Document analysis device and document analysis program

Abstract

To enable past software assets to be efficiently used in software development and increase efficiency in the software development.SOLUTION: A document analysis device comprises: a group classification unit which discriminates requirements included in a first document to be analyzed and classifies the discriminated requirements into a plurality of groups; a topic extraction unit which extracts terms related to the requirements classified into the plurality of groups as a topic; a topic difference extraction unit which compares a topic included in a group of an analyzed second document different from the first document with a topic included in the group of the first document and extracts the difference; and an analysis result output unit which outputs the analysis results indicative of the analysis results including the difference to the outside.SELECTED DRAWING: Figure 1B

Description

[Technical field]

[0001] The present invention relates to a document analysis device and a document analysis program. [Background technology]

[0002] In software development, it is commonly known that documents describing the requirements for the new software to be developed, presented by a new client, are analyzed, and based on the results of that analysis, consideration is given to whether past software assets can be reused, and if so, they are used.

[0003] Currently, such analysis and consideration is mainly done manually by developers, etc., based on their knowledge and experience, but as customer requirements become more diverse, the analysis work becomes more complicated, and as past software assets increase, searching through them takes a very long time. As a result, it becomes difficult to effectively use past software assets.

[0004] A computer-assisted system for such analysis and review is also known, for example from Patent Document 1. Patent Document 1 discloses a technology for using a computer to compare the paragraphs and chapters of documents to determine the similarity between two documents. This technology can only determine whether a new document contains new paragraphs by comparing it with past documents, and it is difficult to use this technology to determine whether past software assets can be used in new software development.

[0005] In addition, if the new customer is different from the customer of the past software assets, the granularity of the requirements description (process, method, standard, etc.) may be different, making it difficult to accurately extract the differences between the requirements of the new customer and the requirements of the past software assets, resulting in a problem in that it is difficult to identify usable past software assets. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] JP 2015-219799 A Summary of the Invention [Problem to be solved by the invention]

[0007] The present disclosure has been made in consideration of the above-mentioned problems, and provides a document analysis device and a document analysis program that enable efficient use of past software assets in software development and improve the efficiency of software development. [Means for solving the problem]

[0008] In order to solve the above problems, the document analysis apparatus of the present disclosure is characterized by comprising a group classification unit that identifies requirements included in a first document that is the subject of analysis and classifies them into a plurality of groups; a topic extraction unit that extracts terms related to the requirements classified into the plurality of groups as topics; a topic difference extraction unit that compares topics included in a group of an analyzed second document different from the first document with topics included in the group of the first document and extracts the differences; and an analysis result output unit that outputs an analysis result indicating the result of the analysis including the differences to the outside. Effect of the Invention

[0009] According to the document analysis device of the present disclosure, it is possible to provide a document analysis device and a document analysis program that enable efficient use of past software assets in software development and improve the efficiency of software development. [Brief description of the drawings]

