JP7141133B2 - Information processing device, information processing method and information processing program - Google Patents

Description

Application of Article 30, Paragraph 2 of the Patent Act 1) Website publication date May 20, 2019 2) Website address https://prtimes. jp/main/html/rd/p/000000005.000037680. html 3) Publisher PR TIMES Co., Ltd. 1) Posting date of website May 29, 2019 2) Website address https://www. cloudsign. jp/media/20190529-lawgue/ 3) Publisher Bengo4.com, Inc. 1) Website publication date December 18, 2019 2) Website address https://jp. techcrunch. com/2019/12/18/jlsi-fundraising/ 3) Publisher Verizon Media Japan K.K. 1) Website publication date March 5, 2020 2) Website address https://lawgue. com/news/94 3) Publishers: Kei Horiguchi, Go Miyasaka, and Tomoyuki Ueki 1) Date of website publication: May 20, 2019 2) Website address: https://lawgue. com/ 3) Publisher Kei Horiguchi, Go Miyasaka and Tomoyuki Ueki

The present invention relates to an information processing device, an information processing method, and an information processing program.

Contracts are generally drawn up for transactions, and contracts are very important because they affect transactions. For this reason, conventionally, systems have been developed to support the creation of contracts. For example, Patent Literature 1 discloses a process of generating a document vector for each of a plurality of legal provisions included in a plurality of laws and regulations, and comparing the document vectors of each of the provisions with each other to obtain a similarity equal to or greater than a predetermined threshold. A process of generating a clause group by combining a plurality of clauses, a process of generating a document vector for each clause group for each clause group, and a process of generating a document vector for each clause for the input contract data. , the document vector for each clause is compared with the document vector for each clause group, and each legal clause included in a similar clause group is identified as a related clause of the relevant contract clause; A contract analysis system is disclosed that executes a process of generating an analysis result screen listing clauses.

In the above contract analysis system, when the user enters contract data, the legal texts closely related to each contract clause are automatically presented, so even users who are unfamiliar with the law can check the related clauses in advance. It is possible to do so. In this way, the above contract analysis system automatically presents legal texts that are closely related to the contract being drafted, but it is not possible to create a contract while comparing it with past contracts. There is room for improvement in

JP 2014-238629 A

The present invention has been made in view of the above problems, and an object of the present invention is to provide a highly convenient information processing apparatus, information processing method, and information processing program.

In order to solve the above-described problems, an information processing apparatus of the present invention includes a calculation unit that calculates the similarity between a first document and a second document that is different from the first document for each predetermined area, and a comparison unit that compares the first document and the second document in units of a predetermined region according to the similarity; and an output unit for outputting comparison information to be displayed in a manner different from others.

According to the present invention, it is possible to provide a highly convenient information processing apparatus, information processing method, and information processing program.

It is a figure showing an example of a schematic structure of an information processing system concerning an embodiment. It is a figure which shows an example of the hardware constitutions of the server which concerns on embodiment. It is a figure which shows an example of the database memorize|stored in the memory|storage device of the server which concerns on embodiment. It is a figure showing an example of functional composition of a server concerning an embodiment. It is a figure which shows an example of the hardware structure and functional structure of the user terminal which concerns on embodiment. It is a figure which shows an example of the screen displayed on the display apparatus of the user terminal which concerns on embodiment. It is a figure which shows an example of the screen displayed on the display apparatus of the user terminal which concerns on embodiment. It is a figure which shows an example of the screen displayed on the display apparatus of the user terminal which concerns on embodiment. 8 is a flowchart illustrating an example of user registration processing executed by the server according to the embodiment; 6 is a flowchart showing an example of document registration processing executed by the server according to the embodiment; 8 is a flowchart illustrating an example of counting processing executed by the server according to the embodiment; 8 is a flowchart illustrating an example of comparison processing executed by the server according to the embodiment; It is a figure which shows an example of the functional structure of the server based on the modification 1 of embodiment. It is a figure which shows an example of the screen displayed on the display apparatus of the user terminal which concerns on the modification 1 of embodiment.

BEST MODE FOR CARRYING OUT THE INVENTION An embodiment of the present invention will be described below with reference to the drawings.
In the following embodiment, the embodiment will be described using a contract as an example of a document, but the document is not limited to the contract. For example, it may be a regulatory document, an ordinance or a treaty, a securities report, a financial statement, or a patent specification.
In the embodiment described below, a vector converted by the conversion unit 205, which will be described later, is stored for each clause of the contract. It is good also as a structure which converts.
Further, in the following embodiment, the similarity is calculated based on the vector converted by the conversion unit 205, but the similarity is calculated by similarity calculation using sequence matching or similarity calculation using edit distance. may

[Embodiment]
FIG. 1 is a diagram showing an example of a schematic configuration of an information processing system 1 according to an embodiment. First, the configuration of the information processing system 1 will be described with reference to FIG. The information processing system 1 includes a server 2 (information processing device) and user terminals 3 connected to the server 2 via a network 4 . The number of servers 2 and user terminals 3 included in the information processing system 1 is arbitrary. Communication between the server 2 and the user terminal 3 may be wireless communication or wired communication.

(Server 2)
FIG. 2 is a diagram showing an example of the hardware configuration of the server 2 (information processing device). As shown in FIG. 2, the server 2 includes a communication IF 200A, a storage device 200B, a CPU 200C, and the like. The server 2 may be provided with an input device (for example, keyboard, touch panel, etc.) and a display device (for example, liquid crystal monitor, organic EL monitor, etc.).

