Determination device, determination method, and determination program
The determination device accurately compares documents of higher and lower concepts by using a concept correspondence table to evaluate matching template variables, addressing the challenge of distinguishing between obligations and prohibitions in rule-based documents.
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2022-06-08
- Publication Date
- 2026-03-04
AI Technical Summary
Conventional techniques struggle to accurately compare documents of higher and lower concepts regarding rules, particularly in distinguishing between obligations and prohibitions, leading to incorrect determinations of compliance.
A determination device that utilizes a memory unit to store correspondence relationships between words representing higher and lower concepts, an extraction unit to identify matching template variables, and an evaluation unit to assess these relationships using a concept correspondence table.
Enables accurate determination of whether a document of a lower concept complies with a document of a higher concept by accounting for differences in wording and eliminating confusing patterns.
Smart Images

Figure 0007823740000001 
Figure 0007823740000002 
Figure 0007823740000003
Abstract
Description
[Technical Field]
[0001] The present invention relates to a determination device, a determination method, and a determination program. [Background technology]
[0002] When estimating whether a document of a lower concept conforms to a document of a higher concept regarding a rule, the two documents are compared to evaluate the relationship. Conventionally, a technique for comparing two documents to evaluate the relationship is known in which the similarity of words is quantified and documents that share highly similar words are determined to be similar (see Patent Document 1 and Non-Patent Document 1). [Prior art documents] [Patent documents]
[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2007-26116 [Non-patent literature]
[0004] [Non-Patent Document 1] Kazuya Uno, "Introduction to Natural Language Processing: Similar Document Search Methods and Accuracy Comparison," [online], March 2019, OGIS Research Institute, [Retrieved April 12, 2022], Internet<URL:https: / / www.ogis-ri.co.jp / otc / hiroba / technical / similar-document-search / part1.html> Summary of the Invention [Problem to be solved by the invention]
[0005] However, with conventional techniques, it has been difficult to compare a document of a higher concept with a document of a lower concept regarding a rule and determine whether the document of the lower concept complies with the document of the higher concept. For example, among documents regarding rules, there are documents that state obligations such as "must" and documents that state prohibitions such as "must not." When conventional techniques evaluate two documents regarding rules based on word similarity, the document that states obligations and the document that states prohibitions may be determined to be similar. This has made it difficult to determine whether a document of a lower concept regarding a rule complies with the document of the higher concept.
[0006] The present invention has been made in view of the above, and aims to make it possible to compare a document of a higher concept with a document of a lower concept regarding a rule and determine whether the document of the lower concept conforms to the document of the higher concept. [Means for solving the problem]
[0007] In order to solve the above-mentioned problems and achieve the object, the determination device of the present invention is characterized by having: a memory unit that stores correspondence relationships between words representing higher-level concepts and words representing lower-level concepts; an extraction unit that extracts words that correspond to variables of the same predetermined boilerplate that are followed by the higher-level concept document and the lower-level concept document, respectively, from a document of the higher level concept related to a rule and a document of the lower level concept related to the rule; and an evaluation unit that evaluates whether the words extracted from the document of the higher level concept and the words extracted from the document of the lower level concept correspond to the correspondence relationships. [Effects of the Invention]
[0008] According to the present invention, it is possible to compare a document of a higher concept with a document of a lower concept regarding a rule and to determine whether the document of the lower concept complies with the document of the higher concept. [Brief explanation of the drawings]
[0009] [Figure 1]FIG. 1 is a diagram for explaining an outline of the determination device of this embodiment. [Figure 2] FIG. 2 is a schematic diagram illustrating the general configuration of the determination device of this embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of the data structure of the concept correspondence table. [Figure 4] FIG. 4 is a flowchart showing the procedure of the determination process. [Figure 5] FIG. 5 is a diagram illustrating an example of a computer that executes a determination program. DETAILED DESCRIPTION OF THE INVENTION
[0010] Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings. Note that the present invention is not limited to this embodiment. In addition, in the description of the drawings, the same parts are designated by the same reference numerals.
[0011] [Outline of the judgment device] 1 is a diagram for explaining an overview of the determination device of this embodiment. The determination device of this embodiment compares a document of a higher concept with a document of a lower concept regarding a rule, and determines whether the document of the lower concept complies with the document of the higher concept.
