Information processing program, information processing method, and information processing device

Abstract

This information processing device is provided with an extended knowledge database (800). An information processing device reads a plurality of hypotheses including a hypothesis "X: A-B", a hypothesis "Y: A-B", and a hypothesis "Z: A-B" from an extended knowledge database (800). The information processing device calculates, as a condition ratio, a ratio of a union set obtained by combining conditions X, Y, and Z to a complete set Omega including conditions X, Y, and Z. When the calculated condition ratio is equal to or greater than a threshold value, the information processing device adds, to the extended knowledge database (800), a hypothesis "Omega: A-B" that unconditionally represents the causal relationship "A-B".

Description

Technical Field

[0001] The present invention relates to an information processing device, an information processing method, and an information processing program. Background Art

[0002] In the past, there was a case where people wanted to add a new hypothesis that represents the causal relationship between elements under specific conditions to an existing knowledge DB (database) that stores hypotheses that represent the causal relationship between elements that are not given conditions and are not determined. For example, consider adding a new hypothesis that represents the causal relationship between elements under specific conditions inferred by AI (artificial intelligence) to the existing knowledge DB.

[0003] As a prior art, for example, there is a technique of changing a prototype of knowledge stored in a knowledge base to meet conditions and adding the knowledge base as new knowledge.

[0004] Patent document 1: Japanese Patent Application Laid-Open No. 04-160536.

[0005] However, in the prior art, it is sometimes difficult to appropriately update the existing knowledge DB. For example, if the formats of the hypothesis that can be stored in the existing knowledge DB and the new hypothesis inferred by AI are different, it is difficult to add the new hypothesis inferred by AI to the existing knowledge DB. In addition, for example, it is unclear how to comprehensively store the hypothesis that represents the causal relationship between elements with undetermined conditions stored in the existing knowledge DB and the new hypothesis inferred by AI that represents the same causal relationship between the same elements under specific conditions. Summary of the invention

[0006] In one aspect, the present invention aims to enable suitable updating of a storage unit.

[0007] According to one embodiment, an information processing program, an information processing method and an information processing device are proposed, for a plurality of hypotheses representing the same first causal relationship under respectively different conditions, it is determined whether the ratio of a union formed by synthesizing the respectively different conditions to a full set including the respectively different conditions is above a threshold, wherein the plurality of hypotheses are stored in a storage unit for storing hypotheses representing causal relationships between elements, and when the ratio is above the threshold, a first hypothesis that is different from the plurality of hypotheses and unconditionally represents the first causal relationship in the full set is added to the storage unit.

[0008] According to one embodiment, an information processing program, an information processing method and an information processing device are proposed, for a plurality of hypotheses representing the same first causal relationship under respectively different conditions, it is determined whether the ratio of a union formed by synthesizing the respectively different conditions to a full set including the respectively different conditions is above a threshold, wherein the plurality of hypotheses are stored in a storage unit for storing hypotheses representing causal relationships between elements, and when the ratio is above the threshold, if a hypothesis representing the first causal relationship under undetermined conditions which is different from the plurality of hypotheses is stored in the storage unit, the hypothesis is deleted from the storage unit.

[0009] According to one embodiment, the storage unit can be appropriately updated. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 It is an explanatory diagram showing an example of an information processing method according to an embodiment.

[0011] Figure 2 It is an explanatory diagram showing another example of the information processing method involved in the embodiment.

[0012] Figure 3 It is an explanatory diagram showing an example of the information processing system 300 .

[0013] Figure 4 It is a block diagram showing a hardware configuration example of the information processing device 100 .

[0014] Figure 5 It is an explanatory diagram showing an example of the storage content of the extended knowledge DB.

[0015] Figure 6 It is a block diagram showing a functional configuration example of the information processing device 100 .

[0016] Figure 7 It is a block diagram showing a functional configuration example of the information processing system 300 .

[0017] Figure 8 This is an explanatory diagram showing operation example 1 of the information processing device 100 .

[0018] Fig. 9 This is an explanatory diagram showing operation example 2 of the information processing device 100 .

[0019] Fig.10 It is an explanatory diagram showing operation example 3 of the information processing device 100 .

[0020] Fig.11 It is an explanatory diagram showing operation example 4 of the information processing device 100 .

[0021] Fig.12It is an explanatory diagram showing operation example 5 of the information processing device 100 .

[0022] Fig.13 It is an explanatory diagram showing operation example 6 of the information processing device 100 .

[0023] Fig.14 This is a flowchart showing an example of the first additional processing procedure.

[0024] Fig.15 : is a flowchart showing an example of the first reduction processing steps.

[0025] Fig.16 This is a flowchart showing an example of the second additional processing procedure.

[0026] Fig.17 : is a flowchart showing an example of the second reduction processing procedure. DETAILED DESCRIPTION

[0027] Hereinafter, embodiments of an information processing program, an information processing method, and an information processing device according to the present invention will be described in detail with reference to the accompanying drawings.

[0028] (One Example of the Information Processing Method According to the Embodiment)

[0029] Figure 1 1 is an explanatory diagram showing an example of an information processing method according to an embodiment. The information processing device 100 is a computer for appropriately updating a storage unit. The information processing device 100 is, for example, a server or a PC (Personal Computer).

[0030] The storage unit stores, for example, hypotheses representing causal relationships between elements. The storage unit is, for example, a prior knowledge DB that stores hypotheses representing causal relationships that are inferred without considering the conditions and that are not determined by the conditions. The conditions are represented by a combination of more than one element. For example, the hypothesis shows the causal relationship between an element representing a gene and an element representing a disease. For example, the hypothesis shows the causal relationship between an element representing a material and an element representing a physical property.

[0031] Assumptions, for example, represent a causal relationship in which if element A holds, element B holds. In the following description, a causal relationship in which if element A holds, element B holds is sometimes expressed as "A→B". Assumptions, for example, may also represent a causal relationship in which if element A does not hold, element B holds, or a causal relationship in which if element A holds, element B does not hold.

[0032] Here, sometimes it is desirable to add a new hypothesis to the existing knowledge DB. For example, consider the case where new hypotheses representing the causal relationship between elements under certain conditions are inferred one by one by AI. In this case, consider adding the new hypothesis to the existing knowledge DB each time a new hypothesis is inferred by AI.

[0033] In the past, it was sometimes difficult to appropriately update the existing knowledge DB. For example, if the formats of the hypothesis that can be stored in the existing knowledge DB and the new hypothesis inferred by AI are different, it is difficult to add the new hypothesis inferred by AI to the existing knowledge DB. Specifically, consider the following situation: the existing knowledge DB contains a field for setting causal relationships, but does not contain a field for setting conditions, and only stores hypotheses that represent causal relationships between elements whose conditions are not determined. In this case, it is impossible to store the new hypothesis inferred by AI that represents the causal relationship between elements under specific conditions in the existing knowledge DB as it is.

[0034] In contrast, it is considered that the existing knowledge DB is expanded to be able to store new hypotheses inferred by AI. For example, consider the case where a field for setting conditions is added to the existing knowledge DB. In this case, for the hypotheses already stored in the existing knowledge DB, a character Φ indicating that the conditions are undetermined is set in the field for setting conditions. Furthermore, a new hypothesis inferred by AI indicating the causal relationship between elements under specific conditions is added to the expanded knowledge DB.

[0035] However, it is unclear how to better store the hypothesis of causal relationship with undetermined conditions stored in the existing knowledge DB and the new hypothesis inferred by AI that represents the same causal relationship under specific conditions. Therefore, it is sometimes difficult to update the knowledge DB appropriately. For example, sometimes it is difficult to add the new hypothesis inferred by AI to the existing knowledge DB considering the relationship between the hypothesis already stored in the existing knowledge DB and the new hypothesis inferred by AI. In addition, there is a problem that it is difficult to suppress the increase in the amount of data in the existing knowledge DB.

[0036] Therefore, in this embodiment, an information processing method that can appropriately update the storage unit will be described.

[0037] exist Figure 1 In the embodiment, the information processing device 100 has a storage unit 101. The storage unit 101 stores hypotheses representing causal relationships between elements. The storage unit 101 may store, for example, a plurality of hypotheses representing the same first causal relationship under different conditions. The condition is represented by a combination of one or more elements, for example. The plurality of elements that can be used to represent the causal relationship and the plurality of elements that can be used to represent the condition may also include the same element.

[0038] (1-1) The information processing device 100 calculates the ratio of a union of the different conditions to the whole set containing the different conditions for a plurality of hypotheses representing the same first causal relationship under different conditions stored in the storage unit 101. For example, the information processing device 100 calculates the ratio of the number of elements used in the union containing the different conditions to the number of elements that can be used to express the conditions. The information processing device 100 determines whether the calculated ratio is above a threshold value. The threshold value is set in advance by the user, for example. In this way, it is possible to obtain a criterion for determining how to update the storage content of the storage unit 101.

[0039] (1-2) When the calculated ratio is greater than or equal to a threshold value, the information processing device 100 adds a first hypothesis that unconditionally expresses the first causal relationship, which is different from the plurality of hypotheses, to the storage unit 101. The unconditional is represented by, for example, Ω. Thus, the information processing device 100 can appropriately update the storage unit 101. After adding the first hypothesis, the information processing device 100 can delete the plurality of hypotheses from the storage unit 101, thereby suppressing an increase in the amount of data in the storage unit 101.

[0040] Before the union of the different conditions becomes larger than a certain value, the information processing device 100 determines that the accuracy of the unconditional first causal relationship is relatively low, and can store and appropriately manage the hypothesis representing the first causal relationship in the storage unit 101 for each individual condition. On the other hand, if the union of the different conditions becomes larger than a certain value, the information processing device 100 determines that the accuracy of the unconditional first causal relationship is relatively high, and can add the first hypothesis representing the unconditional first causal relationship to the storage unit 101 and appropriately manage it.

[0041] In this way, the information processing device 100 can appropriately manage the hypothesis representing the first causal relationship in the storage unit 101 according to the accuracy of the unconditional establishment of the first causal relationship, and can appropriately update the storage unit 101.

[0042] Here, the case where the information processing device 100 has the storage unit 101 is described, but the present invention is not limited to this. For example, there may be a case where another computer other than the information processing device 100 has the storage unit 101. For example, there may be a case where the information processing device 100 can access the storage unit 101 of another computer.

[0043] Here, the case where the information processing device 100 acts alone is described, but the present invention is not limited thereto. For example, there may be a case where the information processing device 100 cooperates with other computers. For example, there may be a case where multiple computers implement the functions of the information processing device 100. Specifically, there may be a case where the functions of the information processing device 100 are implemented on the cloud.

[0044] (Another Example of the Information Processing Method According to the Embodiment)

[0045] Next, use Figure 2 Another example of the information processing method according to the embodiment will be described. Figure 2 It is an explanatory diagram showing another example of the information processing method involved in the embodiment.

[0046] exist Figure 2 In the information processing device 100, there is a storage unit 201. The storage unit 201 stores hypotheses representing causal relationships between elements. The storage unit 201 may also store a second hypothesis representing a first causal relationship under an undetermined condition. The undetermined condition is represented by Φ, for example. The storage unit 201 may also store, for example, a plurality of hypotheses representing the same first causal relationship under different conditions. The condition is represented by a combination of one or more elements, for example. The plurality of elements that can be used to represent the causal relationship and the plurality of elements that can be used to represent the condition may also include the same element.

[0047] (2-1) The information processing device 100 calculates the ratio of a union of the different conditions to the whole set containing the different conditions for a plurality of hypotheses representing the same first causal relationship under different conditions stored in the storage unit 201. For example, the information processing device 100 calculates the ratio of the number of elements used in the union containing the different conditions to the number of elements that can be used to express the conditions. The information processing device 100 determines whether the calculated ratio is above a threshold value. The threshold value is set in advance by the user, for example. In this way, it is possible to obtain a criterion for determining how to update the storage content of the storage unit 201.