[0010] [Figure 1A] FIG. 1 is a schematic diagram illustrating a document analysis apparatus 200 and a user terminal 100 according to a first embodiment. [Figure 1B] FIG. 2 is a block diagram for explaining in further detail the configuration of the document analysis apparatus 200 according to the first embodiment. [Diagram 2] FIG. 2 is a schematic diagram for explaining an analysis process of a new request document in the document analysis apparatus 200 according to the first embodiment. [Diagram 3] FIG. 1 is a schematic diagram illustrating a document analysis apparatus 200 and a user terminal 100 according to a second embodiment. [Figure 4A] 13 is a flowchart illustrating a procedure of a new request document analysis process, a display control process of a new request document analysis result, a process of verifying group classification, a process of verifying topic extraction, and a process of calculating a score in the document analysis apparatus 200 according to the second embodiment. [Figure 4B] 13 is a flowchart illustrating a procedure of a new request document analysis process, a display control process of a new request document analysis result, a process of verifying group classification, a process of verifying topic extraction, and a process of calculating a score in the document analysis apparatus 200 according to the second embodiment. [Diagram 5] An example of a screen display of a comparison result between a new request document and a past request document in the user terminal 100 according to the second embodiment will be described. [Figure 6] An example of a screen display of a comparison result between a new request document and a past request document in the user terminal 100 according to the second embodiment will be described. [Figure 7] An example of a screen display of a comparison result between a new request document and a past request document in the user terminal 100 according to the second embodiment will be described. [Figure 8] An example of a screen display of a comparison result between a new request document and a past request document in the user terminal 100 according to the second embodiment will be described. [Figure 9] An example of a screen display of a comparison result between a new request document and a past request document in the user terminal 100 according to the second embodiment will be described. [Figure 10] An example of a screen display of a comparison result between a new request document and a past request document in the user terminal 100 according to the second embodiment will be described. [Figure 11] 13 is a flowchart illustrating an example of a procedure for a display control process of an analysis result in a user terminal 100 according to the second embodiment. [Figure 12A] 13 is a flowchart illustrating an example of a procedure for a display control process of an analysis result in a user terminal 100 according to the second embodiment. [Figure 12B] 13 is a flowchart illustrating an example of a procedure for a display control process of an analysis result in a user terminal 100 according to the second embodiment. [Figure 13] 13 is a flowchart illustrating an example of a procedure for controlling update of a display of an analysis result according to the second embodiment. [Figure 14] 13 is a flowchart illustrating an example of a procedure for controlling update of a display of an analysis result according to the second embodiment. [Figure 15] 13 is a flowchart illustrating a procedure of update control for updating an analysis result of a new request document according to the second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] Hereinafter, the present embodiment will be described with reference to the accompanying drawings. In the accompanying drawings, functionally identical elements may be indicated by the same numbers. Note that the accompanying drawings show embodiments and implementation examples according to the principles of the present disclosure, but these are for understanding the present disclosure and are not to be used to interpret the present disclosure in a limiting manner. The description in this specification is merely a typical example and does not limit the scope or application of the present disclosure in any sense.

[0012] In the present embodiment, the description is given in sufficient detail for a person skilled in the art to implement the present disclosure, but it should be understood that other implementations and forms are possible, and that changes in configuration and structure and substitutions of various elements are possible without departing from the scope and spirit of the technical ideas of the present disclosure. Therefore, the following description should not be interpreted as being limited thereto.

[0013] [First embodiment] 1A, a document analysis device 200 and a user terminal 100 according to the first embodiment will be described. The document analysis device 200 according to the first embodiment is connected to the user terminal 100, and is provided with a document related to design specifications of newly developed software (hereinafter referred to as a "new requirement document" or a "first document") from the user terminal 100.

[0014] The document analysis device 200 analyzes the new requirement document and, according to the analysis result, identifies documents that have commonalities with the new requirement document from among past requirement documents (hereinafter referred to as "past requirement documents" or "second documents") that have already been analyzed and whose analysis results have been stored. Then, the document analysis device 200 identifies commonalities / differences / new features, etc. between the identified related past requirement documents and the new requirement document, and presents them to the user terminal 100. A user (software developer) of the user terminal 100 can view the presented past requirement documents and information related to the commonalities, differences, and new features to determine whether past software assets related to the past requirement documents can be used for developing new software related to the new requirement document.

[0015] The user terminal 100 may be configured with a general-purpose personal computer or the like, and includes, for example, a CPU 101, a ROM 102, a RAM 103, a hard disk drive 104, an input / output control unit 105, a communication control unit 106, a display control unit 107, an input device 108, and a display 109. A user interface application constituting a part of a document analysis program for operating the document analysis apparatus 200 of this embodiment is stored in a storage device such as the hard disk drive 104. Various instructions from the user and inputs for editing operations and the like are made from the input device 108. An execution screen of the user interface application can be displayed on the display 109.

[0016] The document analysis device 200 can similarly be configured with a general-purpose personal computer or the like, and includes, as an example, a CPU 201, a ROM 202, a RAM 203, a hard disk drive 204, an input / output control unit 205, a communication control unit 206, and a display control unit 207. A document analysis program for operating the document analysis device 200 of this embodiment is stored in a storage device such as the hard disk drive 204. Although not shown in Fig. 1A, the document analysis device 200 can include an input device operated by an administrator of the document analysis device 200, and a display for checking the analysis operation.

[0017] The document analysis program realizes a document analysis processing unit 211, a document analysis model generation unit 212, a document analysis result management unit 213, and a document analysis result input / output unit 214 in the document analysis device 200. The document analysis processing unit 211 is a unit that receives data of a new request document and executes various analyses related to the new request document. The document analysis model generation unit 212 is a unit that generates document analysis models (requirement classification model, named entity extraction model) used in the analysis by the document analysis processing unit 211.