Communication IF 200A is an interface for communicating with an external terminal (user terminal 3 in the embodiment).

The storage device 200B is, for example, an HDD or a semiconductor storage device. Information processing programs and databases used by the server 2 are stored in the storage device 200B. In the embodiment, the information processing program and database are stored in the storage device 200B of the server 2, but may be stored in an external storage device such as a USB memory or an external server connected via a network, It may be configured so that it can be referred to or downloaded by the user.

FIG. 3 is an example of a database stored in the storage device 200B. As shown in FIG. 3, the storage device 200B stores a user database 1 (hereinafter referred to as user DB1) and a document database 2 (hereinafter referred to as document DB2). It is arbitrary how the information of the databases DB1 and DB2 described below is associated and stored in the storage device 200B, and is not limited to the example shown in FIG. Also, it is not always necessary to store the data in the storage device 200B as a database.

FIG. 3 is a diagram showing an example of information (data) stored in the storage device 200B as a database.
(User database 1)
The user DB 1 stores user information such as password, name, gender, age, date of birth, contact information, self-portrait data for icons, etc. in association with the user ID. The user ID is identification information different for each user, and also serves as an ID for logging into the information processing system 1 . The password is a password for logging into the information processing system 1 . The name, gender, age and date of birth are the user's name, gender, age and date of birth. The contact information is the user's e-mail address, telephone number, address, and the like. In addition, what kind of information is stored in the user DB 1 in association with the user ID is arbitrary, and is not limited to the above information.

(Document DB2)
The document DB 2 stores information such as contracts and various tables. Information stored in the document DB 2 will be described below.
The contract type master table M1 stores records of pairs of contract type IDs and clause names. Here, the contract type ID is an example of contract type identification information for identifying the type of contract.
The type master table M2 stores records of sets of clause type IDs and clause names. Here, the clause type ID is an example of clause type identification information that identifies the type of clause.
The standard clause table T1 stores information on clauses included in standard contracts prepared in advance.
The standard clause table T1 stores records of pairs of contract type IDs, clause type IDs, vectors, and clauses. A vector is obtained by transforming a clause, that is, a group of sentences for each clause.
Clauses included in contracts input (uploaded) by users are accumulated in the clause table T2. Also, the clause table T2 stores records of sets of contract type IDs, clause type IDs, clauses, and vectors obtained by converting the clauses.
Further, in the document DB 2, a contract type is stored for a set of a vector corresponding to each clause included in the standard contract and clause type identification information (contract type ID in this case) attached to the clause. They are further associated and stored.

The CPU 200C controls the server 2 and includes ROM (Read Only Memory) and RAM (Random Access Memory) not shown.

FIG. 4 is a diagram showing an example of the functional configuration of the server 2 according to the embodiment. As shown in FIG. 4, the server 2 includes a receiving unit 201 (first and second receiving units), a transmitting unit 202 (output unit), a storage device control unit 203, a dividing unit 204, a converting unit 205, a calculating unit 206, It has functions such as a classifying section 207, a counting section 208, a comparing section 209, and the like. The functions shown in FIG. 4 are realized by the CPU 200C executing an information processing program stored in the ROM (not shown) of the server 2. FIG.

The receiving unit 201 receives information transmitted from the user terminal 3 via the network 4 . The receiving unit 201 receives, for example, a first instruction to display the second contracts sorted by the sorting unit 207 for each group. The receiving unit 201 also receives, for example, a second instruction to display an area other than the predetermined area in the second contract compared by the comparing unit 209 .

The storage device control unit 203 controls the storage device 200B. Specifically, the storage device control unit 203 writes and reads information to and from the storage device 200B.

The dividing unit 204 divides the contract into predetermined area units. In the embodiment, the dividing unit 204 divides the contract by clause. Specifically, the dividing unit 204 extracts the word "article" from the contract, and divides the contract into clauses using the "article" as a boundary. It should be noted that any unit may be used as the predetermined area unit. For example, the target contract may be divided with the paragraph or number as a predetermined area unit. In this case, the dividing unit 204 extracts the word “paragraph” or “issue” from the target contract, and divides the contract for each paragraph or issue using this “paragraph” or “issue” as a boundary. . In addition, instead of extracting the word "article" and dividing, it is also possible to divide by judging that it is a paragraph from the text information in the continuous lines. Regarding the extraction of ``section'' and ``number'', instead of extracting and dividing the words ``section'' and ``number'' in the same way, the text in the continuous line that is the paragraph and paragraph It is possible to divide by judging from the information

The conversion unit 205 converts the terms of the contract into vectors. Specifically, the conversion unit 205 converts the clause after division by the division unit 204 into a vector. The vector is, for example, a high-dimensional real vector. Clauses with closer semantics are converted to closer vectors by the conversion unit 205 . By comparing vectors resulting from this conversion, the similarity of contracts can be calculated for each clause.