[0048] (2-2) When the calculated ratio is equal to or greater than a threshold value, the information processing device 100 deletes the second hypothesis from the storage unit 201 if the second hypothesis that is different from the plurality of hypotheses and represents the first causal relationship under undetermined conditions is stored in the storage unit 201. In this way, the information processing device 100 can appropriately update the storage unit 201. For example, the information processing device 100 can delete the second hypothesis and suppress an increase in the amount of data in the storage unit 201.

[0049] Before the union of the combined different conditions becomes larger than a certain value, the information processing device 100 determines that the first causal relationship is established unconditionally, although the conditions are not determined temporarily, and can store the second hypothesis in the storage unit 201. Therefore, the information processing device 100 can appropriately manage the storage unit 201 so as to respect the second hypothesis obtained through existing research or the like.

[0050] On the other hand, if the union formed by synthesizing the different conditions becomes larger than a certain value, the information processing device 100 can determine that the first causal relationship holds under conditions that are wider than a certain value. The second hypothesis sometimes does not consider whether the first causal relationship holds under other conditions that are not included in the union formed by synthesizing the different conditions. In existing research, the information processing device 100 considers the possibility that the second hypothesis is generated without judging whether the first causal relationship holds under other conditions, and can delete the second hypothesis from the storage unit 201.

[0051] Therefore, the information processing device 100 can distinguish between conditions under which the first causal relationship is determined to be established and conditions under which the first causal relationship is not determined to be established, and can appropriately update the storage unit 201. The information processing device 100 can determine whether it is preferable to study under which condition the first causal relationship is established, which can help future studies.

[0052] In this way, the information processing device 100 infers and considers the range of conditions verified in the existing research, and can appropriately manage the second hypothesis representing the first causal relationship under uncertain conditions and multiple hypotheses representing the same first causal relationship under different conditions. The information processing device 100 can appropriately update the storage unit 201.

[0053] Here, the case where the information processing device 100 has the storage unit 201 is described, but the present invention is not limited to this. For example, there may be a case where another computer other than the information processing device 100 has the storage unit 201. For example, there may be a case where the information processing device 100 can access the storage unit 201 of another computer.

[0054] Here, the case where the information processing device 100 acts alone is described, but the present invention is not limited thereto. For example, there may be a case where the information processing device 100 cooperates with other computers. For example, there may be a case where multiple computers implement the functions of the information processing device 100. Specifically, there may be a case where the functions of the information processing device 100 are implemented on the cloud.

[0055] Here, there may be a case where the information processing device 100 has both the function of implementing one of the above-mentioned embodiments and the function of implementing another of the above-mentioned embodiments. There may also be a case where the information processing device 100 has only one of the function of implementing one of the above-mentioned embodiments and the function of implementing another of the above-mentioned embodiments. In the following description, the case where the information processing device 100 has both the function of implementing one of the above-mentioned embodiments and the function of implementing another of the above-mentioned embodiments will be mainly described.

[0056] (An example of information processing system 300)

[0057] Next, use Figure 3 For application Figure 1 or Figure 2 An example of an information processing system 300 of the information processing device 100 shown will be described.

[0058] Figure 3 3 is an explanatory diagram showing an example of the information processing system 300. Figure 3 In the embodiment, the information processing system 300 includes an information processing device 100 , a knowledge learning device 301 and a client device 302 .

[0059] In the information processing system 300, the information processing device 100 and the knowledge learning device 301 are connected via a wired or wireless network 310. The network 310 is, for example, a LAN (Local Area Network), a WAN (Wide Area Network), the Internet, etc. In the information processing system 300, the information processing device 100 and the client device 302 are connected via a wired or wireless network 310.

[0060] The information processing device 100 is a computer that manages the storage unit 311. The storage unit 311 stores hypotheses that represent causal relationships between elements. The storage unit 311 may also store hypotheses that represent first causal relationships when conditions are not determined. The storage unit 311 may also store, for example, multiple hypotheses that represent the same first causal relationship under different conditions. The conditions are represented, for example, by a combination of more than one element. The multiple elements that can be used to represent the causal relationship and the multiple elements that can be used to represent the conditions may also include the same elements.

[0061] The storage unit 311 may be included in the information processing device 100. The storage unit 311 may be included in a computer other than the information processing device 100. In this case, the information processing device 100 can access the storage unit 311 included in the other computer. Figure 1 The storage unit 101 shown, or Figure 2 Specifically, the storage unit 311 is composed of Figure 5 The extended knowledge DB500 described later is implemented.

[0062] The information processing device 100 receives a new hypothesis indicating a causal relationship between elements from the knowledge learning device 301. The information processing device 100 adds the received new hypothesis to the storage unit 311.

[0063] The information processing device 100 calculates the ratio of the union of the different conditions to the whole set containing the different conditions for the plurality of hypotheses representing the same first causal relationship under different conditions stored in the storage unit 311. The information processing device 100 determines whether the calculated ratio is greater than a threshold value. The threshold value is set in advance by the user, for example. The information processing device 100 updates the storage unit 311 based on the result of the determination.

[0064] The information processing device 100 receives an inquiry about the storage content of the storage unit 311. The information processing device 100 receives an inquiry about the storage content of the storage unit 311 from, for example, the knowledge learning device 301 or the client device 302. The information processing device 100 transmits the storage content of the storage unit 311 to the knowledge learning device 301 or the client device 302 in response to the inquiry. The information processing device 100 is used, for example, by a system administrator. The information processing device 100 is, for example, a server or a PC.

[0065] The knowledge learning device 301 is a computer that learns new hypotheses that represent the causal relationship between elements. The knowledge learning device 301 learns new hypotheses that represent the causal relationship between elements, for example, through AI. Specifically, the knowledge learning device 301 may also send a query of the storage content of the storage unit 311 to the information processing device 100, and receive the storage content of the storage unit 311 from the information processing device 100. Specifically, the knowledge learning device 301 may also refer to the storage content of the storage unit 311 and learn new hypotheses that represent the causal relationship between elements through AI. The knowledge learning device 301 sends the learned new hypothesis to the information processing device 100. The knowledge learning device 301 is used, for example, by a system administrator. The knowledge learning device 301 is, for example, a server or a PC.

[0066] The client device 302 is a computer used by a system user. Based on the operation input of the system user, an inquiry about the storage content of the storage unit 311 is sent from the client device 302 to the information processing device 100. The client device 302 receives the storage content of the storage unit 311 from the information processing device 100. The client device 302 outputs the storage content of the storage unit 311 in a manner that the system user can refer to. The client device 302 is, for example, a PC, a tablet terminal, or a smartphone.

[0067] Here, the information processing device 100 is described as a device different from the knowledge learning device 301 , but the present invention is not limited thereto. For example, the information processing device 100 may have the function of the knowledge learning device 301 and may also operate as the knowledge learning device 301 .

[0068] Here, the case where the information processing device 100 is a device different from the client device 302 is described, but the present invention is not limited to this. For example, there may be a case where the information processing device 100 has a function as the client device 302 and also operates as the client device 302.

[0069] (Example of using the information processing system 300)

[0070] Next, Figure 3 The information processing system 300 shown in the figure is used for explanation. For example, the information processing system 300 can be applied to the field of material research. Specifically, the information processing system 300 can be applied to the field of exploring catalysts for manufacturing materials with preferred physical properties. The storage unit 311 stores, for example, hypotheses representing the causal relationship between catalysts and physical properties. Thus, the information processing system 300 can easily explore catalysts for manufacturing materials with preferred physical properties.

[0071] For example, the information processing system 300 can be applied to the field of gene research. Specifically, the information processing system 300 can be applied to the field of verifying the relationship between a specific gene and a disease. The storage unit 311 stores, for example, a hypothesis representing the causal relationship between a gene and a disease. Thus, the information processing system 300 can easily verify the relationship between a specific gene and a disease.

[0072] (Hardware Configuration Example of Information Processing Device 100)

[0073] Next, use Figure 4 A hardware configuration example of the information processing device 100 will be described.

[0074] Figure 4 is a block diagram showing an example of the hardware configuration of the information processing device 100. Figure 4 In the embodiment, the information processing device 100 includes a CPU (Central Processing Unit) 401 , a memory 402 , a network I / F (Interface) 403 , a recording medium I / F 404 , and a recording medium 405 . The components are connected to each other via a bus 400 .

[0075] Here, the CPU 401 is in charge of the overall control of the information processing device 100. The memory 402 includes, for example, a ROM (Read Only Memory), a RAM (Random Access Memory), and a flash ROM. Specifically, for example, the flash ROM and the ROM store various programs, and the RAM is used as a work area for the CPU 401. The program stored in the memory 402 is loaded into the CPU 401, so that the CPU 401 executes the coded processing.

[0076] The network I / F 403 is connected to the network 310 through a communication line, and is connected to other computers via the network 310. The network I / F 403 manages the interface between the network 310 and the inside, and controls the input and output of data from other computers. The network I / F 403 is, for example, a modem, a LAN adapter, or the like.

[0077] The recording medium I / F 404 controls the reading / writing of data on the recording medium 405 according to the control of the CPU 401. The recording medium I / F 404 is, for example, a magnetic disk drive, an SSD (Solid State Drive), a USB (Universal Serial Bus) port, etc. The recording medium 405 is a non-volatile memory that stores written data under the control of the recording medium I / F 404. The recording medium 405 is, for example, a magnetic disk, a semiconductor memory, a USB memory, etc. The recording medium 405 can also be loaded and unloaded from the information processing device 100.

[0078] In addition to the above-mentioned components, the information processing device 100 may also include a keyboard, a mouse, a display, a printer, a scanner, a microphone, a speaker, etc. In addition, the information processing device 100 may also include a plurality of recording medium I / Fs 404 and recording media 405. In addition, the information processing device 100 may not include a recording medium I / F 404 and a recording medium 405.

[0079] (Storage content of extended knowledge DB500)

[0080] Next, use Figure 5 An example of the storage content of the extended knowledge DB 500 is described. The extended knowledge DB 500 is composed of, for example, Figure 4 The information processing device 100 shown is implemented by storage areas such as the memory 402 and the recording medium 405.

[0081] Figure 5 5 is an explanatory diagram showing an example of the storage content of the extended knowledge DB 500. Figure 5 As shown, the extended knowledge DB 500 has fields for conditions and causal relationships. The extended knowledge DB 500 sets information in each field for each hypothesis, and the hypothesis information is stored as a record 500 - a. a is an arbitrary integer.

[0082] The condition for forming a hypothesis is set in the condition field. For example, the condition represented by a combination of one or more elements is set in the condition field. For example, Φ indicating that the condition is undetermined may be set in the condition field. For example, Ω indicating that there is no condition may be set in the condition field. The causal relationship for forming a hypothesis under the above conditions is set in the causal relationship field.

[0083] (Hardware Configuration Example of Knowledge Learning Device 301)

[0084] Specifically, the hardware structure example of the knowledge learning device 301 is similar to Figure 4 The hardware configuration example of the information processing device 100 shown is the same, and therefore the description thereof will be omitted.

[0085] (Hardware Configuration Example of Client Device 302)

[0086] Specifically, the hardware configuration example of the client device 302 is similar to Figure 4 The hardware configuration example of the information processing device 100 shown is the same, and therefore the description thereof will be omitted.

[0087] (Functional Configuration Example of Information Processing Device 100)

[0088] Next, use Figure 6 A functional configuration example of the information processing device 100 will be described.

[0089] Figure 6 1 is a block diagram showing an example of a functional configuration of the information processing device 100. The information processing device 100 includes a storage unit 600, an acquisition unit 601, a determination unit 602, an update unit 603, and an output unit 604.