[0018] The document analysis result management unit 213 has a role of managing data related to the analysis results of new request documents, data related to the analysis results of past request documents, and various other data used in analysis. The document analysis result input / output unit 214 has a function of generating display data for displaying the analysis results of new request documents on the user terminal 100 and outputting it to the user terminal 100, as well as receiving various inputs from the user terminal 100, etc., and changing this display data.

[0019] As shown in FIG. 1B, the document analysis processing unit 211 further includes, as an example, a group classification unit 2111, a topic extraction unit 2112, a topic difference extraction unit 2113, and a new request document creation unit 2114. The group classification unit 2111 has a function of determining requirements included in a new request document to be analyzed and classifying them into a plurality of groups. The topic extraction unit 2112 has a role of extracting, as topics, terms related to terms (keywords) included in the requirements classified into a plurality of groups. The topic difference extraction unit 2113 has a role of comparing a topic included in one group of the analyzed past request document with a topic included in a group of the new request document and extracting the difference. The new request document creation unit 2114 has a function of generating a new request document including the result of the difference extraction. The topic difference extraction unit 2113 may also have a function of calculating a topic match rate and a vector similarity calculated based on the difference.

[0020] The document analysis model generation unit 212 generates a request classification model 2121 used in classification processing in the group classification unit 2111 of the document analysis processing unit 211, and also generates a named entity extraction model 2122 used in topic extraction in the topic extraction unit 2112. The request classification model 2121 and the named entity extraction model 2122 together constitute a document analysis model. The document analysis model can be updated as appropriate using natural language processing and machine learning techniques. The topic extraction unit 2112 can be configured by either or both of a multi-label request classification model 2121' and a named entity extraction model 2122. The multi-label request classification model 2121' is a model for giving the topic extraction unit 2112 the ability to extract multiple topics. On the other hand, the request classification model 2121 is limited to a single label (group). The request classification models 2121, 2121' and the named entity extraction model 2122 can be implemented as different models (software).

[0021] The named entity extraction model 2122 may be omitted depending on the case. Also, the request classification model 2121 and the named entity extraction model 2122 may be generated as separate models according to the groups. For example, if the number of groups is 10, 10 named entity extraction models 2122 and 10 request classification models 2121 may be generated.

[0022] The document analysis result management unit 213 further includes, for example, a new request document management unit 2131, a past request document management unit 2132, a topic data management unit 2133, a group data management unit 2134, a document analysis result data management unit 2135, and a document analysis result update control unit 2136.

[0023] The new requirement document management unit 2131 has a role of managing new requirement documents, and specifically manages, for example, original data of new requirement documents, classification results for new requirement documents by the group classification unit 2111, extraction results by the topic extraction unit 2112, and other data related to new requirement documents. The past requirement document management unit 2132 has a role of managing past requirement documents, and specifically manages original data of past requirement documents, classification results for past requirement documents by the group classification unit 2111, extraction results by the topic extraction unit 2112, and other data related to past requirement documents.

[0024] The topic data management unit 2133 is used in the topic extraction process in the topic extraction unit 2112, and manages data related to topics using a database. The group data management unit 2134 is used in the classification process in the group classification unit 2111, and manages data related to groups using a database. The document analysis result data management unit 2135 has a role of managing analysis result data as a result of the analysis of new request documents. The document analysis result update control unit 2136 is in charge of update control for updating the analysis result data.

[0025] The analysis process of a new requirement document in the document analysis device 200 will be described with reference to Fig. 2. As shown in the upper left of Fig. 2, the new requirement document includes multiple requirement items New Req-i. Similarly, the old requirement document also includes multiple requirement items Old Req-i. Here, a "requirement item" is a sentence that expresses various requirements regarding the development of a system or service in one document. A requirement item may be a single sentence (a sentence having only one period) or multiple sentences.

[0026] The requirements New Req-i of the new requirement document are classified into a plurality of groups in the group classification unit 2111 according to the requirements classification model and the group database according to their contents. As an example, the groups include "object detection", "diagnosis", "sensor performance", etc., as shown in Fig. 2. The requirements Old Req-i of the past requirement document are also classified into a plurality of groups in the same manner.

[0027] The requirement NewReq-i classified into one of the multiple groups is subjected to topic extraction processing in the topic extraction unit 2112, and terms included in the requirement NewReq-i are extracted as topics. The results of group classification and topic extraction are stored in the new requirement document management unit 2131.