[0012] For example, the determination device performs pattern matching between a document of a higher concept and a document of a lower concept with a fixed phrase, and identifies the same fixed phrase that matches both. Figure 1 illustrates a case where the same fixed phrase related to the rule of obligation that both the document of the higher concept and the document of the lower concept follow is identified, as illustrated in Figure 1(a).
[0013] Next, the determination device extracts words that correspond to the identified template variables from the higher-level document and the lower-level document. In the example shown in Figure 1(a), the words "at the start of use (regularly)," "antivirus software," "virus definition file," and "updating" from the higher-level document that correspond to the template variable XX, and the words "at the start of use (regularly)," "AAA," "virus definition file," and "updating" from the lower-level document are extracted.
[0014] Then, for words among the extracted words that differ between the superordinate concept document and the subordinate concept document, the determination device evaluates whether or not there is a superordinate concept-subordinate concept correspondence relationship defined in advance in a concept correspondence table between the word in the superordinate concept document and the word in the subordinate concept document.
[0015] In the example shown in Figure 1, a correspondence between a superordinate concept and a subordinate concept is defined between the word "antivirus software" extracted from the superordinate concept document shown in Figure 1(b) and the word "AAA" extracted from the subordinate concept document, as shown in Figure 1(c). In this way, when a correspondence between a superordinate concept and a subordinate concept is defined between a word in the superordinate concept document and a word in the subordinate concept document, the determination device determines that the subordinate concept document conforms to the superordinate concept document.
[0016] On the other hand, if a correspondence between a higher concept and a lower concept is not defined between the words in the higher concept document and the words in the lower concept document, the determination device determines that the lower concept document does not conform to the higher concept document.
[0017] In this way, the determination device of this embodiment can compare a document of a higher concept with a document of a lower concept regarding a rule and determine whether the document of the lower concept complies with the document of the higher concept.
[0018] [Configuration of the judgment device] Fig. 2 is a schematic diagram illustrating the general configuration of a determination device of this embodiment. As illustrated in Fig. 2, a determination device 10 of this embodiment is realized by a general-purpose computer such as a personal computer, and includes an input unit 11, an output unit 12, a communication control unit 13, a storage unit 14, and a control unit 15.
[0019] The input unit 11 is realized using input devices such as a keyboard and a mouse, and inputs various instruction information such as a command to start processing to the control unit 15 in response to an input operation by an operator. The output unit 12 is realized by a display device such as a liquid crystal display, a printing device such as a printer, etc. For example, the output unit 12 displays the results of the determination processing described below, etc.
[0020] The communication control unit 13 is realized by a NIC (Network Interface Card) or the like, and controls communication between the control unit 15 and an external device via an electric communication line such as a LAN (Local Area Network) or the Internet. For example, the communication control unit 13 controls communication between the control unit 15 and a management device or the like that manages higher-level concept documents and lower-level concept documents related to rules.
[0021] The storage unit 14 is realized by a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 14 stores in advance the processing program that operates the determination device 10, data used during execution of the processing program, and the like, or temporarily stores the data each time processing is performed. The storage unit 14 may be configured to communicate with the control unit 15 via the communication control unit 13.
[0022] In this embodiment, the storage unit 14 stores predetermined template sentences 14a describing rules, and a concept correspondence table 14b, which is information indicating the correspondence between words representing higher concepts and words representing lower concepts.
[0023] Here, the template 14a includes a template of obligations and a template of prohibitions. The template of obligations is a template that expresses obligations such as "must" or "do." The template of prohibitions is a template that expresses prohibitions such as "do not." Each template includes a portion that corresponds to a variable of the template, as shown by 〇〇 in Figure 1(a), and various words are applied to that portion.
[0024] 3 is a diagram illustrating an example of the data structure of the concept correspondence table, which shows, for example, the subordinate concept words "AAA" and "BBB" corresponding to the superordinate concept word "antivirus software."
[0025] Returning to the explanation of FIG. 2, the control unit 15 is realized using a CPU (Central Processing Unit) or the like, and executes a processing program stored in memory. As a result, the control unit 15 functions as an acquisition unit 15a, an identification unit 15b, an extraction unit 15c, and an evaluation unit 15d, as exemplified in FIG. 2, to execute the determination process. Note that these functional units may be implemented individually or in part in different hardware. For example, the acquisition unit 15a and the identification unit 15b may be implemented in the hardware different from that in which the extraction unit 15c and the evaluation unit 15d are implemented. The control unit 15 may also include other functional units.