[0090] The storage unit 600 is composed of, for example, Figure 4 The storage unit 600 is implemented in a storage area such as the memory 402 and the recording medium 405 shown. In the following, the case where the storage unit 600 is included in the information processing device 100 is described, but the present invention is not limited to this. For example, there may be a case where the storage unit 600 is included in a device different from the information processing device 100, and the storage content of the storage unit 600 can be referenced from the information processing device 100.

[0091] The acquisition unit 601 to the output unit 604 function as an example of a control unit. Specifically, for example, by causing the CPU 401 to execute the Figure 4 The functions of the acquisition unit 601 to the output unit 604 are realized by a program in a storage area such as the memory 402 or the recording medium 405 shown in the figure, or through the network I / F 403. The processing results of each functional unit are stored in, for example, Figure 4 The memory 402, recording medium 405 and other storage areas are shown.

[0092] The storage unit 600 stores various information that is referenced or updated in the processing of each functional unit. The storage unit 600 stores hypotheses that represent the causal relationship between elements. The storage unit 600, for example, stores multiple hypotheses that represent the same causal relationship under different conditions. The condition is represented by a combination of more than one element, for example. The element can also be a value.

[0093] The storage unit 600 may also store, for example, hypotheses that represent causal relationships when conditions are not determined. Undetermined conditions may also be processed as temporarily unconditional. Unconditional, for example, includes all conditions. An unconditional causal relationship is, for example, a causal relationship that is established under all conditions. The storage unit 600 may also store, for example, hypotheses that represent causal relationships unconditionally. Specifically, the storage unit 600 stores the extended knowledge DB 500.

[0094] The acquisition unit 601 acquires various information used for processing by each functional unit. The acquisition unit 601 stores the acquired various information in the storage unit 600, or outputs it to each functional unit. In addition, the acquisition unit 601 may also output the various information stored in the storage unit 600 to each functional unit. The acquisition unit 601 acquires various information based on, for example, the operation input of the user of the device. The acquisition unit 601 may also receive various information from, for example, a device different from the information processing device 100.

[0095] The acquisition unit 601 acquires, for example, a new hypothesis different from the multiple hypotheses already stored in the storage unit 600. Specifically, the acquisition unit 601 acquires the new hypothesis by accepting the input of the new hypothesis based on the operation input of the user of the device. Specifically, the acquisition unit 601 can also acquire the new hypothesis by receiving it from other computers. The other computer is, for example, the knowledge learning device 301.

[0096] The acquisition unit 601 acquires, for example, an output request of the storage content of the storage unit 600. Specifically, the acquisition unit 601 acquires the output request by receiving the input of the output request based on the operation input of the user of the device. Specifically, the acquisition unit 601 can also acquire the output request by receiving it from another computer. The other computer is, for example, the client device 302.

[0097] The acquisition unit 601 may also receive a start trigger for starting the processing of any functional unit. The start trigger may be, for example, a predetermined operation input by the user of the device. The start trigger may also be, for example, receiving predetermined information from another computer. The start trigger may also be, for example, any functional unit outputting predetermined information. The start trigger may also be, for example, a signal output by a timer detected at regular intervals.

[0098] The acquisition unit 601 may accept, for example, the acquisition of a new hypothesis as a trigger to start the processes of the determination unit 602 and the update unit 603. The acquisition unit 601 may accept, for example, the acquisition of an output request as a trigger to start the processes of the output unit 604.

[0099] The determination unit 602 calculates the ratio of the union of the different conditions to the whole set including the different conditions for the plurality of hypotheses representing the same first causal relationship under different conditions stored in the storage unit 600. The whole set includes, for example, all conditions. The ratio can be, for example, a criterion for updating the storage unit 600. The ratio can be, for example, a criterion for evaluating whether the first causal relationship is established unconditionally. The ratio can be, for example, a criterion for evaluating whether the conditions for the establishment of the first causal relationship above a certain level have been determined.

[0100] The determination unit 602 calculates the ratio of the number of elements used in the union to the number of elements that can be used to express the condition, for example, for a plurality of hypotheses representing the same first causal relationship under different conditions stored in the storage unit 600. For example, the number of elements that can be used to express the condition is set in advance by the user of the device. For example, the number of elements that can be used to express the condition can also be set to the total number of elements contained in the storage unit 600 obtained by listing the elements used by all the hypotheses stored in the storage unit 600 without duplication.

[0101] Here, the case where the condition represents a range of values ​​is considered. In this case, the determination unit 602 may, for example, calculate the ratio of the range of values ​​of the union to the total range of possible values ​​for multiple hypotheses representing the same first causal relationship under different conditions stored in the storage unit 600. Thus, the determination unit 602 can obtain a criterion for updating the storage unit 600. The determination unit 602 can, for example, obtain a criterion for evaluating whether the first causal relationship is established unconditionally. The determination unit 602 can, for example, obtain a criterion for evaluating whether the conditions for the establishment of a certain first causal relationship have been determined.

[0102] The determination unit 602 determines whether the calculated ratio is above a threshold value. The threshold value is set in advance by the user of the device, for example. Thus, the determination unit 602 can determine how to update the storage unit 600 in the update unit 603. For example, if the ratio is above the threshold value, the determination unit 602 can determine that the accuracy of the first causal relationship being established unconditionally is relatively high. For example, if the ratio is above the threshold value, the determination unit 602 can determine that the conditions for the establishment of the first causal relationship above a certain level have been determined.

[0103] The updating unit 603 updates the storage content of the storage unit 600. For example, when the determining unit 602 determines that the ratio is above the threshold, the updating unit 603 adds the first hypothesis that unconditionally represents the first causal relationship to the storage unit 600. The first hypothesis is a hypothesis that is different from a plurality of hypotheses that represent the same first causal relationship under respectively different conditions. Thus, when the accuracy of the first causal relationship being established unconditionally is relatively high, the updating unit 603 can add the first hypothesis that unconditionally represents the first causal relationship to the storage unit 600. Moreover, the updating unit 603 can appropriately update the storage unit 600 so that the storage content of the storage unit 600 expresses the conditions under which the determination of the establishment of the first causal relationship has been completed.

[0104] For example, when the determination unit 602 determines that the ratio is greater than the threshold, the updating unit 603 deletes a plurality of hypotheses representing the same first causal relationship under different conditions from the storage unit 600. Specifically, the updating unit 603 deletes a plurality of hypotheses representing the same first causal relationship under different conditions from the storage unit 600 instead of adding the first hypothesis to the storage unit 600. For example, when the determination unit 602 determines that the ratio is less than the threshold, the updating unit 603 leaves a plurality of hypotheses representing the same first causal relationship under different conditions in the storage unit 600.

[0105] Thus, since a plurality of hypotheses representing the same first causal relationship under different conditions are included in the first hypothesis, the update unit 603 can determine that the plurality of hypotheses do not need to be stored in the storage unit 600. Therefore, the update unit 603 can delete the plurality of hypotheses representing the same first causal relationship under different conditions from the storage unit 600, and can suppress the increase in the amount of data in the storage unit 600. The update unit 603 can keep the plurality of hypotheses representing the same first causal relationship under different conditions in the storage unit 600 before adding the first hypothesis to the storage unit 600, and can control the storage unit 600 in a manner that respects existing research.

[0106] For example, when the determination unit 602 determines that the ratio is greater than a threshold value, the update unit 603 deletes the second hypothesis representing the first causal relationship under undetermined conditions from the storage unit 600 if the second hypothesis representing the first causal relationship under undetermined conditions is stored in the storage unit 600. The second hypothesis is a hypothesis different from a plurality of hypotheses representing the same first causal relationship under different conditions. Specifically, the update unit 603 deletes the second hypothesis representing the first causal relationship under undetermined conditions from the storage unit 600 instead of adding the first hypothesis to the storage unit 600. For example, when the determination unit 602 determines that the ratio is less than a threshold value, the update unit 603 leaves the second hypothesis representing the first causal relationship under undetermined conditions in the storage unit 600.

[0107] Thus, the second hypothesis representing the first causal relationship under undetermined conditions is included in the first hypothesis, and therefore the update unit 603 can determine that the second hypothesis does not need to be stored in the storage unit 600. Therefore, the update unit 603 can delete the second hypothesis representing the first causal relationship under undetermined conditions from the storage unit 600, and can suppress the increase in the amount of data in the storage unit 600. The update unit 603 can leave the second hypothesis representing the first causal relationship under undetermined conditions in the storage unit 600 before adding the first hypothesis to the storage unit 600, and can control the storage unit 600 in a manner that respects existing research.

[0108] When the third hypothesis representing the first causal relationship under the new condition is acquired in the acquisition unit 601, if the first hypothesis is not stored in the storage unit 600, the updating unit 603 adds the input third hypothesis to the storage unit 600. The third hypothesis is a hypothesis that has not been stored in the storage unit 600, and is a hypothesis different from the plurality of hypotheses representing the same first causal relationship under different conditions. Thus, the updating unit 603 can add the new hypothesis to the storage unit 600, and can appropriately update the storage unit 600.

[0109] When the third hypothesis representing the first causal relationship under the new condition is acquired in the acquisition unit 601, if the first hypothesis is stored in the storage unit 600, the update unit 603 discards the input third hypothesis. Thus, if the first hypothesis including the third hypothesis is already stored in the storage unit 600, the update unit 603 does not need to add the third hypothesis to the storage unit 600, and the increase in the amount of data in the storage unit 600 can be suppressed. In addition, the update unit 603 can prevent the storage unit 600 from storing the first hypothesis and the third hypothesis included in the first hypothesis at the same time. Therefore, the update unit 603 can make the storage content of the storage unit 600 in a form that is easy for the system user to intuitively grasp.

[0110] The output unit 604 outputs the processing result of at least one of the functional units. The output form is, for example, display on a display, print output to a printer, transmission to an external device via the network I / F 403, or storage in a storage area such as the memory 402 or the recording medium 405. Thus, the output unit 604 can notify the user of the device of the processing result of at least one of the functional units, and the convenience of the information processing device 100 can be improved.

[0111] The output unit 604 outputs, for example, the storage content of the storage unit 600. Specifically, the output unit 604 outputs the storage content of the storage unit 600 in a manner that the system user can refer to in response to the output request acquired by the acquisition unit 601. More specifically, the output unit 604 sends the storage content of the storage unit 600 to the client device 302, which is the source of the output request. Thus, the output unit 604 can allow the system user to refer to the storage content of the storage unit 600.

[0112] Here, the determination unit 602 calculates the ratio of the union of the different conditions to the whole set for the plurality of hypotheses representing the same first causal relationship under the different conditions included in the whole set, but the present invention is not limited to this. For example, there may be a case where the information processing device 100 uses the first condition instead of the whole set.

[0113] Specifically, the determination unit 602 calculates the ratio of the union of the different conditions to the first condition for the plurality of hypotheses representing the same first causal relationship under the different conditions included in the first condition stored in the storage unit 600. The determination unit 602 determines whether the calculated ratio is greater than a threshold value.

[0114] Thus, the determination unit 602 can determine how to update the storage unit 600 in the update unit 603. For example, if the ratio is greater than the threshold, the determination unit 602 can determine that the accuracy of the first causal relationship being established unconditionally in the first condition is relatively high. For example, if the ratio is greater than the threshold, the determination unit 602 can determine that it is a single condition that determines that the first causal relationship is established in a certain first condition or more.

[0115] Specifically, when the calculated ratio is greater than or equal to the threshold value, the updating unit 603 adds the first hypothesis that is different from the plurality of hypotheses and that unconditionally expresses the first causal relationship in the first condition to the storage unit 600. Thus, when the accuracy of the first causal relationship being unconditionally established in the first condition is relatively high, the updating unit 603 can add the first hypothesis that unconditionally expresses the first causal relationship in the first condition to the storage unit 600. Furthermore, the updating unit 603 can appropriately update the storage unit 600 so that the storage content of the storage unit 600 expresses the conditions under which the first causal relationship is established.