[0028] The expressions (terms) of the extracted topics are appropriately converted to other terms according to the topic database (for example, "driving lane" is changed to "white line"). In other words, a "topic" may include not only the terms themselves contained in the original text of a new or past request document, but also related terms (for example, superordinate terms, subordinate terms, synonyms, etc.). Past request documents are also subject to topic extraction, and the results of this extraction are stored in the past request document management unit 2132.

[0029] When the results of group classification and topic extraction of the new requirement document are stored in the new requirement document management unit 2131, the topic difference extraction unit 2113 of the document analysis processing unit 211 executes a comparison of the topics between the past requirement document stored in the past requirement document management unit 2132 and the corresponding groups, and extracts topic differences between the two (topics that match between the new requirement document and the past requirement document, topics missing in the new requirement document, and new topics in the new requirement document). Such extraction is executed between the new requirement document and multiple past requirement documents. The user of the user terminal 100 can look at the result of this extraction, identify the past requirement document that is closest to the new requirement document, and use the past software assets related to that past requirement document in the software development related to the new requirement document.

[0030] The topic difference extraction unit 2113 may extract topic differences between groups having the same or related group names, but is not limited thereto and may be capable of extracting topic differences between groups having different group names. Also, the objects of comparison and analysis in the topic difference extraction unit 2113 do not need to be limited to two groups, and any objects of comparison and analysis are acceptable as long as the topics can be compared. For example, the object of comparison may be a requirement item New Req in a new requirement document and a group of past requirement documents to be compared.

[0031] As described above, according to the document analysis device 200 of the first embodiment, requirements included in a document are classified into groups, and within each group, terms in the requirements are extracted as topics. Then, the topics are compared for each group to determine the similarity with past requirement documents. This makes it possible to accurately identify past requirement documents that are similar to a new requirement document.

[0032] [Second embodiment] Next, a document analysis device 200 according to a second embodiment will be described with reference to FIG. 3. The document analysis device 200 according to the second embodiment is connected to a user terminal 100, as in the first embodiment, and is provided with a document related to design specifications of software to be newly developed from the user terminal 100 (hereinafter, referred to as a "new requirement document" or a "first document"). However, the document analysis device according to the second embodiment is different from the first embodiment in that it includes a document analysis reliability calculation unit 215 that calculates the reliability of the document analysis result, and the document analysis model generation unit 212 includes a vector similarity calculation model generation unit 2123. The reliability of the document analysis result is calculated and presented to the user terminal 100, making it possible to more accurately judge the document analysis result.

[0033] The document analysis reliability calculation unit 215 includes, for example, a topic matching rate calculation unit 2151, a vector similarity calculation unit 2152, and a topic matching rate / vector similarity difference calculation unit 2153. The topic matching rate calculation unit 2151 has a function of calculating a topic matching rate indicating the degree of matching of topics within a group between a new request document and a past request document. The vector similarity calculation unit 2152 has a function of calculating the topic similarity within a group between a new request document and a past request document as a vector similarity such as a cosine similarity. The topic matching rate / vector similarity difference calculation unit 2153 has a function of calculating the difference between the topic matching rate calculated by the topic matching rate calculation unit 2151 and the vector similarity calculated by the vector similarity calculation unit 2152, and comparing this difference with a threshold value. The reliability of the document analysis can be determined according to the difference between the difference and the threshold value.

[0034] Next, with reference to the flowcharts of FIG. 4A and FIG. 4B, procedures of a new requirement document analysis process, a display control process of a new requirement document analysis result, a group classification verification process, a topic extraction verification process, and a score calculation process in the document analysis device 200 of the second embodiment will be described.

[0035] In the new requirement document analysis process, first, requirements included in the new requirement document are classified into groups (step S11). Then, terms included in the classified requirements are extracted as topics (steps S12 and S13). In step S12, topic extraction from the new requirement document is performed according to a named entity extraction model, and in step S13, terms related to the topics extracted from the new requirement document are converted into other terms according to a topic database. According to the results of the topic extraction in steps S12 and S13, a new requirement document with group classification and topic extraction is created (step S14).

[0036] Next, the group information of the past request document is obtained from the past request document management unit 2132, and topic extraction information of the past request document is obtained (steps S15 and S16). Then, a past request document in which the topic is replaced in group units as necessary is created (step S17). The new request document thus generated and the past request document are subjected to topic difference extraction in group units (step S18).

