and the amount of static information.

As can be seen from Table 4, it is possible to compare the discrimination ability of a plurality of events for determining each conclusion also by the amount of static information. However, since the relative discrimination ability is difficult to intuitively understand as it is, the static information amount is normalized for each conclusion as shown in the table below, and the normalized value is used to clarify each event for each conclusion. To be Cl.

However, Cl ₁₁ = a _{Cl 12 = If1 S / (If1} S + If2 S) Cl 21 = Cl 22 = If2 S / (If1 S + If2 S).

In this way, the clarity calculation device 20 calculates the clarity of each event for each conclusion.

(11) Clarity storage device The clarity storage device 21 is a device that stores the clarity of each event for each conclusion calculated by the clarity calculation device 20. The operation of clarity need not be performed for each inference. Therefore, the clarity calculated when the knowledge is synthesized is stored in the clarity storage device 21, and the value stored in the clarity storage device 21 is read each time inference is performed. This can speed up the inference processing.

(12) Clarity adding device The clarity adding device 22 is a device that calculates the clarity of an event in which data is actually input. Here, for the reasoning that can be actually performed, the sum of the clarity of the events for which data has been input is calculated. This sum of clarity indicates the clarity of the inference result. It can be said that the higher the clarity, the greater the amount of information for deriving the inference result. Therefore, clarity can be used as an index for judging the reliability of the inference result itself.

Clarity for the inference result is calculated as follows.

a) When data is input only for event 1 (f1) ・ Clearness to the inference result of conclusion 1 (c1) Cl ₁ = Cl ₁₁・ Clarity to the inference result of conclusion 2 (c2) Cl ₂ = Cl ₁₂ b ) When data is input only for event 2 (f2) ・ Clearness to the inference result of conclusion 1 (c1) Cl ₁ = Cl ₂₁・ Clarity to the inference result of inference 2 (c2) Cl ₂ = Cl ₂₂ c) When data is input for both event 1 (f1) and event 2 (f2) ・ Clearness to the inference result of conclusion 1 (c1) Cl ₁ = Cl ₁₁
+ Cl ₂₁ = 1.0 ・ Clarity to the inference result of conclusion 2 (c2) Cl ₂ = Cl ₁₂
+ Cl ₂₂ = 1.0 Clarity of the inference result The possible range of Cl is 0.0 ≦ Cl ≦ 1.0. That is, if inferences are made by inputting data on all the events that can be used to draw a conclusion in the knowledge given before inference,
The clarity of the conclusion is 1.0. In addition, when data is entered for only some of the events that can be used to draw a conclusion, the clarity is from 0.0.
It will be a value between 1.0. At this time, if many events with high clarity are used among the events that can be used, it can be said that the clarity of the conclusion increases, and a highly reliable inference result can be obtained.

(13) Clarity display device The clarity display device 23 is a device that displays clarity with respect to the inference result (the possibility described above as an example) calculated by the clarity addition device 22. The clarity may be displayed together with the inference result, or the clarity may be transmitted to another device or stored in a memory or a file.

This statement of clarity indicates all conclusions of the inference result. Therefore, when there are multiple conclusions, the corresponding clarity is displayed for each conclusion.

In this way, every time data is input, the amount of information of the event to which the input data belongs is calculated and the clarity of the inference result is displayed, so that the user can judge the reliability of the inference result. Become.

(14) Legitimacy information input device The legitimacy information input device 31 is mainly used by humans to make a correct conclusion regarding the possibility of a conclusion displayed on the possibility display device 18 or a conclusion not displayed on the display device 18. It is for input. For example, in the case of a failure diagnosis, when the possibility of failure is displayed on the display device 18 (for example,
The one with the possibility of 50% or more is displayed.) Of the displayed failures, the one that has actually occurred is specified, and even if it is not displayed on the display device 17, it actually occurs. Specify the fault that has occurred. In addition, for a specified fault, data on an event related to the fault (conclusion) is input. Since it is possible to know which part has failed based on information from a sensor or the like attached to the device, it is also possible to automatically input information on such a failure and on event value data.

The validity information input device 31 creates history storage data as shown in Table 6 when a conclusion and event value data related thereto are input.

Here, ci: correct correct conclusion (failure) fj: event related to ci xj: event value data of event fj.

FIG. 6 shows a history storage data creation processing procedure in the validity information input device 31. When a correct conclusion (failure) is input from a keyboard or the like, all events related to the conclusion are selected (steps 41 and 42). The event related to the conclusion can be understood from the knowledge or the operation result stored in the knowledge storage device 11, the knowledge synthesis device 12, the synthesized knowledge storage device 13, or the possibility operation device 17. If the event value data of all the events related to the input conclusion is input from the event value input device 14 (may be input from a keyboard, a sensor, or the like), it is associated with the conclusion. And stored in a history storage data file as shown in Table 6 (steps 43, 44, 45).

