WO2020044412A1 - Dispositif d'inférence, procédé d'inférence et support d'enregistrement lisible par ordinateur - Google Patents

Dispositif d'inférence, procédé d'inférence et support d'enregistrement lisible par ordinateur Download PDF

Info

Publication number
WO2020044412A1
WO2020044412A1 PCT/JP2018/031621 JP2018031621W WO2020044412A1 WO 2020044412 A1 WO2020044412 A1 WO 2020044412A1 JP 2018031621 W JP2018031621 W JP 2018031621W WO 2020044412 A1 WO2020044412 A1 WO 2020044412A1
Authority
WO
WIPO (PCT)
Prior art keywords
inference
knowledge
inference knowledge
consequent
new
Prior art date
Application number
PCT/JP2018/031621
Other languages
English (en)
Japanese (ja)
Inventor
大地 木村
風人 山本
Original Assignee
日本電気株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 日本電気株式会社 filed Critical 日本電気株式会社
Priority to PCT/JP2018/031621 priority Critical patent/WO2020044412A1/fr
Priority to JP2020539186A priority patent/JP7140195B2/ja
Publication of WO2020044412A1 publication Critical patent/WO2020044412A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/04—Inference or reasoning models

Definitions

  • the present invention relates to an inference apparatus and an inference method for deriving a hypothesis by applying inference knowledge to an observed event, and further relates to a computer-readable recording medium for realizing the same.
  • Hypothesis reasoning is to derive a valid hypothesis from inference knowledge (rules) given by a logical expression and observed events (observed events). Therefore, in the above-described example, if a hypothesis is derived by applying an observation event to a rule prepared in advance for the computer system, it is possible to easily determine whether a cyber attack has occurred.
  • weighted hypothesis inference for example, see Non-Patent Document 1.
  • weighted hypothesis inference a weight is assigned to each rule, and a cost is assigned to each observed event. Then, backward inference is performed on the weighted rule and the costed observation event to generate hypothesis candidates, and the cost of each hypothesis candidate is calculated by a unification operation. Further, among the generated hypothesis candidates, the hypothesis candidate with lower cost is regarded as a better hypothesis.
  • hypothesis candidates may not be generated in some cases.
  • O1 Apple (x) ⁇ Food (x)
  • R2 Buy (x, y) ⁇ Get (x, y)
  • R3 Eat (x, y) ⁇ Get (x, y) ⁇ Food (y)
  • O1 Buy (X, Y) ⁇ Apple (Y)
  • Non-Patent Document 1 proposes a method of exchanging the antecedent and the consequent to create a new rule, and applying backward inference using the created new rule.
  • this method for example, the following antecedents and consequents of the rules R1 and R2 are exchanged to create the following R1 ′ and R2 ′, so that these and the observation event O1 are applied to the rule R3.
  • a hypothesis candidate Eat (X, Y) is generated.
  • R2 ' Get (x, y) ⁇ Buy (x, y)
  • Non Patent Literature 1 states that 'can be adopted as inference knowledge of weighted hypothesis inference.
  • Non-Patent Document 1 it is possible to generate a hypothesis candidate that cannot be obtained only by backward inference.
  • this method has a problem that unnecessary hypothesis candidates are generated and the calculation cost in hypothesis inference increases.
  • the hypothesis candidate Food (Y) is generated by the observation event O1 and the new rule R1 ′. Furthermore, the hypothesis candidate Get (X, Y) is also generated by the observation event O1 and the new rule R2 '. These generated hypothesis candidates are unnecessary hypothesis candidates, and increase the calculation cost.
  • An example of an object of the present invention is to provide an inference apparatus, an inference method, and a computer-readable recording medium that can solve the above problem and can suppress an increase in calculation cost while expanding a range in which hypothesis candidates can be generated. It is in.
  • an inference device for deriving a hypothesis by applying inference knowledge to an observed event
  • An inference knowledge extension unit that generates new inference knowledge using the inference derived by deduction based on the inference knowledge, Applying the inference knowledge or the new inference knowledge to an observation logical expression expressing the observed event by a logical expression to perform inference to generate a hypothesis candidate capable of deriving the observation logical expression
  • a candidate generator It is characterized by having.
  • the inference method is an inference method for applying inference knowledge to an observed event to derive a hypothesis, (A) generating new inference knowledge using the inference knowledge derived by the deduction based on the inference knowledge; (B) Applying the inference knowledge or the new inference knowledge to an observation logical expression expressing the observed event by a logical expression to perform inference to generate a hypothesis candidate capable of deriving the observation logical expression
  • the steps It is characterized by having.
  • a computer readable recording medium is a computer readable recording medium which records a program for deriving a hypothesis by applying inference knowledge to an observed event by a computer.
  • Recording medium On the computer, (A) generating new inference knowledge using the inference knowledge derived by the deduction based on the inference knowledge; (B) Applying the inference knowledge or the new inference knowledge to an observation logical expression expressing the observed event by a logical expression to perform inference to generate a hypothesis candidate capable of deriving the observation logical expression
  • FIG. 1 is a block diagram illustrating a schematic configuration of an inference apparatus according to an embodiment of the present invention.