[0116] Specifically, when the update unit 603 determines that the calculated ratio is greater than the threshold, the update unit 603 deletes the plurality of hypotheses representing the same first causal relationship under the respectively different conditions included in the first condition from the storage unit 600. More specifically, the update unit 603 deletes the plurality of hypotheses representing the same first causal relationship under the respectively different conditions included in the first condition from the storage unit 600, instead of adding the first hypothesis to the storage unit 600. Specifically, when the update unit 603 determines that the ratio is less than the threshold, the update unit 603 leaves the plurality of hypotheses representing the same first causal relationship under the respectively different conditions included in the first condition in the storage unit 600.

[0117] Thus, since a plurality of hypotheses representing the same first causal relationship under different conditions included in the first condition are included in the first hypothesis, the update unit 603 can determine that the plurality of hypotheses do not need to be stored in the storage unit 600. Therefore, the update unit 603 can delete the plurality of hypotheses representing the same first causal relationship under different conditions included in the first condition from the storage unit 600, and can suppress the increase in the amount of data in the storage unit 600. The update unit 603 can keep the plurality of hypotheses representing the same first causal relationship under different conditions included in the first condition in the storage unit 600 before adding the first hypothesis to the storage unit 600, and can control the storage unit 600 in a manner that respects existing research.

[0118] Specifically, when the calculated ratio is greater than or equal to the threshold, if the second hypothesis that is different from the plurality of hypotheses and temporarily represents the first causal relationship under the first condition when the condition is not determined is stored in the storage unit 600, the updating unit 603 deletes the second hypothesis from the storage unit 600. More specifically, the updating unit 603 deletes the second hypothesis from the storage unit 600 instead of adding the first hypothesis to the storage unit 600. Specifically, when the ratio is less than the threshold, the updating unit 603 leaves the second hypothesis in the storage unit 600.

[0119] Thus, the second hypothesis is included in the first hypothesis, and the update unit 603 can determine that the second hypothesis does not need to be stored in the storage unit 600. Therefore, the update unit 603 can delete the second hypothesis from the storage unit 600, and can suppress the increase in the amount of data in the storage unit 600. The update unit 603 can leave the second hypothesis in the storage unit 600 before adding the first hypothesis to the storage unit 600, and can control the storage unit 600 in a manner that respects existing research.

[0120] (Functional Configuration Example of Information Processing System 300)

[0121] Next, use Figure 7 A functional configuration example of the information processing system 300 will be described.

[0122] Figure 7 1 is a block diagram showing a functional configuration example of the information processing system 300. In the information processing system 300, the information processing device 100 includes a condition ratio calculation unit 711, a knowledge reduction unit 712, and a hypothesis addition unit 713. The knowledge learning device 301 includes a condition assignment unit 721 and a knowledge comparison unit 722.

[0123] The knowledge learning device 301 can access the knowledge DB 701 and the hypothesis DB 702. The knowledge learning device 301 has, for example, the knowledge DB 701. The information processing device 100 can access the hypothesis DB 702 and the extended knowledge DB 703. The extended knowledge DB 703 corresponds to, for example, the extended knowledge DB 500. The information processing device 100 has, for example, the extended knowledge DB 703.

[0124] The knowledge DB 701 stores hypotheses obtained through existing research. For example, the knowledge DB 701 stores hypotheses that represent the causal relationship between elements when conditions are not determined. The hypothesis DB 702 stores new hypotheses generated by the knowledge learning device 301. For example, the hypothesis DB 702 stores new hypotheses with conditions generated by the knowledge learning device 301. Specifically, the hypothesis DB 702 stores new hypotheses that represent the causal relationship between elements under certain conditions.

[0125] The extended knowledge DB 703 stores conditional hypotheses. The extended knowledge DB 703 stores hypotheses that represent causal relationships between elements under certain conditions. The extended knowledge DB 703 may also store hypotheses that correspond to hypotheses stored in the knowledge DB 701. Specifically, the extended knowledge DB 703 may also store hypotheses that establish correspondence between a symbol Φ that represents an undetermined condition and a causal relationship represented by a hypothesis stored in the knowledge DB 701.

[0126] For example, it is considered that the information processing device 100 generates a hypothesis by associating a symbol Φ indicating an undetermined condition with a causal relationship indicated by a hypothesis stored in the knowledge DB 701 , and adds the hypothesis to the extended knowledge DB 703 .

[0127] The condition assignment unit 721 refers to the extended knowledge DB 703, determines the conditions of the object to be verified, and outputs them to the knowledge comparison unit 722. The knowledge comparison unit 722 receives the conditions of the object to be verified, and generates a new hypothesis representing the causal relationship between the elements under the conditions of the object through AI. The knowledge comparison unit 722 adds the generated new hypothesis to the hypothesis DB 702.

[0128] The condition ratio calculation unit 711 extracts one or more hypotheses that represent the causal relationship under different conditions for each causal relationship, and calculates the condition ratio for the extracted one or more hypotheses. The condition ratio is the ratio of the number of elements used in the union formed by combining the extracted one or more hypotheses to the number of elements that can be used to express the condition. In this way, the condition ratio calculation unit 711 can obtain a more preferred criterion for determining how to update the storage content of the extended knowledge DB 703.

[0129] The knowledge reduction unit 712 updates the storage content of the extended knowledge DB 703. The knowledge reduction unit 712 determines whether the calculated condition ratio is above a threshold value for each causal relationship. The threshold value is set in advance by the user, for example. The knowledge reduction unit 712 updates the storage content of the extended knowledge DB 703 based on whether the calculated condition ratio is above the threshold value for each causal relationship.

[0130] For example, for the first causal relationship, when the calculated condition ratio is greater than a threshold, the knowledge reduction unit 712 generates a new hypothesis that unconditionally represents the first causal relationship, and adds it to the extended knowledge DB 703. For example, for the first causal relationship, when the calculated condition ratio is less than a threshold, the knowledge reduction unit 712 does not generate a new hypothesis that unconditionally represents the first causal relationship.

[0131] Thus, when the accuracy of the first causal relationship being established unconditionally is relatively high, the knowledge reduction unit 712 can add a new hypothesis that unconditionally expresses the first causal relationship to the extended knowledge DB 703. Furthermore, the knowledge reduction unit 712 can appropriately update the storage content of the extended knowledge DB 703 so that the storage content of the extended knowledge DB 703 expresses the conditions under which the first causal relationship is established.

[0132] For example, when the calculated condition ratio is greater than a threshold value for the first causal relationship, the knowledge reduction unit 712 deletes one or more hypotheses extracted from the extended knowledge DB 703 representing the first causal relationship, and adds a new hypothesis that unconditionally represents the first causal relationship to the extended knowledge DB 703. For example, when the calculated condition ratio is less than a threshold value for the first causal relationship, the knowledge reduction unit 712 does not delete one or more hypotheses extracted from the extended knowledge DB 703 representing the first causal relationship.

[0133] Here, one or more hypotheses representing the first causal relationship under different conditions are included in the new hypothesis added to the extended knowledge DB 703. Therefore, the knowledge reduction unit 712 can determine that it is not necessary to store one or more hypotheses representing the first causal relationship under different conditions in the extended knowledge DB 703. The knowledge reduction unit 712 can delete multiple hypotheses representing the same first causal relationship under different conditions from the extended knowledge DB 703, and can suppress the increase in the amount of data in the extended knowledge DB 703.

[0134] For example, when the calculated condition ratio is greater than a threshold value for the first causal relationship, the knowledge reduction unit 712 deletes the existing hypothesis representing the first causal relationship under undetermined conditions from the extended knowledge DB 703 if the existing hypothesis representing the first causal relationship under undetermined conditions exists in the extended knowledge DB 703. For example, when the calculated condition ratio is less than a threshold value for the first causal relationship, the knowledge reduction unit 712 does not delete the existing hypothesis representing the first causal relationship under undetermined conditions from the extended knowledge DB 703.

[0135] Thus, the knowledge reduction unit 712 can delete the existing assumptions that represent the first causal relationship under undetermined conditions from the extended knowledge DB 703, and can suppress the increase in the amount of data in the extended knowledge DB 703. The knowledge reduction unit 712 can appropriately update the storage content of the extended knowledge DB 703 so that the storage content of the extended knowledge DB 703 represents the conditions that have been determined that the first causal relationship is established.

[0136] Here, the case where the knowledge reduction unit 712 adds a new hypothesis that unconditionally represents the first causal relationship to the extended knowledge DB 703 when the calculated condition ratio is greater than the threshold value for the first causal relationship is described, but the present invention is not limited thereto. For example, there may be a case where the knowledge reduction unit 712 does not add a new hypothesis that unconditionally represents the first causal relationship to the extended knowledge DB 703 when the calculated condition ratio is greater than the threshold value for the first causal relationship.

[0137] The hypothesis adding unit 713 extracts a new hypothesis added to the hypothesis DB 702 and adds it to the extended knowledge DB 703. If the new hypothesis added to the hypothesis DB 702 is not included in the hypothesis stored in the extended knowledge DB 703, the hypothesis adding unit 713 extracts the new hypothesis added to the hypothesis DB 702 and adds it to the extended knowledge DB 703. If the new hypothesis added to the hypothesis DB 702 is included in the hypothesis stored in the extended knowledge DB 703, the hypothesis adding unit 713 does not extract the new hypothesis added to the hypothesis DB 702.

[0138] (Operation Example of Information Processing Device 100)

[0139] Next, use Figure 8 to Figure 13 An example of the operation of the information processing device 100 is described. Figure 8 Operation Example 1 of the information processing device 100 will be described.

[0140] Figure 8 1 is an explanatory diagram showing an operation example 1 of the information processing device 100. Figure 8 In the example, the information processing device 100 has an extended knowledge DB 800. The extended knowledge DB 800 stores, for example, a hypothesis "X: A→B" representing a causal relationship "A→B" under condition X, a hypothesis "Y: A→B" representing a causal relationship "A→B" under condition Y, and a hypothesis "Z: A→B" representing a causal relationship "A→B" under condition Z.

[0141] For example, the extended knowledge DB 800 can also store a hypothesis "Φ: A→B" that represents the causal relationship "A→B" under undetermined conditions. Φ means that the conditions are undetermined. Specifically, although Φ is an undetermined condition, it is temporarily processed as a symbol representing the conditions of the full set Ω. Ω, for example, includes condition X, condition Y, and condition Z. Specifically, Ω includes all conditions.

[0142] For example, the information processing device 100 generates a hypothesis by associating a symbol Φ indicating an undetermined condition with a causal relationship represented by a hypothesis stored in the existing knowledge DB, and adds the hypothesis to the extended knowledge DB 800. Therefore, there is a case where the extended knowledge DB 800 stores the hypothesis "Φ: A→B". The extended knowledge DB 800 corresponds to the extended knowledge DB 500, for example.

[0143] The information processing device 100 reads out one or more hypotheses representing the causal relationship "A→B" under different conditions stored in the extended knowledge DB 800. For example, the information processing device 100 reads out a plurality of hypotheses including a hypothesis "X: A→B" representing the causal relationship "A→B" under condition X, a hypothesis "Y: A→B" representing the causal relationship "A→B" under condition Y, and a hypothesis "Z: A→B" representing the causal relationship "A→B" under condition Z.

[0144] The information processing device 100 calculates the condition ratio for the plurality of read hypotheses. For example, the information processing device 100 calculates the ratio of the union formed by combining the condition X, the condition Y, and the condition Z to the whole set Ω including the condition X, the condition Y, and the condition Z as the condition ratio. Specifically, the information processing device 100 calculates the ratio of the number of elements representing the conditions included in the union to the total number of elements representing the conditions included in the whole set Ω as the condition ratio. An example of calculating the condition ratio is described below.