[0037] When the topic difference between the groups between the new request document and the past request document is extracted, the topic match rate between the groups is calculated based on the difference (step S21). Furthermore, in the new request document, the average value of the vector similarity is calculated in units of groups (step S22), and information on the average value of the vector similarity in units of groups in the past request document is read and acquired from the past request document management unit 2132 (step S23). Then, the difference in the vector similarity between the groups between the new request document and the past request document is calculated (step S24). Furthermore, the difference in the topic match rate and the vector similarity between the new request document and the past request document is calculated, and the reliability of the document analysis is determined based on this (step S25). Then, an analysis is performed according to the results of the above various calculations, and the analysis result is displayed on the user terminal 100 (step S26).

[0038] An example of a screen display showing the results of a comparison between a new request document and a past request document in the user terminal 100 will be described with reference to Figs. 5 and 6. Fig. 5 shows an overview of the screen, and Fig. 6 shows a detailed example. This screen includes, as an example, an analysis / comparison target selection display screen 2, an analysis result list display / analysis result detail selection screen 3, and an analysis result detail display / editing screen 4. The analysis / comparison target selection display screen 2 includes a screen for specifying (selecting) the new request document as an analysis / comparison target, a screen for specifying (selecting) a past request document to be compared with the new request document, and a screen for selecting the analysis scores of both documents.

[0039] The analysis result list display / analysis result detail selection screen 3 is a screen for displaying a list of analysis results of new requirement documents and selectively displaying details of the analysis results. The analysis result list display / analysis result detail selection screen 3 further includes, as an example, a classification reliability score table 10 and a topic extraction reliability score table 11. The classification reliability score table 10 displays the reliability of judgment in group classification as a score. The topic extraction reliability score table 11 displays the reliability of the topic extraction process in the topic extraction unit 2112 as a score.

[0040] The analysis result detail display / edit screen 4 includes, for example, a new requirement document display / edit screen 12, a past requirement document display / edit screen 13, and a topic difference display screen 14. The new requirement document display / edit screen 12 is a screen for displaying and editing the analysis results for a new requirement document. The past requirement document display / edit screen 13 is a screen for displaying and editing the analysis results for a past requirement document to be compared with a new requirement document. The topic difference display screen 14 is a screen for displaying the differences between the new requirement screen and the past requirement screen, and various factors related to the differences.

[0041] As shown in FIG. 6, the new requirement document display / edit screen 12 includes a group name display field 12A as a result of group classification of the new requirement document, an original text display field 12B that displays the original text data of the new requirement document, and a topic / original text word display field 12C that displays the correspondence between the extracted topic and the corresponding word in the original text. Below the fields 12A-12C, icons for instructing editing, saving, and analysis completion of these data may be displayed. FIG. 7 shows a specific example of display in the fields 12A-12C. In the original text display field 12B, for example, it is possible to indicate the location of the topic in the original text by using a symbol (<>, etc.). In the topic / original text word display field 12C in FIG. 12C, the relationship between the topic and the corresponding part in the original text can be grasped, and the user can also edit the expression of the topic on the user terminal 100 side. It is also possible to check the topic character string and the corresponding part in the original text and register the term in a topic database, etc. The fields 12B and 12C may be displayed in a single field as shown in FIG. 8.

[0042] The past requirement document display / edit screen 13 includes a group name display field 13A showing the group classification results for the past requirement documents to be compared with the new requirement document, an original text display field 13B showing the original text data of the past requirement documents, and a topic / original text word display field 13C showing the correspondence between the extracted topics and the corresponding words in the original text. Icons for instructing editing and saving of these data may be displayed below the fields 13A to 13C. Fig. 7 shows a specific example of the display in the fields 13A to 13C.

[0043] The analysis result detail display / edit screen 4 is equipped with a re-analysis start instruction button 15A, a Prev button 15B, and a Next button 15C. The re-analysis start instruction button 15A is a screen for instructing to re-run the analysis of the new requirement document and past requirement document displayed in the columns 12 and 13. The Prev button 15B and the Next button 15C are buttons for switching the display of the analysis result list narrowed down on the analysis / comparison target selection display screen 2. These are buttons for switching the past requirement documents displayed on the past requirement document display / edit screen 13, and when these are pressed, the new requirement document, past requirement document, and others displayed on the analysis / comparison target selection display screen 2 are switched, and new analysis results are displayed on the topic difference display screen 14.