For example, suppose that the possibility display device 18 displays the following failure possibility.

Failure c1: possibility 0.8 Failure c2: possibility 0.6 At this time, if a failure of c1 has actually occurred, a human inputs failure c1. Then, the input device 31 returns the conclusion c1.
Are determined to be f1 and f2. Assuming that 35 is input as an event value of f1 and 5 is input as an event value of f2, history storage data as shown in Table 7 is created.

In the case of failure diagnosis, if there is a maintenance report or the like that reports the failure and the state (event value) of the machine when the failure occurred, the maintenance report may be directly input to the input device 31. With this maintenance report, it is not necessary to input the validity of the conclusion each time the failure diagnosis is executed, and the validity information input processing can be performed in a batch manner.

(15) History storage device The history storage device 32 accumulates and stores the history storage data created by the validity information input device 31 in the form of a table (file) for each conclusion as shown in FIG. Is what you do. The newly created history storage data may be stored in a form added to the end of the previously stored history storage data file. In FIG. 7, n represents the number of times ci was specified as a correct conclusion. The event value data input by the event value input device 14 is input to the input device 31 or the storage device 32.
May be given to any of them. As will be described later, when the knowledge is corrected by the knowledge correcting device 34, the history storage data relating to the corrected conclusion is deleted.

For example, if the history storage data shown in Table 7 for the conclusion c1 is added by the third specification of the c1, the history data for the conclusion c1 in the history storage device 32
The files are as shown in Table 8.

(16) Discrepancy Calculation Device The discrepancy calculation device 33 is activated when a certain amount of history is accumulated for each conclusion stored in the history storage device 32, or when one day's work is completed. Therefore, the processing can be performed in batches, and the degree of mismatch calculation can be performed when the load on the CPU is small, so that the amount of load on the CPU during operation of the device does not increase.

The inconsistency calculating device 33 calculates the range of the event value data stored in the history storage device 32 and the same for each expert stored in the knowledge storage device 11 for each of all events fj associated with each conclusion ci. The purpose is to calculate the degree of disagreement between the conclusion and the knowledge about the same event. An example of the algorithm for calculating the degree of inconsistency is shown in FIG. 8 for the event fj of the conclusion ci.

First, the minimum value fj _min and the maximum value fj _max of the event value data relating to the event fj are selected from the history data file for the conclusion ci stored in the history storage device 32 (step 51). Next, the minimum value a _k and the maximum value b _k of the knowledge of the expert exk regarding the event fj of the conclusion ci stored in the knowledge storage device 11
Are read (step 52). Subsequently, the degree of mismatch is calculated by the following equation using the selected and read data (step 53).

Inconsistency = | a _k −fj _min | + | b _k −fj _max | (25) The calculated inconsistency is stored in a corresponding location of the inconsistency data file as shown in FIG. 9 (step 5).
Four). This inconsistency data file has an area for storing the inconsistency of all events for each expert for the conclusion ci.

If the above processing is performed for all experts, the inconsistency degree calculation processing for one event fj related to one conclusion ci ends (step 55).

The same applies to all other events related to the conclusion ci. In addition, such processing is performed for all conclusions or necessary conclusions.

For example, the experts ex1, shown in Tables 1 and 2
The degree of inconsistency of the event f1 relating to the conclusion c1 of ex2 with the history data shown in Table 8 is 30, 10 as shown in FIG. Further, the degree of inconsistency of the event f2 relating to the conclusion c1 of the experts ex1 and ex2 with the history data shown in Table 8 is 10, 10 as shown in FIG.

(17) Knowledge correction device The knowledge correction device 34 uses the inconsistency degree data obtained as described above in accordance with the following algorithm.
The knowledge of the relevant expert stored in the knowledge storage device 11 is corrected.

1) For each event of the conclusion, the range of the event value in the knowledge of the expert with the highest degree of mismatch is corrected to the range of the minimum value and the maximum value of the history data.

2) However, if all the inconsistencies are within a certain threshold,
Do not make this modification.

 This threshold is determined, for example, as follows.

Threshold value = (possible range of each event value) × 0.1 (26) If the range (definition range) of the event value in event f1 or f2 is 100, the threshold value is 10.

3) Update the knowledge of the relevant expert in the knowledge storage device 11 with the corrected knowledge.

As described above, it is possible to automatically correct the knowledge of an expert who is considered to be not very correct, instead of making a judgment based on human judgment.