[0026] The acquisition unit 15a acquires a document of a higher concept related to a rule and a document of a lower concept related to the rule. For example, the acquisition unit 15a acquires the document of a higher concept related to a rule to be subjected to the determination process and the document of a lower concept related to the rule via the input unit 11 or via the communication control unit 13 from a management device that manages documents of higher concepts and documents of lower concepts related to the rule.
[0027] Prior to the processing described below, the acquisition unit 15a may store the acquired superordinate document related to the rule and the subordinate document related to the rule in the storage unit 14. In this case, the acquisition unit 15a may store and manage the document group created as the superordinate document related to the rule and the document group created as the subordinate document related to the rule separately in the storage unit 14.
[0028] The identification unit 15b identifies the same fixed phrases in the fixed phrases 14a that are followed by both a document with a higher concept related to the rule and a document with a lower concept related to the rule. For example, the identification unit 15b identifies which fixed phrases each document is similar to by comparing each document with each fixed phrase in the fixed phrases 14a using pattern matching. Then, the identification unit 15b identifies the same fixed phrases that are similar to both a document with a higher concept related to the rule and a document with a lower concept related to the rule.
[0029] If the identifying unit 15b cannot identify the same template, it means that the two documents to be processed are not in a conforming-non-conforming relationship. In this case, it is determined that the subordinate document does not conform to the superordinate document, and the subsequent processing is omitted.
[0030] The extraction unit 15c extracts words corresponding to variables of the same predetermined boilerplate that are followed by the document of the superordinate concept related to the rule and the document of the subordinate concept related to the rule, respectively.
[0031] Specifically, the extraction unit 15c extracts words corresponding to the variables of the specified template from each of the documents of the higher concept related to the rule and the documents of the lower concept related to the rule. For example, the extraction unit 15c compares the specified template with each of the documents of the higher concept related to the rule and the documents of the lower concept related to the rule by pattern matching, thereby extracting words corresponding to the variables of the template from each document.
[0032] The evaluation unit 15d evaluates whether or not the words extracted from the document of the higher concept and the words extracted from the document of the lower concept correspond to the correspondence relationship in the concept correspondence table 14b. That is, the evaluation unit 15d evaluates whether or not the correspondence relationship between the words extracted from the document of the higher concept and the words extracted from the document of the lower concept, which differ from each other among the extracted words in the document of the higher concept, is defined in the concept correspondence table 14b.
[0033] Then, the evaluation unit 15d determines that the document of the subordinate concept related to the rule conforms to the document of the superior concept related to the rule when the words extracted from the document of the superior concept and the words extracted from the document of the subordinate concept correspond to the correspondence relationship in the concept correspondence table 14b.
[0034] That is, the evaluation unit 15d determines that the document of the lower concept conforms to the document of the higher concept when the correspondence between the words extracted from the document of the higher concept and the words extracted from the document of the lower concept is specified in the concept correspondence table 14b.On the other hand, when the correspondence between the words extracted from the document of the higher concept and the words extracted from the document of the lower concept is not specified in the concept correspondence table 14b, the evaluation unit 15d determines that the document of the lower concept does not conform to the document of the higher concept.
[0035] In this way, by comparing the document of the superordinate concept with the document of the subordinate concept regarding the rule, it is possible to accurately determine whether the document of the subordinate concept complies with the document of the superordinate concept.
[0036] [Determination process] Next, Fig. 4 is a flowchart showing the procedure of the determination process. The flowchart in Fig. 4 starts, for example, at the timing when an inspector gives an instruction to the determination device.
[0037] First, the acquisition unit 15a acquires a document of a higher concept related to the rule and a document of a lower concept related to the rule. The identification unit 15b then identifies, among the fixed phrases 14a, the same fixed phrase that the document of the higher concept related to the rule and the document of the lower concept related to the rule follow (step S1). For example, the identification unit 15b compares each document with each fixed phrase in the fixed phrases 14a by pattern matching, thereby identifying which fixed phrase the document is similar to. The identification unit 15b then identifies the same fixed phrase that both the document of the higher concept related to the rule and the document of the lower concept related to the rule are similar to.
[0038] Next, the extraction unit 15c extracts words corresponding to the variables of the specified same predetermined template from each of the documents of the higher concept related to the rule and the documents of the lower concept related to the rule (step S2). For example, the extraction unit 15c compares each of the documents of the higher concept related to the rule and the documents of the lower concept related to the rule with the specified template by pattern matching, thereby extracting words corresponding to the variables of the template from each document.