<Conversion processing by conversion unit 205>
Next, an example of processing for converting each sentence into a vector will be described.
First, the conversion unit 205 decomposes the text into morphemes. For example, if the sentence is ``It's nice weather today'', it is broken down into ``today'', ``ha'', ``nice'', ``weather'', and ``desu''.
Next, the conversion unit 205 defines N consecutive morphemes (N is a natural number) as n-grams. For example, when N is 2, the conversion unit 205 defines n-grams as follows.
N=2: (today, ha), (ha, nice), (nice weather), (weather)
Transformation unit 205 then computes the matrix. Here, it is assumed that there are three contracts S1, S2, and S3. Conversion unit 205 determines that all n-grams of contract S1 appear most in contract S1, different n-grams included in contract S2 and contract S3 do not appear, and the same applies to contract S2 and contract S3. Compute the matrices U and V such that The matrix U is a set of values for each sentence, and by performing learning (optimization function) by optimizing the matrices U and V, a contract vector (distributed representation) is derived. Matrix U is a matrix that has the same size as matrix V and is tilted by 90 degrees, and is a set of values for each sentence. Based on V, which is one side of the matrix, the transformation unit 205 averages all the included n-gram distributed representations to obtain a sentence vector (also called a distributed representation).
An example of a specific technique for converting a target sentence (sentence) S into a vector will be briefly described below. At the time of learning, a matrix V is used to obtain an expression for each word. We also use the parameter U to learn patterns of occurrence of words within sentences. Also, the matrices U and V are optimized using the error function. When deriving the distributed representation, the Bag of Words vector D of the sentence S is obtained. The vector representation of the sentence S is obtained by multiplying the vector D and the matrix V, and taking the average of the vector representation for each n-gram with appearance frequency added.
Note that a known library or a known method may be used for conversion into a vector by the conversion unit 205 .
Note that when the clause includes three sentences (the first to third sentences exist), the converting unit 205 converts the first to third sentences into vectors. , the average of each vector is taken as the vector corresponding to the clause.

The calculation unit 206 calculates the terms of the contract to be edited by the user (hereinafter also referred to as the first contract) and the terms of other contracts stored in the document DB 2 (hereinafter also referred to as the second contract). based on the vectors. Specifically, the calculation unit 206 calculates the similarity (for example, cosine similarity) between the vector of the clauses of the first contract and the vector of the clauses of the second contract. In the embodiment, the calculation unit 206 calculates the similarity between contract clauses based on the cosine similarity between vectors. You may make it calculate gender. For example, similarity may be calculated by similarity calculation using Euclidean distance.

The classification unit 207 classifies the second contract into a predetermined group (one or more groups) according to the similarity between the clauses of the contract. Specifically, the classifying unit 207 classifies the second contracts whose similarity calculated by the calculating unit 206 is greater than or equal to the first predetermined value and less than the second predetermined value into the first group. A second contract whose similarity calculated by the calculation unit 206 is greater than or equal to a second predetermined value and less than a third predetermined value is classified into a second group. A second contract whose similarity calculated by the calculator 206 is greater than or equal to a third predetermined value and less than a fourth predetermined value is classified into a third group. In addition, although classification is made into three groups in the embodiment, the classification into any number of groups is arbitrary. Also, it is arbitrary as to what values the first to fourth predetermined values are set to.

When classifying contracts, the classification unit 207 clusters the vectorized clauses in advance using a Gaussian mixture model (one example), and determines grouping according to the clustering results. good too. Alternatively, a predetermined value of similarity and clustering may be combined, and groups may be determined based on the condition that the range of the predetermined value of similarity and belonging to the same clustering are met.

The counting unit 208 counts the number of second contracts sorted by the sorting unit 207 for each group.

The comparison unit 209 compares the first document and the second document in predetermined area units (sections in the embodiment) according to the similarity calculated by the calculation unit 206 . Specifically, the comparison unit 209 compares the clauses of the first contract and the clauses of the second contract, and detects different portions (characters) between the two contracts.

The transmission unit 202 transmits information to the user terminal 3 via the network 4 . For example, the transmission unit 202 transmits (outputs) comparison information for displaying the same parts and different parts of the compared contracts in different modes according to the comparison result of the comparison unit 209 .
Further, when the receiving unit 201 receives the first instruction to display the second contracts sorted by the classifying unit 207 for each group, the transmitting unit 202 displays information for displaying the second contracts belonging to the specified group. is transmitted (output).
Further, when the receiving unit 201 receives a second instruction to display an area other than the predetermined area in the second contract compared by the comparing unit 209, the transmitting unit 202 displays information for displaying an area other than the predetermined area. is transmitted (output).
Also, the transmitting unit 202 transmits (outputs) a predetermined area of the second contract whose similarity is equal to or less than a predetermined value.

(User terminal 3)
FIG. 5 is a diagram showing an example of the hardware configuration and functional configuration of the user terminal 3 according to the embodiment. FIG. 5(a) is a diagram showing an example of the hardware configuration of the user terminal 3, and FIG. 5(b) is a diagram showing an example of the functional configuration of the user terminal 3. As shown in FIG. The user terminal 3 is a PC (Personal Computer), a mobile terminal (for example, a tablet terminal), or the like. As shown in FIG. 5A, the user terminal 3 includes a communication IF 300A, a storage device 300B, an input device 300C, a display device 300D, a CPU 300E, and the like.

Communication IF 300A is an interface for communicating with another device (server 2 in the embodiment).

The storage device 300B is, for example, a HDD (Hard Disk Drive) or a semiconductor storage device (SSD (Solid State Drive)). The storage device 300B stores an identifier (ID) of the user terminal 3, an information processing program, and the like. The identifier may be newly assigned to the user terminal 3 by the server 2, or may be an IP (Internet Protocol) address, MAC (Media Access Control) address, or the like.

The input device 300C is, for example, a keyboard, a touch panel, or the like, and the user can input information necessary for using the information processing system 1 by operating the input device 300C.