[0044] The topic difference display screen 14 is a screen for displaying the topic differences between the new requirement document displayed on the screen 12 and the past requirement document displayed on the screen 13 in groups, and specifically, it displays topics common to both documents as "common topics", topics that exist only in the past requirement document but are missing (defective) in the new requirement document as "missing topics", and topics that appear only in the new requirement document as "new topics". Figure 7 shows a specific example of the display of the topic difference display screen 14.

[0045] A first modified example of the screen display of the comparison result between a new request document and a past request document in the user terminal 100 will be described with reference to Fig. 9. The screen display in Fig. 9 is different from the display example in Fig. 6 in that it has topic string / in-original-text position display fields 12D, 13D that show the extracted topic string and the position where the term corresponding to the topic appears in the original text on the new request document display / edit screen 12 and the past request document display / edit screen 13. By showing the topic string and the position where the corresponding term appears in the original text, it becomes easier to compare the new request document with the past request document.

[0046] With reference to Fig. 10, a second modified example of the screen display of the comparison results between a new request document and a past request document in the user terminal 100 will be described. The screen display in Fig. 10 differs from the display example in Fig. 6 in that multiple sets of a new request document display / edit screen 12 and a past request document display / edit screen 13 are displayed in parallel. This allows the comparison results of multiple past request documents to be displayed on one screen. The user of the user terminal 100 can more easily determine which of the multiple past request documents has a high similarity with the new request document.

[0047] An example of the procedure of the display control process of the analysis results in the user terminal 100 will be described with reference to the flowcharts of FIG. 11 to FIG. 12B. First, steps S31 and S32 are executed as a procedure for rearranging the analysis results list as a result of comparing and analyzing a new request document with a plurality of past request documents. In step S31, as an example, vector similarity scores are compared between a plurality of past request documents, and the analysis results are rearranged in descending order of vector similarity scores. In addition, in step S32, as an example, matching degrees of group classification between a plurality of past request documents, and the analysis results are rearranged in descending order of matching degrees (see FIG. 12B). In step S31, as shown in FIG. 12A, the analysis results are rearranged in ascending order of vector similarity scores (step S31A), and the analysis results can also be rearranged in descending order according to the score of the difference between the topic matching rate and the vector similarity (step S31B). Furthermore, the analysis results can be sorted in ascending order by topic match rate (step S31C), and can also be sorted in descending order according to the score of the difference between the vector similarity and the topic match rate (step S31D).

[0048] In step S33, it is determined whether or not an instruction to end the analysis result display has been issued. If it has been issued (Y), the procedure in FIG. 11 ends, and if it has not been issued (N), the process proceeds to step S34.

[0049] In step S34, data selection and filtering are performed based on information of the new requirement document as the specified analysis target. The analysis target can be specified, for example, by specifying the document name, group name, and topic name. In the following step S35, data selection and filtering are performed based on information of the past requirement document as the specified comparison target. The analysis target can be specified, for example, by specifying the document name, group name, and topic name of the past requirement document.

[0050] In step S36, it is determined whether or not a group is specified in the designation of the analysis target. If a group is specified (N), the process proceeds to step S37, and if a group is not specified (Y), the process proceeds to step S38.

[0051] In step S37, the grouping results for the specified group, the original text of the group, the topic extraction results within the group, and the topic differences between the extracted topics and the corresponding group of the past requirement document being compared are displayed according to the specified group.

[0052] On the other hand, in step S38, according to the specified new requirement document, the grouping results for each of the multiple groups included in the specified new requirement document, the original text of the multiple groups, the topic extraction results for each of the multiple groups, the topic differences between the extracted topics and the corresponding groups of the past requirement document to be compared, etc. are displayed. The above-mentioned display control procedure continues until an instruction to end the display of the analysis results is issued (step S33).

[0053] Next, an example of a procedure for controlling update of the display of analysis results will be described with reference to FIG. First, when a reanalysis start instruction is given by the reanalysis start instruction button 15A or the like (Y in step S51), the procedures in Fig. 4A and Fig. 4B are executed for the new and past requirement documents displayed on the screen, and the procedure in Fig. 13 ends. On the other hand, when an instruction to update the display of the analysis results is given (N in step S51), data of the new requirement document as the subject of the new analysis is displayed, for example, on the new requirement document display / edit screen 12 (step S52).