  • FIG. 2 is a block diagram illustrating a specific configuration of the inference apparatus according to the embodiment of the present invention.
  • FIG. 3 is a flowchart showing the operation of the inference apparatus according to the embodiment of the present invention.
  • FIG. 4 is a block diagram illustrating an example of a computer that implements the inference apparatus according to the embodiment of the present invention.
  • FIG. 1 is a block diagram illustrating a schematic configuration of an inference apparatus according to an embodiment of the present invention.
  • the inference apparatus 10 according to the present embodiment shown in FIG. 1 is an apparatus for deriving a hypothesis by applying inference knowledge to an observed event. As shown in FIG. 1, the inference apparatus 10 according to the present embodiment includes an inference knowledge extension unit 11 and a hypothesis candidate generation unit 12.
  • the inference knowledge extension unit 11 generates new inference knowledge by using the conclusion derived by deduction based on the inference knowledge.
  • the hypothesis candidate generation unit 12 performs inference by applying inference knowledge or new inference knowledge to an observation logical expression that expresses an observed event by a logical expression, and generates a hypothesis candidate that can derive the observation logical expression. I do.
  • the inference apparatus 10 does not generate new inference knowledge by exchanging the antecedent and the consequent as in the related art, but generates new inference knowledge using the conclusion derived by deduction. ing. According to the inference apparatus 10, since no extra hypothesis candidates are generated, it is possible to suppress an increase in calculation cost while expanding the range in which hypothesis candidates can be generated.
  • FIG. 2 is a block diagram illustrating a specific configuration of the inference apparatus according to the embodiment of the present invention.
  • the inference apparatus 10 includes, in addition to the inference knowledge extension unit 11 and the hypothesis candidate generation unit 12 described above, an inference knowledge storage unit 13 and an observation logical expression storage unit 14. It has.
  • the inference knowledge storage unit 13 stores inference knowledge having antecedent and consequent.
  • the observation logical expression storage unit 14 stores an observation logical expression that expresses an observed event by a logical expression. Note that, unlike the example of FIG. 2, the inference knowledge storage unit 13 and the observation logical formula storage unit 14 may be provided in another device different from the inference device 10. In the following, it is assumed that inference knowledge is also referred to as “rule”.
  • the inference knowledge extension unit 11 first obtains a rule from the inference knowledge storage unit 13. Then, the inference knowledge extending unit 11 replaces all or a part of the consequent in one specific rule with an antecedent of another rule in which all or part of the consequent is common, and replaces the new rule with a new rule. Generate. For example, when the consequent of Rule A includes the consequent of Rule B, the inference knowledge extending unit 11 generates a new rule in which the consequent of Rule B replaces the consequent of Rule A.
  • temporal contexts and the like can be individually written down.
  • the temporal context refers to a relationship in which one event occurs and then another event occurs, such as "raining ⁇ the ground is wet” or "water spraying ⁇ the ground is wet”. I do.
  • R3 ' (Eat (x, y) (Buy (x, y) ⁇ Apple (y)) cannot be deductively interpreted, and the meaning of “ ⁇ ” differs from other rules. That is, in R3 ', even if the antecedent is true, the consequent is not always true, so R3' is a rule applied only to backward inference.
  • the inference knowledge extending unit 11 derives R3 ′ at a stretch from R1, R2, and R3, but may also derive R3 ′ by sequentially substituting as shown below. it can. Specifically, the inference knowledge extending unit 11 first generates the following R3'-1 by replacing the food () of the consequent of R3 with the antecedent of R1. Further, similarly, the inference knowledge extending unit 11 generates the following R3'-2 from R2 and R3.
  • R3'-1 Eat (x, y) ⁇ Get (x, y) ⁇ Apple (y)
  • R3'-2 Eat (x, y) ⁇ Buy (x, y) ⁇ Food (y)
  • the inference knowledge extending unit 11 replaces the consequent of R3′-1 with the antecedent of R2. 'Is generated. Further, the inference knowledge extending unit 11 can similarly generate R3 'from R3'-2 and R1.
  • the inference knowledge extending unit 11 can discard the new rule when the generated new rule violates a preset constraint. That is, when there is a contradiction event, the inference knowledge extension unit 11 does not perform replacement that violates this.
  • the inference knowledge extending unit 11 generates the following rules R1 'and R10', which violate R11 (Apple () and Orange () do not hold at the same time). Therefore, the inference knowledge extending unit 11 immediately discards the following rules R1 ′ and R10 ′.
  • the hypothesis candidate generation unit 12 acquires an observation formula that expresses an observed event by a logical expression from the observation formula storage unit 14. Then, the hypothesis candidate generation unit 12 can apply the rule stored in the inference knowledge storage unit 13 or the newly generated rule to the obtained observation logical expression to perform inference, thereby deriving the observation logical expression. Generate a new hypothesis candidate.
  • FIG. 3 is a flowchart showing the operation of the inference apparatus according to the embodiment of the present invention.
  • FIGS. 1 and 2 are appropriately referred to.