The display device 300D is, for example, a liquid crystal monitor or an organic EL monitor. The display device 300</b>D displays screens necessary for using the information processing system 1 .

The CPU 300E controls the user terminal 3 and has ROM and RAM (not shown).

As shown in FIG. 5B, the user terminal 3 has functions such as a receiving section 301, a transmitting section 302, a storage device control section 303, an operation receiving section 304, a display device control section 305, and the like. Note that the function shown in FIG. 5B is implemented by the CPU 300E executing an information processing program stored in the storage device 300B.

The receiving unit 301 receives information transmitted from the server 2 .

The transmission unit 302 assigns an identifier to information input using the input device 300C and transmits the information to the server 2 . By assigning an identifier to the information transmitted from the user terminal 3, the server 2 can recognize from which user terminal 3 the received information is transmitted.

The storage device control unit 303 controls the storage device 300B. Specifically, the storage device control unit 303 controls the storage device 300B to write and read information.

The operation reception unit 304 receives an input operation on the input device 300C.

The display device control unit 305 controls the display device 300D. Specifically, the display device control unit 305 controls the display device 300D to display a screen necessary for using the information processing system 1 according to the embodiment.

(Example of display screen)
6 to 8 are diagrams showing examples of screens displayed on the display device 300D of the user terminal 3 according to the embodiment. Screens displayed on the display device 300D of the user terminal 3 will be described below with reference to FIGS. 6 to 8. FIG. In the following description, the same components are denoted by the same reference numerals, and overlapping descriptions are omitted. In the explanation below, the display includes a modal display that displays a type of window that prevents operations on the parent window from being accepted until the operation is completed, a display that switches tabs (tab display), and a window that is sized separately from the parent window. A display (sub-window display) that opens a small window (sub-window) of .

FIG. 6 is an example of a screen displayed on the display device 300D of the user terminal 3. As shown in FIG. On the screen shown in FIG. 6, the first contract D1 specified by the user is displayed on the left side of the screen. In addition, clause J1, which is the subject of editing of the first contract document D1, is displayed in the central part on the left side of the screen. When the similar contract display button B1 is selected, on the right side of the screen, the clauses of the second contract classified by the classification unit 207 according to the similarity calculated by the calculation unit 206 are grouped according to the similarity. It is displayed for each of G1 to G3 (in the example shown in FIG. 6, the terms of the second contract with the highest similarity among the groups G1 to G3 are displayed). In the example shown in FIG. 6, they are displayed in a state classified into three groups G1 to G3. In the example shown in Table 7, the groups are displayed in descending order (from the top of the screen toward the bottom of the screen) from the group with the highest similarity.

The screen shown in FIG. 6 also displays the number of second contracts N1 to N3 containing the clauses classified into each group counted by the counting unit 208 . In the example shown in FIG. 6, two second contracts are classified into group G1, three second contracts are classified into group G2, and one second contract is classified into group G3. I understand. Further, by selecting and operating the button B2 shown in FIG. 6, a screen shown in FIG. 7, which will be described later, is displayed. Further, by sliding the button B3 shown in FIG. 6 from left to right, a screen (difference display screen) shown in FIG. 8, which will be described later, is displayed.

In the screen shown in FIG. 6, the first contract D1 to be edited designated by the user is displayed on the left side of the screen, and the similarity calculated by the calculation unit 206 is displayed on the right side of the screen. Although the second contract classified by the classification unit 207 is displayed in a classified state, the first contract D1 to be edited specified by the user is displayed on the right side of the screen, and the first contract D1 to be edited is displayed on the left side of the screen. 2, the second contract classified by the classification unit 207 according to the similarity calculated by the calculation unit 206 may be displayed in a classified state.

FIG. 7 is an example of a screen displayed on the display device 300D of the user terminal 3. As shown in FIG. FIG. 7 is an example of displaying the second contract classified into group G1 in FIG. As shown in FIG. 7, the file names F1 and F2 of the second contract are displayed on the left side of the screen. Also, in the center of the screen in FIG. 7, the contents of the second contract with the file name F1 selected on the right side of the screen are displayed. In the example shown in FIG. 7, the background of the file name F1 is changed (highlighted) to indicate that the file name F1 is selected. In the example shown in FIG. 7, among the contents of the second contract with the file name F1, the background of the region of the clause compared in FIG. 6 is changed (highlighted). Further, in the upper center of FIG. 7, the status S of the second contract with the selected file name F1, the creation date D1, the number of days elapsed from the creation date D2, the creator/editor icon U, etc. are displayed. .

In other words, when the reception unit 201 receives an instruction (first instruction) to display the second contracts classified by the classification unit 207 by group by selecting the button B2 shown in FIG. The unit 202 (output unit) transmits to the user terminal 3 information for displaying the second contract belonging to the designated group. The transmitted information is received by the receiving section 301 of the user terminal 3, and the display device control section 305 of the user terminal 3 displays the screen shown in FIG. 7 on the display device 300D.

FIG. 8 is an example of a screen displayed on the display device 300D of the user terminal 3. As shown in FIG. On the screen shown in FIG. 8, the first contract D1 specified by the user is displayed on the left side of the screen. Also, on the left side of the screen, clause J1, which is the subject of editing of the first contract document D1, is displayed. In addition, clause J1 of the first contract D1 to be edited is displayed on the upper right side of the screen, and clause J1 of the second contract to be compared is displayed on the lower right side of the screen. Clause J2 is displayed. On the right side of the screen, the section J1 to be edited in the first contract D1 and the section J2 corresponding to section J1 in the second contract D2 to be compared differ from each other (hereinafter referred to as difference ) is displayed in a recognizable manner.