[0054] Then, it is determined whether or not the group to be analyzed needs to be changed (step S53), and if so (Y), a group change flow for changing the group is implemented (step S54). It is also determined whether or not the topic to be analyzed needs to be changed (step S55), and if so, a topic change flow for changing the topic to be analyzed is implemented (step S56). In this way, the update control of the analysis target is completed, and the re-analysis start instruction button 15A is pressed, and the analysis process is executed in the same manner.

[0055] The flowchart on the left side of FIG. 14 shows an example of the detailed procedure of the group change flow (step S54). When a group change is instructed, a list of groups included in the new request document to be analyzed is displayed on the analysis / comparison target designation display screen 2 (step S54A). The user of the user terminal 100 looks at this list of groups and judges whether or not a group to be a candidate for the next analysis is present in the list (step S54B). If a group that is a candidate for the next analysis is present in the list (Y), the group is selected from the group list (step S54C). If a candidate group is not found (N), a new group name is entered in a search box (not shown) to search and identify the corresponding group (step S54D). When the group to be the target of the next analysis is identified, an edit flag indicating whether or not the corresponding new request document has been edited is set to "TRUE".

[0056] Also, the flowchart on the right side of FIG. 14 shows an example of detailed procedures of the topic change flow (step S56). When a topic change is instructed, the analysis / comparison target designation display screen 2 deletes the topic to be changed from among the topics included in the new requirement document to be analyzed (step S56A), and selects the position of the topic in the new requirement document (step S56B), and displays a list of topics corresponding to the position (step S56C). The user of the user terminal 100 checks the list and determines whether or not there is a topic that is a candidate for judgment in the list (step S56D). If there is a candidate topic (Y), the candidate is selected from the list of topics (step S56E). If there is no candidate topic (N), a search is performed by inputting the name of a new topic in a search box (not shown) to identify the corresponding topic (step S56F). When the topic to be the target of the next analysis is identified, the edited flag indicating the editing of the corresponding new requirement document is set to "TRUE".

[0057] Next, the procedure of update control for updating the analysis result of a new request document will be described with reference to the flowchart of FIG. 15. First, when the new request document management unit 2131 and the past request document management unit 2132 receive and acquire the latest new and past request documents updated by the user (step S61), it is determined whether there is a request to update the document analysis result for the new request document (step S62). If there is no update request, the operation is terminated (N), but if there is an update request (Y), it is determined whether the reanalysis necessity flag is set to "TRUE" (step S63). If it is TRUE, the document analysis model is updated (re-learned) in the document analysis model generation unit 212 (step S64), and the new request document is re-analyzed by the document analysis model (steps S65 to S69). Specifically, in step S66, if the flag indicating whether the analysis of the new request document has been determined is "FALSE" (analysis is undetermined), the procedure of FIG. 4A (steps S11 to S18: new request document analysis flow (1)) is executed. If the analysis of the new requirement document has been confirmed and the document analysis confirmation flag is set to “TRUE” (N), steps S11 to S18 are omitted and the procedure of FIG. 4B (steps S21 to S26: new requirement document analysis flow (2), (3)) is executed.

[0058] Although the embodiment has been described above, it is also possible to employ the following document analysis method. (1) The reliability coefficient R, which is set based on the number of matches between new and past requirement documents and customers (= document issuers) NCU The reliability score can be recalculated by multiplying the numerical value indicating the inter-document similarity, the topic matching rate, etc. by the above. The reliability of the analysis result is improved as the number of document issuer matches between the new requirement document and the past requirement document increases. (2) The reliability coefficient R, which is set based on the number of matching requirement groups between the new requirement document and the past requirement document. NRG The reliability score is recalculated by multiplying the document similarity value and topic match rate by this. The reliability of the analysis results increases as the number of occurrences of the same group increases. (3) A reliability coefficient R according to the ratio of the total number of requests in the new requirement document (M) to the total number of requests in the past requirement document (N)RNR The reliability score is recalculated by multiplying the value indicating the inter-document similarity or the topic matching rate by M. The reliability of the analysis results is improved as the ratio of the total number of new requirement documents (M) to the total number of past requirement documents (N) is closer to 1.