[0145] The information processing device 100 determines whether the calculated condition ratio is above a threshold value. The threshold value is set in advance by the user, for example. The threshold value is, for example, 0<ε≤1. For example, when the calculated condition ratio is above the threshold value, the information processing device 100 adds the hypothesis "Ω: A→B" which unconditionally represents the causal relationship "A→B" to the extended knowledge DB 800. Ω means that the causal relationship "A→B" is judged to be established under any condition.

[0146] Thus, when the accuracy of the causal relationship "A→B" being established unconditionally is relatively high, the information processing device 100 can add the hypothesis "Ω: A→B" that unconditionally represents the causal relationship "A→B" to the extended knowledge DB 800. The information processing device 100 can appropriately update the storage content of the extended knowledge DB 800 so that the storage content of the extended knowledge DB 800 expresses the conditions under which the causal relationship "A→B" is established.

[0147] When the calculated condition ratio is greater than or equal to a threshold, the information processing device 100 deletes one or more read hypotheses from the extended knowledge DB 800. For example, when the calculated condition ratio is greater than or equal to a threshold, the information processing device 100 deletes the hypothesis "X: A→B", the hypothesis "Y: A→B", and the hypothesis "Z: A→B" from the extended knowledge DB 800.

[0148] Thus, the information processing device 100 determines that the hypothesis "X: A→B", the hypothesis "Y: A→B", and the hypothesis "Z: A→B" are included in the hypothesis "Ω: A→B", and can be determined not to be stored in the extended knowledge DB 800. The information processing device 100 can delete the hypothesis "X: A→B", the hypothesis "Y: A→B", and the hypothesis "Z: A→B" from the extended knowledge DB 800, and can suppress the increase in the amount of data in the extended knowledge DB 800.

[0149] For example, when the calculated condition ratio is greater than a threshold value, the information processing device 100 deletes the hypothesis "Φ: A→B" that indicates the causal relationship "A→B" under an undetermined condition from the extended knowledge DB 800. Thus, the information processing device 100 can suppress the increase in the amount of data in the extended knowledge DB 800. The information processing device 100 can appropriately update the storage content of the extended knowledge DB 800 so that the storage content of the extended knowledge DB 800 indicates that the condition under which the causal relationship "A→B" is established is not undetermined.

[0150] Then, the information processing device 100 obtains a new hypothesis "P: A→B" representing the causal relationship "A→B" under the condition P. The new hypothesis "P: A→B" is included in the hypothesis "Ω: A→B", so the information processing device 100 does not add the new hypothesis "P: A→B" to the extended knowledge DB 800 but discards it.

[0151] Thus, Ω indicates that the causal relationship "A→B" is determined to hold under any condition, so the information processing device 100 does not need to add the conditional causal relationship "A→B" to the extended knowledge DB 800. Thus, the information processing device 100 can suppress the increase in the amount of data in the extended knowledge DB 800.

[0152] The information processing device 100 can prevent the user from referring to both the hypothesis “Ω: A→B” and the hypothesis “P: A→B” when referring to the contents stored in the extended knowledge DB 800. Therefore, the information processing device 100 can prevent the user from misunderstanding the conditions under which the causal relationship “A→B” holds.

[0153] The information processing device 100 can prevent the user from being confused about which of the assumptions "Ω: A→B" and "P: A→B" is appropriate. The information processing device 100 can prevent the user from misunderstanding the conditions under which the causal relationship "A→B" is established by overlooking the assumption "Ω: A→B" and referring only to the assumption "P: A→B".

[0154] Here, an example of calculating the condition ratio is described. For example, there is a set Σ of all elements that express the condition. The set Σ is a set of all elements used to extract the assumptions of the extended knowledge DB800 without duplication. Here, it is set as Σ = {A, B, C, D, E}. The condition is expressed by a logical expression using one or more elements of Σ. For example, X = A∪B. The condition ratio of the union of conditions X, Y, Z... to the whole set Ω is expressed by Rate(X, Y, Z...; Ω) = |X∪Y∪Z∪...| / |Σ|. |X| is the number of elements covered by the logical expression X. |Σ| is the number of elements contained in Σ.

[0155] Specifically, consider the case where the condition X = A∪B and the condition Y = C∪D. In this case, Rate(X, Y;Ω) = |X∪Y| / |Σ| = |A∪B∪C∪D| / |{A, B, C, D, E}| = 4 / 5 = 0.8.

[0156] Specifically, consider the case where the conditions X = A∩C, Y = B∪C, and Z = D. In this case, X∪Y∪Z = (A∩C)∪(B∪C)∪D = (A∪B∪C∪D)∩(B∪C∪D) = B∪C∪D. Therefore, Rate(X, Y, Z; Ω) = |X∪Y∪Z| / |Σ| = |B∪C∪D| / |Σ| = 3 / 5 = 0.6. The information processing device 100 may also calculate the rate without considering the instance of the observed data related to the hypothesis. Next, use Fig. 9 Operation Example 2 of the information processing device 100 will be described.

[0157] Fig. 92 is an explanatory diagram showing an operation example 2 of the information processing device 100. Fig. 9 In the example, the information processing device 100 has an extended knowledge DB 900. The extended knowledge DB 900 stores, for example, a hypothesis "X: A→B" representing a causal relationship "A→B" under condition X, a hypothesis "Y: A→B" representing a causal relationship "A→B" under condition Y, and a hypothesis "Z: A→B" representing a causal relationship "A→B" under condition Z.

[0158] The information processing device 100 reads out one or more hypotheses representing the causal relationship "A→B" under different conditions stored in the extended knowledge DB 900. For example, the information processing device 100 reads out a plurality of hypotheses including a hypothesis "X:A→B" representing the causal relationship "A→B" under condition X, a hypothesis "Y:A→B" representing the causal relationship "A→B" under condition Y, and a hypothesis "Z:A→B" representing the causal relationship "A→B" under condition Z.

[0159] The information processing device 100 calculates the condition ratio for the plurality of read hypotheses. For example, the information processing device 100 calculates the ratio of the union formed by combining the condition X, the condition Y, and the condition Z to the full set Ω including the condition X, the condition Y, and the condition Z as the condition ratio. Specifically, the information processing device 100 calculates the ratio of the number of elements representing the conditions included in the union to the total number of elements representing the conditions included in the full set Ω as the condition ratio.

[0160] The information processing device 100 determines whether the calculated condition ratio is above a threshold value. The threshold value is set in advance by the user, for example. The threshold value is, for example, 0<ε≤1. For example, when the calculated condition ratio is above the threshold value, the information processing device 100 adds the hypothesis "Ω: A→B" that unconditionally represents the causal relationship "A→B" to the extended knowledge DB 900. Ω means that the causal relationship "A→B" is judged to be established under any condition.

[0161] Thus, when the accuracy of the causal relationship "A→B" being established unconditionally is relatively high, the information processing device 100 can add the hypothesis "Ω: A→B" that unconditionally represents the causal relationship "A→B" to the extended knowledge DB 900. The information processing device 100 can appropriately update the storage content of the extended knowledge DB 900 so that the storage content of the extended knowledge DB 900 expresses the conditions under which the causal relationship "A→B" is established.

[0162] When the calculated condition ratio is greater than or equal to a threshold, the information processing device 100 deletes one or more read hypotheses from the extended knowledge DB 900. For example, when the calculated condition ratio is greater than or equal to a threshold, the information processing device 100 deletes the hypothesis "X: A→B", the hypothesis "Y: A→B", and the hypothesis "Z: A→B" from the extended knowledge DB 900.

[0163] Thus, the information processing device 100 determines that the assumptions "X: A→B", "Y: A→B", and "Z: A→B" are included in the assumption "Ω: A→B", and can be determined not to be stored in the extended knowledge DB 900. The information processing device 100 can delete the assumptions "X: A→B", "Y: A→B", and "Z: A→B" from the extended knowledge DB 900, and can suppress the increase in the amount of data in the extended knowledge DB 900.

[0164] Then, the information processing device 100 obtains a new hypothesis "P: A→B" representing the causal relationship "A→B" under the condition P. The new hypothesis "P: A→B" is included in the hypothesis "Ω: A→B", so the information processing device 100 does not add the new hypothesis "P: A→B" to the extended knowledge DB 900 but discards it.

[0165] Thus, Ω indicates that the causal relationship "A→B" is determined to hold under any condition, so the information processing device 100 does not need to add the conditional causal relationship "A→B" to the extended knowledge DB 900. Thus, the information processing device 100 can suppress the increase in the amount of data in the extended knowledge DB 900.

[0166] The information processing device 100 can prevent the user from referring to both the hypothesis “Ω: A→B” and the hypothesis “P: A→B” when referring to the contents stored in the extended knowledge DB 900. Therefore, the information processing device 100 can prevent the user from misunderstanding the conditions under which the causal relationship “A→B” holds.

[0167] The information processing device 100 can prevent the user from being confused about which of the assumptions "Ω: A→B" and "P: A→B" is appropriate. The information processing device 100 can prevent the user from misunderstanding the conditions under which the causal relationship "A→B" is established by overlooking the assumption "Ω: A→B" and referring only to the assumption "P: A→B". Fig.10 Operation Example 3 of the information processing device 100 will be described.

[0168] Fig.10 3 is an explanatory diagram showing operation example 3 of the information processing device 100. Fig.10In the example, the information processing device 100 has an extended knowledge DB 1000. The extended knowledge DB 1000 stores, for example, a hypothesis "X: A→B" representing a causal relationship "A→B" under condition X, a hypothesis "Y: A→B" representing a causal relationship "A→B" under condition Y, and a hypothesis "Z: A→B" representing a causal relationship "A→B" under condition Z.

[0169] For example, the extended knowledge DB 1000 can also store a hypothesis "Φ: A→B" that represents the causal relationship "A→B" under undetermined conditions. Φ means that the conditions are undetermined. Specifically, although Φ is an undetermined condition, it is temporarily processed as a symbol representing the conditions of the full set Ω. Ω, for example, includes condition X, condition Y, and condition Z. Specifically, Ω includes all conditions.

[0170] For example, the information processing device 100 generates a hypothesis by associating a symbol Φ indicating an undetermined condition with a causal relationship represented by a hypothesis stored in the existing knowledge DB, and adds it to the extended knowledge DB 1000. Therefore, there is a case where the extended knowledge DB 1000 stores the hypothesis "Φ: A→B".

[0171] The information processing device 100 reads out one or more hypotheses representing the causal relationship "A→B" under different conditions stored in the extended knowledge DB 1000. For example, the information processing device 100 reads out a plurality of hypotheses including a hypothesis "X:A→B" representing the causal relationship "A→B" under condition X, a hypothesis "Y:A→B" representing the causal relationship "A→B" under condition Y, and a hypothesis "Z:A→B" representing the causal relationship "A→B" under condition Z.

[0172] The information processing device 100 calculates the condition ratio for the plurality of read hypotheses. For example, the information processing device 100 calculates the ratio of the union formed by combining the condition X, the condition Y, and the condition Z to the full set Ω including the condition X, the condition Y, and the condition Z as the condition ratio. Specifically, the information processing device 100 calculates the ratio of the number of elements representing the conditions included in the union to the total number of elements representing the conditions included in the full set Ω as the condition ratio.

[0173] The information processing device 100 determines whether the calculated condition ratio is above a threshold value. The threshold value is set in advance by the user, for example. The threshold value is, for example, 0<ε≤1. For example, when the calculated condition ratio is above the threshold value, the information processing device 100 deletes the hypothesis "Φ: A→B" representing the causal relationship "A→B" under an undetermined condition from the extended knowledge DB 1000. In this way, the information processing device 100 can suppress the increase in the amount of data in the extended knowledge DB 1000.