In the example shown in FIG. 8, the parts of Clause J1 that differ from Clause J2 are displayed in bold, and the parts of Clause J2 that differ from Clause J1 are displayed in italics. Other aspects, for example, different parts (characters) may be highlighted. In the example shown in FIG. 8, different parts (characters) are underlined in order to make the positions of different parts (characters) easier to understand, but they are not actually underlined.

In this way, on the screen shown in FIG. 8, while checking the differences (differences) from clause J2 of the second contract to be compared on the right side of the screen, on the left side of the screen is the first contract to be edited. Clause J1 of document D1 can be edited. Note that in FIG. 8, when the clause J1 of the first contract D1 is edited on the left side of the screen, the edited contents are reflected in real time on the clause J1 of the first contract D1 displayed on the right side of the screen. , the difference between the clause J1 of the first contract document D1 reflecting the edited content and the clause J2 of the second contract document to be compared can be confirmed. Therefore, it is very convenient.

In the screen shown in FIG. 8, the first contract D1 to be edited designated by the user is displayed on the left side of the screen, and the first contract D1 and the second contract are displayed on the right side of the screen. The first contract D1 to be edited specified by the user is displayed on the right side of the screen, and the first contract D1 is displayed on the left side of the screen. D1 and the second contract may be configured to be displayed in such a manner that the difference between them can be recognized. In addition, although the screen shown in FIG. 8 is configured to display the difference between clauses at the top and bottom of the screen in units of clauses, it is configured to display the difference at the top and bottom of the screen in units of lines in a manner in which differences can be recognized. Alternatively, the configuration may be such that the difference is displayed on the left and right sides of the screen in such a manner that the difference can be recognized. In addition, a configuration may be adopted in which the difference is displayed in a manner in which the difference can be recognized inline (a method of displaying the difference in a hidden display).

(Processing executed by information processing system 1)
9 to 12 are flowcharts showing an example of the processing executed by the server 2. FIG. The processing executed by the server 2 will be described below with reference to FIGS. 9 to 12, and the same components as those described with reference to FIGS. 1 to 8 are denoted by the same reference numerals. omit the description.

(User registration process)
FIG. 9 is a flowchart showing an example of user registration processing executed by the server 2. As shown in FIG. User registration processing executed by the server 2 will be described below with reference to FIG.

(Step S101)
The user operates the input device 300C of the user terminal 3 to input user information such as a password, name, gender, age, date of birth, contact information, and self-portrait data for icons. The input user information is received by the operation receiving unit 304 . The accepted user information is transmitted from the transmission unit 302 to the server 2 . The receiving unit 201 of the server 2 receives user information transmitted from the user terminal 3 .

(Step S102)
The user information received by the receiving unit 201 of the server 2 is stored in the user DB 1 of the storage device 200B by the storage device control unit 203 in association with the user ID.

(Contract registration process)
FIG. 10 is a flow chart showing an example of contract registration processing executed by the server 2 . The contract registration process executed by the server 2 will be described below with reference to FIG.

(Step S201)
The user operates the input device 300</b>C of the user terminal 3 to specify the contract to be registered in the server 2 . This contract is specified by dragging and dropping the contract to be registered in the predetermined area displayed in 300D, but it may be specified by other methods. The designated contract is transmitted from the transmission unit 302 to the server 2 . The receiving unit 201 of the server 2 receives the contract sent from the user terminal 3 .

(Step S202)
The dividing unit 204 of the server 2 divides the contract received by the receiving unit 201 into predetermined area units. In the embodiment, the dividing unit 204 divides the target contract for each clause.

(Step S203)
The conversion unit 205 of the server 2 converts the contract received by the reception unit 201 into a vector for each predetermined area unit. Specifically, the conversion unit 205 converts the clause after division by the division unit 204 into a vector.

(Step S204)
The storage device control unit 203 of the server 2 stores the contract received by the receiving unit 201 and the vector for each clause converted by the conversion unit 205 in the document DB 2 of the storage device 200B in association with the user ID.

(count processing)
FIG. 11 is a flow chart showing an example of the counting process executed by the server 2. As shown in FIG. The counting process executed by the server 2 will be described below with reference to FIG. 11 .

(Step S301)
The user operates the input device 300C of the user terminal 3 to specify the terms of the contract to be edited. This designation is transmitted from the transmission unit 302 to the server 2 . The receiving unit 201 of the server 2 receives the designation transmitted from the user terminal 3 .

(Step S302)
The calculation unit 206 of the server 2 refers to the document DB 2 and extracts other contracts associated with the same user ID as the user ID associated with the specified contract.

(Step S303)
The calculation unit 206 of the server 2 calculates the similarity between the clause of the designated contract and the clause of the other contract extracted in step S302. More specifically, the cosine similarity is calculated based on the clause vectors converted by the conversion unit 205 .

(Step S304)
The classification unit 207 of the server 2 classifies the contracts into predetermined groups according to the similarity between the clauses of the contracts. Since the details of the classification by the classification unit 207 have already been explained, they will be omitted.

(Step S305)
The counting unit 208 of the server 2 counts the number of second contracts sorted by the sorting unit 207 for each group.