[0059] The present invention is not limited to the above-described embodiments, but includes various modified examples. The above-described embodiments have been described in detail to clearly explain the present invention, and are not necessarily limited to those having all of the configurations described. Furthermore, it is possible to replace a part of the configuration of one embodiment with the configuration of another embodiment, and it is also possible to add the configuration of another embodiment to the configuration of one embodiment. Furthermore, it is possible to add, delete, or replace a part of the configuration of each embodiment with another configuration.

[0060] Furthermore, each of the above configurations, functions, processing units, and processing means may be realized in hardware by designing a part or all of them in an integrated circuit. Furthermore, each of the above configurations and functions may be realized in software by a processor interpreting and executing a program that realizes each function. Information such as programs, tables, and files that realize each function may be stored in a memory, a hard disk, or an SSD storage device, or a storage medium such as an IC card, an SD card, or a DVD. [Explanation of symbols]

[0061] 2. Analysis and comparison target selection display screen 3. Analysis result list display / analysis result detail selection screen 4. Analysis result details display / edit screen 10…Classification confidence score table 11…Topic extraction confidence score table 12…New requirement document display / edit screen 13…Past requirement document display / edit screen 14…Topic difference display screen 15A…Reanalysis start button 15B…Prev button 15C…Next button 100...User terminal 104…Hard disk drive 105... Input / output control unit 106...Communication control unit 107...Display control unit 108…Input device 109…Display 200…Document analysis device 204...Hard disk drive 205... Input / output control unit 206...Communication control unit 207...Display control unit 211...Document analysis processing unit 212…Document analysis model generation unit 213…Document Analysis Results Management Department 214…Document analysis result input / output unit 215…Document analysis reliability calculation unit 2111…Group Classification Department 2112…Topic extraction section 2113…Topic difference extraction section 2114…New Requirement Document Creation Department 2123: Vector similarity calculation model generation unit 2131…New Requirement Document Management Department 2132…Past request document management department 2133…Topic Data Management Department 2134…Group Data Management Department 2135…Document Analysis Results Data Management Department 2136...Document analysis result update control unit 2151…Topic Match Rate Calculation Section 2152...Vector similarity calculation unit 2153…Topic matching rate and vector similarity difference calculation unit

Claims

1. a group classification unit that classifies requirements included in a first document to be analyzed into a plurality of groups; a topic extraction unit that extracts, as topics, terms related to the requirements classified into the plurality of groups; a topic difference extraction unit that compares topics included in a group of an analyzed second document different from the first document with topics included in the group of the first document and extracts differences therebetween; an analysis result output unit that outputs an analysis result indicating the result of the analysis including the difference to an outside; A document analysis device comprising:

2. An analysis reliability calculation unit that calculates a reliability of the analysis of the first document, The analytical reliability calculation unit a topic match rate calculation unit that calculates a topic match rate by comparing the topic included in the requirements of the first document with the topic included in the requirements of the second document; a vector similarity calculation unit that calculates a vector similarity of terms included in the first document; a topic match rate / vector similarity difference calculation unit that calculates a difference between the topic match rate and the vector similarity and calculates a reliability of the analysis of the first document; The document analysis apparatus of claim 1 , further comprising:

3. 2. The document analysis device according to claim 1, wherein the topic difference extraction unit identifies common topics commonly included in the first document and the second document, missing topics that are missing in the first document, and new topics that exist only in the first document, according to differences between the topics of the first document and the topics of the second document.

4. The document analysis apparatus according to claim 1 , wherein the topic extraction unit is configured to convert the terms extracted as the topics into other terms according to a database.

5. 2 . The document analysis device according to claim 1 , wherein the analysis result output unit outputs the analysis result including the result of classification by the group classification unit and the topics extracted by the topic extraction unit, and makes the topics editable in an external device.

6. identifying and classifying requirements contained in a first document to be analyzed into a number of groups; extracting, as topics, terms related to the requirements classified into the plurality of groups; comparing topics included in a group of a second analyzed document different from the first document with topics included in the group of the first document and extracting differences; outputting an analysis result indicating the result of the analysis including the difference to an external device; A document analysis program configured to cause a computer to execute the following:

7. calculating a confidence level of the analysis of the first document; The step of calculating the reliability includes: calculating a topic match rate by comparing the topics contained in the requirements of the first document with the topics contained in the requirements of the second document; calculating a vector similarity of terms contained in the first document; calculating a difference between the topic match rate and the vector similarity to calculate a confidence level of the analysis of the first document; The document analysis program of claim 6 , further comprising:

Images