[0174] The information processing device 100 can appropriately update the storage content of the extended knowledge DB 1000 so that the storage content of the extended knowledge DB 1000 can distinguish between the conditions under which the causal relationship "A→B" is established and the undetermined conditions. The information processing device 100 can determine whether it is preferable to study under which conditions the causal relationship "A→B" is established, which can be helpful for future research.

[0175] Before the calculated condition ratio becomes equal to or greater than the threshold, the information processing device 100 determines that the causal relationship "A→B" is established unconditionally, although the condition is temporarily uncertain, and can keep the hypothesis "Φ: A→B" in the extended knowledge DB 1000. Therefore, the information processing device 100 can appropriately manage the extended knowledge DB 1000 in a manner that respects the hypothesis "Φ: A→B" obtained through existing research or the like.

[0176] Then, the information processing device 100 obtains a new hypothesis "P: A→B" that represents the causal relationship "A→B" under the condition P. The new hypothesis "P: A→B" is not included in the hypothesis stored in the extended knowledge DB 1000, so the information processing device 100 adds the new hypothesis "P: A→B" to the extended knowledge DB 1000. Thus, the information processing device 100 can appropriately update the extended knowledge DB 1000.

[0177] As shown above, the information processing device 100 can use the symbol Φ indicating an undetermined condition to import the hypothesis stored in the existing knowledge DB into the extended knowledge DB without contradiction. When the information processing device 100 accumulates a large number of hypotheses representing the same causal relationship under different conditions in the extended knowledge DB, the symbol Ω indicating the whole set can be used to integrate the hypothesis, thereby suppressing the increase in the amount of data in the extended knowledge DB.

[0178] When the information processing device 100 accumulates a large number of hypotheses representing the same causal relationship under different conditions in the extended knowledge DB, the information processing device 100 can delete the hypotheses using the symbol Φ that temporarily represents the entire set, thereby suppressing the increase in the amount of data in the extended knowledge DB. The information processing device 100 can also selectively implement the update policy of the extended knowledge DB according to the user's update policy. Figure 8 as well as Fig. 9 The actions shown and Fig.10 Action shown.

[0179] exist Figure 8 as well as Fig. 9In the example of , the information processing device 100 uses a plurality of assumptions of conditions X, Y, and Z included in the full set Ω in the assumption that the full set Ω includes all conditions, but the present invention is not limited to this. For example, there may be a case where the information processing device 100 uses a plurality of assumptions of conditions X1, X2, and X3 included in the condition XΩ in the assumption that the condition XΩ is used. Specifically, in this case, Fig.11 as well as Fig.12 To be described later.

[0180] Similarly, in Fig.10 In the example, the information processing device 100 determines whether to delete the assumption that the condition of the entire set Ω is temporarily represented and the symbol Φ of the condition is used based on the number of determined conditional assumptions, but the present invention is not limited to this. For example, there may be a case where the information processing device 100 determines whether to delete the assumption that the condition XΩ is temporarily represented and the symbol XΦ of the condition is used based on the number of determined conditional assumptions contained in the condition XΩ. In this case, specifically, using Fig.13 Next, use Fig.11 Operation Example 4 of the information processing device 100 will be described.

[0181] Fig.11 4 is an explanatory diagram showing an operation example 4 of the information processing device 100. Fig.11 In the example, the information processing device 100 has an extended knowledge DB 1100. The extended knowledge DB 1100 stores, for example, a hypothesis "X1: A→B" representing a causal relationship "A→B" under a condition X1, a hypothesis "X2: A→B" representing a causal relationship "A→B" under a condition X2, and a hypothesis "X3: A→B" representing a causal relationship "A→B" under a condition X3.

[0182] For example, the extended knowledge DB 1100 may also store a hypothesis "XΦ: A→B" that temporarily represents the causal relationship "A→B" under the condition XΩ when the condition is not determined. XΦ indicates that the condition is not determined. Specifically, although XΦ is an undetermined condition, it is temporarily processed as a symbol of the condition representing the condition XΩ. XΩ includes, for example, condition X1, condition X2, and condition X3. XΩ may also include other conditions Xi. i=4, 5, ...

[0183] For example, it is considered that the information processing device 100 generates a hypothesis by associating a symbol XΦ indicating that the condition is undetermined in the condition X with a causal relationship temporarily processed as being established under the condition XΩ represented by the hypothesis stored in the existing knowledge DB, and adds it to the extended knowledge DB 1100. Therefore, there is a case where the extended knowledge DB 1100 stores the hypothesis "Φ: A→B".

[0184] The information processing device 100 reads out one or more hypotheses of the causal relationship "A→B" under different conditions included in the expression condition XΩ stored in the extended knowledge DB 1100. For example, the information processing device 100 reads out a plurality of hypotheses including a hypothesis "X1: A→B" representing the causal relationship "A→B", a hypothesis "X2: A→B" representing the causal relationship "A→B", and a hypothesis "X3: A→B" representing the causal relationship "A→B".

[0185] The information processing device 100 calculates the condition ratio for the plurality of read hypotheses. For example, the information processing device 100 calculates the ratio of the union of the conditions X1, X2, and X3 to the condition XΩ including the conditions X1, X2, and X3 as the condition ratio. Specifically, the information processing device 100 calculates the ratio of the number of elements representing the conditions included in the union to the total number of elements representing the conditions included in the condition XΩ as the condition ratio.

[0186] The information processing device 100 determines whether the calculated condition ratio is above a threshold value. The threshold value is set in advance by the user, for example. The threshold value is, for example, 0<ε≤1. For example, when the calculated condition ratio is above the threshold value, the information processing device 100 determines that the causal relationship "A→B" is established under the condition XΩ, and adds the hypothesis "XΩ: A→B" that unconditionally represents the causal relationship "A→B" in the condition XΩ to the extended knowledge DB1100. XΩ indicates that the causal relationship "A→B" is determined to be established under any condition in the condition XΩ.

[0187] Thus, when the accuracy of the causal relationship "A→B" being established unconditionally within the condition XΩ is relatively high, the information processing device 100 can add the hypothesis "XΩ: A→B" that unconditionally expresses the causal relationship "A→B" within the condition XΩ to the extended knowledge DB 1100. The information processing device 100 can appropriately update the storage content of the extended knowledge DB 1100 so that the storage content of the extended knowledge DB 1100 expresses the conditions under which the causal relationship "A→B" is established.

[0188] When the calculated condition ratio is greater than or equal to a threshold, the information processing device 100 deletes one or more read hypotheses from the extended knowledge DB 1100. For example, when the calculated condition ratio is greater than or equal to a threshold, the information processing device 100 deletes the hypothesis "X1: A→B", the hypothesis "X2: A→B", and the hypothesis "X3: A→B" from the extended knowledge DB 1100.

[0189] Thus, the information processing device 100 determines that the assumptions "X1: A→B", "X2: A→B", and "X3: A→B" are included in the assumption "XΩ: A→B", and can be determined not to be stored in the extended knowledge DB 1100. The information processing device 100 can delete the assumptions "X1: A→B", "X2: A→B", and "X3: A→B" from the extended knowledge DB 1100, and can suppress the increase in the amount of data in the extended knowledge DB 1100.

[0190] For example, when the calculated condition ratio is greater than a threshold value, the information processing device 100 deletes the hypothesis "XΦ: A→B" temporarily indicating the causal relationship "A→B" under the condition XΩ when the condition is not determined from the extended knowledge DB 1100. Thus, the information processing device 100 can suppress the increase in the amount of data in the extended knowledge DB 1100. The information processing device 100 can appropriately update the storage content of the extended knowledge DB 1100 so that the storage content of the extended knowledge DB 1100 indicates that the condition under which the causal relationship "A→B" is established is not undetermined.

[0191] Then, the information processing device 100 obtains a new hypothesis "XP: A→B" representing the causal relationship "A→B" under the condition XP. The new hypothesis "XP: A→B" is included in the hypothesis "XΩ: A→B", so the information processing device 100 does not add the new hypothesis "XP: A→B" to the extended knowledge DB 1100 but discards it.

[0192] Thus, XΩ indicates that the causal relationship "A→B" is determined to be established under any condition in the condition XΩ, so the information processing device 100 does not need to add the conditional causal relationship "A→B" included in the condition XΩ to the extended knowledge DB 1100. Thus, the information processing device 100 can suppress the increase in the amount of data in the extended knowledge DB 1100.

[0193] The information processing device 100 can prevent the user from referring to both the hypothesis "XΩ: A→B" and the hypothesis "XP: A→B" when referring to the contents stored in the extended knowledge DB 1100. Therefore, the information processing device 100 can prevent the user from misunderstanding the conditions under which the causal relationship "A→B" is established.

[0194] The information processing device 100 can prevent the user from being confused about which of the assumptions "XΩ: A→B" and "XP: A→B" is appropriate. The information processing device 100 can prevent the user from misunderstanding the conditions under which the causal relationship "A→B" is established by overlooking the assumption "XΩ: A→B" and referring only to the assumption "XP: A→B". Fig.12 Operation Example 5 of the information processing device 100 will be described.

[0195] Fig.12 is an explanatory diagram showing an operation example 5 of the information processing device 100. Fig.12 In the example, the information processing device 100 has an extended knowledge DB 1200. The extended knowledge DB 1200 stores, for example, a hypothesis "X1: A→B" representing a causal relationship "A→B" under condition X1, a hypothesis "X2: A→B" representing a causal relationship "A→B" under condition X2, and a hypothesis "X3: A→B" representing a causal relationship "A→B" under condition X3.

[0196] The information processing device 100 reads out one or more hypotheses representing the causal relationship "A→B" under different conditions included in the condition XΩ, which are stored in the extended knowledge DB 1200. For example, the information processing device 100 reads out a plurality of hypotheses including a hypothesis "X1: A→B" representing the causal relationship "A→B", a hypothesis "X2: A→B" representing the causal relationship "A→B", and a hypothesis "X3: A→B" representing the causal relationship "A→B".

[0197] The information processing device 100 calculates the condition ratio for the plurality of read hypotheses. For example, the information processing device 100 calculates the ratio of the union of the conditions X1, X2, and X3 to the condition XΩ including the conditions X1, X2, and X3 as the condition ratio. Specifically, the information processing device 100 calculates the ratio of the number of elements representing the conditions included in the union to the total number of elements representing the conditions included in the condition XΩ as the condition ratio.

[0198] The information processing device 100 determines whether the calculated condition ratio is above a threshold value. The threshold value is set in advance by the user, for example. The threshold value is, for example, 0<ε≤1. For example, when the calculated condition ratio is above the threshold value, the information processing device 100 adds the hypothesis "XΩ: A→B" that unconditionally represents the causal relationship "A→B" in the condition XΩ to the extended knowledge DB 1200. XΩ indicates that the causal relationship "A→B" is judged to be established under any condition in the condition XΩ.

[0199] Thus, when the accuracy of the causal relationship "A→B" being established unconditionally within the condition XΩ is relatively high, the information processing device 100 can add the hypothesis "XΩ: A→B" that unconditionally expresses the causal relationship "A→B" within the condition XΩ to the extended knowledge DB 1200. The information processing device 100 can appropriately update the storage content of the extended knowledge DB 1200 so that the storage content of the extended knowledge DB 1200 expresses the conditions under which the causal relationship "A→B" is established.

[0200] When the calculated condition ratio is greater than or equal to a threshold, the information processing device 100 deletes one or more read hypotheses from the extended knowledge DB 1200. For example, when the calculated condition ratio is greater than or equal to a threshold, the information processing device 100 deletes the hypothesis "X1: A→B", the hypothesis "X2: A→B", and the hypothesis "X3: A→B" from the extended knowledge DB 1200.

[0201] Thus, the information processing device 100 determines that the assumptions "X1: A→B", "X2: A→B", and "X3: A→B" are included in the assumption "XΩ: A→B", and can be determined not to be stored in the extended knowledge DB 1200. The information processing device 100 can delete the assumptions "X1: A→B", "X2: A→B", and "X3: A→B" from the extended knowledge DB 1200, and can suppress the increase in the amount of data in the extended knowledge DB 1200.