  • the inference method is performed by operating the inference device 10. Therefore, the description of the inference method in the present embodiment will be replaced with the following description of the operation of the inference apparatus 10.
  • the inference knowledge expanding unit 11 acquires a rule from the inference knowledge storage unit 13 (step S1).
  • Step S2 the inference knowledge extending unit 11 replaces all or a part of the consequent in the rule acquired in step S1 with an antecedent of another rule in which all or part of the consequent is common, and A rule is generated (Step S2).
  • Step S2 is executed for all existing rules.
  • the hypothesis candidate generation unit 12 acquires an observation formula from the observation formula storage unit 14 (step S3).
  • the hypothesis candidate generation unit 12 performs inference by applying the rule obtained in step S1 or the new rule generated in step S2 to the observation logical expression obtained in step S3, and obtains the inference in step S3.
  • a hypothesis candidate capable of deriving the observed logical expression is generated (step S4).
  • step S4 the processing in the inference apparatus 10 ends once. If the inference knowledge storage unit 13 stores a rule for which the processing of steps S1 to S4 has not been performed, steps S1 to S4 are executed again for this rule and the existing rule. Another new hypothesis candidate is generated.
  • step S2 [Concrete example]
  • specific examples 1 and 2 of step S2 will be described below.
  • Example 1 Specific example 1 is an example in which variables are different between the antecedent and the consequent of the rule. For example, it is assumed that the following rules R21 and R22 exist.
  • Arrest (z, x) is not explicitly hypothesized.
  • z arrests x is interpreted as meaning that z does not matter who it is.
  • the specific example 2 is an example in which the replacing rule includes a variable that appears only in the antecedent or the consequent.
  • R31 and R32 exist.
  • the inference knowledge extending unit 11 replaces the consequent M (y, z) of R32 with the antecedent A (x, y, z) of R31, and generates the following R32 ′.
  • R32 ' D (y, z, u) ⁇ A (x, y, z) ⁇ N (u)
  • variable x that appears only in the antecedent of the replacing rule R31
  • the variable x that appears only in the antecedent appears only in the consequent of the generated rule R32 '.
  • R32 ' is used for backward inference, the variable x does not affect the antecedent of R32'.
  • R33 A (x, y) ⁇ M (w, x, y)
  • R34 D (w, x, y, u) ⁇ M (w, x, y) ⁇ N (u)
  • the inference knowledge extending unit 11 replaces the consequent M (w, x, y) of R34 with the antecedent A (x, y) of R33, and generates the following R34 '.
  • R34 ' D (w, x, y, u) ⁇ A (x, y) ⁇ N (u)
  • Specific example 3 is an example showing handling of conjunctions. First, a case in which the antecedent of the replacing rule takes a conjunction is described.
  • R41 A (x) ⁇ B (y) ⁇ M (x, y)
  • R42 D (x, y, u) ⁇ M (x, y) ⁇ N (u)
  • the inference knowledge extending unit 11 replaces the consequent M (x, y) of R42 with the antecedent A (x) ⁇ B (y) of R41, and generates the following R42 ′.
  • R42 ' D (x, y, u) ⁇ A (x) ⁇ B (y) ⁇ N (u)
  • R43 and R44 exist.
  • R43 A (x, y) ⁇ L (x) ⁇ M (y)
  • R44 D (x, y, z) ⁇ L (x) ⁇ M (y) ⁇ N (z)
  • the inference knowledge extending unit 11 replaces L (x) ⁇ M (y) of the consequent of R44 with the antecedent A (x, y) of R43, and generates the following R44 ′.
  • R44 ′ D (x, y, z) ⁇ A (x, y) ⁇ N (z)
  • the trouble of rejecting inconsistent hypotheses at the time of inference can be omitted.
  • the processing time can be pushed into the preprocessing of the rule, so that the inference processing time can be reduced when performing inference many times.
  • the inference knowledge extending unit 11 first applies rules to observed events to generate provisional rules. Then, the inference knowledge extending unit 11 replaces all or a part of the consequent in the specific one rule with a tentative rule antecedent in which all or part of the consequent is common, and adds a new rule. Generate
  • the inference knowledge extending unit 11 generates the following rules R51 and R52 as provisional rules.
  • R51 Buy (X, Y) ⁇ Get (X, Y)
  • R52 Apple (Y) ⁇ Food (Y)
  • the inference knowledge extending unit 11 replaces all or a part of the consequent with the rule using Food () and Get () in the rule, that is, R3 in the above example, before the provisional rule.
  • the inference knowledge extending unit 11 replaces all or a part of the consequent with the rule using Food () and Get () in the rule, that is, R3 in the above example, before the provisional rule.
  • R3 ' Eat (X, Y) is directly hypothesized from observation O1 by R3 '.
  • R3 ' Eat (X, Y) ⁇ Buy (X, Y) ⁇ Apple (Y)
  • the preprocessing is performed only on the rule related to the currently obtained observation, so that the number of rules to be added does not need to be increased.
  • one of the above-described embodiment and the first modification is selected based on a trade-off between the time required for rule preprocessing and the time required for inference processing based on the number of rules.
  • Modification Example 2 In the second modification, when the consequent of a specific one rule is a conjunction, the inference knowledge extending unit 11 shares a part of the consequent in the specific one rule and a part of the consequent with the specific one rule. To generate a new rule, replacing it with the antecedent of another rule.
  • R61 A (x, y) ⁇ M (x) ⁇ L (y)
  • R62 D (x, u) ⁇ M (x) ⁇ N (u)
  • R62 ′ D (x, u) ⁇ A (x, y) ⁇ N (u)
  • R1 ' Apple (x) ⁇ Eat (y, x)
  • R2 ' Buy (x, y) ⁇ Eat (x, y)
  • Modification 2 is effective when emphasis is placed on the completeness of a hypothesis.