For example, the degrees of inconsistency of experts ex1 and ex2 shown in FIG. 10 are 30, 10 respectively. Since the degree of inconsistency 30 of the expert ex1 is the largest, and the degree of inconsistency 30 is equal to or greater than the threshold value 10, the knowledge of the expert ex1 regarding the event f1 related to the conclusion c1 is reduced to a minimum value Modified to a maximum value of 45. Therefore, Table 1 is as shown in the following table.

Since the degrees of inconsistency shown in FIG. 11 are 10 for both the experts ex1 and ex2 and are equal to or less than the threshold value 10, the knowledge of the event f2 of the conclusion c1 is not corrected.

(18) Knowledge re-synthesizing unit The knowledge re-synthesizing unit 35 re-synthesizes knowledge only for the part related to the corrected knowledge. The method of synthesis is the same as the method performed by the knowledge synthesis device 12. The re-synthesis result is provided to the post-synthesis knowledge storage device 13 and stored. In the above example, only the event f1 of the conclusion c1 has been corrected, so it is only necessary to recalculate the average and standard deviation of the minimum value and the average value and standard deviation of the maximum value.

Since the re-synthesis is not performed for the entire knowledge but only for the related parts, the processing can be speeded up. After the knowledge is re-synthesized, it goes without saying that approximate inference is performed using the re-synthesized new knowledge.

(19) Clarity recalculation execution device The clarity recalculation execution device 36 performs the clarity recalculation only for a portion related to the modified knowledge. The method of calculating clarity is the same as the method in the clarity calculation device 20. In the above example, the correction is made only for the event f1 of the conclusion c1, so the static information amount is obtained for the conclusion related to the event f1, and the clarity is calculated from the static information amount.

This calculation is also executed in batches (for example, during a break or at night), so that the load on the CPU during the operation of the device is not increased.

In the above embodiment, the expert's knowledge stored in the knowledge storage device is corrected based on the information of the history data, but the average value and the standard deviation stored in the combined knowledge storage device are directly calculated. May be corrected.

If there are multiple identical approximation inference devices, the same (standard) knowledge is initially entered in all, but the knowledge is automatically corrected. It is possible to perform a failure diagnosis.

Needless to say, each of the devices 11 to 23 and 31 to 36 described above can be realized by a computer including a memory and a display device. For example, the knowledge synthesizing unit 12, various arithmetic units 15, 16, 1
7, 19, 20, 22, 33, 35, and 36 are preferably realized by a CPU that operates according to a program.

[Brief description of the drawings]

FIG. 1 is a block diagram showing an example of the overall configuration of an approximate inference device and an automatic knowledge correction device. FIG. 2 is a graph showing a Gaussian distribution. FIGS. 3a to 3c are graphs showing how a membership function is formed. FIGS. 4a and 4b are graphs showing membership functions obtained for each event. FIGS. 5a and 5b are graphs showing how to determine the degree of conformity. FIG. 6 is a flowchart showing a history storage data creation processing procedure. FIG. 7 shows an example of a history data file. FIG. 8 is a flow chart showing the procedure for calculating the degree of mismatch. FIG. 9 shows an example of the mismatch degree data file. FIG. 10 and FIG. 11 show examples of the degree of mismatch. 11 ... Knowledge storage device, 12 ... Knowledge synthesis device, 13 ... Knowledge storage device after synthesis, 14 ... Event value input device, 15 ... Compatibility calculation device, 16 ... Dynamic information amount calculation device, 17 ...... Possibility calculation device, 18 ... Possibility display device, 19 ... Static information amount calculation device, 20 ... Clarity calculation device, 21 ... Clarity storage device, 22 ... Clarity addition device, 23 …… Clarity display device, 31… Validity information input device, 32 …… History storage device, 33 …… Dissimilarity calculation device, 34 …… Knowledge correction device, 35 …… Knowledge resynthesis device, 36 …… Clarity Sex recalculation execution device.

Claims (1)

(57) [Claims] An approximate inference apparatus for calculating the possibility of knowledge by applying input data to the knowledge of an expert, comprising: an expert representing the relationship between a range of event values indicated by a maximum value and a minimum value and a conclusion. Knowledge storage means for storing knowledge, validity information input means for inputting information on the correctness of conclusions, history storage means for cumulatively storing event value data input regarding the conclusions on which correctness information has been input, The degree of inconsistency between the event value data stored in the history storage means for the predetermined conclusion and the range of event values in the expert knowledge stored in the knowledge storage means for the same conclusion as the predetermined conclusion Means for calculating the degree of mismatch,
And when the degree of inconsistency calculated by the degree of inconsistency calculation means is equal to or greater than a predetermined value, a range of event values in the expert's knowledge stored in the knowledge storage means is stored in the history storage means. Automatic knowledge correction means for approximation inference, comprising: knowledge correction means for correcting in accordance with a range consisting of a maximum value and a minimum value of event value data stored in memory.