[0202] Then, the information processing device 100 obtains a new hypothesis "XP: A→B" representing the causal relationship "A→B" under the condition XP. The new hypothesis "XP: A→B" is included in the hypothesis "XΩ: A→B", so the information processing device 100 does not add the new hypothesis "XP: A→B" to the extended knowledge DB 1200 but discards it.

[0203] Thus, XΩ indicates that the causal relationship "A→B" is determined to be established under any condition, so the information processing device 100 does not need to add the conditional causal relationship "A→B" to the extended knowledge DB 1200. Thus, the information processing device 100 can suppress the increase in the amount of data in the extended knowledge DB 1200.

[0204] The information processing device 100 can prevent the user from referring to both the hypothesis "XΩ: A→B" and the hypothesis "XP: A→B" when referring to the contents stored in the extended knowledge DB 1200. Therefore, the information processing device 100 can prevent the user from misunderstanding the conditions under which the causal relationship "A→B" holds.

[0205] The information processing device 100 can prevent the user from being confused about which of the assumptions "XΩ: A→B" and "XP: A→B" is appropriate. The information processing device 100 can prevent the user from misunderstanding the conditions under which the causal relationship "A→B" is established by overlooking the assumption "XΩ: A→B" and referring only to the assumption "XP: A→B". Fig.13 Operation Example 6 of the information processing device 100 will be described.

[0206] Fig.13 is an explanatory diagram showing an operation example 6 of the information processing device 100. Fig.13In the example, the information processing device 100 has an extended knowledge DB 1300. The extended knowledge DB 1300 stores, for example, a hypothesis "X1: A→B" representing a causal relationship "A→B" under a condition X1, a hypothesis "X2: A→B" representing a causal relationship "A→B" under a condition X2, and a hypothesis "X3: A→B" representing a causal relationship "A→B" under a condition X3.

[0207] For example, the extended knowledge DB 1300 may also store a hypothesis "XΦ: A→B" that temporarily represents the causal relationship "A→B" under the condition XΩ when the condition is not determined. XΦ indicates that the condition is not determined. Specifically, although XΦ is an undetermined condition, it is temporarily processed as a symbol of the condition representing the condition XΩ. XΩ includes, for example, condition X1, condition X2, and condition X3. XΩ may also include other conditions Xi. i=4, 5, ...

[0208] For example, it is considered that the information processing device 100 generates a hypothesis by associating a symbol XΦ indicating that the condition is undetermined in the condition X with a causal relationship temporarily processed as being established under the condition XΩ represented by the hypothesis stored in the existing knowledge DB, and adds it to the extended knowledge DB 1300. Therefore, there is a case where the extended knowledge DB 1300 stores the hypothesis "Φ: A→B".

[0209] The information processing device 100 reads out one or more hypotheses representing the causal relationship "A→B" under different conditions included in the condition XΩ, which are stored in the extended knowledge DB 1300. For example, the information processing device 100 reads out a plurality of hypotheses including a hypothesis "X1: A→B" representing the causal relationship "A→B", a hypothesis "X2: A→B" representing the causal relationship "A→B", and a hypothesis "X3: A→B" representing the causal relationship "A→B".

[0210] The information processing device 100 calculates the condition ratio for the plurality of read hypotheses. For example, the information processing device 100 calculates the ratio of the union of the conditions X1, X2, and X3 to the condition XΩ including the conditions X1, X2, and X3 as the condition ratio. Specifically, the information processing device 100 calculates the ratio of the number of elements representing the conditions included in the union to the total number of elements representing the conditions included in the condition XΩ as the condition ratio.

[0211] The information processing device 100 determines whether the calculated condition ratio is above a threshold value. The threshold value is set in advance by the user, for example. The threshold value is, for example, 0<ε≤1. For example, when the calculated condition ratio is above the threshold value, the information processing device 100 deletes the hypothesis "XΦ: A→B" temporarily representing the causal relationship "A→B" under the condition XΩ when the condition is not determined from the extended knowledge DB 1300. In this way, the information processing device 100 can suppress the increase in the amount of data in the extended knowledge DB 1300.

[0212] The information processing device 100 can appropriately update the storage content of the extended knowledge DB 1300 so that the storage content of the extended knowledge DB 1300 can distinguish between the conditions under which the causal relationship "A→B" is established and the undetermined conditions. The information processing device 100 can determine whether it is preferable to study under which conditions the causal relationship "A→B" is established, which can be helpful for future research.

[0213] Before the calculated condition ratio becomes equal to or greater than the threshold, the information processing device 100 temporarily determines that the causal relationship "A→B" is temporarily established unconditionally within the condition XΩ under the condition that is not determined, and can keep the hypothesis "XΦ: A→B" in the extended knowledge DB 1300. Therefore, the information processing device 100 can appropriately manage the extended knowledge DB 1300 so as to respect the hypothesis "XΦ: A→B" obtained through existing research or the like.

[0214] Then, the information processing device 100 obtains a new hypothesis "X4: A→B" representing the causal relationship "A→B" under condition X4. The new hypothesis "X4: A→B" is not included in the hypothesis stored in the extended knowledge DB 1300, so the information processing device 100 adds the new hypothesis "X4: A→B" to the extended knowledge DB 1300. Thus, the information processing device 100 can appropriately update the extended knowledge DB 1300.

[0215] As shown above, the information processing device 100 can import the hypothesis stored in the existing knowledge DB into the extended knowledge DB without contradiction by using the symbol XΦ indicating an undetermined condition. When the information processing device 100 accumulates a large number of hypotheses representing the same causal relationship under different conditions included in the condition XΩ in the extended knowledge DB, the information processing device 100 can integrate the hypothesis by using the symbol XΩ indicating the condition. Therefore, the information processing device 100 can suppress the increase in the amount of data in the extended knowledge DB.

[0216] When the information processing device 100 accumulates a relatively large number of hypotheses representing the same causal relationship under different conditions included in the condition XΩ in the extended knowledge DB, the information processing device 100 can delete the hypothesis using the symbol XΦ temporarily representing the condition XΩ. Therefore, the information processing device 100 can suppress the increase in the amount of data in the extended knowledge DB. The information processing device 100 can also selectively implement the update policy of the extended knowledge DB according to the user's update policy. Fig.11 as well as Fig.12 The actions shown and Fig.13 Action shown.

[0217] (First additional processing step)

[0218] Next, use Fig.14An example of the first additional processing steps performed by the information processing device 100 is described below. The first additional processing is, for example, Figure 4 The CPU 401, memory 402, storage areas such as a recording medium 405, and a network I / F 403 are shown to realize the same.

[0219] Fig.14 is a flowchart showing an example of the first additional processing step. Fig.14 In step S1401 , the current extended knowledge DB is set to “D”. First, the information processing device 100 receives an input of a hypothesis “P: A→B” (step S1401 ).

[0220] Next, the information processing device 100 determines whether there is a record of the assumption "P: A→B" in D (step S1402). Here, if there is a record (step S1402: Yes), the information processing device 100 moves to the process of step S1404. On the other hand, if there is no record (step S1402: No), the information processing device 100 moves to the process of step S1403.

[0221] In step S1403, the information processing device 100 generates a record of the assumption "P: A→B" and appends it to D (step S1403). Next, the information processing device 100 outputs D (step S1404). Then, the information processing device 100 ends the first appending process. Thus, the information processing device 100 can appropriately update the extended knowledge DB.

[0222] (First reduction process step)

[0223] Next, use Fig.15 An example of the first reduction process performed by the information processing device 100 is described below. The first reduction process is performed by, for example, Figure 4 The CPU 401, memory 402, storage areas such as a recording medium 405, and a network I / F 403 are shown to realize the same.

[0224] Fig.15 is a flowchart showing an example of the first reduction process step. Fig.15 In step S1501, the current extended knowledge DB is set to "D1". The information processing device 100 prepares an empty extended knowledge DB "D2". First, the information processing device 100 determines whether there is a record in D1 (step S1501).

[0225] Here, if there is no record (step S1501: No), the information processing apparatus 100 proceeds to the process of step S1507. On the other hand, if there is a record (step S1501: Yes), the information processing apparatus 100 proceeds to the process of step S1502.

[0226] In step S1502, the information processing device 100 extracts one or more records indicating the same causal relationship "A→B" from D1 and deletes them from D1 (step S1502). Next, the information processing device 100 calculates the condition ratio based on the extracted one or more records (step S1503).

[0227] Then, the information processing device 100 determines whether the calculated condition ratio is ≥ε (step S1504). Here, if the condition ratio is ≥ε (step S1504: Yes), the information processing device 100 moves to the process of step S1506. On the other hand, if the condition ratio is <ε (step S1504: No), the information processing device 100 moves to the process of step S1505.

[0228] In step S1505, the information processing device 100 adds the extracted one or more records to D2 (step S1505). Then, the information processing device 100 returns to the process of step S1501.

[0229] In step S1506, the information processing device 100 adds a new record indicating the causal relationship "Ω: A→B" which is a collection of the extracted one or more records to D2 (step S1506). Then, the information processing device 100 returns to the process of step S1501.

[0230] In step S1507, the information processing device 100 outputs D2 (step S1507). Then, the information processing device 100 ends the first reduction process. Thus, the information processing device 100 can suppress the increase in the amount of data in the knowledge DB.

[0231] (Second additional processing step)

[0232] Next, use Fig.16 An example of the second additional processing steps performed by the information processing device 100 is described below. The second additional processing is, for example, Figure 4 The CPU 401, memory 402, storage areas such as recording medium 405, and network I / F 403 shown are implemented.

[0233] Fig.16 is a flowchart showing an example of the second additional processing steps. Fig.16 In step S1601 , the current extended knowledge DB is set to “D”. First, the information processing device 100 receives an input of a hypothesis “P: A→B” (step S1601 ).

[0234] Next, the information processing device 100 determines whether there is at least one of a record assuming "P: A→B" or a record assuming "Ω: A→B" in D (step S1602). Here, if there is a record (step S1602: Yes), the information processing device 100 moves to the process of step S1604. On the other hand, if there is no record (step S1602: No), the information processing device 100 moves to the process of step S1603.

[0235] In step S1603, the information processing device 100 generates a record of the assumption "P: A→B" and appends it to D (step S1603). Next, the information processing device 100 outputs D (step S1604). Then, the information processing device 100 ends the second appending process. Thus, the information processing device 100 can appropriately update the extended knowledge DB.

[0236] (Second reduction process step)

[0237] Next, use Fig.17 An example of the second reduction process performed by the information processing device 100 is described below. The second reduction process is performed by, for example, Figure 4 The CPU 401, memory 402, storage areas such as recording medium 405, and network I / F 403 shown are implemented.

[0238] Fig.17 is a flowchart showing an example of the second reduction process step. Fig.17 In the example, the current extended knowledge DB is set to "D1". The information processing device 100 prepares an empty extended knowledge DB "D2".

[0239] First, the information processing device 100 determines whether there is a record in D1 (step S1701). Here, if there is no record (step S1701: No), the information processing device 100 moves to the process of step S1708. On the other hand, if there is a record (step S1701: Yes), the information processing device 100 moves to the process of step S1702.

[0240] In step S1702, the information processing device 100 extracts one or more records indicating the same causal relationship "A→B" from D1 and deletes them from D1 (step S1702). Next, the information processing device 100 calculates the condition ratio based on the extracted one or more records (step S1703).

[0241] Then, the information processing device 100 determines whether the calculated condition ratio is ≥ε (step S1704). Here, when the condition ratio is ≥ε (step S1704: Yes), the information processing device 100 moves to the process of step S1705. On the other hand, when the condition ratio is <ε (step S1704: No), the information processing device 100 moves to the process of step S1706.