  • the program in the present embodiment may be any program that causes a computer to execute steps S1 to S4 shown in FIG. By installing and executing this program on a computer, the inference apparatus 10 and the inference method according to the present embodiment can be realized.
  • the processor of the computer functions as the inference knowledge extension unit 11 and the hypothesis candidate generation unit 12 and performs processing.
  • the inference knowledge storage unit 13 and the observation logical expression storage unit 14 can be realized by storing the data files constituting them in a storage device such as a hard disk provided in a computer.
  • the program according to the present embodiment may be executed by a computer system configured by a plurality of computers.
  • each computer may function as one of the inference knowledge extension unit 11 and the hypothesis candidate generation unit 12, respectively.
  • the inference knowledge storage unit 13 and the observation logical formula storage unit 14 may be configured on a computer different from the computer that executes the program according to the present embodiment.
  • FIG. 4 is a block diagram illustrating an example of a computer that implements the inference apparatus according to the embodiment of the present invention.
  • the computer 110 includes a CPU (Central Processing Unit) 111, a main memory 112, a storage device 113, an input interface 114, a display controller 115, a data reader / writer 116, and a communication interface 117. Is provided. These units are connected via a bus 121 so as to be able to perform data communication with each other.
  • the computer 110 may include a GPU (Graphics Processing Unit) or an FPGA (Field-Programmable Gate Array) in addition to or instead of the CPU 111.
  • the CPU 111 loads the program (code) according to the present embodiment stored in the storage device 113 into the main memory 112 and executes the programs in a predetermined order to perform various operations.
  • the main memory 112 is typically a volatile storage device such as a DRAM (Dynamic Random Access Memory).
  • the program according to the present embodiment is provided in a state stored in computer-readable recording medium 120.
  • the program according to the present embodiment may be distributed on the Internet connected via the communication interface 117.
  • the storage device 113 includes a semiconductor storage device such as a flash memory in addition to a hard disk drive.
  • the input interface 114 mediates data transmission between the CPU 111 and input devices 118 such as a keyboard and a mouse.
  • the display controller 115 is connected to the display device 119 and controls display on the display device 119.
  • the data reader / writer 116 mediates data transmission between the CPU 111 and the recording medium 120, reads out a program from the recording medium 120, and writes a processing result of the computer 110 to the recording medium 120.
  • the communication interface 117 mediates data transmission between the CPU 111 and another computer.
  • the recording medium 120 include a general-purpose semiconductor storage device such as CF (Compact @ Flash (registered trademark)) and SD (Secure Digital), a magnetic recording medium such as a flexible disk (Flexible @ Disk), or a CD-ROM.
  • CF Compact @ Flash
  • SD Secure Digital
  • An optical recording medium such as a ROM (Compact Disk Read Only Memory) may be used.
  • the inference apparatus 10 can also be realized by using hardware corresponding to each unit instead of a computer in which a program is installed. Further, part of the inference apparatus 10 may be realized by a program, and the remaining part may be realized by hardware.
  • An inference apparatus for applying inference knowledge to observed events to derive a hypothesis
  • An inference knowledge extension unit that generates new inference knowledge using the inference derived by deduction based on the inference knowledge, Applying the inference knowledge or the new inference knowledge to an observation logical expression expressing the observed event by a logical expression to perform inference to generate a hypothesis candidate capable of deriving the observation logical expression,
  • a candidate generator An inference apparatus comprising:
  • An inference method for applying inference knowledge to observed events to derive a hypothesis (A) generating new inference knowledge using the inference knowledge derived by the deduction based on the inference knowledge; (B) Applying the inference knowledge or the new inference knowledge to an observation logical expression expressing the observed event by a logical expression to perform inference to generate a hypothesis candidate capable of deriving the observation logical expression
  • An inference method comprising:
  • a computer-readable recording medium recording a program for deriving a hypothesis by applying inference knowledge to an observed event by a computer, On the computer, (A) generating new inference knowledge using the inference knowledge derived by the deduction based on the inference knowledge; (B) Applying the inference knowledge or the new inference knowledge to an observation logical expression expressing the observed event by a logical expression to perform inference to generate a hypothesis candidate capable of deriving the observation logical expression The steps A computer-readable recording medium on which a program including instructions for executing the program is recorded.
  • the present invention it is possible to suppress an increase in calculation cost while expanding the range in which hypothesis candidates can be generated.
  • the present invention is useful for various systems required to generate a hypothesis.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computing Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