(Step S306)
The transmitting unit 202 of the server 2 transmits information on the number of second contracts counted for each group by the counting unit 208 . Information on the number of cases is received by the receiving unit 301 of the user terminal 3 . The display device control unit 305 causes the display device 300D to display the number of second contracts counted for each group based on the received information on the number of cases.

In the above description, in step S302, the calculation unit 206 of the server 2 refers to the document DB 2 and extracts other contracts associated with the same user ID as the user ID associated with the designated contract. However, contracts may be extracted in units of the same group (for example, company, department, task force, etc.). In this case, the same group ID is associated with the user IDs of users belonging to the same group. Then, in step S302, the calculation unit 206 of the server 2 refers to the document DB 2 and searches for other contracts associated with the same group ID as the group ID associated with the user ID associated with the specified contract. Extract.

(comparison processing)
FIG. 12 is a flow chart showing an example of comparison processing executed by the server 2. As shown in FIG. The comparison processing executed by the server 2 will be described below with reference to FIG. 12 .

(Step S401)
The user operates the input device 300C of the user terminal 3 to instruct contract comparison. This instruction is transmitted from the transmission unit 302 to the server 2 . The receiving unit 201 of the server 2 receives the instruction transmitted from the user terminal 3 .

(Step S402)
The comparison unit 209 of the server 2 compares the first contract to be edited and the second contract in units of predetermined regions (clauses in the embodiment) according to the similarity calculated by the calculation unit 206 . Specifically, the comparison unit 209 compares the clauses of the target first contract with the clauses of the second contract whose similarity calculated by the calculation unit 206 is equal to or greater than a predetermined value, and compares the clauses of both contracts. Detect different parts (characters).

(Step S403)
The transmitting unit 202 transmits (outputs) comparison information for displaying the same parts and different parts of the compared contracts in different modes according to the comparison result of the comparing unit 209 . The comparison information is received by the receiving section 301 of the user terminal 3 . Based on the received comparison information, the display device control unit 305 causes the display device 300D to display the same parts and different parts of the compared contracts in different modes.

As described above, the server 2 (information processing device) according to the embodiment can edit the first contract (first document) to be edited and the second contract, which is another contract different from the first contract. Calculation unit 206 that calculates similarity with (second document) in units of predetermined areas (clauses, paragraphs, issues, etc.); A comparison unit 209 that compares the contract with the contract in units of a predetermined area, and according to the comparison result of the comparison unit 209, the same part or different part of the first contract and the second contract is displayed in a different manner from the others. and a transmission unit 202 (output unit) that transmits (outputs) the comparison information. In this way, differences between contracts (documents) can be compared not by contract (document) unit, but by predetermined area unit, thereby improving convenience.

In addition, the server 2 according to the embodiment has a classification unit 207 that classifies the second contracts (second documents) into predetermined groups according to similarity, and the number of second contracts classified by the classification unit 207. is provided for each group.
In this way, it is possible to know the number of second contracts in which clauses similar to the clause to be edited exist for each group classified according to similarity, thereby improving convenience.

The server 2 according to the embodiment also includes a receiving unit 201 (first receiving unit) that receives a first instruction to display the second contracts (second documents) classified by the classifying unit 207 for each group. Further, when the receiving unit 201 (first receiving unit) receives the first instruction, the transmitting unit 202 (output unit) of the server 2 according to the embodiment displays information for displaying the second contract belonging to the designated group. is transmitted (output). In this way, the convenience is improved because the second contract can be displayed for each similar group.

The server 2 according to the embodiment also includes the receiving unit 201 (second receiving unit ). Then, when the receiving unit 201 (second receiving unit) receives the second instruction, the transmitting unit 202 (output unit) of the server 2 transmits (outputs) information for displaying an area other than the predetermined area. In this way, areas other than the predetermined area being compared can also be displayed for confirmation, etc., thereby improving convenience.

Also, in the embodiment, the predetermined area unit is a clause unit or a paragraph unit. In general, a contract is written on a clause-by-clause basis, and each clause consists of clauses. For this reason, by setting the predetermined area unit to the clause unit or the clause unit, it becomes easy to compare contracts. As a result, convenience is improved.

The server 2 according to the embodiment also includes a conversion unit 205 that converts the first contract (first document) and the second contract (second document) into vectors in units of predetermined areas. Then, the calculation unit 206 of the server 2 calculates the similarity between the first contract (first document) and the second contract (second document) based on the vectors converted in units of predetermined areas. Calculated by In this way, the similarity is calculated based on the vector used when determining the similarity of sentences, so the accuracy of the similarity is improved.

[Modification 1 of Embodiment]
Modification 1 of the embodiment will be described below, but the same components as those described with reference to FIGS. 13 is a diagram illustrating an example of a functional configuration of a server (information processing device) according to Modification 1 of the embodiment; FIG. As shown in FIG. 13, the server 2 according to Modification 1 of the embodiment includes a receiving unit 201 (third receiving unit), a transmitting unit 202 (output unit), a storage device control unit 203, a dividing unit 204, a converting unit 205 , a calculation unit 206 , a classification unit 207 , a count unit 208 , a comparison unit 209 , a replacement unit 210 and a search unit 211 .

The replacement unit 210 allows the server 2 (information processing device) according to Modification 1 of the embodiment to display the second contract D2 according to the similarity with the target first contract D1 (first contract). Swap the order by region. Specifically, the replacement unit 210 replaces the second contract to be compared on a clause-by-clause basis according to the similarity with each clause of the first contract to be edited. In other words, the replacement unit 210 replaces the clauses of the second contract so that the clause with the highest similarity is right next to the corresponding clause of the first contract.