[0039] The evaluation unit 15d evaluates whether or not the words extracted from the document of the higher concept and the words extracted from the document of the lower concept correspond to the correspondence relationship in the concept correspondence table 14b (step S3). That is, the evaluation unit 15d evaluates whether or not the correspondence relationship between the words extracted from the document of the higher concept and the words extracted from the document of the lower concept, which differ from each other among the extracted words in the document of the higher concept, is defined in the concept correspondence table 14b.
[0040] Then, if the words extracted from the document of the superordinate concept and the words extracted from the document of the subordinate concept correspond to the correspondence relationship in the concept correspondence table 14b (step S3, Yes), the evaluation unit 15d determines that the document of the subordinate concept related to the rule conforms to the document of the superordinate concept related to the rule (step S4), and ends the series of determination processes.
[0041] On the other hand, if the words extracted from the document of the superordinate concept and the words extracted from the document of the subordinate concept do not correspond to the correspondence relationship in the concept correspondence table 14b (step S3, No), the evaluation unit 15d determines that the document of the subordinate concept regarding the rule does not conform to the document of the superordinate concept regarding the rule (step S5), and ends the series of determination processes.
[0042] [effect] As described above, in the determination device 10 of this embodiment, the storage unit 14 stores the concept correspondence table 14b, which indicates the correspondence between words representing higher concepts and words representing lower concepts. The extraction unit 15c extracts words corresponding to variables of the same predetermined formula that are used by the higher concept document and the lower concept document, respectively, from the higher concept document and the lower concept document. The evaluation unit 15d evaluates whether the words extracted from the higher concept document and the lower concept document conform to the correspondence in the concept correspondence table 14b.
[0043] Specifically, the memory unit 14 stores predetermined template sentences 14a that describe rules, and the identification unit 15b identifies, from the template sentences 14a, the same template sentence that is followed by a document with a higher concept regarding the rule and a document with a lower concept regarding the rule.
[0044] Furthermore, the evaluation unit 15d determines that the document of the subordinate concept related to the rule conforms to the document of the superior concept related to the rule when a word extracted from the document of the superior concept and a word extracted from the document of the subordinate concept correspond to the concept correspondence table 14b.
[0045] This makes it possible to compare rule documents by taking into account differences in wording such as obligations and prohibitions related to the rule and eliminating confusing patterns. Therefore, it becomes possible to accurately determine the relationship between two documents that would previously have been mistaken for similar. In this way, it becomes possible to compare a document of a higher concept with a document of a lower concept related to a rule and determine whether the document of the lower concept complies with the document of the higher concept.
[0046] [program] A program written in a computer-executable language may be created to execute the processes executed by the determination device 10 according to the above embodiment. In one embodiment, the determination device 10 can be implemented by installing a determination program for executing the above determination process as package software or online software on a desired computer. For example, by executing the determination program on an information processing device, the information processing device can function as the determination device 10. The information processing device referred to here includes desktop and notebook personal computers. Other examples of information processing devices include mobile communication terminals such as smartphones, mobile phones, and PHS (Personal Handyphone Systems), as well as slate terminals such as PDAs (Personal Digital Assistants). The functions of the determination device 10 may also be implemented on a cloud server.
[0047] 5 is a diagram showing an example of a computer that executes a determination program. The computer 1000 includes, for example, a memory 1010, a CPU 1020, a hard disk drive interface 1030, a disk drive interface 1040, a serial port interface 1050, a video adapter 1060, and a network interface 1070. These components are connected by a bus 1080.
[0048] The memory 1010 includes a ROM (Read Only Memory) 1011 and a RAM 1012. The ROM 1011 stores, for example, a boot program such as a BIOS (Basic Input Output System). The hard disk drive interface 1030 is connected to a hard disk drive 1031. The disk drive interface 1040 is connected to a disk drive 1041. A removable storage medium such as a magnetic disk or optical disk is inserted into the disk drive 1041. The serial port interface 1050 is connected to, for example, a mouse 1051 and a keyboard 1052. The video adapter 1060 is connected to, for example, a display 1061.
[0049] Here, the hard disk drive 1031 stores, for example, an OS 1091, an application program 1092, a program module 1093, and program data 1094. Each piece of information described in the above embodiment is stored in the hard disk drive 1031 or memory 1010, for example.