L'invention concerne un dispositif d'inférence (10) destiné à déduire une hypothèse en appliquant une connaissance inférentielle à un phénomène observé. Le dispositif d'inférence (10) est pourvu : d'une unité d'extension de connaissances inférentielles (11) qui utilise, par rapport à des connaissances inférentielles, une conclusion dérivée par déduction sur la base des connaissances inférentielles pour générer de nouvelles connaissances inférentielles ; et d'une unité de génération de candidat d'hypothèse (12) qui effectue une inférence en appliquant les connaissances inférentielles ou les nouvelles connaissances inférentielles à une formule logique d'observation exprimant un phénomène observé par une expression logique et qui génère un candidat d'hypothèse pour lequel la formule logique d'observation peut être déduite.
PCT/JP2018/031621 2018-08-27 2018-08-27 Dispositif d'inférence, procédé d'inférence et support d'enregistrement lisible par ordinateur WO2020044412A1 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/JP2018/031621 WO2020044412A1 (fr) 2018-08-27 2018-08-27 Dispositif d'inférence, procédé d'inférence et support d'enregistrement lisible par ordinateur
JP2020539186A JP7140195B2 (ja) 2018-08-27 2018-08-27 推論装置、推論方法、及びプログラム

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2018/031621 WO2020044412A1 (fr) 2018-08-27 2018-08-27 Dispositif d'inférence, procédé d'inférence et support d'enregistrement lisible par ordinateur