FIG. 14 is an example of a screen displayed on the display device 300D of the user terminal 3 according to Modification 1 of the embodiment. The replacement unit 210 replaces the second contract to be compared on a clause-by-clause basis according to the similarity with each clause of the first contract to be edited. Therefore, as shown in FIG. are displayed on the display device 300D of the user terminal 3 in a state in which they are replaced in an order similar to the clauses J1 to J3 of the first contract document D1, rather than in the order described in . In the example shown in FIG. 14, since the clauses J1 to J3 of the first contract D1 are replaced in an order similar to that of the clauses J1 to J3, the second contract D2 includes clauses J4, J5, and J6 in this order. is displayed on the display device 300D. That is, to the right of clause J1 of the first contract D1, clause J4, which is most similar to clause J1 among the clauses of the second contract, is displayed, and to the right of clause J2 of the first contract D1, , the clause J5 that is most similar to clause J2 among the clauses of the second contract is displayed, and to the right of clause J3 of the first contract D1 is the clause that is most similar to clause J3 among the clauses of the second contract. Clause J6 is displayed.

As in the example shown in FIG. 8, also in FIG. 14, the first contract D1 (first document) to be edited and the second contract D2 (second document) to be compared are different. The part (hereinafter also referred to as difference) is displayed in a recognizable manner. In the example shown in FIG. 14, the portions of the first contract D1 that differ from the second contract D2 are displayed in bold, and the portions of the second contract D2 that differ from the first contract D1 are displayed in italics. However, if the different parts (characters) can be recognized, another aspect, for example, the different parts (characters) may be highlighted. In the example shown in FIG. 14 as well, the different parts (characters) are underlined in order to make the positions of the different parts (characters) easier to understand, but they are not actually underlined.

In this way, with the replacement unit 210, the user can replace clause J1 of the first contract and clause J4 of the second contract, which is similar to clause J1, with clause J2 and clause J2 of the first contract. Clause J5 of the second contract that . In this way, originally, there is no need to scroll the screen to search for a corresponding clause, and the descriptions of clauses can be compared on the same screen, thus improving convenience.

In the description with reference to FIG. 14, the order of the clauses of the second contract D2 is changed according to the first contract D1 to be edited. The order of the clauses in one contract D1 may be changed.

Also, the search unit 211 searches for a contract based on the keyword (search word) received by the reception unit 201 . The transmission unit 202 outputs search information for displaying the search word searched by the search unit 211 in a manner different from that of other words (for example, highlighted display). As a result, on the display device 300D of the user terminal 3, the location of the retrieved search word is displayed in a manner different from other words. As a result, convenience is improved.

Further, the transmission unit 202 may be configured to output a predetermined area of the second contract D2 (this second contract may be a standard contract) whose similarity is equal to or less than a predetermined value. good. By configuring in this way, clauses missing in the first contract document D1 to be edited are displayed on the display device 300D of the user terminal 3. FIG.

[Modification 2 of Embodiment]
Further, revision management of a document may be performed by storing the editing history, and the same portion or different portion (difference) between specific revisions in the editing history of the document may be displayed in a manner different from others. . In this case, the storage device control unit 203 of the server 2 associates the editing history of the contract (document) by the user with the document ID and revision information and stores it in the DB 2 . Then, the calculation unit 206 calculates the similarity between the editing history of the specific revision of the first contract (first document) to be edited and the editing history of the second contract (second document) for each predetermined region. do. Next, the comparison unit 209 compares the editing history of the first contract with the editing history of the second contract in units of predetermined regions (clauses in the embodiment) according to the similarity calculated by the calculation unit 206. . The transmission unit 202 transmits (outputs) comparison information for displaying the same portions and different portions of the compared variant histories of the contracts in different modes according to the comparison result of the comparison unit 209 . The comparison information is received by the receiving section 301 of the user terminal 3 . Based on the received comparison information, the display device control unit 305 causes the display device 300D to display the same portions and different portions in the compared edit histories of the contracts in different modes. In this manner, differences between contracts (documents) can be compared in units of predetermined areas not only for contracts (documents) but also for editing histories, thereby improving convenience.

[Modification 3 of Embodiment]
It should be noted that an operation button (hereinafter, also referred to as an expansion button) for instructing expanded display of clauses other than the clauses to be compared in the second contract may be arranged on the screen. By selecting the expand button, the receiving unit 201 of the server 2 causes the second contract (second document) compared by the comparing unit 209 to be compared with clauses (predetermined areas) other than the clauses (predetermined area) to be compared. ), the transmission unit 202 of the server 2 receives an instruction (second instruction) to display Transmits (outputs) information for displaying clauses (areas) other than clauses (predetermined area) to be compared. The transmitted information is received by the receiving unit 301 of the user terminal 3, and is displayed on the display device 300D by the display device control unit 305 of the user terminal 3. The clause is expanded and displayed.

In addition, the above embodiments and modifications are merely examples of specific implementations of the present invention, and the technical scope of the present invention should not be construed in a limited manner. be. Thus, the invention may be embodied in various forms without departing from its spirit or essential characteristics.