[0050] The determination program is stored in the hard disk drive 1031 as, for example, a program module 1093 in which instructions to be executed by the computer 1000 are written. Specifically, the program module 1093 in which each process executed by the determination device 10 described in the above embodiment is written is stored in the hard disk drive 1031.
[0051] Furthermore, data used for information processing by the determination program is stored as program data 1094, for example, in the hard disk drive 1031. Then, the CPU 1020 reads the program module 1093 and the program data 1094 stored in the hard disk drive 1031 into the RAM 1012 as necessary, and executes each of the above-described procedures.
[0052] The program module 1093 and program data 1094 related to the determination program are not limited to being stored in the hard disk drive 1031, but may be stored in a removable storage medium and read by the CPU 1020 via the disk drive 1041, etc. Alternatively, the program module 1093 and program data 1094 related to the determination program may be stored in another computer connected via a network such as a LAN or a WAN (Wide Area Network), and read by the CPU 1020 via the network interface 1070.
[0053] Although the present invention has been described above as an embodiment, the present invention is not limited to the description and drawings that form part of the disclosure of the present invention. In other words, other embodiments, examples, and operational techniques that can be made by those skilled in the art based on the present invention are all included in the scope of the present invention. [Explanation of symbols]
[0054] 10 Judgment device 11 Input section 12 Output section 13 Communication control section 14 Storage section 14a Fixed text 14b Conceptual Correspondence Table 15 Control Unit 15a Acquisition part 15b Specific part 15c Extraction part 15d Evaluation Section
Claims
1. a storage unit that stores words representing higher concepts and words representing lower concepts in association with each other; an extraction unit that extracts, from each of a document of a higher concept related to a rule and a document of a lower concept related to a rule, words corresponding to variables of the same predetermined boilerplate that is followed by the document of the higher concept related to the rule and the document of the lower concept related to the rule; an evaluation unit that evaluates whether or not the words extracted from the document of the higher concept and the words extracted from the document of the lower concept are stored in the storage unit in association with each other; and The evaluation unit determines that a subordinate concept document related to the rule conforms to a superordinate concept document related to the rule when a word extracted from the superordinate concept document and a word extracted from the subordinate concept document are stored in the storage unit in association with each other.
2. A predetermined template describing the rule is further stored in a storage unit; 2. The determination device according to claim 1, further comprising an identification unit that identifies, from the fixed phrases, the same fixed phrase that is followed by a document of a higher concept related to the rule and a document of a lower concept related to the rule.
3. A determination method executed by a determination device, the determination device has a storage unit that stores words representing higher concepts and words representing lower concepts in association with each other, an extraction step of extracting words corresponding to variables of the same predetermined formula that are followed by the document of the higher concept related to the rule and the document of the lower concept related to the rule, from each of the document of the higher concept related to the rule and the document of the lower concept related to the rule; an evaluation step of evaluating whether or not the words extracted from the document of the higher concept and the words extracted from the document of the lower concept are stored in the storage unit in association with each other; Including, The evaluation step is characterized by determining that a document of a lower concept related to the rule conforms to a document of a higher concept related to the rule when a word extracted from the document of the higher concept and a word extracted from the document of the lower concept are stored in the storage unit in association with each other.
4. Refer to a storage unit that stores words representing higher concepts and words representing lower concepts in association with each other, an extraction step of extracting words corresponding to variables of the same predetermined formula that are followed by the document of the higher concept related to the rule and the document of the lower concept related to the rule, from each of the document of the higher concept related to the rule and the document of the lower concept related to the rule; an evaluation step of evaluating whether or not the words extracted from the document of the higher concept and the words extracted from the document of the lower concept are stored in the storage unit in association with each other; on the computer, The evaluation step is characterized by determining that a document of a subordinate concept related to the rule conforms to a document of a superior concept related to the rule when a word extracted from the document of the superior concept and a word extracted from the document of the subordinate concept are stored in the storage unit in correspondence with each other.
Citation Information
Patent Citations
Sentence preparation supporting device and dictionary preparing device for sentence preparation
JP1995210564A
Concept search system and concept search method
JP2007026116A
Pseudo conversation device and computer program
JP2012141713A
Synonym extraction system, method and program
JP2014132406A
Synonym extraction system, method, and recording medium
WO2014002774A1