Publications (1)

Publication Number Publication Date
WO2020044412A1 true WO2020044412A1 (fr) 2020-03-05

Family

ID=69642766

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2018/031621 WO2020044412A1 (fr) 2018-08-27 2018-08-27 Dispositif d'inférence, procédé d'inférence et support d'enregistrement lisible par ordinateur

Country Status (2)

Country Link
JP (1) JP7140195B2 (fr)
WO (1) WO2020044412A1 (fr)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0588896A (ja) * 1991-07-16 1993-04-09 Nkk Corp 操業知識の学習方法
JP2007520805A (ja) * 2004-01-06 2007-07-26 本田技研工業株式会社 ノイズの多いデータで推論するために統計的技術を使用するシステムおよび方法
JP2011253270A (ja) * 2010-06-01 2011-12-15 Nippon Telegr & Teleph Corp <Ntt> 推論装置、推論プログラム

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2016091039A (ja) * 2014-10-29 2016-05-23 株式会社デンソー 危険予測装置、運転支援システム

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0588896A (ja) * 1991-07-16 1993-04-09 Nkk Corp 操業知識の学習方法
JP2007520805A (ja) * 2004-01-06 2007-07-26 本田技研工業株式会社 ノイズの多いデータで推論するために統計的技術を使用するシステムおよび方法
JP2011253270A (ja) * 2010-06-01 2011-12-15 Nippon Telegr & Teleph Corp <Ntt> 推論装置、推論プログラム

Also Published As

Publication number Publication date
JPWO2020044412A1 (ja) 2021-08-12
JP7140195B2 (ja) 2022-09-21

Similar Documents

Publication Publication Date Title
US10015199B2 (en) Processing security-relevant events using tagged trees
US10692007B2 (en) Behavioral rules discovery for intelligent computing environment administration
US20220182406A1 (en) Analysis apparatus, analysis system, analysis method, and non-transitory computer readable medium storing program
US20110302566A1 (en) Fixing security vulnerability in a source code
JP7127688B2 (ja) 仮説推論装置、仮説推論方法、及びプログラム
US20100049558A1 (en) System and method for automatically generating suggested entries for policy sets with incomplete coverage
JP6253862B1 (ja) 情報処理装置、情報処理方法及び情報処理プログラム
JP6992343B2 (ja) 情報処理装置、情報処理方法、および情報処理プログラム
WO2020044412A1 (fr) Dispositif d&#39;inférence, procédé d&#39;inférence et support d&#39;enregistrement lisible par ordinateur
JP7127687B2 (ja) 仮説推論装置、仮説推論方法、及びプログラム
WO2018167830A1 (fr) Dispositif de dialogue, système de dialogue et support d&#39;enregistrement lisible par ordinateur
US9754213B2 (en) Reasoning over cyclical directed graphical models
Pop et al. A tabu search optimization approach for semantic web service composition
JP7322966B2 (ja) 情報処理装置、情報処理方法及びプログラム
JP7338697B2 (ja) 推論装置、推論方法、及びプログラム
Benson-Tilsen UDT with known search order
WO2024009471A1 (fr) Dispositif d&#39;inférence logique, procédé d&#39;inférence logique et programme
WO2020008632A1 (fr) Dispositif d&#39;inférence d&#39;hypothèse, procédé d&#39;inférence d&#39;hypothèse, et support d&#39;enregistrement lisible par ordinateur
JP7485034B2 (ja) 推論装置、推論方法、及びプログラム
JP7485036B2 (ja) 推論装置、推論方法、及びプログラム
WO2022180729A1 (fr) Dispositif d&#39;inférence, procédé d&#39;inférence et support d&#39;enregistrement
JP6908134B2 (ja) 仮説生成装置、仮説生成方法、及びプログラム
JP7485035B2 (ja) 推論装置、推論方法、及びプログラム
WO2020044413A1 (fr) Dispositif d&#39;inférence d&#39;hypothèse, procédé d&#39;inférence d&#39;hypothèse, et support d&#39;enregistrement lisible par ordinateur
EP3859520B1 (fr) Procédé mis en oeuvre par ordinateur permettant de décider si un nombre aléatoire est supérieur ou inférieur à un seuil donné

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18931921

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2020539186

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18931921

Country of ref document: EP

Kind code of ref document: A1