1 information processing system 2 server (information processing device)
200A communication interface
200B storage device 200C CPU
201 receiving unit (first to third receiving units)
202 transmitter (output unit)
203 Storage device control unit 204 Division unit 205 Conversion unit 206 Calculation unit 207 Classification unit 208 Count unit 209 Comparison unit 210 Replacement unit 211 Search unit 3 User terminal 300A Communication IF
300B storage device 300C input device 300D display device 300E CPU
301 Reception unit 302 Transmission unit 303 Storage device control unit 304 Operation reception unit 305 Display device control unit 4 Network DB1 User database DB2 Document database

Claims (13)

a calculation unit that calculates the similarity between a first document and a second document different from the first document in units of predetermined regions;
a comparison unit that compares the first document and the second document in units of the predetermined area according to the similarity calculated by the calculation unit;
an output unit for outputting comparison information for displaying the same or different portions of the first document and the second document in a manner different from the others according to the comparison result of the comparison unit ;
a classification unit that classifies the second document into a predetermined group according to the similarity;
a counting unit that counts the number of the second documents classified by the classifying unit for each group;
The output unit
outputting the number of the second documents for each group counted by the counting unit;
An information processing device characterized by: a calculation unit that calculates the similarity between a first document and a second document different from the first document in units of predetermined regions;
a comparison unit that compares the first document and the second document in units of the predetermined area according to the similarity calculated by the calculation unit;
an output unit that outputs comparison information for displaying the same or different portions of the first document and the second document in a manner different from the others, according to the comparison result of the comparison unit;
The output unit
outputting a predetermined region of the second document lacking in the first document whose similarity with the first document is equal to or less than a predetermined value;
An information processing device characterized by: 2. The information processing apparatus according to claim 1, further comprising a switching unit that switches a display order of said first document or said second document in units of said predetermined area according to said similarity. a first reception unit that receives a first instruction to display the second documents classified by the classification unit for each group;
The output unit
2. The information processing apparatus according to claim 1 , wherein when said first reception unit receives said first instruction, it outputs information for displaying said second document belonging to a designated group. a storage control unit that stores an edit history of at least one of the first document and the second document;
The calculation unit
calculating the similarity between the editing history of the first document and the editing history of the second document for each predetermined area;
The comparison unit
5. The history of the first document and the history of the second document are compared in units of the predetermined area according to the similarity calculated by the calculation unit. 1. The information processing device according to claim 1. a second reception unit that receives a second instruction to display an area other than the predetermined area in the second document compared by the comparison unit;
The output unit
6. The information processing apparatus according to any one of claims 1 to 5, wherein when the second reception unit receives the second instruction, it outputs information for displaying an area other than the predetermined area. The predetermined area unit is
7. The information processing apparatus according to any one of claims 1 to 6 , wherein the information is provided on a clause-by-clause basis or on a claim-by-claim basis. a conversion unit that converts the first document and the second document into vectors in units of the predetermined area;
The calculation unit
8. The method according to any one of claims 1 to 7 , wherein the similarity between said first document and said second document is calculated in units of predetermined areas based on the vectors converted in units of said predetermined areas. The information processing device described. a third reception unit that receives a search word for searching the first document or the second document;
a search unit that searches for the first document or the second document based on the search word received by the third reception unit;
with
The output unit
The information processing apparatus according to any one of claims 1 to 8 , wherein search information for displaying the search word searched by the search unit in a manner different from other words is output. a step of calculating a similarity between a first document and a second document different from the first document by a calculation unit in units of predetermined regions;
a comparing unit comparing the first document and the second document in units of the predetermined area according to the similarity calculated by the calculating unit;
an output unit outputting comparison information for displaying the same or different portions of the first document and the second document in a manner different from the others, according to the comparison result of the comparison unit ;
a classifying unit classifying the second document into a predetermined group according to the similarity;
a counting unit counting the number of the second documents classified by the classifying unit for each group;
a step in which the output unit outputs the number of the second documents for each group counted by the counting unit;
An information processing method characterized by having the computer,
a calculation unit that calculates the similarity between a first document and a second document different from the first document in units of predetermined regions;
a comparison unit that compares the first document and the second document in units of the predetermined area according to the similarity calculated by the calculation unit;
an output unit for outputting comparison information for displaying the same or different portions of the first document and the second document in a manner different from the others according to the comparison result of the comparison unit ;
a classification unit that classifies the second document into a predetermined group according to the similarity;
functioning as a counting unit that counts the number of the second documents classified by the classifying unit for each group;
The output unit
outputting the number of the second documents for each group counted by the counting unit;
An information processing program characterized by: a step of calculating a similarity between a first document and a second document different from the first document by a calculation unit in units of predetermined regions;
a comparing unit comparing the first document and the second document in units of the predetermined area according to the similarity calculated by the calculating unit;
an output unit outputting comparison information for displaying the same or different portions of the first document and the second document in a manner different from the others, according to the comparison result of the comparison unit. ,
The output unit
outputting a predetermined region of the second document lacking in the first document whose similarity with the first document is equal to or less than a predetermined value;
An information processing method characterized by: the computer,
a calculation unit that calculates the similarity between a first document and a second document different from the first document in units of predetermined regions;
a comparison unit that compares the first document and the second document in units of the predetermined area according to the similarity calculated by the calculation unit;
functioning as an output unit for outputting comparison information for displaying the same or different portions of the first document and the second document in a different manner according to the comparison result of the comparison unit;
The output unit
outputting a predetermined region of the second document lacking in the first document whose similarity with the first document is equal to or less than a predetermined value;
An information processing program characterized by:

Images