[0242] In step S1705, the information processing device 100 determines whether there is a record of the condition Φ among the one or more extracted records (step S1705). Here, if there is no record (step S1705: No), the information processing device 100 moves to the processing of step S1706. On the other hand, if there is a record (step S1705: Yes), the information processing device 100 moves to the processing of step S1707.

[0243] In step S1706, the information processing device 100 adds the extracted one or more records to D2 (step S1706). Then, the information processing device 100 returns to the process of step S1701.

[0244] In step S1707, the information processing device 100 adds records other than the records satisfying the condition Φ among the one or more extracted records to D2 (step S1707). Then, the information processing device 100 returns to the process of step S1701.

[0245] In step S1708, the information processing device 100 outputs D2 (step S1708). Then, the information processing device 100 ends the second reduction process. Thus, the information processing device 100 can suppress the increase in the amount of data in the knowledge DB.

[0246] Here, the information processing device 100 may also Figure 14 to Figure 17 The information processing device 100 may also omit the processing sequence of some steps in each flowchart. Figure 14 to Figure 17 Processing of some steps in each flowchart.

[0247] As described above, according to the information processing device 100, for a plurality of hypotheses representing the same first causal relationship under respectively different conditions stored in the storage unit, the ratio of the union formed by synthesizing the respectively different conditions to the whole set can be calculated. According to the information processing device 100, it can be determined whether the calculated ratio is above a threshold value. According to the information processing device 100, when the ratio is above the threshold value, a first hypothesis that is different from the plurality of hypotheses and that unconditionally represents the first causal relationship in the whole set can be added to the storage unit. Thus, the information processing device 100 can appropriately update the storage unit.

[0248] According to the information processing device 100, when the ratio is equal to or greater than a threshold value, a plurality of hypotheses can be deleted from the storage unit. Thus, the information processing device 100 can suppress an increase in the amount of data in the storage unit.

[0249] According to the information processing device 100, when the ratio is greater than a threshold value, if a second hypothesis that is different from the plurality of hypotheses and represents the first causal relationship under undetermined conditions is stored in the storage unit, the second hypothesis can be deleted from the storage unit. Thus, the information processing device 100 can suppress an increase in the amount of data in the storage unit.

[0250] According to the information processing device 100, it is possible to accept input of a third hypothesis that is different from the plurality of hypotheses and represents a first causal relationship under new conditions. According to the information processing device 100, when the input of the third hypothesis is accepted, if the first hypothesis is not stored in the storage unit, the input third hypothesis can be added to the storage unit. According to the information processing device 100, when the input of the third hypothesis is accepted, if the first hypothesis is stored in the storage unit, the input third hypothesis can be discarded. Thus, the information processing device 100 can appropriately update the storage unit and suppress the increase in the amount of data in the storage unit.

[0251] According to the information processing device 100, for a plurality of hypotheses stored in the storage unit, the ratio of the number of elements used for the union to the number of elements that can be used to express the condition can be calculated. According to the information processing device 100, it can be determined whether the calculated ratio is greater than a threshold value. Thus, the information processing device 100 can calculate the ratio with high accuracy.

[0252] According to the information processing device 100, the storage content of the storage unit can be output. The information processing device 100 can use the storage content of the storage unit. The information processing device 100 can allow the user to refer to the storage content of the storage unit.

[0253] According to the information processing device 100, for a plurality of hypotheses representing the same first causal relationship under the respectively different conditions included in the first condition stored in the storage unit, it is possible to calculate the ratio of the union formed by synthesizing the respectively different conditions to the first condition. According to the information processing device 100, it is possible to determine whether the calculated ratio is above a threshold value. According to the information processing device 100, when the ratio is above the threshold value, it is possible to add a first hypothesis that is different from the plurality of hypotheses and unconditionally represents the first causal relationship in the first condition to the storage unit. Thus, the information processing device 100 can appropriately update the storage unit.

[0254] According to the information processing device 100, when the ratio is greater than or equal to a threshold value, if a second hypothesis different from the plurality of hypotheses and temporarily representing the first causal relationship under the first condition when the condition is not determined is stored in the storage unit, the second hypothesis can be deleted from the storage unit. Thus, the information processing device 100 can suppress an increase in the amount of data in the storage unit.

[0255] According to the information processing device 100, for a plurality of hypotheses representing the same first causal relationship under different conditions stored in the storage unit, it is possible to calculate the ratio of the union formed by synthesizing the different conditions to the full set containing the different conditions. According to the information processing device 100, it is possible to determine whether the calculated ratio is above a threshold. According to the information processing device 100, when the ratio is above the threshold, if a hypothesis representing the first causal relationship under undetermined conditions that is different from the plurality of hypotheses is stored in the storage unit, the hypothesis can be deleted from the storage unit. Thus, the information processing device 100 can suppress the increase in the amount of data in the storage unit.

[0256] In addition, the information processing method described in this embodiment can be implemented by executing a pre-prepared program by a computer such as a PC or a workstation. The information processing program described in this embodiment is recorded in a computer-readable recording medium and is executed by reading it out from the recording medium using a computer. The recording medium is a hard disk, a floppy disk, a CD (CompactDisc: optical disk)-ROM, an MO (Magneto Optical Disc: magnetic optical disk), a DVD (Digital Versatile Disc: digital versatile disc), etc. In addition, the information processing program described in this embodiment can also be distributed via a network such as the Internet.

[0257] Description of Reference Numerals

[0258] 100…information processing device; 101, 201, 311, 600…storage unit; 300…information processing system; 301…knowledge learning device; 302…client device; 310…network; 400…bus; 401…CPU; 402…memory; 403…network I / F; 404…recording medium I / F; 405…recording medium; 601…acquisition unit; 602…judgment unit; 603…update unit; 604…output unit; 701…knowledge DB; 702…hypothesis DB; 703, 800, 900, 1000, 1100, 1200, 1300…extended knowledge DB; 711…condition ratio calculation unit; 712…knowledge reduction unit; 713…hypothesis addition unit; 721…condition assignment unit; 722…knowledge comparison unit.

Claims

1. An information processing program, characterized in that: The computer is made to execute the following processing: For a plurality of hypotheses representing the same first causal relationship under respectively different conditions, determining whether a ratio of a union formed by synthesizing the respectively different conditions to a full set including the respectively different conditions is greater than a threshold, wherein the plurality of hypotheses are stored in a storage unit storing hypotheses representing causal relationships between elements, When the ratio is equal to or greater than the threshold, a first hypothesis that is different from the plurality of hypotheses and that unconditionally expresses the first causal relationship in the entire set is added to the storage unit.

2. The information processing program according to claim 1, characterized in that The computer is caused to execute the following processing: When the ratio is equal to or greater than the threshold, the plurality of hypotheses are deleted from the storage unit.

3. The information processing program according to claim 2, characterized in that The computer is caused to execute the following processing: When the ratio is equal to or greater than the threshold, if a second hypothesis different from the plurality of hypotheses and representing the first causal relationship under undetermined conditions is stored in the storage unit, the second hypothesis is deleted from the storage unit.

4. The information processing program according to any one of claims 1 to 3, characterized in that: The computer is caused to execute the following processing: When receiving input of a third hypothesis (P: A→B) that is different from the multiple hypotheses and represents the first causal relationship under new conditions, if the first hypothesis is not stored in the storage unit, the input third hypothesis is added to the storage unit; if the first hypothesis is stored in the storage unit, the input third hypothesis is discarded.

5. The information processing program according to any one of claims 1 to 3, characterized in that: The different conditions are represented by a combination of one or more elements. The program causes the computer to execute the following processing: For the plurality of hypotheses stored in the storage unit, calculating a ratio of the number of elements used in the union to the number of elements that can be used to express the condition, In the determination process, it is determined whether the calculated ratio is equal to or greater than the threshold value.

6. The information processing program according to any one of claims 1 to 3, characterized in that: The computer is caused to execute the following processing: The storage content of the storage unit is output.

7. The information processing program according to claim 1 or 2, characterized in that: The plurality of hypotheses represent the same first causal relationship under respectively different conditions included in the first condition, In the process of performing the determination, for the plurality of hypotheses stored in the storage unit, it is determined whether a ratio of a union of the respectively different conditions to the first condition is greater than a threshold value, In the process of performing the adding, when the ratio is equal to or greater than the threshold value, a first hypothesis that is different from the plurality of hypotheses and unconditionally expresses the first causal relationship within the first condition is added to the storage unit.

8. The information processing program according to claim 7, characterized in that The computer is caused to execute the following processing: When the ratio is equal to or greater than the threshold, if a second hypothesis different from the plurality of hypotheses and temporarily representing the first causal relationship under the first condition when conditions are not determined is stored in the storage unit, the second hypothesis is deleted from the storage unit.

9. An information processing method, characterized in that: The following processing is performed by a computer: For a plurality of hypotheses (X: A→B, Y: A→B, Z: A→B) representing the same first causal relationship under respectively different conditions, determining whether a ratio of a union formed by synthesizing the respectively different conditions to a whole set including the respectively different conditions is greater than a threshold, wherein the plurality of hypotheses are stored in a storage unit storing hypotheses representing causal relationships between elements, When the ratio is equal to or greater than the threshold, a first hypothesis (Ω: A→B) that is different from the plurality of hypotheses and unconditionally represents the first causal relationship in the entire set is added to the storage unit.

10. An information processing device, characterized in that: A control unit is provided. For a plurality of hypotheses (X: A→B, Y: A→B, Z: A→B) representing the same first causal relationship under respectively different conditions, determining whether a ratio of a union formed by synthesizing the respectively different conditions to a whole set including the respectively different conditions is greater than a threshold, wherein the plurality of hypotheses are stored in a storage unit storing hypotheses representing causal relationships between elements, When the ratio is equal to or greater than the threshold, a first hypothesis (Ω: A→B) that is different from the plurality of hypotheses and unconditionally represents the first causal relationship in the entire set is added to the storage unit.

11. An information processing program, characterized in that: The computer is made to execute the following processing: For a plurality of hypotheses (X: A→B, Y: A→B, Z: A→B) representing the same first causal relationship under respectively different conditions, determining whether a ratio of a union formed by synthesizing the respectively different conditions to a whole set including the respectively different conditions is greater than a threshold, wherein the plurality of hypotheses are stored in a storage unit storing hypotheses representing causal relationships between elements, When the ratio is equal to or greater than the threshold, if a hypothesis that is different from the plurality of hypotheses and represents the first causal relationship under undetermined conditions is stored in the storage unit, the hypothesis is deleted from the storage unit.

12. An information processing method, characterized in that: The following processing is performed by a computer: For a plurality of hypotheses (X: A→B, Y: A→B, Z: A→B) representing the same first causal relationship under respectively different conditions, determining whether a ratio of a union formed by synthesizing the respectively different conditions to a whole set including the respectively different conditions is greater than a threshold, wherein the plurality of hypotheses are stored in a storage unit storing hypotheses representing causal relationships between elements, When the ratio is equal to or greater than the threshold, if a hypothesis that is different from the plurality of hypotheses and represents the first causal relationship under undetermined conditions is stored in the storage unit, the hypothesis is deleted from the storage unit.

13. An information processing device, characterized in that: A control unit is provided. For a plurality of hypotheses (X: A→B, Y: A→B, Z: A→B) representing the same first causal relationship under respectively different conditions, determining whether a ratio of a union formed by synthesizing the respectively different conditions to a whole set including the respectively different conditions is greater than a threshold, wherein the plurality of hypotheses are stored in a storage unit storing hypotheses representing causal relationships between elements, When the ratio is equal to or greater than the threshold, if a hypothesis different from the plurality of hypotheses and representing the first causal relationship under undetermined conditions is stored in the storage unit, the hypothesis is deleted from the storage unit.

Images